Daily edition · AI
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
Update the torch-xpu-ops commit to intel/torch-xpu-ops@1a3415: Avoid register spilling in elementwise ops for mixed fp32/bf16/fp16 inputs by adding vectorized type-casting loads Fix group_reduce assert on XPU to avoid…
[Test][XPU] Refactor reuse_ir tests to device-type harness and enable…
This PR is auto-generated nightly by this action. Updates the Metamates merge rule with active team members. Pull Request resolved: #194306 Approved by: https://github.com/pytorchbot
[inductor] Preserve SDPA mask locality in combo-kernel scheduling (#1…
[inductor] Preserve SDPA mask locality in combo-kernel scheduling (#1…
Revert "[Test] Make dynamo test_streams.py device-agnostic for out-of…
Enable eager tests for inductor-unittest - - Enabel more tests in tes…
Summary Add scheduled and manually dispatched Better Benchmark CI on an eight-GPU B200 runner. Run the merged upstream eellison/better-benchmark implementation. Export measured kernel latency and projected model latency…
[inductor] AOTI lite mode: support HigherOrderOperators (user-defined…
[Test] Make dynamo test_streams.py device-agnostic for out-of-tree ba…
Description drafted with an AI assistant, quoted below; I've reviewed the change. LpNormFunctor and lpnorm_cleanup each spell the sum-vs-max predicate twice in mutually inverse forms -- an L0 || L1 || L2 enumeration at…
Description drafted with an AI assistant, quoted below; I've reviewed the change. LpNormFunctor and lpnorm_cleanup each spell the sum-vs-max predicate twice in mutually inverse forms -- an L0 || L1 || L2 enumeration at…
This test cases executes the functional_autograd_benchmark.py, which had CUDA hardcoded as the GPU device. This commit generalizes it to the torch.accelerator API Replace hardcoded cuda references with torch.accelerator…
[Test] Refactor test/test_comparition_utils.py according to accelerat…
[ROCm] Restore preview_unsafeAtomicAdd for ROCm < 6.4 in headeronly (…
_PyThreadState_PushFrame is public in 3.15 (and also renamed from _PyThreadState_BumpFramePointerSlow). Using it directly allows us to remove THP_PyThreadState_BumpFramePointerSlow and its supporing definitions Pull…
[inductor] Disable batch_linear_lhs by default on XPU(fixes Qwen regr…
[inductor] Disable batch_linear_lhs by default on XPU(fixes Qwen regr…
Following the CRCR Onboarding Guide - Step 2, add Isalia20/pytorch-mps-ci to the allowlist at L1. The repository will run MPS tests against upstream PyTorch events on macOS arm64 runners. The relay GitHub App is…
arXiv:2608.19488v1 Announce Type: new Abstract: Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain. Retraining is costly, retraining…
arXiv:2608.19879v1 Announce Type: cross Abstract: This document describes the application of a first order linearised nonlinear repeated measurements approach to the analysis of battery cell ageing profiles generated…
arXiv:2608.20038v1 Announce Type: new Abstract: Artificial intelligence can support cultural heritage and digital humanities through large-scale retrieval and analysis of digitized collections. However, cultural…
arXiv:2602.05541v3 Announce Type: replace-cross Abstract: Matrix multiplication is a fundamental operation in compute-intensive tasks and a key component of modern quantum acceleration frameworks. Here we present a…
arXiv:2608.19232v1 Announce Type: cross Abstract: Spiking point cloud networks usually scan space in a fixed, input-agnostic order, which leaves the most distinctive resource of spiking computation, the temporal…
arXiv:2606.08926v2 Announce Type: replace Abstract: Knowledge graph completion (KGC) models are commonly evaluated using rank-based metrics such as MRR and Hits@K, despite different users often requiring different…
arXiv:2608.19762v1 Announce Type: new Abstract: A minibatch can influence training beyond the update at which it is observed because AdamW stores past gradient information in its optimizer states. We study this delayed…
arXiv:2608.19285v1 Announce Type: cross Abstract: Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing…
arXiv:2608.20202v1 Announce Type: cross Abstract: Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing memory…
arXiv:2608.19688v1 Announce Type: cross Abstract: We develop a geometric framework for learning deterministic and stochastic forced Hamiltonian systems with neural networks. Motivated by the Lagrange-d'Alembert…
arXiv:2608.19632v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) embed governing partial differential equations directly into the training loss, offering a promising alternative to costly CFD…
arXiv:2605.05488v2 Announce Type: replace Abstract: We propose an architecture that augments the Flux Neural Operator (Flux NO), which combines the classical finite volume method (FVM) with neural operators, with…
arXiv:2510.17529v3 Announce Type: replace-cross Abstract: Active Surveillance (AS) is a treatment option for managing low and intermediate-risk prostate cancer (PCa), aiming to avoid overtreatment while monitoring…
arXiv:2512.20872v2 Announce Type: replace-cross Abstract: Function call graphs (FCGs) have emerged as a powerful abstraction for malware detection, capturing the behavioral structure of applications beyond surface-level…
arXiv:2608.19643v1 Announce Type: new Abstract: Self-normalized concentration inequalities are standard tools in bandit and reinforcement-learning analyses. A widely used weighted extension claims an analogous…
arXiv:2608.19584v1 Announce Type: new Abstract: We study landscapes for complex-parameterized networks. Our approach is motivated with an information-theoretic manifold perspective of the parameter and via classical…
arXiv:2608.20169v1 Announce Type: cross Abstract: We present a novel approach to efficient LLM agent harness optimization through adaptive validation task selection. Harness optimization iteratively rewrites the harness…
arXiv:2605.24960v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) faithfulness, i.e., whether CoTs genuinely reflect large language models' (LLM) underlying behavior, is typically evaluated with metrics…
arXiv:2608.19861v1 Announce Type: cross Abstract: Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting…
arXiv:2608.19677v1 Announce Type: cross Abstract: Prefix caching avoids prefill only when a repeated request returns to a server that still holds the prefix KV. Cache-blind balancing disperses that reuse; fixed affinity…
arXiv:2608.20285v1 Announce Type: new Abstract: The causal dynamics of sleep-disordered breathing are complex and vary across patient populations, hindering the development of targeted interventions. We learn dynamic…
arXiv:2608.20061v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures significantly expand model capacity without a proportional increase in computational cost. However, optimizing their…
arXiv:2608.19202v1 Announce Type: cross Abstract: Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed…
arXiv:2608.19568v1 Announce Type: new Abstract: Drafting a new Magic: The Gathering expansion begins before any pick from it has been observed: the complete card list is public, but the draft logs that supervised pick…
arXiv:2608.09276v2 Announce Type: replace-cross Abstract: Planetary geology relies on historical, interpretive reasoning to reconstruct past events from diverse observations. Here, we investigate how far this…
arXiv:2604.06501v2 Announce Type: replace Abstract: Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet, developing…
arXiv:1905.11395v2 Announce Type: replace Abstract: Graph convolution network based approaches have been recently used to model region-wise relationships in region-level prediction problems in urban computing. Each…
arXiv:2608.19693v1 Announce Type: cross Abstract: Sparse keypoint extraction and matching underpin core tasks in geometric computer vision, including structure-from-motion, visual SLAM, augmented reality, and medical…
arXiv:2608.19899v1 Announce Type: cross Abstract: Machine learning (ML) is widely used for the development of ocean colour algorithms, but most studies focus on model parameter training and hyperparameter tuning. The…
arXiv:2608.20326v1 Announce Type: cross Abstract: Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions. Consequently, users lack a reliable signal for deciding when a…
arXiv:2608.19726v1 Announce Type: cross Abstract: The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a…
arXiv:2608.20044v1 Announce Type: new Abstract: Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments. Yet, most existing…
arXiv:2602.17853v2 Announce Type: replace Abstract: Logit adjustment corrects class imbalance using the empirical class prior. We study whether a comparable class-frequency signal can instead be learned from the network…
arXiv:2608.19425v1 Announce Type: cross Abstract: Reliable performance evaluation is a central bottleneck for deploying robot-learning policies in real-world conditions. Real-world testing is faithful but costly and…
arXiv:2505.20894v3 Announce Type: replace Abstract: Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to…
arXiv:2608.19338v1 Announce Type: new Abstract: Mechanistic interpretability seeks quantities that models do not expose directly: represented states, component effects, interactions, and responses to interventions.…
arXiv:2608.19907v1 Announce Type: cross Abstract: This paper presents a Bayesian control framework that integrates spike-based dynamics with probabilistic inference for adaptive control. Bayesian inference is widely…
arXiv:2608.19210v1 Announce Type: new Abstract: This paper focuses on the implementation of a novel supervised Machine Learning model for estimating helicopter weight during takeoff, utilizing extensive datasets from…
arXiv:2608.20047v1 Announce Type: cross Abstract: Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narrow set of quality…
arXiv:2608.19880v1 Announce Type: cross Abstract: LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it…
arXiv:2608.20183v1 Announce Type: new Abstract: Classical information criteria such as the Bayesian Information Criterion (BIC) rely on regularity assumptions that break down for singular models, leading to incorrect…
arXiv:2608.19611v1 Announce Type: cross Abstract: LLM reasoning is stochastic, and so understanding a model requires grappling with the distribution of reasoning chains that it might produce for a given question, i.e.,…
arXiv:2608.19224v1 Announce Type: cross Abstract: Exposure mappings are often assumed to be known in causal spillover analyses. In environmental settings, however, they are typically induced by transport processes that…
arXiv:2602.15648v2 Announce Type: replace Abstract: Inverse design problems are common in engineering and materials science. The forward direction, i.e., computing output quantities from design parameters, typically…
arXiv:2509.05441v4 Announce Type: replace-cross Abstract: Latent generative models compress images into learned embeddings prior to synthesis, and the generation quality critically depends on how faithfully these…
arXiv:2608.19748v1 Announce Type: new Abstract: Inference-time selection methods, such as Best-of-N, improve generation by sampling a pool of candidates and selecting the top-ranked completion according to a reward…
arXiv:2608.19739v1 Announce Type: cross Abstract: Multimodal LLMs can see a document, but they often can't read it reliably. Small text, tables, visual cues, and topological elements still trip them up under direct…
arXiv:2608.19767v1 Announce Type: cross Abstract: Skchange is an open-source Python library for detecting structural changes in time series. It implements modern change detection algorithms within a unified and…
arXiv:2608.20315v1 Announce Type: new Abstract: Predictive models over structured electronic health records (EHRs) remain central to machine learning for healthcare, but few have jointly emphasized quantitative…
arXiv:2607.07382v2 Announce Type: replace Abstract: Fast Radio Burst (FRB) detection increasingly relies on specialized deep learning models that require large task-specific training sets and cannot be redefined without…
arXiv:2608.19994v1 Announce Type: new Abstract: We summarise the outcome of two summer internship projects based at the University of Manchester, focused on the break-even point in terms of environmental sustainability…
arXiv:2608.19323v1 Announce Type: new Abstract: Uncertainty quantification (UQ) is essential for the safe deployment of large language models (LLMs). Existing methods, from verbalized confidence to ones requiring…
arXiv:2606.21900v2 Announce Type: replace-cross Abstract: Continuous authentication for mobile and zero-trust systems requires nonintrusive evidence confirming the enrolled user-device context remains valid after…
arXiv:2605.22950v2 Announce Type: replace-cross Abstract: Score matching is an alternative to maximum likelihood estimation when the normalizing constant is unknown or too costly to evaluate. However, vanilla score…
arXiv:2608.20186v1 Announce Type: new Abstract: Non-invasive decoding of inner speech faces a fundamental data problem: a corpus pairing brain activity with a person's spontaneous inner monologue cannot be collected,…
arXiv:2606.05605v2 Announce Type: replace Abstract: How does a system that merely predicts the world come to distinguish its own causal influence from everything else? We trace this transition in a minimal…
arXiv:2608.20026v1 Announce Type: cross Abstract: Streetscape quality has become a central concern in contemporary urban planning, particularly within the framework of the pedestrian-friendly 15-minute city, where…
arXiv:2608.19377v1 Announce Type: cross Abstract: Bayesian inference via Markov Chain Monte Carlo (MCMC) provides effective parameter estimation, but its real-time application in complex physical systems is hindered by…
arXiv:2506.07459v4 Announce Type: replace Abstract: Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequence-structure…
arXiv:2608.19203v1 Announce Type: cross Abstract: Standard multi-head attention (MHA) gives every head the same full causal context span, although heads can serve different contextual roles. Some heads may rely mainly…
arXiv:2608.19407v1 Announce Type: cross Abstract: Deep Learning models can include billions of parameters or more, making it difficult to explain their internal transformations and outputs. However, explainability is…
arXiv:2608.19389v1 Announce Type: cross Abstract: Automated market makers (AMMs) are a cornerstone of decentralised finance (DeFi). Constant product markets with concentrated liquidity, such as UniswapV3, are now a…
arXiv:2608.15639v2 Announce Type: replace-cross Abstract: \textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients. However, under client…
arXiv:2605.25848v2 Announce Type: replace Abstract: A concept probe is only as reliable as the layer it is taken from. Probing at a fixed late layer, or at the peak of a separation curve, ignores a structural feature of…
arXiv:2608.18936v2 Announce Type: replace Abstract: Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of…
arXiv:1808.08763v3 Announce Type: replace Abstract: In this paper, we prove some convergence results of a special case of optimistic policy iteration algorithm for stochastic shortest path problem. We consider both…
arXiv:2604.01476v3 Announce Type: replace Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically…
arXiv:2608.20337v1 Announce Type: cross Abstract: Accounting for information flow on the path space of trajectories of a nonnegative martingale yields exact variational identities for it, even at arbitrary random times.…
arXiv:2608.18574v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as new tasks are…
arXiv:2608.19885v1 Announce Type: new Abstract: Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one, or defer. We present…
arXiv:2403.15509v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) has been widely used to improve lightweight AI models by transferring soft-label knowledge from a large teacher model to a student…
arXiv:2608.19857v1 Announce Type: new Abstract: For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data. We study whether…
arXiv:2608.20099v1 Announce Type: cross Abstract: LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token…
arXiv:2606.13172v4 Announce Type: replace Abstract: Learned representations are central to modern machine learning, but predictive performance, robustness, uncertainty estimation, and generalization do not by themselves…
arXiv:2401.07468v4 Announce Type: replace Abstract: The proposed model, CarSpeedNet, estimates scalar vehicle speed from a window of three-axis smartphone acceleration, without gyroscope, wheel-odometry, vehicle-bus, or…
arXiv:2608.19760v1 Announce Type: new Abstract: Audited against causal ground truth from executed replay in a single-agent tool environment (ALFWorld), none of the step-level credit signals used to train LLM agents --…
arXiv:2608.19903v1 Announce Type: cross Abstract: In fixed-confidence best-arm identification, proofs often use a union bound across the competing arms. From a multiple-testing point of view this can look puzzling: if…
arXiv:2607.21847v2 Announce Type: replace-cross Abstract: We introduce the distributional determinantal point process (dDPP) as a novel repulsive point process whose atoms are probability distributions rather than…
arXiv:2608.19779v1 Announce Type: cross Abstract: World models provide digital simulacra of the true world, allowing agents to be trained and tested before costly real-world deployment. At each time step, they receive…
arXiv:2607.23287v2 Announce Type: replace-cross Abstract: We introduce a new research area that is called Asymptotics Learning Theory (ALT) and combines optimization with asymptotic analysis. In particular, ALT provides…
arXiv:2607.29530v2 Announce Type: replace Abstract: Identifying reliable Alzheimer's disease (AD) markers typically requires manual, labor-intensive transcription and expert analysis, limiting its scale. We introduce an…
arXiv:2608.19492v1 Announce Type: new Abstract: World models increasingly treat compact multimodal representations as interfaces between perception and physical interaction, yet existing probes do not establish whether…
arXiv:2608.19908v1 Announce Type: cross Abstract: Probability estimation over large alphabets under log loss is a well-studied problem, with celebrated methods such as the Good-Turing estimator. We introduce and study a…
arXiv:2608.19803v1 Announce Type: new Abstract: Credit assignment is challenging in long-horizon agentic reinforcement learning, where supervision often comes only from final rewards. Existing methods refine…
arXiv:2608.19735v1 Announce Type: new Abstract: We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic clickstream…
arXiv:2605.10546v2 Announce Type: replace Abstract: Pixel-based deep reinforcement learning agents are typically trained on heavily downsampled visual observations, a convention inherited from early benchmarks rather…
arXiv:2608.19727v1 Announce Type: new Abstract: Watermarking is a central tool for provenance in generative models, yet its application to multivariate time series remains hindered by reliability failures under…
arXiv:2608.19914v1 Announce Type: new Abstract: Network topology inference from graph signals is central to graph signal processing with applications in neuroscience, sensor, and social networks. In practice,…
arXiv:2608.19394v1 Announce Type: cross Abstract: We introduce Deep-MKV-TS, a path-dependent McKean-Vlasov framework for financial scenario generation. The stochastic dynamics are chosen by matching selected path and…
arXiv:2608.19888v1 Announce Type: new Abstract: Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one, or defer. We present…
arXiv:2608.19684v1 Announce Type: cross Abstract: Recent studies investigate how to leverage pre-collected datasets to improve the policy performance and sample efficiency of RL. One promising approach to achieve this…
arXiv:2605.29411v2 Announce Type: replace Abstract: Under standard graphical assumptions, the Markov boundary of a target variable is the smallest set of features that renders every other feature redundant. Once the…
arXiv:2608.19587v1 Announce Type: new Abstract: While entropy regularization is widely used to stabilize and accelerate Natural Policy Gradient methods, its ability to yield faster convergence rates for the…
arXiv:2608.17034v2 Announce Type: replace Abstract: Post-training can unlock new capabilities and improve performance on specialized tasks, but sometimes at the cost of catastrophic forgetting in other domains. This…
arXiv:2608.15949v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendation accuracy…
arXiv:2605.24856v2 Announce Type: replace Abstract: Concept formation in transformer language models is a depth-extended process, not a single-layer event: a concept becomes separable across one or more contiguous…
arXiv:2608.19366v1 Announce Type: cross Abstract: Mission-critical intelligent systems often operate under time-varying limitations that reduce control authority and change the admissible safe operating envelope. In…
arXiv:2608.01548v3 Announce Type: replace-cross Abstract: Test-time emergence in LLM systems has a deployment boundary: additional computation can realize decisions already supported by the deployed…
arXiv:2608.19890v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) methods aim to bridge the domain gap between the source and target domains. However, traditional TTA methods become ineffective when the label…
arXiv:2608.19491v1 Announce Type: new Abstract: Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate. However, the inputs a…
arXiv:2608.18578v2 Announce Type: replace-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…
arXiv:2602.00511v3 Announce Type: replace Abstract: We introduce \emph{Partition of Unity Neural Networks} (PUNNs), a neural-network architecture for multiclass classification based on the classical mathematical notion…
arXiv:2608.19447v1 Announce Type: new Abstract: Shocks that spread through the web, such as cybersecurity breach disclosures, can abruptly disrupt financial time series and cause substantial abnormal losses. While these…
arXiv:2608.19906v1 Announce Type: new Abstract: Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening. DrugCLIP and its recent…
arXiv:2608.05686v2 Announce Type: replace-cross Abstract: Quantum error correction protects logical information only when every physical operation remains below the fault-tolerance threshold, a condition that must be…
arXiv:2602.13710v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment on…
arXiv:2608.19490v1 Announce Type: cross Abstract: State-of-the-art vision-language-action (VLA) models such as $\pi_{0.5}$ exhibit strong semantic understanding, instruction following and task behavior. However, when…
arXiv:2608.17965v2 Announce Type: replace Abstract: Online log anomaly detection is critical for maintaining the reliability of large-scale computing systems. Although recent language model-based log anomaly detectors…
arXiv:2510.07758v3 Announce Type: replace Abstract: Sharpness (of the loss minima) is widely believed to be a good indicator of generalization of neural networks. Unfortunately, the correlation between existing…
arXiv:2608.19514v1 Announce Type: new Abstract: Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared to…
arXiv:2603.18853v3 Announce Type: replace-cross Abstract: Autonomous aerial vehicles (AAVs) enable data collection for sixth-generation Internet-of-Things networks, but their trajectories couple nonlinear wireless rates…
arXiv:2606.00140v3 Announce Type: replace Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and…
arXiv:2608.19234v1 Announce Type: new Abstract: Decision-making in complex systems often involves dealing with imprecise or uncertain information, frequently represented using fuzzy sets, particularly Triangular Fuzzy…
arXiv:2608.20210v1 Announce Type: cross Abstract: Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite: we fixed the target first, one user, one token at a…
arXiv:2608.20024v1 Announce Type: new Abstract: District heating energy hubs require reliable heat load forecasts for efficient operational scheduling. Conventional forecasting workflows train system-specific models on…
arXiv:2607.18652v3 Announce Type: replace-cross Abstract: We establish improved lower bounds on the minimax expected regret of stochastic bandit convex optimization for $1$-Lipschitz functions on the $d$-dimensional…
arXiv:2608.19858v1 Announce Type: new Abstract: Generalizable dynamic graph anomaly detection (DGAD) enables pretrained detectors to identify anomalies in unseen target domains without costly retraining. However,…
arXiv:2412.00107v3 Announce Type: replace Abstract: Real-time monitoring of safety-critical interior states is an open problem across energy, environmental and industrial systems where direct instrumentation is…
arXiv:2607.08756v2 Announce Type: replace-cross Abstract: We present MulTTiPop, a dataset of pop music segments and their associated multitrack MIDI recordings for the evaluation of automatic music transcription models.…
arXiv:2608.20295v1 Announce Type: new Abstract: Sparse pursuit after dictionary learning can yield a precise atom support even when its physical interpretation is not justified by the calibration data, especially for…
arXiv:2608.11922v2 Announce Type: replace-cross Abstract: Predictive-distribution entropy is a strong answer-selection rule in retrieval-augmented generation (RAG) for question answering: across five QA benchmarks,…
arXiv:2608.16541v2 Announce Type: replace-cross Abstract: Objective assessment of learning remains a fundamental challenge in education. Electroencephalography (EEG) provides a direct, non-invasive window into the…
arXiv:2406.09770v2 Announce Type: replace Abstract: Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive…
arXiv:2608.19331v1 Announce Type: cross Abstract: We modify the NN/QFT duality [1] to incorporate the layerwise permutation symmetry of the network, resulting in a $(0\!+\!1)$-dimensional lattice gauge theory, in which…
arXiv:2608.19463v1 Announce Type: new Abstract: Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations.…
arXiv:2608.19408v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dense token-level…
arXiv:2608.19497v1 Announce Type: new Abstract: We characterize the learning dynamics of a compact hybrid quantum forecasting model through comparison with a structurally aligned classical baseline. Using stationary…
arXiv:2608.19836v1 Announce Type: new Abstract: Probabilistic shielding is a technique for safe reinforcement learning (RL). Typically, a static observer -- called the shield -- constrains the learning agent's actions…
arXiv:2608.18572v1 Announce Type: cross Abstract: Tactile Internet services couple cyber events directly to physical actuation, so security decisions must improve risk discrimination without perturbing the control path.…
arXiv:2608.20318v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI systems, so that the next system inherits the improvement. That…
arXiv:2409.06282v5 Announce Type: replace Abstract: Time series forecasting, particularly in few-shot learning scenarios, is challenging due to the limited availability of high-quality training data. To address this, we…
arXiv:2511.03618v2 Announce Type: replace Abstract: In this paper, we formalize the almost sure convergence of $Q$-learning and linear temporal difference (TD) learning with Markovian samples using the Lean 4 theorem…
arXiv:2103.04021v4 Announce Type: replace-cross Abstract: In the standard data analysis framework, data is collected (once and for all), and then data analysis is carried out. However, with the advancement of digital…
arXiv:2608.20065v1 Announce Type: new Abstract: World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a…
arXiv:2608.19922v1 Announce Type: new Abstract: Under the US Lead and Copper Rule Revisions, a utility may determine a service line's material with a predictive model instead of inspecting it. New York State publishes,…
arXiv:2607.29078v2 Announce Type: replace Abstract: On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias. However, in multi-turn agent scenarios, early student errors can lead…
arXiv:2608.19227v1 Announce Type: cross Abstract: Market microstructure simulation aims to model how liquidity, prices, and order flow evolve in electronic financial markets. Since market data reveal only one realized…
arXiv:2608.20149v1 Announce Type: new Abstract: This article explores the performance of analytical and neural-based hillshading methods in a dense urban environment using high-resolution digital elevation model (DEM)…
arXiv:2608.19419v1 Announce Type: cross Abstract: Microlensing can reveal populations of faint compact objects that are otherwise difficult to detect. Depending on their design, all-sky surveys have the potential to…
arXiv:2607.17417v2 Announce Type: replace Abstract: Language models are moving into chemistry and materials discovery workflows, where a wrong molecular formula, space group, or formation energy can silently propagate…
arXiv:2512.07847v2 Announce Type: replace Abstract: Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving algorithmic innovation…
arXiv:2608.19306v1 Announce Type: cross Abstract: Given a set of input states, we consider the task of predicting the expectation value of a Pauli observable at the output of an unknown quantum evolution, using only a…
arXiv:2608.19395v1 Announce Type: cross Abstract: Hybrid Transformer-Mamba large language models (LLMs) enhance long-context efficiency, but their heterogeneous computation and communication patterns complicate…
arXiv:2608.19881v1 Announce Type: cross Abstract: Radio frequency (RF) fingerprinting authenticates wireless devices from hardware-induced I/Q impairments, typically with deep learning feature extractors that are…
arXiv:2608.19938v1 Announce Type: cross Abstract: Existing approaches to anomalous behaviour log detection, such as Wazuh rely primarily on predefined detection rules, while statistical anomaly detection approaches such…
arXiv:2602.02710v2 Announce Type: replace Abstract: Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our…
arXiv:2608.19436v1 Announce Type: new Abstract: Alzheimer's disease (AD) progresses as a continuous biological process, whereas most existing neuroimaging-based artificial intelligence methods remain limited to discrete…
arXiv:2608.19965v1 Announce Type: cross Abstract: Segmentation of curvilinear anatomical structures in 3D medical images remains challenging due to complex topology, severe class imbalance, weak contrast, and large…
arXiv:2608.18521v2 Announce Type: replace-cross Abstract: Dense-caption retrieval has recently been improved by introducing segmentation, edge maps, LLM-filtered captions, and cross-modal modules into contrastive…
arXiv:2608.20172v1 Announce Type: new Abstract: Attention directly derives normalized information flow from pairwise scores. We introduce Relation, an alternative token-mixing primitive that first organizes pairwise…
arXiv:2608.19807v1 Announce Type: new Abstract: Vision-language models (VLMs) can estimate physical quantities such as duration, speed, and acceleration from visual observations, but existing benchmarks primarily assess…
arXiv:2608.20322v1 Announce Type: new Abstract: Despite their growing importance for contact-free radio frequency (RF) based healthcare monitoring, different radio technologies such as frequency-modulated continuous…
arXiv:2509.23689v2 Announce Type: replace Abstract: Model Merging (MM) has proven to be an effective alternative to multi-task learning, where several fine-tuned models are merged, without access to the tasks' training…
arXiv:2412.06265v3 Announce Type: replace Abstract: Deep tabular models should ideally balance predictive performance, parameter efficiency, and robustness to imperfect learning signals---properties that are rarely…
arXiv:2608.11288v2 Announce Type: replace-cross Abstract: Assessing catheter and tube placement on chest X-rays is safety-critical yet tedious and error-prone. Current deep learning methods either classify placement…
arXiv:2608.19297v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) excel in medical applications, most of them favor static images or short-term signals. In the critical field of dynamic…
arXiv:2608.06834v2 Announce Type: replace Abstract: Transformers provide a powerful architecture for global content-based matching, but reasoning problems may benefit from a stronger inductive bias toward iterative…
arXiv:2608.20258v1 Announce Type: new Abstract: Decision tree-based models are widely used in machine learning due to their interpretability and strong empirical performance. However, training decision trees can be…
arXiv:2605.23955v3 Announce Type: replace-cross Abstract: Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabilities in…
arXiv:2605.11644v3 Announce Type: replace-cross Abstract: Positive data can show that two tuple occurrences share a successful sentence context without certifying that they are safely interchangeable. We study finite…
arXiv:2608.20104v1 Announce Type: cross Abstract: Artificial immune networks (AINs) are naturally memory-forming systems, but conventional visual AINs often rely on flattened vector affinity that ignores spatial…
arXiv:2608.19669v1 Announce Type: cross Abstract: Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual…
arXiv:2608.20280v1 Announce Type: cross Abstract: Semantic caches reuse an LLM response when the incoming query embedding lies near a cached query, but proposed eviction policies have rarely been compared under one…
arXiv:2608.19672v1 Announce Type: new Abstract: Natural hazard susceptibility mapping is often constrained by limited labeled data, reducing the generalizability of conventional machine learning and limiting the…
arXiv:2509.21489v4 Announce Type: replace Abstract: Graph foundation models face several fundamental challenges including transferability across diverse domains and data scarcity, which calls into question the very…
arXiv:2608.19658v1 Announce Type: new Abstract: This study demonstrates a rationally enriched Chebyshev (REC) trunk for deep operator network (DeepONet) surrogate models of singularly perturbed and high-P\'eclet…
arXiv:2608.19653v1 Announce Type: new Abstract: Autonomous agents for machine learning experimentation must navigate heterogeneous repositories, repair training pipelines, and evaluate candidate improvements under…
arXiv:2608.19304v1 Announce Type: new Abstract: Lung cancer screening with low-dose chest computed tomography reduces mortality, but its impact is limited by uptake, adherence, and management challenges. Blood-based…
arXiv:2608.20134v1 Announce Type: cross Abstract: We present a novel view on feature evolution in Vision Transformers (ViTs) by visualizing the training process over two dimensions -- network depth (layer) and training…
arXiv:2608.12447v3 Announce Type: replace Abstract: Trained transformer models develop privileged bases: coordinate axes whose statistics differ from the rest of the residual stream. But what kind of direction does such…
arXiv:2608.19578v1 Announce Type: new Abstract: Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) can worsen rapidly, making timely prediction a clinical priority. Most existing machine learning…
arXiv:2608.20052v1 Announce Type: new Abstract: Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches. Existing methods…
arXiv:2608.19218v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems are increasingly being explored for domain-specific maintenance and prognostics tasks, raising the question of…
arXiv:2608.19964v1 Announce Type: new Abstract: Autonomous driving systems must operate under partial observability, where safety-critical objects may be occluded or visible only to neighboring connected vehicles.…
arXiv:2608.19808v1 Announce Type: new Abstract: Cyclic peptides are emerging as promising molecular scaffolds in drug discovery due to their high binding affinity and structural stability. However, extending generative…
arXiv:2608.19282v1 Announce Type: cross Abstract: When factor scores replace true latent scores in nonlinear prediction, measurement error attenuates the recoverable variance of any $k$th-order component of the…
arXiv:2608.19785v1 Announce Type: cross Abstract: Discovering dynamical systems from trajectory data is a central problem in applied mathematics and engineering. Whilst recent advances in machine learning have led to…
arXiv:2605.23057v2 Announce Type: replace Abstract: RequestRouter is a lightweight request-boundary controller for reducing the latency and energy cost of single-GPU large language model inference. Rather than serving…
arXiv:2608.20005v1 Announce Type: new Abstract: Pretraining time series foundation models across heterogeneous datasets necessitates effective handling of varying sampling frequencies. Current methods either employ…
arXiv:2608.20123v1 Announce Type: cross Abstract: We study inference-time control for text generation in discrete diffusion language models, where the goal is to steer sampling toward sequence-level rewards without…
arXiv:2606.07303v4 Announce Type: replace Abstract: Representation learning is central to modern machine learning, yet most research focuses on optimizing representations after a framework has been selected. The…
arXiv:2608.19351v1 Announce Type: new Abstract: Robustness verification of neural networks is increasingly important, due to their use in many critical domains. In certain scenarios, proof sharing has been shown to…
arXiv:2608.20054v1 Announce Type: cross Abstract: Multi-module systems often expose every module to the full input. We test whether restricting evidence visibility changes which solutions gradient-based training…
arXiv:2608.19544v1 Announce Type: cross Abstract: Functionalities of ferroelectric materials are governed by the spatial organization and coupling of polarization, strain, lattice rotation, and structural order…
arXiv:2608.20025v1 Announce Type: new Abstract: Probabilistic forecasting models are widely used for time series forecasting in domains such as energy systems, finance, medicine, and transportation. In recent years,…
arXiv:2608.20117v1 Announce Type: new Abstract: The emergence of large-scale Weather and Climate (W&C) datasets offers new opportunities for modeling extreme Earth events (ExEE) and their impacts using deep learning.…
arXiv:2608.11256v2 Announce Type: replace Abstract: Institutions use commercial AI detectors for academic integrity, yet detectors cannot distinguish AI editing from full LLM drafts and may treat both as misconduct. In…
arXiv:2509.04222v2 Announce Type: replace Abstract: Dimensionality Reduction (DR) is widely used for visualizing high-dimensional data, often with the goal of revealing expected cluster structure. However, such a…
arXiv:2608.19248v1 Announce Type: cross Abstract: Monitored quantum circuits exhibit a measurement-induced phase transition between volume-law and area-law entanglement as a function of the measurement rate $p$. Prior…
arXiv:2608.19540v1 Announce Type: new Abstract: Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to a new domain leaves…
arXiv:2608.19801v1 Announce Type: new Abstract: Financial anomaly detection often relies on large unlabeled transaction logs, where anomalous samples may already be present during training. Such training-set…
arXiv:2608.19659v1 Announce Type: new Abstract: Choosing tensor-parallel (TP) degrees and replica counts for an LLM serving fleet is difficult because performance is not monotonic in TP and the feasible choice can…
arXiv:2602.13811v3 Announce Type: replace-cross Abstract: Physics-Informed Neural Networks present a novel approach in SciML that integrates physical laws in the form of partial differential equations directly into the…
arXiv:2608.03259v2 Announce Type: replace Abstract: As time-series foundation models have emerged, the need for benchmarks that can evaluate their forecasting ability in meaningful ways has become increasingly…
arXiv:2608.20255v1 Announce Type: cross Abstract: This paper develops a general transfer learning framework for nonparametric regression with data consisting of multiple groups. Under the assumption that groups share a…
arXiv:2608.19766v1 Announce Type: cross Abstract: Self-supervised pretraining on remote sensing imagery typically treats all samples as equally informative, despite large variability in geographic and visual structure.…
arXiv:2608.19231v1 Announce Type: cross Abstract: Estimating large and simulation-intensive discrete choice models (DCMs) requires repeated evaluation of utilities, probabilities, derivatives, and simulated likelihoods…
arXiv:2607.19020v2 Announce Type: replace Abstract: Clinical decision support degrades as treatment protocols evolve, but the obstacle to updating a deployed model is governance as much as accuracy: once retraining…
arXiv:2608.20181v1 Announce Type: new Abstract: Studies of machine-learning-based power-system protection increasingly report near-perfect scores, yet the meaning of those scores depends strongly on the evaluation…
arXiv:2608.20222v1 Announce Type: cross Abstract: The worldwide network of gravitational-wave detectors have detected more than 350 binary coalescence events till date. Future third-generation detectors, like Einstein…
arXiv:2606.17168v3 Announce Type: replace Abstract: When LLM weights are open or fine-tuning is available through an API, suppressing hazardous knowledge and tendencies is not enough: removal has to be deep enough that…
arXiv:2608.19875v1 Announce Type: new Abstract: Patients often submit short, underspecified queries to healthcare chatbots that lack the patient-specific information needed to determine an appropriate response. Although…
arXiv:2608.19981v1 Announce Type: new Abstract: We present HealMed, an expert-reviewed benchmark for multilingual evaluation of large language models in medicine. HealMed contains 1,000 examples in each of nine…
arXiv:2608.19652v1 Announce Type: cross Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmarks focus largely…
arXiv:2508.00554v5 Announce Type: replace-cross Abstract: In financial trading, large language model (LLM)-based agents demonstrate significant potential, but their decisions can be sensitive to noisy and non-stationary…
arXiv:2603.19997v2 Announce Type: replace Abstract: We investigate the separation of literal interpretation from contextual inference in a collaborative block-building tasks, where an agent must resolve underspecified…
arXiv:2608.19207v1 Announce Type: new Abstract: Production deployments of Multimodal Large Language Models (MLLMs) increasingly rely on system messages to govern model behavior. Yet existing benchmarks either evaluate…
arXiv:2608.20281v1 Announce Type: new Abstract: Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time. We study this…
arXiv:2608.20204v1 Announce Type: cross Abstract: Legal work, with its heavy reliance on processing large amounts of text, is often considered one of the domains most exposed to the use of LLMs. Contract ``scrubbing,''…
arXiv:2608.17379v2 Announce Type: replace Abstract: We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench…
arXiv:2608.19920v1 Announce Type: new Abstract: A lot of prior work addressed key-value (KV) cache selection and compression by sparse attention to enable long-context inference for transformer language models without…
arXiv:2608.20319v1 Announce Type: new Abstract: Naturalistic computer-use traces, passively recorded screenshots and mouse or keyboard actions, are a valuable resource for deriving symbolic, auditable, and reusable…
arXiv:2501.16106v2 Announce Type: replace Abstract: Recent advances in multimodal depression recognition for clinical interviews (MDRC) have demonstrated the potential of AI systems by integrating textual, acoustic, and…
arXiv:2603.23522v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context. Binary scores and static…
arXiv:2608.20320v1 Announce Type: cross Abstract: Travel behavior research increasingly combines digital data collection with predictive modeling, yet these stages are often developed and evaluated separately. This…
arXiv:2608.18041v2 Announce Type: replace Abstract: Reading fiction or encountering narrative generally does not merely add information. The encounter changes the reader. This paper proposes that encounters alter…
arXiv:2608.19971v1 Announce Type: new Abstract: Multimodal sentiment analysis aims to infer affective states by integrating language, visual, and acoustic cues. However, real-world multimodal inputs are often incomplete…
arXiv:2608.19549v1 Announce Type: new Abstract: This paper addresses the issue of the significant labor required to test interview dialogue systems. While interview dialogue systems are expected to be useful in various…
arXiv:2607.13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps. Existing reinforcement learning methods reduce…
arXiv:2608.19621v1 Announce Type: new Abstract: Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially…
arXiv:2608.19527v1 Announce Type: cross Abstract: AI clones that imitate a specific person typically reproduce what the person says and how they sound, but not how they listen. We investigate whether adding multimodal…
arXiv:2608.20290v1 Announce Type: cross Abstract: Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses. Tracking these transitions…
arXiv:2603.21875v2 Announce Type: replace-cross Abstract: Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator, often assuming…
arXiv:2605.28969v2 Announce Type: replace Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how faithfully a…
arXiv:2608.19662v1 Announce Type: new Abstract: Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from…
arXiv:2608.19369v1 Announce Type: new Abstract: Statistical watermarks for language models live in the freedom of the signifier: they choose among tokens that are nearly equivalent in meaning, and they are therefore…
arXiv:2604.13731v2 Announce Type: replace Abstract: Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free…
arXiv:2608.19670v1 Announce Type: new Abstract: Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying behavioral shifts. In…
arXiv:2608.19802v1 Announce Type: new Abstract: LLM evaluation pipelines often have many candidate judges: general LLM-as-a-judge prompts, reward models, safety classifiers, confidence variants, and task-specific…
arXiv:2608.20129v1 Announce Type: cross Abstract: Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based…
arXiv:2501.14728v2 Announce Type: replace-cross Abstract: While generative artificial intelligence (GenAI) models have achieved significant success, their misuse for generating deceptive content raises growing concerns…
arXiv:2604.26170v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge. Such adaptation often requires iteratively…
arXiv:2608.19526v1 Announce Type: new Abstract: Stock market analysts and investors face a daily challenge: too much financial news, too little time. Manually reading and synthesizing hundreds of company-specific…
arXiv:2608.19361v1 Announce Type: new Abstract: This study reports the development of an Automatic Speech Recognition (ASR) system in Mizo, a low-resource language. The development included collecting 17.62 hours of…
arXiv:2604.18738v3 Announce Type: replace Abstract: Diffusion language models (dLLMs) generate text through iterative denoising, filling multiple masked positions at each step. Positions filled in the same step are…
arXiv:2608.19957v1 Announce Type: new Abstract: Natural language code retrieval is a rapidly evolving task in computer science. However, the 1C:Enterprise ecosystem combines Russian syntax with highly domain-specific…
arXiv:2608.19825v1 Announce Type: cross Abstract: Medical image captioning is a technique that accelerates early-stage diagnostic workflows and enhances the interpretability of medical diagnostic AI systems. However,…
arXiv:2608.19475v1 Announce Type: cross Abstract: This work introduces a formal semantic-block model for specifications and an execution-judged benchmark for evaluating specification quality independently of model…
arXiv:2608.19208v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are frequently exposed to auxiliary textual context, the impact of which on visually grounded tasks remains underexplored. In this…
arXiv:2608.19558v1 Announce Type: new Abstract: Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores…
arXiv:2608.19200v1 Announce Type: new Abstract: Text summarization refers to the task of condensing a document into a shorter version while preserving its key information. Automatic text summarization (ATS), driven by…
arXiv:2608.19515v1 Announce Type: new Abstract: Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged. Yet…
arXiv:2608.20083v1 Announce Type: new Abstract: Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step…
arXiv:2608.19758v1 Announce Type: new Abstract: Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the…
arXiv:2608.19800v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is a prominent fine-tuning method for large models, achieving competitive performance with reduced memory overhead. However, a persistent…
arXiv:2509.08022v3 Announce Type: replace Abstract: Aligning large language models (LLMs) with diverse human values is essential for safe and effective deployment, yet existing benchmarks often overlook cultural and…
arXiv:2606.09498v3 Announce Type: replace Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different…
arXiv:2608.19535v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context…
arXiv:2608.20106v1 Announce Type: new Abstract: We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking,…
arXiv:2608.19212v1 Announce Type: new Abstract: Out-of-context (OOC) misinformation pairs authentic images with misleading captions to construct false narratives without image manipulation, making detection a problem of…
arXiv:2606.15910v2 Announce Type: replace Abstract: A vision-language model can answer a question about a chest radiograph or a pathology slide fluently and confidently while barely using the image, relying instead on…
arXiv:2606.01034v2 Announce Type: replace Abstract: Deploying an LLM judge panel spends human labels on fitting a calibrator, constructing candidate judge paths, and validating which candidate to deploy. We study when…
arXiv:2608.20116v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in settings where textual summaries, numerical observations, and external tool outputs may provide conflicting evidence.…
arXiv:2608.19303v1 Announce Type: cross Abstract: When a tool call times out, the agent sees the failure and can route around it. A cached error page or negative price can instead arrive in the expected format and be…
arXiv:2608.20274v1 Announce Type: cross Abstract: Large language model (LLM) agents can induce skills from completed tasks and reuse them later to grow more capable with experience. In practice, induced skills may…
arXiv:2608.19746v1 Announce Type: new Abstract: Personalized text generation aims to make LLMs write in a specific individual's style, yet existing benchmarks measure task accuracy or preference alignment rather than…
arXiv:2608.19199v1 Announce Type: new Abstract: We describe the evolution of a virtual assistant, called ATHENA, designed to support the capture, retrieval, and dissemination of knowledge for members of a Community of…
arXiv:2608.19437v1 Announce Type: new Abstract: Many benchmarks track Large Language Model (LLM) performance on tasks with verifiable answers, but less is known about how LLM performance is evolving on open-ended tasks,…
arXiv:2608.19220v1 Announce Type: new Abstract: Rising immigration has intensified intergroup tensions in many countries. Traditional bias-reduction programs remain difficult to scale and increasingly constrained by…
arXiv:2608.19009v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that…
arXiv:2608.19893v1 Announce Type: new Abstract: Where does the novelty a base language model produces with no task come from, and what can an LLM judge of a long stream actually see? We dismantle a cognitively inspired…
arXiv:2608.19206v1 Announce Type: new Abstract: Contemporary Large Language Models (LLMs) are increasingly aligned to suppress hallucinations, prioritizing factual retrieval over combinatorial creativity. While crucial…
arXiv:2608.19723v1 Announce Type: cross Abstract: Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be…
arXiv:2608.20153v1 Announce Type: new Abstract: Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research, yet existing benchmarks remain far from realistic…
arXiv:2608.18752v2 Announce Type: replace-cross Abstract: Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval, a public…
arXiv:2608.19799v1 Announce Type: new Abstract: Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also…
arXiv:2608.19942v1 Announce Type: new Abstract: Multimodal sarcasm detection aims to identify sarcastic intent from multimodal content, where inconsistencies between literal meaning and contextual cues often signal…
arXiv:2608.19430v1 Announce Type: cross Abstract: Vulnerability prioritization is inherently preference dependent, since the same CVE can receive different remediation priority under different operational preference…
arXiv:2608.12323v2 Announce Type: replace Abstract: Specifying a penalty can turn a legal obligation into a cost-benefit calculation that favors violation. We show that this enforcement information paradox occurs in AI…
arXiv:2608.20338v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and benchmarks fail to…
arXiv:2608.19472v1 Announce Type: new Abstract: Lexical semantic change (LSC) is commonly modelled through vector-space representations, but these approaches often provide limited insight into which aspects of usage are…
arXiv:2608.19598v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its adaptation to…
arXiv:2608.20331v1 Announce Type: new Abstract: Personalized interpretation of medical reports has emerged as an increasingly important need among patients. Addressing this need requires both evidence-grounded medical…
arXiv:2608.19737v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and image-based…
arXiv:2608.19211v1 Announce Type: new Abstract: Human speech is richly expressive, with prosody carrying linguistic and emotional information beyond the lexical content. A capable large audio-language model (audio-LLM)…
arXiv:2510.03519v3 Announce Type: replace Abstract: Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time series foundation…
arXiv:2502.15411v5 Announce Type: replace Abstract: Accurate tagging of earnings reports can yield significant short-term returns for stakeholders. The machine-readable inline eXtensible Business Reporting Language…
arXiv:2608.19741v1 Announce Type: new Abstract: Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Yet completing…
arXiv:2608.19564v1 Announce Type: new Abstract: Persistent memory can personalize an LLM agent, but an incorrect durable update can silently distort future behavior. We study the memory-clarification boundary: whether…
arXiv:2608.19201v1 Announce Type: new Abstract: Bioinformatics software and databases are essential components of modern life science research, yet their mentions in the scientific literature are often inconsistent and…
arXiv:2511.20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.g.,…
arXiv:2608.19529v1 Announce Type: new Abstract: Many real-world AI systems represent entities, behaviors, and structured information using discrete machine-native symbols rather than natural language. While these…
arXiv:2608.19838v1 Announce Type: new Abstract: Spec Driven Development SDD has consolidated the idea that the specification rather than the code should be the primary artefact governing AI assisted work. Tools such as…
arXiv:2508.12682v2 Announce Type: replace Abstract: The global shift towards renewable energy presents unprecedented challenges for the electricity industry, making regulatory reasoning and compliance increasingly…
arXiv:2507.06127v2 Announce Type: replace-cross Abstract: Prefix adders are fundamental arithmetic circuits, but their design space grows exponentially with bit-width, posing significant optimization challenges.…
arXiv:2608.19579v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes applications, yet their tendency to generate toxic, harmful, or policy-violating content poses…
arXiv:2608.19966v1 Announce Type: new Abstract: Multivariate time series forecasting (MTSF) is a fundamental task in many real world applications. Existing patch based forecasting methods generally fall into three…
arXiv:2604.12616v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual perception with text generation. Existing multimodal jailbreak…
arXiv:2606.06245v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) policies remain brittle in long-horizon and high-uncertainty control, where one-pass action decoding provides limited inference-time…
arXiv:2608.19759v1 Announce Type: cross Abstract: Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to generalize to new objects because they are trained on…
arXiv:2608.19536v1 Announce Type: cross Abstract: Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to…
arXiv:2608.11907v2 Announce Type: replace-cross Abstract: As Large Vision-Language Models increasingly aim to integrate visual generation and understanding within a single parameter space, evaluating such structural…
arXiv:2606.27918v2 Announce Type: replace-cross Abstract: As a prominent symptom of Parkinson's disease (PD), turning impairment is evaluated through parameters such as turning angle, duration, and particularly, the…
arXiv:2608.19751v1 Announce Type: new Abstract: Micro-View Order-Dispatching assigns available drivers to passenger orders within each dispatch batch and is critical to the service quality and operational efficiency of…
arXiv:2604.02567v2 Announce Type: replace-cross Abstract: Despite the growing use of generative artificial intelligence (GenAI) in entrepreneurship, research on its impact remains fragmented. To address this limitation,…
arXiv:2510.25960v2 Announce Type: replace-cross Abstract: In this paper, we present a framework that uses acoustic side-channel analysis (ASCA) to monitor and verify whether a robot correctly executes its intended…
arXiv:2510.14642v2 Announce Type: replace-cross Abstract: In blockchain networks, the strategic ordering of transactions within blocks has emerged as a significant source of profit extraction, known as Maximal…
arXiv:2501.12289v3 Announce Type: replace-cross Abstract: Internet overuse is a widespread phenomenon in today's digital society. Existing interventions, such as time limits or grayscaling, often rely on restrictive…
arXiv:2608.19804v1 Announce Type: new Abstract: Buildings account for roughly one-third of global energy consumption and CO$_2$ emissions. Optimizing indoor climate systems plays a critical role for urban climate…
arXiv:2608.19863v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has driven substantial progress in audio representation learning, though existing methods have increasingly relied on elaborate…
arXiv:2608.19266v1 Announce Type: cross Abstract: The OWASP Top 10 for LLM Applications ranks the risks that a community of security practitioners judges most important. We ask a narrower question: checked against the…
arXiv:2608.19703v1 Announce Type: cross Abstract: Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the…
arXiv:2608.19831v1 Announce Type: new Abstract: Causal Bayesian networks (CBNs) and structural causal models (SCMs) are the dominant frameworks for graphical causal reasoning, but they cannot adequately represent all…
arXiv:2605.10555v2 Announce Type: replace Abstract: As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms.…
arXiv:2607.25497v3 Announce Type: replace-cross Abstract: Pathology foundation models encode non-biological variation introduced by tissue preparation, staining and scanning, enabling shortcut learning that undermines…
arXiv:2608.15242v2 Announce Type: replace Abstract: When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the trajectory. Developers…
arXiv:2506.05616v3 Announce Type: replace Abstract: We aim at designing language agents with greater autonomy for crystal materials discovery. While most of existing studies restrict the agents to perform specific tasks…
arXiv:2608.09921v2 Announce Type: replace Abstract: Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power system analysis,…
arXiv:2608.19936v1 Announce Type: cross Abstract: Public benchmarks are important measures of Automatic Speech Recognition (ASR) model capabilities. However, by nature of being public, there is risk of models being…
arXiv:2608.19719v1 Announce Type: cross Abstract: Reference-based diffusion stylization requires separating target geometry from transferable appearance. Existing tuning-based methods often rely on aligned…
arXiv:2608.20218v1 Announce Type: new Abstract: Electronic Navigational Charts (ENCs) are geospatial vector datasets used in maritime navigation systems that represent hydrographic and navigational information such as…
arXiv:2608.20084v1 Announce Type: cross Abstract: Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. However,…
arXiv:2608.19625v1 Announce Type: new Abstract: Scientific data are increasingly used by AI agents, yet existing dataset representations provide limited support for autonomous discovery, interpretation, and invocation.…
arXiv:2608.19583v1 Announce Type: cross Abstract: Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains…
arXiv:2608.15052v2 Announce Type: replace Abstract: Andy is an autonomous mathematical research agent that turns a mathematical problem into a traceable proof. It solves or verifies a submitted problem, formulates a…
arXiv:2607.04234v2 Announce Type: replace-cross Abstract: Deformable object manipulation poses challenges beyond task completion: successful execution must also maintain safe physical interaction, holding the object…
arXiv:2606.00089v2 Announce Type: replace-cross Abstract: Can learned state-action proposals exist in the physical world? To filter infeasible commands before execution, policies are often wrapped in a runtime monitor.…
arXiv:2608.19789v1 Announce Type: new Abstract: Developed as a workhorse for classical simulations of quantum algorithms and quantum many-body systems, Tensor Network methods have entered the scientific mainstream in…
arXiv:2608.19993v1 Announce Type: new Abstract: Loading reusable skill documents into a bounded context window is now the primary way large language model (LLM) agents acquire task-specific capabilities, which makes…
arXiv:2608.20201v1 Announce Type: new Abstract: Software form has undergone two paradigm shifts since its inception: Software 1.0, in which instructions determine behavior, and Software 2.0, in which data determines…
arXiv:2608.19381v1 Announce Type: cross Abstract: Network embedding methods learn low-dimensional representations of graph-structured data to support downstream tasks such as node classification, link prediction, and…
arXiv:2608.19214v1 Announce Type: new Abstract: The berth allocation and quay crane assignment problem (BACAP) is a representative port-terminal scheduling problem in maritime transportation and freight logistics, where…
arXiv:2608.19812v1 Announce Type: new Abstract: To prevent the adoption of aesthetically polished but pedagogically flawed AI content, we study a video authoring pipeline featuring two layers of structured refusal. The…
arXiv:2608.19230v1 Announce Type: cross Abstract: As language models move from drafting prose to running literature-search agents with tool calls, fabricated references are becoming easier to catch and constrain. The…
arXiv:2507.05888v2 Announce Type: replace-cross Abstract: Vernon Mountcastle hypothesized that the basis for intelligence in mammals is the replication of a general computational unit, the cortical column. The Thousand…
arXiv:2608.06108v2 Announce Type: replace Abstract: Investment competence is inherently personalized: the same market evidence can justify different actions for investors with different goals, horizons, portfolios, and…
arXiv:2608.18900v2 Announce Type: replace Abstract: As AI systems are increasingly deployed in safety-critical application domains (e.g., autonomous driving), associated risks increase too. Deep learning models…
arXiv:2608.19794v1 Announce Type: new Abstract: The convergence of large language models (LLMs), structured knowledge bases (KBs), and reasoning ability (RA) presents a promising trajectory toward general embodied…
arXiv:2608.19701v1 Announce Type: new Abstract: Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent…
arXiv:2608.20240v1 Announce Type: new Abstract: X-band SAR satellites (8-12 GHz) play a critical role in disaster response, environmental monitoring, and military intelligence. Yet, they lack robust physical-layer…
arXiv:2608.20220v1 Announce Type: new Abstract: Legal AI systems are increasingly used to answer legal questions, yet existing benchmarks assume queries arrive fully specified. In practice, users omit facts that…
arXiv:2606.10388v2 Announce Type: replace-cross Abstract: Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions…
arXiv:2608.20256v1 Announce Type: new Abstract: Reasoning language models trained with reinforcement learning typically operate under a fixed token budget rather than an explicitly adaptive one, which can lead to…
arXiv:2606.15654v2 Announce Type: replace-cross Abstract: Real-world robot task planning must operate under both stochastic action execution and partial observability, yet constructing Partially Observable Markov…
arXiv:2608.20053v1 Announce Type: new Abstract: The integration of Artificial Intelligence (AI) in safety-critical aviation systems presents significant challenges for certification and deployment. Aviation, often…
arXiv:2608.19776v1 Announce Type: cross Abstract: Current dexterous grasp planners primarily optimize for physical stability, focusing on whether an object can be grasped rather than how it should be grasped to support…
arXiv:2608.19902v1 Announce Type: new Abstract: AI agents can execute scientific analyses, but an analytic output becomes a defensible claim only after alternatives are weighed and the claim is limited to what the…
arXiv:2605.14398v3 Announce Type: replace Abstract: Video-based world models generate visually plausible rollouts, but since they infer dynamics in latent states, they enforce no explicit physical constraints: contacts…
arXiv:2608.19932v1 Announce Type: new Abstract: Public cardiac cohorts annotate different subsets of the heart, so shapes from separate sources cannot be pooled without shared correspondence. Among released cardiac…
arXiv:2606.12428v2 Announce Type: replace-cross Abstract: In this work, we locate and analyze existing undergraduate Artificial Intelligence (AI) programs in the United States in Spring 2026, creating a historic record…
arXiv:2608.20019v1 Announce Type: new Abstract: Incomplete multimodal sentiment analysis has garnered significant attention in recent years. Existing approaches typically assume that data is missing at random or are…
arXiv:2608.19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy…
arXiv:2608.20314v1 Announce Type: new Abstract: Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Recent work has shown that targeted mid-training can…
arXiv:2607.21596v2 Announce Type: replace Abstract: Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures discovered in one episode are usually discarded…
arXiv:2607.27154v2 Announce Type: replace-cross Abstract: CT vision-language foundation models have demonstrated promising performance across downstream tasks, but are typically trained with whole-volume representations…
arXiv:2608.19790v1 Announce Type: new Abstract: Discovering materials with desirable properties often requires searching large candidate spaces while experimental or computational evaluations remain costly. Active…
arXiv:2608.20055v1 Announce Type: cross Abstract: Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs…
arXiv:2608.19674v1 Announce Type: cross Abstract: Computing has been an astonishing success - but the accumulated technical debt exposes us all to huge costs in business and societal risk. For 75 years, we've built…
arXiv:2603.26678v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) and renewable energy are increasingly being described as a \mbox{``power couple,''} based on the idea that rapid growth in AI will…
arXiv:2608.19710v1 Announce Type: cross Abstract: Reliable underwater robotic perception remains difficult because optical imagery degrades under turbidity, wavelength-dependent attenuation, low illumination,…
arXiv:2608.20187v1 Announce Type: cross Abstract: Practitioners inferring causality from observational data usually rely on a single method and treat its output as causal truth. Recent tools select an optimal method for…
arXiv:2503.04500v3 Announce Type: replace-cross Abstract: Video understanding has largely relied on deep spatiotemporal architectures, including 3D convolutional networks and optical flow (OF) based models. While…
arXiv:2608.19511v1 Announce Type: new Abstract: Symposium is a formal framework and practical implementation to record the operation of AI agents deployed by small scientific research communities. Symposium provides…
arXiv:2608.20041v1 Announce Type: new Abstract: Research on the agency of advanced artificial intelligence (AI) systems focuses on agency as a normative concept and on the agency of particularly agentic AI systems.…
arXiv:2605.06094v5 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long,…
arXiv:2608.19299v1 Announce Type: new Abstract: Air traffic control (ATC) communication is a safety-critical dialogue that remains largely human-driven even as other parts of air traffic management have been…
arXiv:2608.19953v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) is a fundamental problem class in operations research and combinatorial optimization, with broad applications to industrial…
arXiv:2510.21874v2 Announce Type: replace-cross Abstract: Unmanned aerial vehicles (UAVs) operating in dynamic wind fields must generate safe and energy-efficient trajectories under physical and environmental…
arXiv:2608.19882v1 Announce Type: new Abstract: Deep learning models remain vulnerable to real-world input perturbations, especially when multiple corruptions co-occur in the same input (e.g., brightness shifts and…
arXiv:2608.19689v1 Announce Type: new Abstract: LLM-based social simulation is a promising complement to traditional methods such as surveys and behavioral experiments. A core question is how to evaluate the fidelity of…
arXiv:2608.19085v2 Announce Type: replace-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:2608.19817v1 Announce Type: cross Abstract: Conventional convolutional kernels are typically defined on fixed discrete grids, limiting their ability to accommodate heterogeneous local structures. Existing adaptive…
arXiv:2510.14357v3 Announce Type: replace-cross Abstract: Agricultural robots are emerging as powerful assistants across a wide range of agricultural tasks, nevertheless, they are still heavily relying on manual…
arXiv:2608.07267v2 Announce Type: replace Abstract: Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map…
arXiv:2608.20271v1 Announce Type: new Abstract: The rapid proliferation of memecoins on blockchain platforms has increased the risk of fraudulent activities, particularly rug pulls. While previous studies have focused…
arXiv:2608.19278v1 Announce Type: cross Abstract: The most capable general-purpose AI (GPAI) models are mostly built in two jurisdictions, the United States and China, but the risks they carry land globally. Regionally…
arXiv:2608.19376v1 Announce Type: cross Abstract: Split-conformal prediction provides marginal coverage under exchangeability and is increasingly used as an abstention layer for zero-shot vision-language models (VLMs).…
arXiv:2606.23487v2 Announce Type: replace Abstract: Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as an accuracy one.…
arXiv:2608.19729v1 Announce Type: new Abstract: Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed as interactive…
arXiv:2602.07104v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications…
arXiv:2604.02022v4 Announce Type: replace Abstract: Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than…
arXiv:2608.19778v1 Announce Type: cross Abstract: Pedestrian simulators need a behaviour rule for every agent, but privacy usually limits the data for setting one to aggregate statistics, namely zone-level device counts…
arXiv:2510.25340v2 Announce Type: replace-cross Abstract: Learning to collaborate with various unfamiliar teammates poses a great challenge in the domain of multi-agent systems. Existing ad hoc teamwork methods…
arXiv:2505.05203v3 Announce Type: replace-cross Abstract: With the increasing penetration of renewable energy and inverter-based resources, traditional physics-based power-system operation faces growing challenges in…
arXiv:2608.20195v1 Announce Type: cross Abstract: Technical documentation is written for human developers, but an increasing share of software changes is now authored by autonomous coding agents. Which documents they…
arXiv:2608.19487v1 Announce Type: cross Abstract: Python is widely used in scientific research because it enables rapid development and provides rich ecosystems for data analysis, artificial intelligence (AI), and…
arXiv:2608.19891v1 Announce Type: new Abstract: How to efficiently finetune robot policies to learn new tasks on the fly? State of the art robotic manipulation policies are based on behaviour cloning of large…
arXiv:2408.08182v5 Announce Type: replace-cross Abstract: People with Parkinson's Disease (PD) often experience progressively worsening gait, including changes in how they turn around, as the disease progresses.…
arXiv:2608.20011v1 Announce Type: new Abstract: Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching,…
arXiv:2608.20087v1 Announce Type: cross Abstract: Humanoid robots have recently demonstrated promising capabilities in real-world ball sports. However, achieving professional motion styles while maintaining strong task…
arXiv:2605.10828v2 Announce Type: replace Abstract: As large language models are increasingly deployed in retrieval-augmented generation and agentic systems that accumulate extensive context, understanding how…
arXiv:2608.19215v1 Announce Type: new Abstract: Given deep uncertainty about the possibility of artificial consciousness, it is unclear how we should treat potentially sentient AI. On the one hand, we could assume…
arXiv:2509.02910v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act on people's behalf: they write emails, buy groceries, and book restaurants. While the outsourcing of human…
arXiv:2608.19854v1 Announce Type: cross Abstract: Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption…
arXiv:2608.19680v1 Announce Type: new Abstract: Smart contract vulnerability detection with Large Language Models (LLMs) faces three causally linked challenges. First, new vulnerability categories demand…
arXiv:2608.19889v1 Announce Type: new Abstract: The entire ecosystem of open-source language models effectively relies on a single platform. What if this platform was forced to shut down tomorrow? Implementing and…
arXiv:2608.19216v1 Announce Type: new Abstract: AI control research asks how to deploy models safely even when they may be misaligned, but many control protocols assume that the deployer can instrument the model and its…
arXiv:2605.22547v3 Announce Type: replace-cross Abstract: Medical image diagnosis has achieved significant progress with deep learning, yet existing methods often rely on isolated visual evidence and lack the ability to…
arXiv:2608.20231v1 Announce Type: cross Abstract: The standard objection to full automation is demand-side: if humans earn nothing, who buys the output? This confuses an accounting role with a biological species. We…
arXiv:2608.20316v1 Announce Type: new Abstract: Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the…
arXiv:2508.19008v3 Announce Type: replace Abstract: Building on a human-led thematic analysis of clinical life-story interviews (> 150,000 words) with inpatients with Borderline Personality Disorder, this study examines…
arXiv:2608.20009v1 Announce Type: new Abstract: Understanding object dynamics requires not only predicting future trajectories but also examining whether a model captures the physical properties that govern motion.…
arXiv:2608.17634v2 Announce Type: replace Abstract: The $\operatorname{do}$-operator is described graphically by deleting arrows into its targets and functionally by replacing their mechanisms with constants. To call…
arXiv:2608.19973v1 Announce Type: cross Abstract: Recently, open-vocabulary 3D object detection (3D-OVD) has gained increasing attention for its ability to detect unseen objects in 3D scenes. Existing approaches…
arXiv:2608.20114v1 Announce Type: new Abstract: Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action models, developed…
arXiv:2604.02794v2 Announce Type: replace Abstract: Charts are ubiquitous in scientific and financial literature for presenting structured data. However, chart reasoning remains challenging for multimodal large language…
arXiv:2608.19556v1 Announce Type: cross Abstract: Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the…
arXiv:2509.13570v2 Announce Type: replace Abstract: With the rapid rise of generative AI in higher education, understanding how students use AI is increasingly important. This exploratory study examines student use and…
arXiv:2608.19738v1 Announce Type: cross Abstract: Full-cycle biventricular geometry is essential for characterizing cardiac function. However, dense and temporally consistent 3D+t biventricular meshes are not routinely…
arXiv:2608.20229v1 Announce Type: cross Abstract: Anatomically plausible segmentation remains challenging because of low contrast, ambiguous boundaries, and modality-specific artifacts. Interactive segmentation has…
arXiv:2608.20237v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) combine linguistic reasoning with visual perception, yet their ability to perform visual spatial planning under explicit or…
arXiv:2509.08521v2 Announce Type: replace-cross Abstract: FMT$^{*}$ plans efficiently in static worlds by expanding a cost-ordered wavefront and collision-checking lazily, but its single-pass unvisited rule cannot…
arXiv:2608.20161v1 Announce Type: new Abstract: Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a diffusion model…
arXiv:2608.19222v1 Announce Type: new Abstract: Social relationships shape access to resources, exposure to conflict and group stability, yet automated livestock monitoring typically treats behaviour as isolated events.…
arXiv:2608.19901v1 Announce Type: cross Abstract: Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a direct distribution…
arXiv:2608.19974v1 Announce Type: new Abstract: LLM agents in financial markets may cite rules yet still submit orders that violate executable constraints or misread surveillance evidence. We introduce ReguSim, a…
arXiv:2501.06491v4 Announce Type: replace-cross Abstract: This study emphasizes the domain of requirements engineering by applying the SMOTE-Tomek preprocessing technique, combined with stratified K-fold…
arXiv:2608.11322v2 Announce Type: replace-cross Abstract: Human-AI research often evaluates individual capabilities, joint performance, or final outputs, but these approaches can lose the interaction process that…
arXiv:2608.19950v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are increasingly used across domains to provide personalized information, recommendations, and decision support. However, in some…
