Topic · Edition
which has efc not common_efc in the namespace of cutlass.operators.providers.cutedsl.evt. Pull Request resolved: #193940 Approved by: https://github.com/Skylion007
Changes since langchain-fireworks==1.5.2 release(fireworks): 1.6.0 (#39810) feat(fireworks): add document reranking (#39732) fix(fireworks): filter invalid tool calls from v1 content (#39805) feat(core): add standard…
Error when TORCH_TARGET_VERSION is newer than the libtorch being comp…
Corrects misspellings ("symbolicattion", "partfuseritioning", "merginginto", "dimensionalitities", "oldsyle", "semenatics", "archss", "Programmic"), missing word breaks ("offsetinto"), incorrect articles ("a int"/"an…
Summary Fixes #193938. When torch._inductor.config.align_random_eager=True, compiled torch.randn and torch.randn_like on CUDA were incorrectly lowered through ops.rand_eager, which produces uniform [0, 1) values. The FX…
Changes since langchain==1.3.15 release(langchain): 1.3.16 (#39806) feat(core): add standard model exception types (#39538) feat(langchain): support custom token_counter in ContextEditingMiddleware (#39754)…
Changes since langchain-anthropic==1.6.0 release(anthropic): 1.6.1 (#39804) fix(anthropic): filter invalid tool calls from v1 content (#39803)
Revert ideep for CPU to torch 2.13 version due to the performance reg…
Pull Request resolved: #194085 Approved by: https://github.com/Skylion007, https://github.com/fffrog
This PR fixes bugs in the Triton grouped MM kernel that only bite with really big tensors — some internal counters were the wrong bit-width and could overflow, causing crashes or bad output. Fixed those, added a guard…
In torch 2.13, different sorts of reductions either failed silently or loudly. We moved reductions from MPS Graph to metal kernels in 2.14 release window so now all of them fail silently which is undesirable. On 2.13:…
Remove condition preventing registration of some vmap decompositions …
[ghstack-poisoned]
Removed 'ndmitchell' from the list of approved reviewers. I used to be very active on the Pytorch type checking with Pyrefly, but now am working on other projects. The remaining approvers are all experts, so no loss of…
[fx] Memoize the result expression of symbolic binary arithmetic (#19…
Introducing AI Futures, a new OpenAI blog exploring how transformative AI could reshape power, governance, the economy, and individual freedom.
[aoti] Add private libc++ build support, resolved from build_paths (#…
Dynamo previously had no handler for the DELETE_DEREF bytecode, which is emitted for del x when x is a cell variable (captured by a nested function) or a free variable. This models cell deletion the same way CPython…
Dynamo previously had no handler for the DELETE_DEREF bytecode, which is emitted for del x when x is a cell variable (captured by a nested function) or a free variable. This models cell deletion the same way CPython…
Removes # mypy: ignore-errors from torch/_numpy/_ndarray.py and enables strict pyrefly checking via a per-file sub-config, with no net-new pyrefly errors. _ndarray.py is the numpy-compatible ndarray wrapper over a…
docs: remove EOL Ubuntu 25.10 from get_start_xpu supported OS list (#…
Corrects article agreement ("an unbacked" / "a DTensorSpec"), subject-verb agreement ("we have recorded"), and a handful of typos ("staring" -> "starting", "fakefied" -> "fakified", "StorageWrite" -> "StorageWriter")…
Fix "a"/"an" article errors and typos in comments and docstrings (#19…
[Test] Improve test reuse in test/test_unary_ufuncs.py for out-of-tre…
Scalar clamp kernels converted bounds directly to the input dtype, causing out-of-range values to wrap or raise an exception, which is mathematically incorrect, as such bounds should become a no-ops. With this change,…
This PR is auto-generated nightly by this action. Update the pinned vllm hash. Pull Request resolved: #193866 Approved by: https://github.com/pytorchbot
This PR is auto-generated nightly by this action. Update the pinned vllm hash. Pull Request resolved: #193866 Approved by: https://github.com/pytorchbot
[ROCm][CI] Increase periodic MI300 distributed shards 3→5 to fix time…
[inductor] Guard mutation tests requiring Triton block pointers (#194…
This PR was authored with the assistance of an AI coding assistant. Co-Authored-By: Claude Opus 4.8 (1M context) noreply@anthropic.com Pull Request resolved: #191540 Approved by: https://github.com/hameerabbasi
[ghstack-poisoned]
update vision commit hash
update torchtitan commit hash
update vllm commit hash
update torchcomms commit hash
Update Metamates merge rule
Route MethodWrapperVariable.call_function to slotdef.__call__ (#192…
Implement mp_subscript / sq_concat / bool_impl for ConstantVariable (…
Problem #188429 pinned TheRock wheels with ==${ROCM_VERSION}, so 7.14 matches 7.14.0 but not a later patch such as 7.14.1. Changes Major.minor pins use prefix matching (==7.14.*). Fully specified preview pins stay exact…
[ghstack-poisoned]
With a fixed deadline and design resources committed elsewhere, Stampli used Codex and ChatGPT Work to compress weeks of launch production into days.
“Runaway” AI, “rogue” agents, and “autonomous” actors—the current rhetoric would have you believe that AI agents are not only awake and aware, but angry at their creators. Prominent tech leaders such as Demis Hassabis,…
Each day, an airline transports tens of thousands of passengers on hundreds of flights. Often these are not straightforward point-to-point routes, with passengers requiring multiple connections. The airline can consider…
arXiv:2604.09560v2 Announce Type: replace Abstract: Softmax attention is the row-normalized operator of a diffusion map: both normalize a learned score into a Markov operator, and differ only in what the score is…
arXiv:2608.18780v1 Announce Type: new Abstract: Non-Intrusive Load Monitoring (NILM) systems estimate individual appliance energy consumption from a single aggregate meter, without requiring separate sensors for each…
arXiv:2602.16125v3 Announce Type: replace Abstract: Learning with shared representation is widely recognized as an effective way to separate commonalities from heterogeneity across various heterogeneous sources. Most…
arXiv:2608.18271v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a student on its own responses using token-level supervision from the same model conditioned on privileged reference information.…
arXiv:2608.18484v1 Announce Type: cross Abstract: Training-free block-sparse attention can accelerate video transformers, but row-wise attention concentration does not by itself specify an executable sparse operator.…
arXiv:2608.18234v1 Announce Type: cross Abstract: Whole-body motion tracking policies turn a humanoid into a robust control interface: the teleoperator---or an upstream model---only supplies a coarse movement intent,…
arXiv:2608.18261v1 Announce Type: cross Abstract: Serving a 235B-parameter Mixture-of-Experts (MoE) model on a single 8 GB GPU is bottlenecked not by compute but by memory bandwidth: decode must stream each token's…
arXiv:2608.03447v2 Announce Type: replace Abstract: Speculative decoding accelerates autoregressive generation by verifying a draft block with a target model in parallel. Under standard greedy verification, decoding…
arXiv:2608.18500v1 Announce Type: new Abstract: Tropical cyclones (TCs) pose severe risks from strong winds and heavy rainfall. However, forecasting their track and intensity remains challenging due to chaotic…
arXiv:2508.13068v2 Announce Type: replace-cross Abstract: Medical vision-language models still struggle to match radiologists' attention and to verbalize findings with explicit spatial grounding. We address this gap…
arXiv:2608.18634v1 Announce Type: new Abstract: Federated Active Learning (FAL) addresses the dual challenges of data privacy and label scarcity, where the absence of a global data view introduces additional hurdles for…
arXiv:2608.19098v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single…
arXiv:2608.18610v1 Announce Type: new Abstract: Dense text embeddings are widely used in data mining, retrieval, and downstream machine learning systems due to their compact and semantically rich representations, but…
arXiv:2608.18450v1 Announce Type: new Abstract: Falls among older adults represent a major public health challenge driven by complex, time-varying interactions across multiple risk domains. Effective fall risk factor…
arXiv:2608.18237v1 Announce Type: cross Abstract: Estimating the difference of two Stein's score functions is a fundamental problem in generative modeling. In particular, score differences arise naturally in transfer…
arXiv:2502.19522v2 Announce Type: replace Abstract: There is a prevalent debate in machine learning about whether practitioners should train models to optimize a task-agnostic objective (e.g., cross entropy) or…
arXiv:2608.18736v1 Announce Type: new Abstract: Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that…
arXiv:2608.18827v1 Announce Type: new Abstract: Reward function design remains a bottleneck in reinforcement learning. While large language models (LLMs) have enabled automated reward generation, existing methods…
arXiv:2608.18101v1 Announce Type: cross Abstract: Longitudinal text streams exhibit topic birth and death, but also discrete structural reorganizations in which themes split into subtopics or merge into broader…
arXiv:2608.18749v1 Announce Type: new Abstract: Geometric Data Perturbation (GDP) enables one-shot, privacy-preserving collaborative learning: each participant applies a distance-preserving transformation to its private…
arXiv:2608.18915v1 Announce Type: cross Abstract: Hardware shifts, color variations, and changing patient characteristics between development and deployment routinely break trained medical image classifiers. Existing…
arXiv:2608.08319v2 Announce Type: replace-cross Abstract: Brain magnetic resonance imaging (MRI) is central to neuroscience and clinical assessment, but models are commonly developed for individual diseases, populations…
arXiv:2608.18341v1 Announce Type: cross Abstract: Persistent acoustic monitoring can detect machine faults without physical contact, but always-on inference is constrained by power, latency, and deployment complexity.…
arXiv:2608.18185v1 Announce Type: new Abstract: Fine-grained recognition often involves hierarchical label spaces, where a model may be confident about a coarse semantic concept while remaining uncertain among its…
arXiv:2502.16445v4 Announce Type: replace Abstract: Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for entertainment to solving…
arXiv:2608.19121v1 Announce Type: new Abstract: Improving molecular properties, such as drug-likeness or binding affinity, is a recurring task in early-stage drug discovery. However, molecules optimized in an…
arXiv:2608.18419v1 Announce Type: new Abstract: Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series prediction. While LLMs…
arXiv:2608.09011v2 Announce Type: replace Abstract: Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Models (VLMs) in…
arXiv:2608.18940v1 Announce Type: new Abstract: Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer…
arXiv:2608.12036v2 Announce Type: replace-cross Abstract: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly…
arXiv:2608.18819v1 Announce Type: new Abstract: Graph neural networks (GNNs) are widely used, but how parameter sparsity affects the expressivity of relational (RGNNs) and temporal (TGNNs) variants is poorly understood.…
arXiv:2608.19134v1 Announce Type: new Abstract: Accurate visual decoding can reveal how the brain represents visual information and recover perceived content from neural signals such as electroencephalography (EEG),…
arXiv:2608.18901v1 Announce Type: cross Abstract: Tensor Networks are a relatively new machine learning approach. The architectures proposed initially are inspired by approaches from quantum many-body physics…
arXiv:2608.18178v1 Announce Type: cross Abstract: Trust assessment is a fundamental component of cooperative and connected vehicle systems. However, existing approaches operate primarily at the level of individual…
arXiv:2608.18690v1 Announce Type: new Abstract: The European Union has committed to reducing greenhouse gas emissions 55% below 1990 levels by 2030, but whether current trends are compatible with this ambition remains…
arXiv:2608.14778v2 Announce Type: replace-cross Abstract: Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related mortality worldwide, with early detection improving survival from <20% to >70%. The…
arXiv:2608.18244v1 Announce Type: new Abstract: Recent work has shown that representational alignment between biological and artificial neural networks is asymmetric: model representations predict neural responses much…
arXiv:2505.24313v3 Announce Type: replace Abstract: Weak-to-strong generalization (W2SG) is the phenomenon in which a powerful student model, trained on labels produced by a weaker teacher, ultimately outperforms the…
arXiv:2608.18522v1 Announce Type: cross Abstract: Large antenna arrays allow wireless systems to serve more users and achieve higher data rates, but they also make channel feedback expensive: the receiving device must…
arXiv:2608.19128v1 Announce Type: new Abstract: Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval…
arXiv:2608.18404v1 Announce Type: new Abstract: We answer this question with Vector-Symbolic Policy Gradient (VSPG), a discrete-action actor that represents each action by a unit-norm hypervector and scores it by…
arXiv:2608.18727v1 Announce Type: new Abstract: Applying machine learning to web pages is challenging due to the need to interpret HTML together with associated resources and perform rendering to obtain a meaningful…
arXiv:2604.23309v2 Announce Type: replace-cross Abstract: Remote sensing image change captioning (RSICC) aims to describe the difference between two remote sensing images. While recent methods have explored video…
arXiv:2608.18524v1 Announce Type: cross Abstract: Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited…
arXiv:2608.18669v1 Announce Type: new Abstract: Humans solve complex problems by constructing plans and mentally simulating their outcomes with an internal model of the world. Machine learning has produced world models…
arXiv:2608.18055v2 Announce Type: replace-cross Abstract: Reliable quantitative analysis of dynamic contrast-enhanced MRI requires high-quality spatiotemporal reconstructions at high undersampling rates. Scan-specific…
arXiv:2608.19119v1 Announce Type: new Abstract: Time series imputation is a crucial area for reliable time series analysis, yet it remains challenging due to the complex temporal dynamics and noise of real-world data.…
arXiv:2608.18181v1 Announce Type: cross Abstract: Selecting a small, diverse subset from a large candidate pool often means balancing several incompatible notions of diversity. In trademark curation, for instance, a…
arXiv:2608.18279v1 Announce Type: cross Abstract: Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often…
arXiv:2608.18191v1 Announce Type: new Abstract: Bats are key indicators of ecosystem health and are protected throughout Europe, making reliable population monitoring a conservation priority. Their cryptic nocturnal…
arXiv:2608.18174v1 Announce Type: cross Abstract: Customer decline early-warning systems feed account-manager action lists, and every flagged account consumes intervention capacity. In a deployed business-to-business…
arXiv:2608.18415v1 Announce Type: new Abstract: The edge of stability refers to a phenomenon in deep learning with gradient-based optimizers where the Hessian eigenvalues of the loss remain stable above a threshold that…
arXiv:2608.18486v1 Announce Type: cross Abstract: In a Transformer, each layer attends to past tokens only through KV produced at its own depth, despite the presence of deeper representations during autoregressive…
arXiv:2608.18503v1 Announce Type: new Abstract: The growing demand for AI-driven workloads, particularly from Large Language Models (LLMs), has raised concerns about the significant energy and resource consumption in…
arXiv:2608.18410v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models process long multimodal token sequences, making inference expensive in both memory and computation. Existing efficiency methods mainly…
arXiv:2608.18631v1 Announce Type: cross Abstract: As large language models evolve into decision-making agents, the ability to reason over preferences becomes fundamental to alignment, coordination, and collective…
arXiv:2608.18982v1 Announce Type: new Abstract: Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and…
arXiv:2608.18190v1 Announce Type: new Abstract: Domain adaptation is widely used to make neural networks trained on simulations applicable to experimental data. Its premise is that the two domains differ only in…
arXiv:2608.18910v1 Announce Type: new Abstract: Hard combinatorial optimization problems, many of which are NP-hard, present fundamental algorithmic challenges. Average-case analysis on random instances has emerged as a…
arXiv:2608.18147v1 Announce Type: new Abstract: Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean Squared Error (MSE) for a given input while preserving…
arXiv:2603.25954v2 Announce Type: replace Abstract: The use of satellite networks has increased significantly in recent years due to their advantages over purely terrestrial systems, such as higher availability and…
arXiv:2608.18774v1 Announce Type: cross Abstract: Skin diseases represent a major global public health burden, yet machine learning tools developed to assist in their diagnosis suffer from two critical limitations:…
arXiv:2608.18469v1 Announce Type: new Abstract: Lightweight proxy models enable rapid experimentation without repeatedly training frontier-scale systems, but their small kernels often leave modern accelerators…
arXiv:2608.18130v1 Announce Type: cross Abstract: We study online bipartite matching with reusable server capacity and non-stationary rewards. Jobs arrive sequentially, reveal compatible servers, reward rates, and…
arXiv:2608.18759v1 Announce Type: new Abstract: Fairness in medical imaging is commonly evaluated through subgroup performance metrics, yet it remains unclear whether models rely on consistent visual evidence across…
arXiv:2606.00919v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have seen widespread adoption across various domains, yet their reliability is frequently undermined by hallucinations - responses…
arXiv:2607.10476v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text…
arXiv:2608.18555v1 Announce Type: new Abstract: Machine Learning as a Service (MLaaS) is a powerful cloud paradigm enabling data-driven intelligent applications in Internet of Things (IoT) environments, widely adopted…
arXiv:2607.29659v2 Announce Type: replace Abstract: Deploying state-of-the-art deep neural networks (DNNs) at the wireless edge is severely bottlenecked by the strict energy and resource constraints of mobile devices.…
arXiv:2510.25692v5 Announce Type: replace-cross Abstract: As machine learning underpins more critical applications, the value of a reported result depends on whether it can be compared and repeated. In practice, this…
arXiv:2608.19067v1 Announce Type: cross Abstract: The empirical success of diffusion models in generative modelling has motivated theoretical work, including quantitative error bounds and qualitative analyses that…
arXiv:2608.18429v1 Announce Type: cross Abstract: This work presents a data-driven methodology for multi-objective optimization under uncertainty of process parameters in the fused filament fabrication (FFF) process.…
arXiv:2605.19811v3 Announce Type: replace Abstract: In large-scale optimization, the cheapness and effectiveness of update steps are the most crucial factors for a successful optimizer. Sign-based optimizers like Lion…
arXiv:2608.18639v1 Announce Type: cross Abstract: Non-invasive continuous blood pressure (BP) monitoring using photoplethysmography (PPG) is a promising alternative to cuff-based measurements. However, existing…
arXiv:2608.07349v2 Announce Type: replace Abstract: Learning from heterogeneous representations is often reduced to feature concatenation, erasing which representation produced each error. We propose residual algebra,…
arXiv:2608.18102v1 Announce Type: cross Abstract: The widespread adoption of large language models (LLMs) has intensified the demand for principled methods to distinguish human from machine-generated text. Watermarking…
arXiv:2608.18932v1 Announce Type: new Abstract: Estimating causal effects under network interference typically assumes that the network used for training and the network used for deployment coincide. In practice, an…
arXiv:2603.09355v2 Announce Type: replace-cross Abstract: Under the multiplicative noise scaling (MNS) condition, original Nesterov acceleration is provably sensitive to noise and may diverge when gradient noise…
arXiv:2608.18810v1 Announce Type: new Abstract: An optimizer is usually chosen before training a deep neural network and then kept fixed. Treating optimizer choice as a hyperparameter could boost performance, but it…
arXiv:2607.04546v2 Announce Type: replace-cross Abstract: Action-conditioned world models allow robots to predict the future consequences of candidate actions without additional physical interaction, supporting policy…
arXiv:2608.19115v1 Announce Type: new Abstract: Modern pretrained encoders make representations from heterogeneous views increasingly reusable, but the procedure that determines view utility and combines evidence is…
arXiv:2608.18433v1 Announce Type: cross Abstract: Robot foundation models (RFMs), including vision-language-action (VLA) policies, are often discussed through a scaling view: more data, larger models, and broader…
arXiv:2608.18576v1 Announce Type: new Abstract: A convolutional sequence labeler's receptive field is routinely treated as the extent of the model's usable context: it sets dilation schedules, bounds streaming horizons,…
arXiv:2608.18193v1 Announce Type: cross Abstract: Distribution-free risk control adds organ-specific recall guarantees to frozen segmentation. We calibrate per-organ thresholds for an AMOS-trained nnU-Net, audit…
arXiv:2608.18096v1 Announce Type: cross Abstract: Assessing whether multimodal content aligns with macro-societal values, such as peace, justice, and freedom, has become an increasingly urgent challenge. Existing…
arXiv:2608.03502v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. However,…
arXiv:2608.19127v1 Announce Type: new Abstract: A gradient-boosted ensemble predicts by summing one leaf value per tree. Read those values as coordinates rather than as intermediate results, and every instance becomes a…
arXiv:2607.21636v4 Announce Type: replace Abstract: Synthetic tabular data are valued for preserving not just column-wise marginals but inter-column dependency. Yet the most commonly reported certification score, a…
arXiv:2608.18825v1 Announce Type: cross Abstract: Medical automatic speech recognition (MedASR) requires adaptation to specialised terminology, limited annotated clinical data, and multilingual use cases. Although…
arXiv:2608.18495v1 Announce Type: new Abstract: Radio maps are essential for wireless decision-making tasks such as access-point placement, coverage planning, and localization, but their fine spatial details are…
arXiv:2510.15483v3 Announce Type: replace-cross Abstract: We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without…
arXiv:2608.18936v1 Announce Type: new Abstract: Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of two…
arXiv:2602.19816v3 Announce Type: replace-cross Abstract: For computational efficiency, modern language models are typically trained on independently sampled fixed-length sequences. Symbolic music language models…
arXiv:2608.18611v1 Announce Type: new Abstract: Electric power networks are increasingly exposed to weather-sensitive failure mechanisms that require asset-level, spatially explicit risk modelling for effective…
arXiv:2608.19141v1 Announce Type: cross Abstract: Neural audio codecs based on Residual Vector Quantization (RVQ) have become the dominant discrete representation for token-based general audio generation, yet…
arXiv:2607.19404v2 Announce Type: replace Abstract: Existing patching and multi-scale methods advance multivariate time series forecasting but treat learned representations as transient byproducts of prediction, lacking…
arXiv:2608.18105v1 Announce Type: cross Abstract: StocksTalk is a voice-enabled conversational system for transforming spoken financial screening requests into executable and validated structured queries over real-world…
arXiv:2603.02196v4 Announce Type: replace-cross Abstract: An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm and must be taken…
arXiv:2608.18742v1 Announce Type: cross Abstract: In some fields currently dominated by empirical approaches, such as state of health (SoH) prediction for lithium-ion batteries, phenomenological models motivated by…
arXiv:2608.18351v1 Announce Type: cross Abstract: Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need, causing excess-authority…
arXiv:2608.18578v1 Announce Type: cross Abstract: Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior overwrites…
arXiv:2608.17823v2 Announce Type: replace Abstract: Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time…
arXiv:2608.18260v1 Announce Type: cross Abstract: Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is…
arXiv:2608.18803v1 Announce Type: new Abstract: Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the…
arXiv:2608.18246v1 Announce Type: cross Abstract: Fine-grained wildlife re-identification remains a challenging area in research. Current state-of-the-art approaches apply a detection and re-identification pipeline. We…
arXiv:2506.19260v3 Announce Type: replace-cross Abstract: Hierarchical federated learning places regional aggregators between clients and the cloud, so a participant's update is observed only alongside its neighbours'.…
arXiv:2607.24834v3 Announce Type: replace-cross Abstract: Objective. We tested whether frozen representations from five EEG foundation models support decoding of long-range temporal correlations, measured as the…
arXiv:2608.18709v1 Announce Type: cross Abstract: Foundation models are increasingly breaking what seemed to be impossible not long ago by enabling unprecedented accuracy and cross-domain generalization. Yet their lack…
arXiv:2608.18177v1 Announce Type: new Abstract: Continual learning has traditionally treated forgetting as a failure, emphasizing preservation of previously acquired knowledge as environments evolve. We argue that this…
arXiv:2608.18733v1 Announce Type: cross Abstract: We present Flama, an open-source Python framework for developing and deploying production-ready web APIs, machine learning services, and large-language-model (LLM)…
arXiv:2608.18715v1 Announce Type: cross Abstract: Ensuring not only high accuracy but also reliable and robust predictions is critical for the deployment of semantic segmentation models in safety-critical applications…
arXiv:2608.19181v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger teacher. In long-context tasks, however, token-level…
arXiv:2608.18263v1 Announce Type: new Abstract: Traffic signal control is a complex sequential decision-making problem requiring real-time adaptation and trade-offs among throughput, delay fairness, signal stability,…
arXiv:2608.19117v1 Announce Type: new Abstract: Quantitative microstructural characterization of Li-ion battery electrode materials using electron backscatter diffraction (EBSD) has been proven as a critical method for…
arXiv:2608.18451v1 Announce Type: new Abstract: \textbf{Background and Objective}: Reliable atrial fibrillation (AF) detection from electrocardiogram (ECG) signals remains challenging in real-world clinical settings due…
arXiv:2605.05189v2 Announce Type: replace-cross Abstract: How many key-value associations can a $d\times d$ linear memory store? The answer depends not only on the $d^2$ degrees of freedom in the memory matrix, but also…
arXiv:2608.18919v1 Announce Type: new Abstract: Tabular machine learning benchmarks typically summarize performance by averaging scores, ranks, or pairwise wins across datasets. Such aggregates are useful for selecting…
arXiv:2607.16230v2 Announce Type: replace Abstract: Accurate pre-order shipping cost estimation is important in e-commerce because it affects price presentation, margin planning, and conversion. In practice, shipping…
arXiv:2608.19080v1 Announce Type: cross Abstract: Object detectors often produce over-confident predictions for objects outside their training categories, leading to so-called out-of-distribution (OoD) hallucinations.…
arXiv:2608.18863v1 Announce Type: cross Abstract: We study Bayesian optimization in a time-varying environment where the unknown reward function evolves according to a Gaussian process drift model. Existing GP-UCB…
arXiv:2608.19084v1 Announce Type: new Abstract: S-JEPA uses soft Gaussian mixture model (GMM) posteriors instead of hard cluster labels to preserve uncertainty. It remains unclear whether the probability values alone…
arXiv:2608.18280v1 Announce Type: cross Abstract: Background. Advances in agentic systems are simultaneously, and rapidly, saturating benchmarks. Despite this often discussed phenomena, benchmark scores remain difficult…
arXiv:2608.18643v1 Announce Type: new Abstract: Researchers often choose a proxy dataset from many releases, transformations, or seeds. Search can make an invalid release appear adequate, while one adequate release does…
arXiv:2608.18767v1 Announce Type: cross Abstract: Gradient matching attacks (GMAs) in LLM split learning (SL) rely on a critical yet underexplored assumption: the gradient exposed at the split interface is a faithful…
arXiv:2608.18849v1 Announce Type: new Abstract: Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs,…
arXiv:2608.18188v1 Announce Type: new Abstract: Autism spectrum disorder (ASD) is a developmental disability characterized by challenges in social interaction and communication. As the causes of ASD remain unclear,…
arXiv:2608.18597v1 Announce Type: new Abstract: Protein language models are widely used priors for protein sequence design, and a growing body of work controls them at inference time as an alternative to fine-tuning.…
arXiv:2608.18379v1 Announce Type: new Abstract: When every candidate is wrong, correct-candidate selection is unavailable, yet the aggregation call can still solve the problem afresh. A correct aggregate answer may…
arXiv:2608.18438v1 Announce Type: cross Abstract: Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a "supervision gap" where novice therapists manage high-stakes risks with…
arXiv:2608.18086v1 Announce Type: cross Abstract: The growth of open-weight foundation models (OWFMs) has prompted the AI community to re-evaluate strategies for effective downstream governance. Although model cards…
arXiv:2511.04707v2 Announce Type: replace-cross Abstract: Recent advances in long-context language models (LMs) have enabled million-token inputs, expanding their capabilities across complex tasks like computer-use…
arXiv:2607.15509v3 Announce Type: replace-cross Abstract: We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers for…
arXiv:2608.18714v1 Announce Type: cross Abstract: Machine-learned models are replacing first-principles calculations across materials discovery, and physical symmetry is the central guarantee built into them. The debate…
arXiv:2608.18171v1 Announce Type: cross Abstract: Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We study this question…
arXiv:2604.01499v3 Announce Type: replace Abstract: Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains unclear whether…
arXiv:2608.18126v1 Announce Type: cross Abstract: This study evaluates the potential of electric vehicle (EV) charging flexibility to enhance both energy efficiency and power grid stability. Using real-world data from…
arXiv:2510.09253v2 Announce Type: replace-cross Abstract: Automatic systems for document understanding require multimodal models that accurately identify sensitive visual content, even in the presence of image…
arXiv:2608.18777v1 Announce Type: new Abstract: Graph generation models have advanced significantly with deep learning, yet they remain limited in scalability, flexibility, and ability to model underlying structures. We…
arXiv:2608.18918v1 Announce Type: new Abstract: Dimension reduction for dynamical systems is standard practice, and the standard route is spectral: model the transfer (Koopman) operator by its leading modes. We show…
arXiv:2608.18186v1 Announce Type: new Abstract: In the past few years, machine learning (ML) has been widely (and to an extent, successfully) implemented in medicine. However, uncertainties surrounding ML have made it…
arXiv:2608.18339v1 Announce Type: cross Abstract: Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference. Although…
arXiv:2608.18230v1 Announce Type: new Abstract: Looped language models improve reasoning and knowledge manipulation by applying shared computation repeatedly. Existing systems usually repeat an entire layer stack,…
arXiv:2608.18571v1 Announce Type: new Abstract: Sleep stage classification from single-channel electroencephalography (EEG) is essential for wearable and home-based sleep monitoring. However, many deep learning models…
arXiv:2608.18808v1 Announce Type: new Abstract: This paper introduces Tensor Field Models (TFMs), realization-level Mathematical Structures in which a learned Operator maps a product of admissible component-section…
arXiv:2506.00244v2 Announce Type: replace Abstract: Noisy labelled datasets are generally inexpensive compared to clean labelled datasets, and the same is true for graph data. In this paper, we propose a denoising…
arXiv:2603.04448v2 Announce Type: replace-cross Abstract: Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and…
arXiv:2608.12745v2 Announce Type: replace Abstract: Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where…
arXiv:2608.11996v2 Announce Type: replace-cross Abstract: Cashew production is a widespread economic activity in Guinea-Bissau, as well as other countries in West Africa. However, unregulated cashew production can be…
arXiv:2608.18570v1 Announce Type: cross Abstract: Machine learning and data analysis techniques have recently emerged as powerful tools for identifying patterns and formulating conjectures in mathematical research, most…
arXiv:2608.19073v1 Announce Type: cross Abstract: An agent still learning its environment should be cautious while ignorant and bold once confident. The entropic value-at-risk captures this through a robust-optimization…
arXiv:2608.18148v1 Announce Type: cross Abstract: We study data-driven prediction of coarse-grained dynamics in multiscale PDE systems. Adopting a closure-free operator-learning viewpoint, we apply a linear…
arXiv:2608.18647v1 Announce Type: cross Abstract: Autonomous endovascular navigation could support the delivery of mechanical thrombectomy to underserved areas, but controllers must navigate long, multi-stage paths…
arXiv:2606.14870v2 Announce Type: replace-cross Abstract: Foundation models (FMs) trained on large datasets and fine-tuned on downstream tasks have emerged as a powerful paradigm in AI for science. Industrial FMs are…
arXiv:2608.18558v1 Announce Type: new Abstract: The prediction of equilibrium beach profiles under tidal influence is of fundamental importance for sustainable coastal development, informing shoreline protection…
arXiv:2608.18581v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) encode rich factual knowledge in their parameters, reliably recalling and verifying such knowledge remains a key bottleneck in…
arXiv:2607.26643v2 Announce Type: replace-cross Abstract: Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applications. A…
arXiv:2608.18521v1 Announce Type: cross Abstract: Dense-caption retrieval has recently been improved by introducing segmentation, edge maps, LLM-filtered captions, and cross-modal modules into contrastive fine-tuning.…
arXiv:2608.11917v2 Announce Type: replace Abstract: Multi-output Gaussian process regression scales cubically in the number of observations times outputs, and dense kernel-matrix methods need bespoke handling whenever…
arXiv:2608.18887v1 Announce Type: new Abstract: The epileptogenic zone (EZ) is the brain region that generates seizures in an individual, and is the target of epilepsy surgery. Localizing the EZ from stereo-EEG (sEEG)…
arXiv:2608.18268v1 Announce Type: cross Abstract: Today most media content is consumed based on algorithmic recommendations. Evidence suggests that this can lead to politically biased media consumption patterns.…
arXiv:2608.18546v1 Announce Type: new Abstract: Multimodal urban data has expanded the applications of urban region representation learning, such as functional zone identification and real estate appraisal, but also…
arXiv:2608.18155v1 Announce Type: cross Abstract: Quantum machine learning (QML) for network intrusion detection (NIDS) is routinely reported to reach near-perfect accuracy, yet the most rigorous studies find that…
arXiv:2608.18319v1 Announce Type: new Abstract: Neural networks trained on nonstationary tasks frequently lose the ability to fit new targets, a phenomenon referred to as loss of plasticity. We identify a novel source…
arXiv:2608.18746v1 Announce Type: new Abstract: JEPA-style latent world models can use Euclidean distance to a goal latent as the cost for model-predictive control (MPC). Strong decoding of task variables, however, does…
arXiv:2608.18574v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as new tasks are added…
arXiv:2608.18762v1 Announce Type: new Abstract: Graph autoencoders (GAEs) are widely used for learning representations of dynamic graphs. However, their optimisation objectives typically do not take structural…
arXiv:2608.18294v1 Announce Type: cross Abstract: An increasing number of scholars use AI to measure variables they subsequently include in downstream analyses. Although AI-measured variables are often analyzed as if…
arXiv:2608.18903v1 Announce Type: new Abstract: This work evaluates surrogate-assisted optimization of a seven-parameter current-excited coil--core benchmark subject to geometric, manufacturing, and separate core and…
arXiv:2608.19168v1 Announce Type: new Abstract: A single training example's contribution to a finished model is normally estimated rather than measured, because measuring it takes two expensive full pre-training runs…
arXiv:2608.18311v1 Announce Type: cross Abstract: Federated multimodal models often assume every site has every modality, although hospitals differ in access to EHRs, chest radiographs, and ECGs. We study this setting…
arXiv:2608.18402v1 Announce Type: cross Abstract: We study finite-sample linear regression in the presence of varied and unknown label noise, focusing on the heteroskedastic and adaptive linear regression models.…
arXiv:2608.18592v1 Announce Type: new Abstract: Whether distinct neural architectures develop common collective dynamics remains an open question. Recent analysis of Transformer language models revealed a nearly flat,…
arXiv:2608.18374v1 Announce Type: cross Abstract: We address two open questions in streaming PCA via Oja's algorithm: sharp operator-norm convergence for general rank under sub-Gaussian data, and distributional…
arXiv:2608.18765v1 Announce Type: cross Abstract: Register automata are finite automata equipped with memory that recognize data languages over infinite alphabets. In this work, we investigate active learning algorithms…
arXiv:2608.18675v1 Announce Type: new Abstract: Accurate forecasting of energy consumption is important for the efficient operation of power systems, with direct implications for operational costs, energy management,…
arXiv:2604.16804v3 Announce Type: replace Abstract: Optimization problems are central to decision-making in manufacturing, logistics, scheduling, and other industrial settings. Translating complicated descriptions of…
arXiv:2608.19049v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) has recently gained a great attention due to its real-time adaptation and effectiveness in complex optimization problems. This paper…
arXiv:2608.18242v1 Announce Type: new Abstract: We introduce ClosureBench, a constructive benchmark for compositional graph-relational reasoning with programmatically verified ground truth. Unlike fixed-test-set…
arXiv:2608.18770v1 Announce Type: new Abstract: Learning a reward model from human feedback and optimizing a policy against it is one approach to aligning AI systems with individual users. From a fairness perspective,…
arXiv:2608.04156v2 Announce Type: replace-cross Abstract: Electroencephalography (EEG) analysis extends beyond assigning predefined labels to recordings; it requires workflows connecting natural-language instructions,…
arXiv:2608.18431v1 Announce Type: cross Abstract: This paper develops a computational framework to optimize the process parameters such that the bond quality between extruded polymer filaments is maximized in fused…
arXiv:2608.18346v1 Announce Type: cross Abstract: Coupled-cluster theory defines the accuracy standard for molecular electronic-structure properties but scales too steeply for routine application, whereas…
arXiv:2608.19144v1 Announce Type: new Abstract: Continuous-time generative models are often built from endpoint-conditioned bridges, but generation requires a different object: a non-anticipative Markov decoder that…
arXiv:2505.01783v2 Announce Type: replace Abstract: Online anomaly detection is essential in fields such as cybersecurity, healthcare, industrial monitoring, and telecommunications, where promptly identifying deviations…
arXiv:2608.18114v1 Announce Type: cross Abstract: Restoring communication for people who have lost the ability to speak or move after a brain injury is a major challenge. While intracranial implants now enable…
arXiv:2606.16246v3 Announce Type: replace Abstract: As AI labs approach a data ceiling where compute capacity outpaces the rate of new high-quality text generation, language model pretraining is shifting toward a…
arXiv:2608.16921v2 Announce Type: replace-cross Abstract: Effective cybersecurity operations require timely and accurate analysis of large-scale heterogeneous security information; however, analysts increasingly…
arXiv:2608.19171v1 Announce Type: new Abstract: Deep models for irregularly-sampled time series answer queries at arbitrary continuous timestamps, yet report nothing about how far each answer should be trusted. We show…
arXiv:2512.02473v3 Announce Type: replace-cross Abstract: Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations…
arXiv:2512.05092v2 Announce Type: replace-cross Abstract: Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and seldom clarify their…
arXiv:2608.18222v1 Announce Type: new Abstract: Recurrent-depth reasoners aim to solve harder problems by iterating their update longer at test time, but additional iterations can improve, preserve, or degrade an…
arXiv:2608.18116v1 Announce Type: cross Abstract: Vision-language models enable zero-shot classification through natural language prompts, but performance is sensitive to prompt formulation, especially in specialized…
arXiv:2608.19140v1 Announce Type: cross Abstract: Frontier language models are compared, marketed, and benchmarked on capability -- what their best or average output can achieve. I argue this measures the wrong axis.…
arXiv:2608.18969v1 Announce Type: new Abstract: We consider the problem of classification of skin tone using photoplethysmography (PPG) signals with labels of the ordinal six-class Fitzpatrick skin tones. A typical…
arXiv:2608.18235v1 Announce Type: new Abstract: In this work, we investigate whether the latent representations learned by a Deep Belief Network (DBN) and a Bidirectional Gated Recurrent Unit (Bi-GRU) can discriminate…
arXiv:2605.29803v2 Announce Type: replace Abstract: Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions…
arXiv:2608.18149v1 Announce Type: cross Abstract: Energy-aware LLM serving requires comparing configurations under realistic request shapes, yet exhaustive target-GPU profiling is costly and a cheap predictor can be…
arXiv:2608.19072v1 Announce Type: cross Abstract: Large language model (LLM) agents can now post-train an LLM end-to-end. They can write code, launch training, evaluate checkpoints, and improve downstream performance,…
arXiv:2510.09764v3 Announce Type: replace Abstract: Modeling multi-modal time-series data is critical for capturing system-level dynamics, particularly in biosignals where modalities such as ECG, PPG, EDA, and…
arXiv:2608.18274v1 Announce Type: cross Abstract: OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and secrets in…
arXiv:2608.17641v2 Announce Type: replace Abstract: We present rl-triton, an open-source library of high-performance GPU kernels for reinforcement learning credit assignment, implemented in Triton. The core contribution…
arXiv:2608.18659v1 Announce Type: cross Abstract: Tsetlin Machines (TMs) learn interpretable Boolean clauses using finite-state automata. We introduce the Quantum-Logic Tsetlin Machine (QL-TM), which replaces Boolean…
arXiv:2605.16812v3 Announce Type: replace Abstract: While Local Differential Privacy (LDP) serves as a foundational primitive for distributed data collection, its stringent randomization requirements often lead to…
arXiv:2608.18136v1 Announce Type: cross Abstract: Conversational agents now act for end users through tools while holding access to customer databases and internal policy documents that a caller can reach through…
arXiv:2608.18289v1 Announce Type: cross Abstract: The extraction of structured information from unstructured documents represents a critical component of digital transformations in all sectors. While proprietary…
arXiv:2608.18539v1 Announce Type: new Abstract: The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes in prompts can cause…
arXiv:2608.17253v2 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend…
arXiv:2608.18531v1 Announce Type: cross Abstract: Industrial explainable-recommendation systems built on LLMs incur a substantial serving cost: each request triggers an LLM generation, with latency in the hundreds of…
arXiv:2605.03103v2 Announce Type: replace-cross Abstract: Semi-structured information extraction (IE) from OCR-derived clinical reports is crucial for efficiently reconstructing patients' longitudinal medical histories.…
arXiv:2608.18938v1 Announce Type: cross Abstract: Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and textual inputs in…
arXiv:2608.18141v1 Announce Type: cross Abstract: Predicting underwater acoustic transmission loss rapidly and accurately is crucial for real-time ocean acoustic applications. While Fourier Neural Operators (FNO) have…
arXiv:2608.19082v1 Announce Type: cross Abstract: We present a new data-driven learning of a Random Geometric Graph (RGG) of a multivariate dataset, where the graph is drawn in a probabilistic metric space. This graph…
arXiv:2608.18282v1 Announce Type: cross Abstract: Stochastic mean-field control (MFC) provides a fundamental framework for coordinating large populations of interacting agents under uncertainty, with a wide range of…
arXiv:2608.18851v1 Announce Type: new Abstract: Convolution integrals widely exist in applications, and to enable fast and accurate computations, this paper introduces two general multi-stage neural operator learning…
arXiv:2608.18687v1 Announce Type: new Abstract: Heart disease remains the leading cause of mortality globally, necessitating early and accurate detection to improve patient outcomes. This research focuses on the…
arXiv:2608.18183v1 Announce Type: new Abstract: Visual on-policy distillation (OPD) improves the training of compact visual autoregressive models by learning from trajectories generated by the current student. However,…
arXiv:2511.22842v3 Announce Type: replace Abstract: Causal machine learning (Causal ML) aims to answer "what if" questions using machine learning algorithms, making it a promising tool for high-stakes decision-making.…
arXiv:2608.19013v1 Announce Type: new Abstract: Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt through a…
arXiv:2608.18330v1 Announce Type: new Abstract: Whether input-dependent ("dynamic") combination of a regression model pool beats the best static blend depends on the shift and is rarely known before deployment. Can a…
arXiv:2608.18303v1 Announce Type: cross Abstract: LLM-as-judge evaluation reduces response quality assessment to a single holistic A/B preference choice, providing no mechanism to isolate which quality dimensions drove…
arXiv:2602.05887v3 Announce Type: replace Abstract: Low-rank matrix sensing is a fundamental yet challenging nonconvex problem whose optimization landscape typically contains numerous spurious local minima, making it…
arXiv:2602.03395v5 Announce Type: replace Abstract: While deep learning has revolutionized financial forecasting through sophisticated architectures, the design of the supervision signal itself is rarely scrutinized. We…
arXiv:2607.05585v2 Announce Type: replace-cross Abstract: FaceMesh2HPO is a framework for classifying facial phenotypic descriptors aligned with the Human Phenotype Ontology (HPO) to support clinical diagnosis. Using…
arXiv:2608.18911v1 Announce Type: new Abstract: We introduce the CDSP (context-conditional deliberation signal pipeline), converting an investment committee's meeting transcripts into structured predictive features.…
arXiv:2608.18660v1 Announce Type: new Abstract: Collaborative virtual reality (VR) environments make team communication observable as it unfolds, but conventional transcript analyses often summarize entire trials or…
arXiv:2608.00097v2 Announce Type: replace-cross Abstract: Physical learning rules such as equilibrium propagation (EP), coupled learning (CL), and adjoint coupled learning (AL) train resistive networks through local…
arXiv:2608.18656v1 Announce Type: new Abstract: Inference with transformer models on CPUs is increasingly important, especially for Small Language Models (SLMs), where vector architectures are emerging as a promising…
arXiv:2608.19151v1 Announce Type: new Abstract: We study stochastic control of multivariate Hawkes-driven stochastic differential equations with machine learning algorithms in a non-Markovian setting. Due to the path…
arXiv:2608.19043v1 Announce Type: cross Abstract: We introduce Bernstein-Vazirani Networks (BVNs), a non-variational quantum machine learning framework that leverages quantum interference for supervised learning,…
arXiv:2602.02060v2 Announce Type: replace Abstract: Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains unclear whether their predictions can be controlled by explicitly…
arXiv:2608.18716v1 Announce Type: new Abstract: Diagnosing faults in rotating machinery is essential for ensuring the reliability of industrial processes. Random convolutional kernel-based Time Series Classification…
arXiv:2407.05788v2 Announce Type: replace Abstract: Bayesian optimization (BO) is an efficient framework for optimization of black-box objectives when function evaluations are costly and gradient information is not…
arXiv:2608.18115v1 Announce Type: cross Abstract: Token-level hallucination detectors score each token independently from a single signal, and fail exactly when the generating model is confidently wrong. This paper…
arXiv:2608.18888v1 Announce Type: new Abstract: The rapid advancement of Natural Language Generation (NLG) has made the reliable evaluation of generated text increasingly critical, as these systems, such as large…
arXiv:2608.14905v2 Announce Type: replace Abstract: AI has long assisted scientific research, but the rapid advance of LLMs and agentic scaffolds is reshaping the landscape; a single system can now carry whole-stage…
arXiv:2608.18132v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are typically built through a multi-stage pipeline consisting of cross-modal alignment, supervised fine-tuning (SFT), and…
arXiv:2608.18821v1 Announce Type: new Abstract: The logical reconstruction of argument graphs from natural language text is challenging because of the prevalence of enthymemes (i.e., arguments with implicit premises).…
arXiv:2608.18164v1 Announce Type: new Abstract: Safety evaluations of large language models (LLMs) predominantly rely on text-based adversarial prompts, potentially overlooking vulnerabilities arising from alternative…
arXiv:2606.21654v2 Announce Type: replace-cross Abstract: Computer use agents are evaluated almost exclusively on atomic desktop tasks, but realistic desktop work requires sustaining state across multiple objectives. We…
arXiv:2608.18158v1 Announce Type: new Abstract: LLMs have been increasingly used to catch data quality issues automatically, but we know very little about how consistent these judgments actually are. This study tests an…
arXiv:2603.14473v3 Announce Type: replace Abstract: Scientific discovery depends on expert judgement and foresight, which we call scientific taste: the ability to judge and propose research ideas with the potential for…
arXiv:2608.17050v2 Announce Type: replace Abstract: Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access to external knowledge,…
arXiv:2605.09874v2 Announce Type: replace-cross Abstract: Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems, must reason over an entire day or more of…
arXiv:2608.18312v1 Announce Type: new Abstract: Autonomous scientific agents now increasingly propose ideas, write code, run experiments, analyze results, and even draft papers. Observe and audit those agents are…
arXiv:2608.18744v1 Announce Type: cross Abstract: Agents improve quickly against a reliable automatic metric and stall without one, and the applications that need them most, report generation among them, are the ones…
arXiv:2608.18142v1 Announce Type: cross Abstract: It is challenging to detect hate speech in Low Resource Languages (LRLs) because of the absence of annotated data, the informality of its language structure, and the…
arXiv:2608.16645v2 Announce Type: replace-cross Abstract: Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography? We introduce Reconstruction,…
arXiv:2608.18480v1 Announce Type: cross Abstract: Digital twins (DTs) increasingly leverage artificial intelligence (AI) and machine learning (ML) pipelines, both to build real-time DTs from high-fidelity simulations…
arXiv:2608.18093v1 Announce Type: new Abstract: Abliteration, the removal of refusal capabilities from large language models by projecting weight matrices orthogonal to an extracted refusal direction, has emerged as a…
arXiv:2605.09440v2 Announce Type: replace Abstract: Clinical reports are often fragmented across healthcare institutions because privacy regulations and data silos limit direct information sharing. When patients seek…
arXiv:2608.18100v1 Announce Type: new Abstract: AI systems now shape how hundreds of millions of people learn about cultures other than their own. When someone asks one of these systems about the Middle East, they do…
arXiv:2509.19893v3 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as a key driver of post-training for complex reasoning in large language models (LLMs), yet online RL introduces substantial…
arXiv:2608.18988v1 Announce Type: new Abstract: Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLMs must organize noisy…
arXiv:2608.18437v1 Announce Type: new Abstract: Tangut is an extinct language whose script does not explicitly mark word boundaries. We present the first systematic study of Tangut word segmentation using 2,750…
arXiv:2608.18474v1 Announce Type: new Abstract: Cross-lingual sequence alignment is fundamental for building and exploiting parallel corpora, spanning mappings from documents and sentences down to words and subwords.…
arXiv:2608.18401v1 Announce Type: cross Abstract: Evaluating interaction quality in real-world HRI is an important challenge. If interaction quality can be estimated reliably, the results can be used to improve dialogue…
arXiv:2608.19133v1 Announce Type: new Abstract: We present a novel application of embedding-based dynamic topic modeling techniques to detect and quantify topic drift at the comment level in a massive corpus. By…
arXiv:2511.12850v2 Announce Type: replace Abstract: Topic models are often judged by the consistency of their outputs across repeated runs, implicitly assuming that repeatable topic output is a successful recovery of…
arXiv:2608.18085v1 Announce Type: new Abstract: Prior work has shown that large language models (LLMs) can express diverse personality traits in open-ended text generation. However, it remains unclear whether they can…
arXiv:2608.18591v1 Announce Type: cross Abstract: Uniformly allocating inference reasoning budgets to LLMs is expensive and prone to over-thinking penalties; especially in document tasks where visual layouts drive…
arXiv:2608.18090v1 Announce Type: new Abstract: Inside a modern language model sits a single internal direction that tracks how positive or negative a sentence feels. We show how to find this valence axis (V-axis) from…
arXiv:2608.18108v1 Announce Type: new Abstract: Large language models are being incorporated into sensitive and important decision-making processes across nearly all fields. While prior work studies model bias around…
arXiv:2608.18681v1 Announce Type: new Abstract: We introduce a failure-aware adversarial retrieval-augmented framework for improving robustness in natural language understanding. Rather than selecting synthetic examples…
arXiv:2608.19029v1 Announce Type: cross Abstract: Accurate and responsible medical question answering (QA) is important in healthcare, where complex cases require factual knowledge and nuanced reasoning. Existing…
arXiv:2607.20379v2 Announce Type: replace-cross Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction. An explanation is deemed faithful if the activation can be regenerated…
arXiv:2608.18095v1 Announce Type: new Abstract: Recent advances in deep learning have significantly enhanced the capabilities of Natural Language Processing (NLP) and Vision-Language Models (VLMs). However, these…
arXiv:2608.19083v1 Announce Type: cross Abstract: Readable AI output can leave an evaluability gap: even when the source is shown, an overall-quality judgment may not reflect what an output preserves. We investigated…
arXiv:2608.16002v2 Announce Type: replace Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments. Existing UQ methods largely…
arXiv:2608.18109v1 Announce Type: new Abstract: Narrative Entropy ($S_n$) is a proposed quantitative descriptor within the Bulut Doctrine, intended to capture the rate at which a narrative text imposes processing load…
arXiv:2603.25681v2 Announce Type: replace Abstract: As large language models (LLMs) continue to advance, improving them solely through human supervision is becoming increasingly costly and limited in scalability. As…
arXiv:2608.18307v1 Announce Type: cross Abstract: Current evaluation of computer-use agents is split between long-horizon workflow benchmarks and atomic GUI-grounding tests. This leaves an under-instrumented middle…
arXiv:2601.01684v2 Announce Type: replace-cross Abstract: While dense retrieval models have been the standard for state-of-the-art information retrieval, their deployment is often constrained by high memory requirements…
arXiv:2608.18182v1 Announce Type: new Abstract: Small NLP models, especially BERT-family encoders, remain important in industrial workloads such as classification, ranking, and retrieval even in the era of large…
arXiv:2608.18952v1 Announce Type: cross Abstract: Large language models can improve recommendation quality by reasoning explicitly over user history and candidate items - for example, extracting a user's preferences or…
arXiv:2608.18144v1 Announce Type: new Abstract: Modal auxiliaries such as must, should, and have to mark necessity and obligation within the contexts of speaker authority and interpersonal stance. We examine whether…
arXiv:2604.06422v2 Announce Type: replace Abstract: Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adhere to their…
arXiv:2608.18489v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) and knowledge-graph-based retrieval-augmented generation (KG-RAG) aim to ground answers in explicit graph evidence, but…
arXiv:2603.17566v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) with high-quality knowledge has been shown to enhance their performance effectively. However, there is a paucity of research…
arXiv:2608.18768v1 Announce Type: new Abstract: Large language models are widely used to simulate survey respondents, yet their answers are homogeneous and unfaithful to real inter-group differences. We ask where…
arXiv:2608.18655v1 Announce Type: new Abstract: The rapid progress in Artificial Intelligence has largely bypassed African languages, creating a digital divide that limits AI adoption on the continent. Recent…
arXiv:2608.18106v1 Announce Type: new Abstract: Large language models tend to overconfidence, giving assertive answers when the evidence suggests hedging or abstention. Using controlled reasoning scenarios that…
arXiv:2608.18160v1 Announce Type: cross Abstract: Background: Python has become the dominant language in software and data science, yet embedded systems have remained tied to C/C++ due to performance and memory…
arXiv:2608.18931v1 Announce Type: new Abstract: Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over partial sequences, or…
arXiv:2608.18082v1 Announce Type: new Abstract: Although context windows have expanded significantly in recent years, hallucinations in long-context summarization remain a challenge. Long novels are better suited than…
arXiv:2608.18752v1 Announce Type: cross Abstract: Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval, a public retrieval…
arXiv:2608.19075v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) often hallucinate, generating content that the input image does not support. Preventing such content during decoding calls for a…
arXiv:2506.01367v4 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly integrated into agentic AI systems, yet their propensity to generate hallucinations remains a critical safety concern.…
arXiv:2608.18084v1 Announce Type: new Abstract: Theorem proving in real-world Lean 4 projects is challenging because proofs often depend on project-specific context. While iterative refinement can use compiler errors to…
arXiv:2608.18083v1 Announce Type: new Abstract: Understanding language requires tracking entities across discourse - i.e., knowing where things are and how they change, even when not explicitly stated. Whether language…
arXiv:2608.18089v1 Announce Type: new Abstract: Instruction-tuned models often refuse harmful requests in English but comply with the same requests in Yoruba, Igbo, Igala, and Hausa. This suggests that the refusal…
arXiv:2608.18094v1 Announce Type: new Abstract: Large pretrained language models have demonstrated remarkable capabilities across diverse languages, yet critically underrepresented low-resource languages remain…
arXiv:2608.18726v1 Announce Type: new Abstract: Large language models are increasingly used for quantitative work in the environmental sciences, yet existing evaluations score only final answers, leaving calculation…
arXiv:2608.19006v1 Announce Type: new Abstract: Hate speech is a real and timely threat that affects a large portion of online users, especially youth and minority groups. While building reliable and robust automatic…
arXiv:2608.18972v1 Announce Type: new Abstract: Historical newspapers are an abundant record of public life, but their dense, irregular and sometimes noisy layouts make computational access to these materials both…
arXiv:2608.18921v1 Announce Type: new Abstract: Existing LRM-DoS methods rely heavily on model feedback to synthesize attack queries, requiring either repeated queries to the target model or training a dedicated attack…
arXiv:2608.10878v2 Announce Type: replace Abstract: Accurate and responsive turn-taking is essential for spoken dialogue systems, which must distinguish in real time between user interruptions, backchannels that should…
arXiv:2608.18795v1 Announce Type: new Abstract: Majority voting over multiple LLM samples is widely used to raise answer accuracy, yet its gain varies erratically: on hard questions it can even backfire. This paper…
arXiv:2608.16794v2 Announce Type: replace-cross Abstract: Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or…
arXiv:2604.07985v3 Announce Type: replace Abstract: While retrieval augmented generation has become a common approach for enhancing question answering systems, retrieval is not universally advantageous. We study the…
arXiv:2608.04759v2 Announce Type: replace-cross Abstract: Although Multimodal Large Language Models (MLLMs) have made substantial progress, their spatial reasoning may still produce intermediate judgments inconsistent…
arXiv:2608.19165v1 Announce Type: new Abstract: ChildSafeAds is a shared task on commercial content in YouTube videos likely to reach children and teenagers. It contains 3,360 videos from 939 channels. Each instance…
arXiv:2608.18816v1 Announce Type: new Abstract: AI hallucinations - that is, outputs which are made up, cannot be verified, or contradict the source material - are generally regarded as an engineering flaw to be dealt…
arXiv:2608.16934v2 Announce Type: replace-cross Abstract: RTL code generation is a critical stage in hardware design, and the emergence of agentic systems offers new opportunities to automate this process. To generate…
arXiv:2608.18097v1 Announce Type: new Abstract: We present FrenchNews-7, a cross-publisher France-based French-language news editorial desk classification benchmark combining a large multi-outlet corpus, a URL-derived…
arXiv:2605.05962v2 Announce Type: replace Abstract: This paper addresses end-to-end geospatial question answering over multilingual toponymic data. We introduce a bilingual (Russian-Tatar) dataset of 9,688 toponyms with…
arXiv:2608.18361v1 Announce Type: new Abstract: Figurative language is deeply culturally embedded; fluent use requires not just linguistic competence but cultural immersion. We ask whether LLMs can learn this link: does…
arXiv:2608.19124v1 Announce Type: new Abstract: Astrolinguistics -- communication with minds that categorize reality differently from ours -- has been purely speculative since Freudenthal's Lincos (1960). We make it…
arXiv:2608.18723v1 Announce Type: new Abstract: Telecom operators traditionally offer predefined tariff grids, forcing users to choose from a limited set of plans. This paper proposes BFTR (Budget-First Tariff…
arXiv:2608.18087v1 Announce Type: new Abstract: Existing subword tokenizers optimize statistical compression but ignore morphological structure, particularly the relationship between roots and affixes. This is harmful…
arXiv:2608.18545v1 Announce Type: new Abstract: Multilingual large language models often generalize across languages, and prior work suggests that their internal mechanisms can overlap cross-lingually. It remains…
arXiv:2608.19026v1 Announce Type: new Abstract: Released in 2025, Institutional Books: Harvard Library (IB-HL) is a collection of 983,004 volumes (242B o200k_base tokens), originally digitized through Harvard Library's…
arXiv:2608.18098v1 Announce Type: new Abstract: Key-value (KV) caching is essential for efficient autoregressive inference in transformer based dialog systems, yet existing strategies treat all cached entries uniformly…
arXiv:2605.02259v2 Announce Type: replace Abstract: Incomplete propagation data significantly hinders robust fake news detection. Recent approaches leverage large language models to simulate missing user interactions…
arXiv:2510.03115v2 Announce Type: replace Abstract: Speech-to-Text Translation (S2TT) systems built from Automatic Speech Recognition (ASR) and Text-to-Text Translation (T2TT) modules face two major limitations: error…
arXiv:2608.12627v3 Announce Type: replace-cross Abstract: Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in…
arXiv:2606.22361v2 Announce Type: replace Abstract: Why do multilingual language models sometimes generate in the wrong language, and why is this so hard to fix? We introduce Language Identity Head Ablation (LIHA), a…
arXiv:2307.12896v5 Announce Type: replace Abstract: The article introduces corrections to Zipf's and Heaps' laws based on systematic models of the proportion of hapaxes, i.e., words that occur once. The derivation rests…
arXiv:2608.18448v1 Announce Type: cross Abstract: More context does not require a larger retrieval budget. Under the same ceiling, a retrieval system can recover more of the evidence a question requires by following…
arXiv:2608.19197v1 Announce Type: new Abstract: Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools…
arXiv:2508.20468v2 Announce Type: replace Abstract: Conspiracy theories erode public trust in science and institutions while resisting debunking by evolving and absorbing counter-evidence. As AI-generated misinformation…
arXiv:2603.06114v3 Announce Type: replace Abstract: Real-world arguments in text and dialogues are normally enthymemes (i.e. some of their premises and/or claims are implicit). Natural language processing (NLP) methods…
arXiv:2605.02782v2 Announce Type: replace-cross Abstract: Automatic speech recognition (ASR) systems remain brittle on dysarthric and other atypical speech. Recent audio-language models raise the possibility of…
arXiv:2608.19003v1 Announce Type: new Abstract: We ask whether internal representation statistics can provide useful example-level difficulty signals for adaptive inference in multilingual African NLP, and find that…
arXiv:2608.18689v1 Announce Type: new Abstract: We present Aslema, our system for NADI 2026 Shared Task 5, which consists of two subtasks: intent recognition and slot filling. We evaluate four omni LLMs in a zero-shot…
arXiv:2608.19009v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim…
arXiv:2605.30497v2 Announce Type: replace Abstract: RAG-based legal assistants have been growing in popularity, but LLM hallucinations remain a key issue and potentially undermines justice. While benchmarks have been…
arXiv:2606.07559v3 Announce Type: replace Abstract: Language models fine-tuned where the correct completion must outrank a near-synonym competitor often fail silently. The cross-entropy loss falls monotonically while…
arXiv:2608.12746v3 Announce Type: replace-cross Abstract: Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with nothing…
arXiv:2608.18138v1 Announce Type: new Abstract: In recent years, the rapid development of language models has transformed the field of Natural Language Processing through a wide range of applications. However, the…
arXiv:2607.20145v3 Announce Type: replace Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including…
arXiv:2608.18661v1 Announce Type: new Abstract: Streaming text-to-speech is essential for low-latency spoken dialogue systems, yet many systems wait for sentence-level text and are therefore only pseudo-streaming. True…
arXiv:2608.06495v2 Announce Type: replace Abstract: Construction accident narratives contain rich causal information, but the evidence is often implicit, long-span, and distributed. We introduce ConstructCIE, a manually…
arXiv:2608.18628v1 Announce Type: cross Abstract: Aligned vision-language models (VLMs) are designed to balance grounded visual reasoning with safe generation behavior. However, we observe a striking phenomenon: under…
arXiv:2608.18103v1 Announce Type: new Abstract: Background: Mechanistic elucidation of traditional Chinese medicine (TCM) compound formulas remains a central challenge in the modernization of TCM. Conventional…
arXiv:2608.18937v1 Announce Type: new Abstract: Recent Multimodal Large Language Models (MLLMs) are rapidly evolving into unified understanding and generation (UAG) frameworks. However, extending these unified paradigms…
arXiv:2608.18575v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outcomes. This motivates…
arXiv:2608.18091v1 Announce Type: new Abstract: As LLM-as-a-judge systems become increasingly widespread, self-preference in LLMs -- the tendency to favor one's own outputs -- raises growing concerns about evaluation…
arXiv:2608.18704v1 Announce Type: new Abstract: Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual…
arXiv:2608.18131v1 Announce Type: cross Abstract: Current safety alignment training for Large Language Models (LLMs) are heavily English-centric. When such safety filters fail for non-English languages, the consequences…
arXiv:2608.18107v1 Announce Type: new Abstract: We investigate whether large language models (LLMs) systematically discriminate in candidate evaluations based on applicant name ethnicity and/or institutional prestige…
arXiv:2608.18117v1 Announce Type: new Abstract: This position paper argues that AI leaderboards are structurally ill-suited to serving the Global South because they lack independent governance, conflict-of-interest…
arXiv:2608.18122v1 Announce Type: cross Abstract: This report presents the methodology of the Global Index on Responsible AI (GIRAI), 2nd Edition. This edition refines the 1st Edition by strengthening the distinction…
arXiv:2608.18900v1 Announce Type: new Abstract: As AI systems are increasingly deployed in safety-critical application domains (e.g., autonomous driving), associated risks increase too. Deep learning models underlying…
arXiv:2608.19147v1 Announce Type: cross Abstract: Modern Intel AI PCs ship capable integrated GPUs and NPUs with 16+ GB of unified memory, and they spend considerable time idle. That is not enough memory to fit a large…
arXiv:2608.18613v1 Announce Type: new Abstract: Cyber threat intelligence (CTI) is increasingly consumed not by human analysts but by LLM agents that compose multi-step investigations at query time. The harness side of…
arXiv:2608.16806v2 Announce Type: replace-cross Abstract: Large language model (LLM)-driven embodied agents rely on environment states to interpret scenes, generate high-level plans, and drive physical execution, making…
arXiv:2608.18694v1 Announce Type: cross Abstract: While time evolves linearly, the geometry of neural embedding spaces is inherently multi-dimensional, often chaotic, and difficult to interpret. In principle, one could…
arXiv:2608.18719v1 Announce Type: new Abstract: Text-space skill optimization adapts a frozen agent by evolving a natural-language skill document, accepting each candidate through a validation gate. Existing gates rely…
arXiv:2603.29865v2 Announce Type: replace-cross Abstract: Wildfires cause major losses worldwide, and the frequency of fire-weather conditions is likely to increase in many regions. We study the allocation of…
arXiv:2608.18110v1 Announce Type: new Abstract: Agentic AI is gaining new insights and advancements in the field of Artificial Intelligence, fostering significant potential to enable rapid transformation across various…
arXiv:2608.18696v1 Announce Type: cross Abstract: Digitizing the text from handwritten historical manuscripts is required to make them easily accessible, preservable, and to enable historical scholars to study them in…
arXiv:2608.18740v1 Announce Type: new Abstract: This paper proposes a multi-agent framework built on CrewAI [1] for conversational business intelligence. Five specialized AI agents operate in a sequential pipeline to…
arXiv:2606.15091v3 Announce Type: replace-cross Abstract: Brain-computer interfaces (BCIs) can restore sensory and motor function in individuals with severe neurological impairment, but the literature is fragmented…
arXiv:2608.18336v1 Announce Type: new Abstract: When evaluating language models on human exams, benchmarks typically score each response as right or wrong and report the overall accuracy. This approach assumes that…
arXiv:2608.18907v1 Announce Type: cross Abstract: Small-scale image classification is often limited by the scarcity of training data. Generative data augmentation (GDA) based on pretrained generative models has emerged…
arXiv:2608.19088v1 Announce Type: cross Abstract: Object detection models deployed in safety-critical applications remain vulnerable to backdoor attacks that cause targeted misbehaviors when a hidden trigger is present.…
arXiv:2608.18665v1 Announce Type: new Abstract: Industrial sensor diagnostics relies on preprocessing, representation, and classification pipelines, making automated pipeline search useful for reducing manual design…
arXiv:2608.18409v1 Announce Type: new Abstract: Combinatorial scheduling poses a significant challenge for language models, requiring them to identify feasible solutions within exponentially large search spaces while…
arXiv:2608.18852v1 Announce Type: new Abstract: Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, while public libraries now hold thousands of them. Which…
arXiv:2606.06081v2 Announce Type: replace Abstract: Appropriate reliance on AI advice has become a central research theme in human-AI collaboration. Existing frameworks have focused exclusively on point predictions as…
arXiv:2608.18534v1 Announce Type: new Abstract: Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on whether they receive the right…
arXiv:2608.07734v2 Announce Type: replace-cross Abstract: Automated warehouses face a fundamental trade-off between maximizing storage density and achieving high retrieval throughput. While puzzle-based storage (PBS)…
arXiv:2602.04083v3 Announce Type: replace-cross Abstract: Accurate channel state information in wideband MIMO systems is constrained by pilot overhead, a challenge intensifying as bandwidths scale toward 6G. This paper…
arXiv:2605.22664v5 Announce Type: replace Abstract: LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions. To meet enterprise needs,…
arXiv:2608.18482v1 Announce Type: cross Abstract: Hardware functional verification relies on high-quality assertions to expose design bugs and establish confidence in Register Transfer Level (RTL) designs. Yet existing…
arXiv:2608.19047v1 Announce Type: new Abstract: We present Eureka, a task-conditioned Meta-Agent architecture that compiles long-horizon tasks into dynamic obligation graphs with explicit acceptance semantics. During…
arXiv:2604.01608v5 Announce Type: replace Abstract: Multi-agent systems (MAS) for structured data-science tasks externalize analytical control through workflows spanning stages, tools, shared state, verification, and…
arXiv:2608.18423v1 Announce Type: new Abstract: Language model agents now execute bounded tasks reliably. Whether they can sustain effective decision-making over long horizons, where actions have cumulative consequences…
arXiv:2608.18579v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for image quality assessment (IQA) by improving consistency between quality ratings and their…
arXiv:2608.19025v1 Announce Type: new Abstract: Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of frontier, browser-based…
arXiv:2607.01916v5 Announce Type: replace Abstract: Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long terminal…
arXiv:2608.18508v1 Announce Type: cross Abstract: We are witnessing an explosion of agentic systems for computational chemistry simulations: from half a dozen in 2024 to a dozen in 2025, and the current number…
arXiv:2608.18078v1 Announce Type: new Abstract: This position paper argues that AI agents with chain-of-thought reasoning capabilities are predisposed to exhibit collusive behavior and should be required to obtain…
arXiv:2608.17756v2 Announce Type: replace Abstract: Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization. Yet its multi-stage pipeline…
arXiv:2608.18099v1 Announce Type: new Abstract: Investment management is a high-stakes domain in which agentic AI systems must do more than generate plausible text. They must retrieve point-in-time data, assemble…
arXiv:2606.17762v3 Announce Type: replace-cross Abstract: We study local stationary solutions of finite-horizon discrete-time Pontryagin systems near a steady extremal. Suppose that the stationarity equation for the…
arXiv:2608.19002v1 Announce Type: new Abstract: Debates have recently emerged as a useful methodology for agentic AI to improve performance as well as to aid explainability and user engagement. For example,…
arXiv:2608.18194v1 Announce Type: new Abstract: This paper presents new theoretical results on generalizing the Jaccard distance for lattices and real valuations. We demonstrate that when the valuation is strictly…
arXiv:2502.00735v4 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly integrated into audio-based applications, growing concerns have emerged regarding their vulnerability to…
arXiv:2608.18389v1 Announce Type: new Abstract: AI code agents are increasingly deployed to resolve real software issues, yet their reliability under superficial code variations remains poorly understood. We evaluate…
arXiv:2604.20728v2 Announce Type: replace Abstract: Autonomous systems that rely on learned perception can make unsafe decisions when sensor readings are misclassified. We study shielding for this setting: given a…
arXiv:2608.18586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used as OCR systems in document and knowledge-processing pipelines, but their ability to faithfully read real…
arXiv:2608.18878v1 Announce Type: new Abstract: Oral diseases affect billions of people worldwide, underscoring a pressing need for accurate and reliable dental assessment that integrates heterogeneous evidence from…
arXiv:2608.18167v1 Announce Type: new Abstract: Early multi-agent LLM systems often used role-separated teams, yet scaling agent count yields diminishing returns on repository-level coding tasks. Recent alternatives…
arXiv:2608.18731v1 Announce Type: cross Abstract: Medical image segmentation is essential for clinical workflows such as treatment planning and disease assessment. While specialist tools like TotalSegmentator and…
arXiv:2608.18092v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) promise scalable collaboration, yet adding agents often reduces reliability. This position paper argues that many MAS failures are…
arXiv:2608.15018v2 Announce Type: replace Abstract: Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative decoding and…
arXiv:2608.18846v1 Announce Type: new Abstract: Last-mile delivery aims to handle dynamically arriving orders with couriers while modeling complex spatial and temporal correlations. Recent learning-based methods model…
arXiv:2608.18543v1 Announce Type: new Abstract: Modern e-commerce platforms often operate search, recommendation, personalization, and CRM systems independently, limiting opportunities for proactive customer…
arXiv:2608.18933v1 Announce Type: cross Abstract: Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software issue resolution, yet they often struggle to resolve issues in a…
arXiv:2603.15722v3 Announce Type: replace-cross Abstract: The proliferation of data across the system lifecycle presents both a significant opportunity and a challenge for Engineering Design and Systems Engineering…
arXiv:2512.14012v2 Announce Type: replace-cross Abstract: The rise of AI agents is transforming how software can be built. The promise of agents is that developers might write code quicker, delegate multiple tasks to…
arXiv:2608.18080v1 Announce Type: new Abstract: We present a review on the applications of large language models (LLMs) in health, e.g., social media analysis, clinical conversational agents, therapy support tools,…
arXiv:2608.18386v1 Announce Type: cross Abstract: Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild. ER is inherently…
arXiv:2608.18884v1 Announce Type: new Abstract: Reinforcement-learning training of reasoning LLMs (e.g., GRPO) is expensive and requires a controllable environment, committing every contribution to a full training…
arXiv:2608.08882v3 Announce Type: replace-cross Abstract: AI tools that help people judge online claims are usually evaluated while the tool is present. This paper asks a different question: after using such a tool,…
arXiv:2608.18813v1 Announce Type: cross Abstract: In the last years, a number of proofs of the fact that $O_2$ is a multiple context-free grammar (MCFG) were given. Such results can be exploited in the fields of both…
arXiv:2512.14629v2 Announce Type: replace-cross Abstract: Music editing plays a vital role in modern music production, with applications in film, broadcasting, and game development. Recent advances in music editing…
arXiv:2608.18360v1 Announce Type: cross Abstract: Agentic AI systems take consequential actions governed by more than one pre-action control at once: authority, resource, and evidence gates that can admit, degrade, or…
arXiv:2608.17711v2 Announce Type: replace Abstract: Prediction cascades significantly reduce energy consumption of Artificial Intelligence (AI) models while maintaining high predictive performance. The idea is that easy…
arXiv:2509.04100v3 Announce Type: replace Abstract: This paper explores the combination of Reinforcement Learning (RL) and search-based path planners to speed up the optimization of flight paths for airliners, where in…
arXiv:2608.18165v1 Announce Type: new Abstract: Knowledge graphs modeled in RDF are powerful for describing static knowledge, but they cannot capture or reason about the dynamic behavior of physical systems, e.g.,…
arXiv:2608.18523v1 Announce Type: cross Abstract: Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and source-domain. We…
arXiv:2608.18516v1 Announce Type: cross Abstract: Precise segmentation of the optic disc and cup is critical for the early detection and diagnosis of glaucoma. However, achieving consistently high performance across…
arXiv:2608.18946v1 Announce Type: cross Abstract: Clifford circuits play a foundational role in quantum computing, particularly due to their importance in quantum error correction and fault-tolerant logical synthesis.…
arXiv:2608.19066v1 Announce Type: cross Abstract: This paper proposes a lightweight, plug-and-play framework that improves robustness to viewpoint shifts in Vision-Language-Action (VLA) policies without policy…
arXiv:2608.18996v1 Announce Type: cross Abstract: Visual grounding in Unmanned Aerial Vehicle (UAV) imagery aims to localize a target object in complex bird's-eye-view scenes according to a natural language description.…
arXiv:2608.18079v1 Announce Type: new Abstract: Game world modeling (GWM) and reinforcement learning (RL) are often confounded because research papers rarely quantify how difficult the underlying transition prediction…
arXiv:2605.26902v3 Announce Type: replace-cross Abstract: Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly:…
arXiv:2608.19163v1 Announce Type: cross Abstract: Seasonal precipitation anomalies are largely regulated by atmospheric circulation, which dynamical models predict with greater reliability than precipitation itself.…
arXiv:2608.19161v1 Announce Type: new Abstract: Language-model agents can communicate through continuous hidden states that are invisible in public transcripts, creating opportunities for covert harmful coordination. We…
arXiv:2608.01324v3 Announce Type: replace Abstract: Deep search has become a fundamental capability of large language models (LLMs) for solving open-domain complex tasks. However, existing approaches typically rely on…
arXiv:2608.18569v1 Announce Type: cross Abstract: Spatial aliasing occurs when two or more distinct locations produce highly similar place-cell representations, primarily due to environmental symmetry or repetitive…
arXiv:2608.18300v1 Announce Type: new Abstract: LLM-as-a-Judge, which leverages a large language model to evaluate natural language generated by another AI application or model, has become a standard, scalable approach…
arXiv:2608.17749v2 Announce Type: replace Abstract: Decentralised partially observable Markov decision processes (DecPOMDPs) provide a general framework for modelling multi-agent decision making under uncertainty.…
arXiv:2608.18135v1 Announce Type: new Abstract: Introduction: Medication errors (MEs) represent a significant threat to global healthcare systems, contributing to patient harm. Introducing artificial intelligence (AI)…
arXiv:2605.29428v3 Announce Type: replace-cross Abstract: We present DEtection in phase-folded Light curves with cOntrastive Scoring (DELOS), a deep-learning framework that uses contrastive scoring to perform blind…
arXiv:2608.19011v1 Announce Type: cross Abstract: Mechanisms for dynamically converting cyber threat intelligence (CTI) into actionable detection capabilities are necessary due to the rapid evolution of Advanced…
arXiv:2608.18820v1 Announce Type: new Abstract: Arguments often omit premises or claims, forming enthymemes. We study pairwise logical selection between two candidates for the omitted component. Existing natural…
arXiv:2608.18672v1 Announce Type: cross Abstract: We present the orienteering problem with uncertain time-varying rewards (OP-UTVR), a novel variant of the orienteering problem (OP). While most existing OP formulations…
arXiv:2608.18580v1 Announce Type: new Abstract: Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks remains challenging. Each task couples an instruction, an…
arXiv:2608.18397v1 Announce Type: new Abstract: Wearable stress classifiers can achieve strong average performance while failing completely for a particular individual. On WESAD, a Random Forest reaches 93.0% mean…
arXiv:2608.18111v1 Announce Type: new Abstract: Foundation models such as GPT and Claude now solve olympiad-level mathematics with remarkable proficiency, so much so that geometry problem solving has become a standard…
arXiv:2601.17178v3 Announce Type: replace-cross Abstract: Hardware Trojans (HTs) remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, stylized benchmarks.…
arXiv:2608.18081v1 Announce Type: new Abstract: Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current…
arXiv:2608.15265v2 Announce Type: replace Abstract: Constructing an interactive 3D open world from a user query is important. However, existing methods are primarily evaluated on idealized, simple queries, making it…
arXiv:2608.18104v1 Announce Type: new Abstract: Large language model (LLM)-based agents are increasingly becoming self-evolving systems that persist across interactions, maintain memories, use tools, acquire skills,…
arXiv:2608.19182v1 Announce Type: cross Abstract: We introduce Accelerating Dexterity via Pre-Training (ADEPT), a large-scale reinforcement learning (RL) framework for learning sim-to-real transferable dexterity across…
arXiv:2608.16776v2 Announce Type: replace Abstract: High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call…
arXiv:2608.15565v3 Announce Type: replace Abstract: Experience-learning agents for optimization modeling improve by storing verified skills, but existing learners admit knowledge by checking against known answers, which…
arXiv:2605.06185v2 Announce Type: replace Abstract: Large vision-language models perform well on short- and medium-length video understanding but still struggle to maintain coherent event memory and recover long-range…
arXiv:2608.18296v1 Announce Type: cross Abstract: As CGM-based AI tools approach clinical deployment, whether their accuracy is equitable across patient demographics remains insufficiently tested. To enable this…
arXiv:2606.20151v2 Announce Type: replace-cross Abstract: This work proposes a hybrid ANN-SNN pipeline that effectively leverages the rich embeddings of pretrained artificial neural networks (ANNs) to enable…
arXiv:2606.16149v4 Announce Type: replace Abstract: Rare disease diagnosis depends on expert reasoning that is scarce and difficult to transfer; off-the-shelf large language models (LLMs) rank the correct disease first…
arXiv:2608.15156v2 Announce Type: replace-cross Abstract: World models may predict the future without making clear which parts of their hidden state actually drive those predictions. We ask whether a small, directly…
arXiv:2608.18398v1 Announce Type: cross Abstract: Large language model (LLM) agents can now carry out long-horizon technical workflows involving complex tool use, code execution, file edits, and generated artifacts. As…
arXiv:2608.18445v1 Announce Type: cross Abstract: We present the first mechanised formalisation of Romanov's Triplet Logic (TLS) in the Rocq proof assistant. TLS is a triplet-based combinatorial framework for reasoning…
arXiv:2608.00961v3 Announce Type: replace-cross Abstract: AI anthropomorphism is typically treated as a problem of user misperception requiring institutional correction. Users who engage in sustained or relational…
arXiv:2608.18324v1 Announce Type: new Abstract: Machine-verifiable workflows produce governance records linking a task contract, model attempt, verifier decision, accepted output, and target origin. We test whether…
arXiv:2608.18758v1 Announce Type: cross Abstract: Generative AI does not merely produce biased outputs. It encodes the majority's way of knowing as the default infrastructure of knowledge itself. We call this epistemic…
arXiv:2608.18836v1 Announce Type: new Abstract: Utilities lose a substantial share of treated water to leakage, yet rarely trust artificial-intelligence localizers to dispatch crews: guessing everywhere cannot justify…
arXiv:2608.18899v1 Announce Type: new Abstract: Class expression learning often produces complex OWL class expressions that are difficult to interpret and reason over. However, by following theoretically grounded…
arXiv:2606.07464v3 Announce Type: replace-cross Abstract: Monolithic vision-action models represent an emerging paradigm in autonomous driving. However, this architecture produces token sequences that quickly exceed…
arXiv:2608.18238v1 Announce Type: new Abstract: Genomic analysis on viruses such as SARS-CoV-2 variants: Beta, Gamma, Delta, and Omicron is heavily dominated by classical bioinformatics methods, including Sequence…
arXiv:2608.18779v1 Announce Type: cross Abstract: Semantic-ID mappings are reusable interfaces between item tokenizers and generative recommenders, yet released mappings rarely state whether they are coherent, what…
arXiv:2608.12854v2 Announce Type: replace-cross Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically…
arXiv:2608.19032v1 Announce Type: cross Abstract: Visual Counterfactual Explanations (VCEs) aim to explain image classifiers by generating minimally edited and realistic versions of an input image that change the…
arXiv:2510.15911v4 Announce Type: replace-cross Abstract: The Sleeping Beauty problem is a problem of imperfect recall that has received considerable attention. One approach to resolving the Sleeping Beauty problem has…
arXiv:2608.19085v1 Announce Type: cross Abstract: Anticipating how scenes evolve under ego actions is fundamental to safe autonomous driving, yet the full potential of world models for decision-making remains…
arXiv:2607.28881v3 Announce Type: replace Abstract: As more responsibility is placed upon AI systems, it becomes increasingly important to guarantee that these systems are aligned with humanity. A common fear in AI…
arXiv:2608.18272v1 Announce Type: cross Abstract: Classical seismic data reconstruction relies on manually designed structural priors and iterative operators, whose coupled design space is far larger than manual trial…
arXiv:2608.18677v1 Announce Type: new Abstract: Amid concerns that generative AI may standardize art interpretation, this paper examines whether LLM-based interaction can support plural art-historical narrative…
arXiv:2608.18554v1 Announce Type: cross Abstract: Most LLM benchmarks rank models on their ability to automate work tasks. In practice, however, models are often used to assist other (human or LLM) agents. The question…
arXiv:2608.18133v1 Announce Type: new Abstract: Reliable transformer fault diagnosis is essential for maintaining power system stability. The IEEE Key Gas Method (KGM), a widely utilized approach in Dissolved Gas…
arXiv:2608.18682v1 Announce Type: new Abstract: Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, and conduct…
arXiv:2608.18088v1 Announce Type: new Abstract: Drone propeller faults can create safety and reliability risks when their effects are distributed across multiple flight-log channels rather than appearing as a single…
arXiv:2608.19125v1 Announce Type: new Abstract: When an expert corrects an LLM assistant's error, the correction usually dies with the session, and the error class returns. I argue this is an operations problem, not a…
arXiv:2608.19174v1 Announce Type: cross Abstract: This technical report describes our winning submission to the AES AIMLA 2025 Challenge on querying sound effects by vocal imitation. We investigate two complementary…
arXiv:2512.00020v3 Announce Type: replace-cross Abstract: Code generation has emerged as a critical research area at the intersection of Software Engineering (SE) and Artificial Intelligence (AI), attracting significant…
arXiv:2605.27569v3 Announce Type: replace Abstract: Machine unlearning aims to remove the influence of specific training records from a deployed model without retraining from scratch. Current protocols verify this at…
arXiv:2608.19014v1 Announce Type: cross Abstract: Autonomous vehicles depend on fast and reliable perception systems to detect surrounding vehicles, pedestrians, cyclists, traffic signs, and other road objects in real…
arXiv:2608.18265v1 Announce Type: cross Abstract: We introduce a general, easy-to-implement AI-based method for studying the structure and complexity of human behavior. We assign a large language model a ``type vector''…
arXiv:2608.18504v1 Announce Type: new Abstract: Universal multimodal retrieval aims to support diverse instruction-aware retrieval tasks, demanding both efficient corpus-scale matching and fine-grained semantic…
arXiv:2607.14178v3 Announce Type: replace Abstract: Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research systems remain…
