Topic · Edition
arXiv:2608.12928v1 Announce Type: new Abstract: We introduce a Polish-language medical visual question answering (VQA) benchmark, built from Polish Board Certification Examination questions for licensed physicians and…
arXiv:2608.12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains…
arXiv:2608.12743v1 Announce Type: new Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ability of VLM agents,…
arXiv:2608.12327v1 Announce Type: cross Abstract: Multilingual pretrained models nominally support Nepali, yet no controlled benchmark has compared them under a single fine-tuning protocol. We fine-tune six pretrained…
arXiv:2608.13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU. Dispatchers balance token counts (EPLB, LPLB, UltraEP) or activated-expert counts…
arXiv:2608.13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants. We challenge this default paradigm by empirically evaluating the…
arXiv:2608.12339v1 Announce Type: cross Abstract: Large Language models (LLMs) were found to be susceptible to a host of social, affective, and cognitive biases. We examined two mechanisms through which such biases can…
arXiv:2605.18793v3 Announce Type: replace-cross Abstract: Accurate spatiotemporal pattern analysis is critical in fields such as urban traffic, meteorology, and public health monitoring. However, existing methods face…
arXiv:2608.12880v1 Announce Type: cross Abstract: Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180…
arXiv:2608.12441v1 Announce Type: cross Abstract: Deep learning detectors for anomalies in dynamic graphs have reached strong accuracy, yet they remain opaque: when an edge is flagged, the analyst receives a score but…
arXiv:2608.13472v1 Announce Type: cross Abstract: Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition. Among recent…
arXiv:2608.12689v1 Announce Type: cross Abstract: Multi-parametric magnetic resonance imaging (mpMRI) is a cornerstone for brain tumor diagnosis and treatment, yet current AI models face critical limitations: their lack…
arXiv:2608.13389v1 Announce Type: new Abstract: Enterprise security topology design requires translating business intent, regulatory requirements, and risk assumptions into zones, boundary devices, inter-zone paths, and…
arXiv:2608.12869v1 Announce Type: cross Abstract: Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure of loss-surface…
arXiv:2605.08756v2 Announce Type: replace Abstract: Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large…
arXiv:2608.12574v1 Announce Type: new Abstract: Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection from a finite set of…
arXiv:2608.12675v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. Existing privacy research on RAG…
arXiv:2608.13558v1 Announce Type: new Abstract: Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to…
arXiv:2608.13258v1 Announce Type: cross Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, but no prior work…
arXiv:2608.12627v1 Announce Type: 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:2608.13262v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain…
arXiv:2608.13144v1 Announce Type: cross Abstract: As edge-side vision services continue to expand toward low-latency, high-throughput scenarios, reducing the inference cost of vision models without sacrificing…
arXiv:2608.13409v1 Announce Type: new Abstract: Existing predictive models in learning analytics often treat student academic history as a simple sequence, overlooking the concurrent nature of courses taken within a…
arXiv:2608.13108v1 Announce Type: new Abstract: Multi-source evidence fusion under Dempster-Shafer theory faces two persistent challenges: existing conflict measures assess inter-evidence inconsistency and…
arXiv:2608.13136v1 Announce Type: cross Abstract: With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention. Existing approaches enable LLMs to retrieve…
arXiv:2608.12428v1 Announce Type: new Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory…
arXiv:2606.29699v2 Announce Type: replace-cross Abstract: Visual shifts can cause a vision-language-action policy to fail after initially plausible behavior. We ask whether OpenVLA's internal activations contain signals…
arXiv:2608.13200v1 Announce Type: cross Abstract: Modern LLMs excel at reasoning and instruction following, enabling users to express complex and diverse information needs. However, conventional retrievers largely rely…
arXiv:2608.12323v1 Announce Type: cross Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation. We demonstrate that this enforcement information…
arXiv:2608.12906v1 Announce Type: cross Abstract: RNA-Protein Interactions (RPIs) are critical for regulating cellular functions. While traditional wet-lab experiments for RPI detection are costly and time-consuming,…
arXiv:2608.13465v1 Announce Type: cross Abstract: Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Machine learning models…
arXiv:2608.12788v1 Announce Type: new Abstract: The rapid advancement of Auto-Research has surfaced a fundamental evaluation challenge: how can we measure the alignment, logical coherence, and evolutionary completeness…
arXiv:2608.13555v1 Announce Type: cross Abstract: Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors…
arXiv:2608.13221v1 Announce Type: new Abstract: The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning…
arXiv:2606.03089v3 Announce Type: replace-cross Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense…
arXiv:2608.03025v3 Announce Type: replace Abstract: Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual evidence.…
arXiv:2608.01735v2 Announce Type: replace Abstract: On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged information but can induce a…
arXiv:2608.12320v1 Announce Type: cross Abstract: This article reviews and updates the framework for accountability in AI based on account- ability ecosystems. We update the framework in light of the latest developments…
arXiv:2608.12600v1 Announce Type: cross Abstract: A critical challenge in deploying online HD map construction systems to real-world scenarios is the scarcity of labeled training data, which limits model generalization…
arXiv:2608.12363v1 Announce Type: cross Abstract: European countries are debating policies to mitigate the increased energy costs caused by renewed geopolitical tensions, while pursuing decarbonization and…
arXiv:2608.12657v1 Announce Type: new Abstract: Probabilities of causation (PoCs) characterize individual causal responses that cannot be directly observed and therefore generally require partial identification. Tian…
arXiv:2605.17985v2 Announce Type: replace-cross Abstract: We propose a new method for compressing physics foundation models (PFMs) which is a new trend in AI for Science. While model compression is essential for…
arXiv:2608.13368v1 Announce Type: cross Abstract: This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance…
arXiv:2510.21805v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by…
arXiv:2608.13341v1 Announce Type: cross Abstract: Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional…
arXiv:2608.12845v1 Announce Type: cross Abstract: Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overlooked fairness issue,…
arXiv:2606.02253v2 Announce Type: replace Abstract: Increasing the circularity of resource use in our society has been recognized as a path to sustainability, i.e., transitioning into a more circular economy. There are…
arXiv:2608.12440v1 Announce Type: cross Abstract: This paper reports a single, fully instrumented case study of a large-scale architectural refactoring by an AI coding agent under a specification-first protocol, with no…
arXiv:2608.13060v1 Announce Type: new Abstract: Machine learning theory studies learning procedures through mathematical setups in which the data model, training protocol, oracle access, loss, metric, and randomness…
arXiv:2605.20088v2 Announce Type: replace-cross Abstract: Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of time-series…
arXiv:2608.13061v1 Announce Type: new Abstract: As the feature representation changes, replay must preserve the earlier classes. However, only a bounded active exemplar set can be replayed. We propose Uniform Herding,…
arXiv:2606.16454v2 Announce Type: replace-cross Abstract: Low-Rank Adaptation (LoRA) enables efficient adaptation of large pretrained models to downstream tasks by parameterizing weight updates with low-rank matrices.…
arXiv:2608.12594v1 Announce Type: cross Abstract: As more investors contemplate private markets and contend with limited transparency, sparse disclosures, and infrequent transactions, identifying economically meaningful…
arXiv:2608.13283v1 Announce Type: new Abstract: Understanding motion in daily living requires context beyond kinematics, because similar inertial patterns during activities of daily living (ADLs) can reflect intentional…
arXiv:2608.13331v1 Announce Type: cross Abstract: The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further experiments. The act…
arXiv:2608.13428v1 Announce Type: new Abstract: Assessing the maturity of artificial intelligence technologies is essential for investment decisions, project management, and policy monitoring, yet the available…
arXiv:2608.12863v1 Announce Type: new Abstract: As AI systems proliferate in consumer facing applications, questions about liability for AI related harms remain unresolved. This working paper examines whether India's…
arXiv:2608.12218v2 Announce Type: replace-cross Abstract: Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories. This scaling…
arXiv:2608.12895v1 Announce Type: new Abstract: Compositional reliability bounds for multi-agent systems multiply component reliabilities, a step licensed by a conditional-independence assumption that is routinely…
arXiv:2508.12220v2 Announce Type: replace-cross Abstract: Can a prospectively instrumented training continuation reproduce a deletion counterfactual exactly after selected examples leave its replay dataset? We study a…
arXiv:2608.12779v1 Announce Type: cross Abstract: Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality assessment. Clinical…
arXiv:2608.12854v1 Announce Type: cross Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only…
arXiv:2608.12374v1 Announce Type: cross Abstract: Language models (LMs) struggle with logical tasks like reasoning on syllogisms. It has been shown that Knowledge Representation (KR) plays a crucial role in expressing…
arXiv:2608.13345v1 Announce Type: new Abstract: Artificial Intelligence (AI) safety systems combine character shaping (e.g., Reinforcement Learning from Human Feedback [RLHF], Constitutional AI), which modifies…
arXiv:2608.13272v1 Announce Type: new Abstract: A small number of firms based in two states produce the most capable frontier AI models. The governments of those states have shown both the legal power and the political…
arXiv:2608.13063v1 Announce Type: new Abstract: Prior work on LLM behavior under anomalous conditions asks whether a model notices anomalies. We ask a narrower question: once a model sits in a workflow with a low,…
arXiv:2608.12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or…
arXiv:2608.13228v1 Announce Type: new Abstract: Agent harnesses combine retrieval, routing, state, provenance, and verification, but locally successful components may disagree on shared state. We model this failure with…
arXiv:2608.13522v1 Announce Type: cross Abstract: AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent…
arXiv:2608.09538v2 Announce Type: replace-cross Abstract: We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench…
arXiv:2608.13087v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identical for every…
arXiv:2506.17337v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings. However, developing specialist medical…
arXiv:2608.12389v1 Announce Type: new Abstract: Cross-domain zero- or few-shot personalization aims to generate user-preferred responses in unseen conversational domains from only a handful of target-domain…
arXiv:2608.12926v1 Announce Type: cross Abstract: Traditional player evaluation in professional handball relies on basic box-score metrics or heuristic indices, which fail to credit the multi-player build-up chain.…
arXiv:2608.13100v1 Announce Type: new Abstract: Contemporary online assessment systems rely primarily on browser lockdown, webcam monitoring, and behavioural analytics, yet remain vulnerable to attacks that extract the…
arXiv:2608.11521v2 Announce Type: replace-cross Abstract: World action models (WAMs) condition robot actions on predicted futures, but iterative video rollout increases deployment latency. We ask whether action…
arXiv:2605.31034v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling multiple…
arXiv:2608.13517v1 Announce Type: cross Abstract: Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and…
arXiv:2608.13476v1 Announce Type: new Abstract: We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent orchestration for…
arXiv:2608.12843v1 Announce Type: cross Abstract: Text-based person anomaly retrieval aims to retrieve pedestrians exhibiting anomalous behaviors from a large image gallery using natural language descriptions. Compared…
arXiv:2608.12356v1 Announce Type: cross Abstract: A college offering several overlapping computing degrees implicitly assumes that its programs are differentiated in line with how the labor market segments computing…
arXiv:2608.12331v1 Announce Type: cross Abstract: Reasoning language models generate lengthy chain-of-thought (CoT) sequences whose key-value (KV) cache grows linearly and becomes a memory bottleneck during decoding.…
arXiv:2604.23859v3 Announce Type: replace Abstract: With spotforecast2-safe we present an integrated Compliance-by-Design approach to Python-based point forecasting of time series in safety-critical environments. A…
arXiv:2506.06331v2 Announce Type: replace-cross Abstract: By retrieving contexts from knowledge graphs, graph-based retrieval-augmented generation (GraphRAG) enhances large language models (LLMs) to generate quality…
arXiv:2608.12334v1 Announce Type: cross Abstract: Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood. In this work, we…
arXiv:2608.13420v1 Announce Type: new Abstract: Embodied intelligent virtual agents are expected to operate as persistent, adaptive, and context-aware entities within complex virtual and Metaverse worlds. However,…
arXiv:2608.10363v2 Announce Type: replace Abstract: AI agents can accelerate nutrition research, but their analyses inherit the identity, semantic, and release ambiguities of the underlying data. We present Nutrition…
arXiv:2608.13048v1 Announce Type: new Abstract: In this work, we introduce DMDIntel which uses dynamic mode decomposition (DMD) to make the predictions made by LLMs in a classification task interpretable. It develops an…
arXiv:2608.12333v1 Announce Type: cross Abstract: Vision-language models must associate visual entities with textual attributes. Whether these associations or concept bindings remain stable when the language of the…
arXiv:2603.14501v2 Announce Type: replace-cross Abstract: Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming…
arXiv:2608.13160v1 Announce Type: cross Abstract: Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex multilingual question…
arXiv:2608.10805v2 Announce Type: replace-cross Abstract: Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive field…
arXiv:2608.05466v3 Announce Type: replace Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must…
arXiv:2608.13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty levels. We propose…
arXiv:2608.12426v1 Announce Type: new Abstract: Large language models are increasingly deployed in settings that require simultaneous adherence to multiple explicit constraints - reasoning structure, safety boundaries,…
arXiv:2608.12977v1 Announce Type: cross Abstract: The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective…
arXiv:2608.13046v1 Announce Type: new Abstract: Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-agent systems, humans…
arXiv:2608.12654v1 Announce Type: new Abstract: Long-running LLM agents act through tools, and a single step can send an email, merge a pull request, or wire a payment. The steering decision is the pre-commit choice at…
arXiv:2502.17666v5 Announce Type: replace-cross Abstract: Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have…
arXiv:2501.14844v3 Announce Type: replace-cross Abstract: Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings.…
arXiv:2608.13344v1 Announce Type: new Abstract: Long-horizon Earth observation reasoning requires models to organize multi-stage geographic evolution, localize spatial changes, detect temporal anomalies, and infer…
arXiv:2608.12593v1 Announce Type: new Abstract: Discovery---formulating novel generalizations---is a central part of the scientific process. Despite its importance, there is a gap in the current AI benchmark landscape,…
arXiv:2608.12640v1 Announce Type: cross Abstract: Causal discovery aims to uncover the underlying causal relationships given data generated from a system. The goal, however, is not merely to predict causal edges given…
arXiv:2608.12582v1 Announce Type: cross Abstract: AI journaling tools can tailor prompts to a person's own sensed behavior, but it is unclear which behaviors respond to them. We analyzed 369 journal entries from an…
arXiv:2608.13082v1 Announce Type: cross Abstract: Generative models of limit orderbook (LOB) data have advanced rapidly, but their evaluation often focuses on stylised facts and selected market statistics. These…
arXiv:2608.12630v1 Announce Type: cross Abstract: While large language models can generate entire novels, there is little information about the level of formal variation in their output over many generations. Rather…
arXiv:2511.07820v4 Announce Type: replace-cross Abstract: Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (GPUs), similar scaling gains have not been shown…
arXiv:2608.12680v1 Announce Type: cross Abstract: Item demand forecasting is an integral component of store assortment optimization. Existing literature focuses on learning a suitable customer choice model and using…
arXiv:2608.13459v1 Announce Type: cross Abstract: We address the use of large language models (LLMs) to help discover Isabelle proofs. An Isabelle build establishes that the submitted theory is accepted, but not that an…
arXiv:2606.07316v2 Announce Type: replace-cross Abstract: Can a committee of LLM agents reach agreement that is certifiable at the level of meaning, not only at the level of a label? We build a protocol to find out.…
arXiv:2608.08443v2 Announce Type: replace-cross Abstract: Previous studies have shown that people can develop shared symbols, partner-specific expressions, personal idioms, inside jokes, and other parts of a relational…
arXiv:2608.13433v1 Announce Type: cross Abstract: Transformer-based language models are known to sometimes generalize to sequences longer than seen during training, but we lack a precise characterization of which tasks…
arXiv:2608.12322v1 Announce Type: cross Abstract: Self-reflection is widely assumed to improve LLM reasoning, yet which component drives the gain remains poorly understood. We present a controlled six-condition ablation…
arXiv:2608.13484v1 Announce Type: cross Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We…
arXiv:2604.15489v2 Announce Type: replace-cross Abstract: The Internet of Medical Things (IoMT) enables intelligent healthcare services but faces challenges such as dynamic topology, energy constraints, and diverse QoS…
arXiv:2608.12720v1 Announce Type: cross Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely…
arXiv:2608.12761v1 Announce Type: new Abstract: Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct action may rely on the…
arXiv:2608.12352v1 Announce Type: cross Abstract: AI governance frameworks can be known, used, and implemented in form without becoming governance in practice. This paper examines that problem through a role-based…
arXiv:2601.11618v3 Announce Type: replace-cross Abstract: Neural architecture is often identified by module syntax, computation graphs, or the composite functions they realize. These descriptions answer different…
arXiv:2608.07335v2 Announce Type: replace-cross Abstract: Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms. Notably, the Parallelized Q-Network (PQN)…
arXiv:2512.19799v2 Announce Type: replace Abstract: Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because research requires…
arXiv:2608.12371v1 Announce Type: new Abstract: Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent…
arXiv:2608.13167v1 Announce Type: cross Abstract: When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that Vision-Language Models (VLMs) can internally distinguish when abstention…
arXiv:2607.23496v2 Announce Type: replace Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards.…
arXiv:2508.14390v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often express verbal confidence that is poorly aligned with actual correctness, limiting their reliability in safety-critical…
arXiv:2608.12935v1 Announce Type: new Abstract: Perturbation methods explain model decisions by measuring prediction changes under altered inputs, but response magnitude tells us only how much a model reacts, not what…
arXiv:2608.12715v1 Announce Type: cross Abstract: Generative speech enhancement faces three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but miss harmonics,…
arXiv:2601.10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high inference latency from…
arXiv:2608.11392v2 Announce Type: replace-cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary. Recent work shows that dropping a standing…
arXiv:2607.15774v3 Announce Type: replace-cross Abstract: Explainable AI (XAI) for time series has seen significant algorithmic growth, but its utility in providing measurable performance gains for downstream tasks…
arXiv:2608.12555v1 Announce Type: new Abstract: Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the real-world outcome. We introduce the Causal…
arXiv:2608.12446v1 Announce Type: cross Abstract: Sleep stage classification is important for the diagnosis and management of sleep disorders, yet most automatic staging studies evaluate models against a single…
arXiv:2608.07070v2 Announce Type: replace-cross Abstract: With the rapid diffusion of AI-generated content, AI-driven misinformation is becoming increasingly pervasive and difficult to govern, undermining information…
arXiv:2608.12670v1 Announce Type: new Abstract: IT service management (ITSM) systems accumulate large volumes of heterogeneous ticket data that are difficult for sales and executive stakeholders to convert into…
arXiv:2607.26661v3 Announce Type: replace Abstract: Ascend C operator optimization is critical for NPU (Neural Processing Unit) inference performance but requires deep hardware expertise. While large language models…
arXiv:2608.13179v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its trajectory-level…
arXiv:2608.11911v2 Announce Type: replace-cross Abstract: A central promise of useful quantum advantage is the ability to compute ground states of Hamiltonian systems beyond the reach of classical simulation methods.…
arXiv:2510.22282v2 Announce Type: replace-cross Abstract: Urban socio-economic sensing plays a vital role in advancing global sustainable development goals. With the advent of Large Vision-Language Models (LVLMs), new…
arXiv:2607.14573v4 Announce Type: replace Abstract: Payment integration is a demanding repository-level software task: agents must select a suitable product, implement coordinated client-server flows, verify payment…
arXiv:2608.12346v1 Announce Type: new Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily be misused by…
arXiv:2608.12325v1 Announce Type: new Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent advances have mainly…
arXiv:2604.09670v3 Announce Type: replace-cross Abstract: Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments. This capacity, known as working memory, is…
arXiv:2608.13113v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video…
arXiv:2608.12385v1 Announce Type: new Abstract: As large language models serve more requests, cumulative inference cost is becoming increasingly important relative to one-time training cost. The two inference phases…
arXiv:2608.13076v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success in natural language understanding and generation, but their deployment is constrained by high computational…
arXiv:2608.12351v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) has challenged the validity of unsupervised online assessment, especially in technical subjects where plausible answers can be…
arXiv:2608.13317v1 Announce Type: new Abstract: Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the…
arXiv:2608.12355v1 Announce Type: cross Abstract: Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering tasks, from editing…
arXiv:2608.13430v1 Announce Type: cross Abstract: Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence.…
arXiv:2608.12674v1 Announce Type: new Abstract: Maintaining price consistency and executing an Every Day Low Price strategy is critical for global retailers. However, with catalogs spanning millions of active items,…
arXiv:2608.12751v1 Announce Type: cross Abstract: Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning…
arXiv:2608.13438v1 Announce Type: cross Abstract: Contact-rich manipulation failures are often detected only after the robot has committed to contact. This is especially limiting in wrist-camera setups: close…
arXiv:2608.13547v1 Announce Type: new Abstract: LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish…
arXiv:2608.13226v1 Announce Type: cross Abstract: While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe…
arXiv:2608.12645v1 Announce Type: new Abstract: LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling. Judges are typically validated by accuracy on golden data, but…
arXiv:2608.13267v1 Announce Type: cross Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with…
arXiv:2608.13410v1 Announce Type: new Abstract: Parliamentary proceedings are a primary record of democratic deliberation, yet their volume and fragmentation make multi-perspective access difficult for citizens,…
arXiv:2512.17897v2 Announce Type: replace-cross Abstract: We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient…
arXiv:2511.22651v2 Announce Type: replace-cross Abstract: Optimization methods have long advanced many fields, yet they struggle when faced with design problems where the search space and design parameters are difficult…
arXiv:2608.12329v1 Announce Type: cross Abstract: Progress on AI for psychosis-risk assessment is limited by a data-access bottleneck. Real clinical interviews are difficult to share because of privacy, governance, and…
arXiv:2608.12345v1 Announce Type: new Abstract: Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasured. We introduce…
arXiv:2608.13277v1 Announce Type: cross Abstract: We ask whether language-model pre-training can be decomposed into smaller, independently trainable jobs that can later be recomposed into a coherent larger model. We…
arXiv:2608.12750v1 Announce Type: cross Abstract: LLM-based simulated clients are increasingly used to train novice counselors, evaluate LLM therapists, and generate synthetic data. However, current simulators produce…
arXiv:2604.23724v4 Announce Type: replace-cross Abstract: Expressway video anomaly detection is important for traffic safety, but remains challenging across diverse scenes, particularly for far-field vehicles with…
arXiv:2608.10766v2 Announce Type: replace Abstract: Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose ''Rule of Thumb''…
arXiv:2608.13545v1 Announce Type: cross Abstract: Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to…
arXiv:2505.13372v2 Announce Type: replace Abstract: Recent work investigated the use of Reinforcement Learning (RL) for the synthesis of heuristic guidance to improve the performance of temporal planners when a domain…
arXiv:2607.19058v2 Announce Type: replace-cross Abstract: Optimizer state is the largest single line item in the memory budget of mixture-of-experts (MoE) training. On a 6.78B-parameter MoE language model AdamW keeps…
arXiv:2505.15274v4 Announce Type: replace Abstract: Probabilities of causation (PoCs) are fundamental quantities for counterfactual analysis and personalized decision making. However, existing analytical results are…
arXiv:2604.05485v2 Announce Type: replace Abstract: LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only…
arXiv:2603.16946v2 Announce Type: replace-cross Abstract: Currently, an excessive amount of event data is being obtained in four-dimensional inelastic neutron-scattering experiments. A method for automatic bin-width…
arXiv:2505.12532v3 Announce Type: replace-cross Abstract: Efficiently adapting large pretrained models is critical under tight compute and memory budgets. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA…
arXiv:2608.12852v1 Announce Type: cross Abstract: Language can describe states of affairs that are false and states of affairs that could not be the case at all. Whether an AI model internally distinguishes these…
arXiv:2608.12395v1 Announce Type: new Abstract: We describe Research Assistant, an internal LLM-based system developed at AstraZeneca to help scientists and clinicians explore biomedical questions across a broad range…
arXiv:2608.13255v1 Announce Type: cross Abstract: Geometry-conditioned multi-view diffusion enables high-quality 3D texture generation, but its repeated per-view denoiser evaluations introduce substantial computational…
arXiv:2608.13129v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong results on mathematical reasoning benchmarks yet remain unreliable on elementary numerical tasks, including magnitude…
arXiv:2608.13293v1 Announce Type: new Abstract: Edge AI deployment demands neural architectures that are simultaneously accurate, computationally efficient, and hardware-deployable - a challenge addressed by…
arXiv:2608.12476v1 Announce Type: new Abstract: Long-term agent memory is usually treated as select--store--retrieve, but retrieval does not decide whether contradictory, superseded, retracted, deleted, or stale records…
arXiv:2608.12358v1 Announce Type: cross Abstract: Product and engineering teams building role-bearing AI agents face an evaluation gap: an agent can produce accurate, safe, and fluent content while still failing the…
arXiv:2608.11344v2 Announce Type: replace-cross Abstract: Financial institutions are delegating consequential decisions to agentic AI systems that decompose goals, coordinate models and tools, and act with little…
arXiv:2608.12987v1 Announce Type: cross Abstract: Generative information retrieval (GIR) has emerged as a compelling alternative to the conventional index-retrieve-then-rank retrieval pipeline by training a generator to…
arXiv:2608.12377v1 Announce Type: cross Abstract: Brains and large language models (LLMs) are fundamentally different memory systems, but they can be compared through shared functional questions: where memory-related…
arXiv:2608.12841v1 Announce Type: cross Abstract: We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve…
arXiv:2608.13328v1 Announce Type: cross Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more…
arXiv:2608.13050v1 Announce Type: cross Abstract: When a security researcher publishes a report on a cyberattack, detection engineers are supposed to turn it into working detection rules. In practice, most automated…
arXiv:2607.23982v4 Announce Type: replace-cross Abstract: Cooperation can fail when socially valuable effort is costly, hard to observe, and benefits mainly someone else. Building on Holmstr\"om's model of moral hazard…
arXiv:2607.22699v2 Announce Type: replace Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond…
arXiv:2607.25497v2 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:2608.03172v3 Announce Type: replace Abstract: Structure-preserving de-identification replaces protected health information (PHI) with realistic same-type surrogates -- "Anna S." becomes "Maria S.", not [NAME] --…
arXiv:2608.12443v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a…
arXiv:2501.09700v2 Announce Type: replace-cross Abstract: Electroencephalogram (EEG) signals have emerged as a promising modality for biometric identification. While previous studies have explored the use of imagined…
arXiv:2510.05678v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have achieved notable progress in multilingual settings, their performance remains uneven across languages as LLMs often rely…
arXiv:2608.13456v1 Announce Type: new Abstract: World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study…
arXiv:2608.13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and…
arXiv:2608.12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is…
arXiv:2608.06161v2 Announce Type: replace Abstract: Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism…
arXiv:2606.21202v2 Announce Type: replace-cross Abstract: Reaching global agreement from purely local interactions is a defining problem of collective intelligence, and most models of it assume that all agents share a…
arXiv:2608.13120v1 Announce Type: new Abstract: Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the…
arXiv:2608.12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signals during…
arXiv:2608.12898v1 Announce Type: cross Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable representations. Recent advances in Vision-Language Models (VLMs) have…
arXiv:2608.13305v1 Announce Type: cross Abstract: Estimating the distribution of relaxation times (DRT) fromelectrochemical impedance spectroscopy (EIS) is an ill-posed inverse problem that is highly sensitive to…
arXiv:2603.08322v2 Announce Type: replace Abstract: We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with symbolic…
arXiv:2608.11195v2 Announce Type: replace Abstract: AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how…
arXiv:2608.12522v1 Announce Type: new Abstract: LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in…
arXiv:2510.06200v4 Announce Type: replace-cross Abstract: Current time series foundation model (TSFM) training corpora largely omit data with certain complexities like irregular temporal sampling. Astronomical time…
arXiv:2608.13210v1 Announce Type: cross Abstract: Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that…
arXiv:2608.13296v1 Announce Type: cross Abstract: Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This…
arXiv:2608.12876v1 Announce Type: cross Abstract: Detecting AI-generated images is only half the task: a deployed detector must also justify its verdict, yet existing detectors inherit three failure modes from their…
arXiv:2606.01896v2 Announce Type: replace-cross Abstract: Generated (or synthetic) image data is increasingly used to augment or replace real training datasets when target imagery is scarce, expensive, or biased. For…
arXiv:2411.16818v2 Announce Type: replace-cross Abstract: To evaluate a multi-representational framework in which large language model (LLM)-generated expert summaries of intensive care unit (ICU) notes are fused with…
arXiv:2604.17299v3 Announce Type: replace-cross Abstract: Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful…
arXiv:2604.27906v3 Announce Type: replace Abstract: Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This…
arXiv:2608.12373v1 Announce Type: new Abstract: Large language models are increasingly used in strategic and advisory contexts, yet their safety alignment is typically evaluated in English only. We test nine models from…
arXiv:2608.12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated,…
arXiv:2606.05389v2 Announce Type: replace Abstract: Lossy compression is essential for massive spatiotemporal data from scientific simulations. Learned compressors can achieve high compression ratios at moderate…
arXiv:2608.12806v1 Announce Type: cross Abstract: The exceptional generation capabilities of text-to-image diffusion models have raised copyright concerns, particularly the unauthorized reproduction of animation…
arXiv:2607.05031v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly decide whether software behaves correctly, either by writing a test oracle or by acting as one. Yet two oracles can…
arXiv:2608.13453v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of…
arXiv:2608.11941v2 Announce Type: replace Abstract: We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conjectures had…
arXiv:2606.00367v2 Announce Type: replace-cross Abstract: Reinforcement learning with scalar rewards is widely used for aligning machine-learning systems with user preferences. But, pairwise preferences are often more…
arXiv:2608.13031v1 Announce Type: cross Abstract: Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents, violations, and…
arXiv:2608.12789v1 Announce Type: cross Abstract: Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should…
arXiv:2608.12995v1 Announce Type: new Abstract: Heterogeneous USV cooperative pursuit in constrained port waterways requires evader interception under navigation, traffic, and role constraints. This paper proposes…
arXiv:2608.12915v1 Announce Type: cross Abstract: The rapid growth of LLM inference is shifting sustainability concerns from one-time training to continuous serving, where infrastructure decisions shape energy use,…
arXiv:2608.13029v1 Announce Type: cross Abstract: The field of bioinformatics struggles with legacy code - old code that is commonly used but may no longer have a maintainer, or may be written in an now-unfamiliar…
arXiv:2608.12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state. An unsafe success can thereby become reusable policy after its triggering input…
arXiv:2608.13394v1 Announce Type: cross Abstract: 6G networks will not be serving as communication infrastructures only; rather, they are expected to evolve into intelligent systems, where thousands of autonomous…
arXiv:2412.17228v4 Announce Type: replace Abstract: Background: Clinical trials are essential to advancing cancer treatments, but fewer than 10% of adults with cancer enroll in therapeutic trials. Open-source AI trial…
arXiv:2606.20077v2 Announce Type: replace-cross Abstract: Visual tokens enter Large Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interact with the language…
arXiv:2608.13415v1 Announce Type: cross Abstract: We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learning algorithm,…
arXiv:2608.11698v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher. Reward-extrapolation methods such as…
arXiv:2608.13426v1 Announce Type: cross Abstract: Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications. We propose…
arXiv:2608.12836v1 Announce Type: cross Abstract: Large language models often fail when answer options require combining atomic judgments under explicit logical operators, even when they judge the individual atoms…
arXiv:2608.05018v3 Announce Type: replace Abstract: Short-term load forecasting (STLF) plays a vital role in the electric power industry. It is relevant for critical infrastructure. STLF is no longer purely a…
arXiv:2608.12365v1 Announce Type: cross Abstract: For fifty years, data systems have answered two questions. The relational model asked which records match a predicate; the vector model asked which vectors lie nearest a…
arXiv:2608.12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs). Yet agreement in final labels does not show that human…
arXiv:2607.27431v4 Announce Type: replace-cross Abstract: Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and…
arXiv:2607.23126v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI tools has created new literacy demands for designers who must verbalize tacit knowledge through natural language prompts. Yet…
arXiv:2608.11616v2 Announce Type: replace Abstract: Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet existing approaches remain confined to a text-only…
arXiv:2606.26902v2 Announce Type: replace Abstract: Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference.…
arXiv:2608.12713v1 Announce Type: cross Abstract: Watermarking LLM-generated text is an important task for tracing its provenance. Existing LLM watermarks preserve provenance under editing, but this same robustness…
arXiv:2608.12336v1 Announce Type: cross Abstract: A story premise is the creative spark from which a full narrative can grow. Yet LLM-based story generation has mostly emphasized later-stage planning, controllability,…
arXiv:2608.13156v1 Announce Type: new Abstract: Pre-norm is the standard normalization placement in modern Transformers because it facilitates joint optimization of full-depth models. We ask whether this preference…
arXiv:2601.19612v4 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this…
arXiv:2608.12597v1 Announce Type: cross Abstract: Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a full parameter update…
arXiv:2608.13250v1 Announce Type: cross Abstract: Normative datasets are often used to train and align AI systems, but the norms they contain can function as action-guiding patterns rather than neutral moral knowledge.…
arXiv:2608.13333v1 Announce Type: new Abstract: Large neighborhood search normally selects a random subset of decision variables for iterative optimization. For efficiently solving different problems, researchers tend…
arXiv:2608.13173v1 Announce Type: new Abstract: Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Existing agent skills…
arXiv:2608.12762v1 Announce Type: new Abstract: Schedulability analysis is essential for certifying real-time systems, but existing tests are often developed through pen-and-paper proofs that are difficult to scale,…
arXiv:2608.12350v1 Announce Type: cross Abstract: The energy demand growth and environmental impacts of artificial intelligence (AI) have generated substantial interest in supplying sufficient low-cost electricity for…
arXiv:2606.04032v3 Announce Type: replace-cross Abstract: Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role. However,…
arXiv:2608.12590v1 Announce Type: new Abstract: Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation…
arXiv:2605.18852v2 Announce Type: replace-cross Abstract: Selecting a final checkpoint for multimodal large language models (MLLMs) is challenging when late-stage candidates are closely matched and downstream evaluation…
arXiv:2608.12959v1 Announce Type: cross Abstract: Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades. On a reproduction of…
arXiv:2608.12671v1 Announce Type: new Abstract: Multi-layer transformers form the critical component of essentially all large language models (LLMs) in use today. Because of their ubiquity and computational capability,…
arXiv:2410.02091v4 Announce Type: replace-cross Abstract: Generative artificial intelligence (AI) facilitates content production and enhances ideation, with potentially important implications for developer productivity…
arXiv:2608.12679v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in discovery domains such as math and science. The usual approach is to present the problem to the model and use its…
arXiv:2608.12348v1 Announce Type: cross Abstract: Streaming systems increasingly hand work to large language models (LLMs) -- writing pipelines, triaging alerts, reading logs -- and all of it assumes the model knows how…
arXiv:2608.13492v1 Announce Type: new Abstract: This report presents an improved version of AlayaWorld. While the backbone architecture, chunk-wise autoregressive generation scheme, and training data remain unchanged…
arXiv:2608.12529v1 Announce Type: cross Abstract: Motivation: LinkML is a suitable language for the representation of the structural and content constraints of different kinds of biomedical data. Even if it is a quite…
arXiv:2608.13560v1 Announce Type: cross Abstract: Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a…
arXiv:2608.12932v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control.…
arXiv:2608.13043v1 Announce Type: new Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead. While cache-based acceleration has emerged as a…
arXiv:2608.12429v1 Announce Type: cross Abstract: Web agents often struggle to generalize to unseen websites because they lack website-specific supervision. Recent exploration-based data synthesis methods reduce manual…
arXiv:2608.12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals. In these settings, finite attention…
arXiv:2608.12961v1 Announce Type: new Abstract: The OWL 2 EL profile is used in some of the largest production ontologies, including the Gene Ontology and SNOMED CT. Existing neuro-symbolic (NeSy) learning methods…
arXiv:2608.13018v1 Announce Type: new Abstract: Standard probabilistic logic programming frameworks typically rely on grounding logic programs into discrete propositional representations. This operational requirement…
arXiv:2608.12831v1 Announce Type: cross Abstract: Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model agents---while each…
arXiv:2608.12892v1 Announce Type: new Abstract: Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime.…
arXiv:2608.13315v1 Announce Type: cross Abstract: We study a large language model (LLM) service in which a provider chooses a per-token price and a default reasoning-token allocation, while a user may accept the…
arXiv:2602.01910v2 Announce Type: replace Abstract: Smart-home sensor-based behavioral monitoring holds significant potential for healthcare, independent living, and early detection of functional or cognitive changes.…
arXiv:2608.12372v1 Announce Type: new Abstract: AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly…
arXiv:2505.04997v3 Announce Type: replace Abstract: Computational fluid dynamics (CFD) has been the main workhorse of computational physics, yet its steep learning curve and fragmented, multi-stage workflow create…
arXiv:2608.12398v1 Announce Type: cross Abstract: We propose IM-LEPP (Integrated Multimodal Latent Energy-based Predictive Processing), a hierarchical, energy-based model of multimodal cognition that extends a…
arXiv:2608.12677v1 Announce Type: new Abstract: Detecting infection-related behavioral changes in mosquitoes from video data is challenging because mosquitoes are small, move rapidly and irregularly, and are affected by…
arXiv:2608.13256v1 Announce Type: cross Abstract: As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, biases, and ethical…
arXiv:2608.12324v1 Announce Type: cross Abstract: People increasingly ask large language models (LLMs) for counsel on questions of faith, doctrine, and pastoral care. These questions are not ordinary information…
arXiv:2608.13072v1 Announce Type: new Abstract: Electroencephalography (EEG) decoding models often generalize poorly across datasets and subjects due to domain shifts in acquisition protocols and individual…
arXiv:2608.12921v1 Announce Type: cross Abstract: The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology generation…
arXiv:2608.12599v1 Announce Type: new Abstract: Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements…
arXiv:2608.12610v1 Announce Type: new Abstract: There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains…
arXiv:2608.12387v1 Announce Type: cross Abstract: Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their…
arXiv:2608.12771v1 Announce Type: cross Abstract: The extent to which large language models for code rely on memorization over genuine understanding remains highly debated. While current literature frequently reports…
arXiv:2608.09696v3 Announce Type: replace Abstract: Predicting the answer to interventional ``what if'' questions --- the outcome of an action never taken --- requires a \emph{mechanistic}, causal model, not a curve…
arXiv:2608.13447v1 Announce Type: new Abstract: Academic leagues have become important mechanisms for promoting extracurricular education and strengthening the integration between universities and society. This paper…
arXiv:2608.10473v2 Announce Type: replace-cross Abstract: Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However,…
arXiv:2608.13417v1 Announce Type: new Abstract: Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation. To understand the current…
arXiv:2608.13263v1 Announce Type: new Abstract: Large language model serving faces a critical memory bottleneck: the KV cache grows with sequence length and batch size. PagedAttention uses fixed-size memory blocks to…
arXiv:2608.12936v1 Announce Type: cross Abstract: As quantum computing progresses from proof-of-principle demonstrations toward practical utility, a significant impediment is the need to augment algorithmic feasibility…
arXiv:2608.12321v1 Announce Type: cross Abstract: When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but aggregate accuracy conflates genuine constraint inference with…
arXiv:2603.25821v3 Announce Type: replace-cross Abstract: We present Doctorina MedBench, an evaluation framework for agent-based medical AI based on the simulation of physician-patient interactions. Unlike traditional…
arXiv:2604.16399v3 Announce Type: replace-cross Abstract: Adoption of AI-assisted development in 2025 exposed a tool-agnostic failure pattern: experienced developers using frontier models were measurably slower while…
arXiv:2607.28166v2 Announce Type: replace-cross Abstract: Diffusion language models expose a provisional prediction at every denoising step, and on many tasks the candidate answer inside it stabilizes before the step…
arXiv:2608.09164v2 Announce Type: replace Abstract: Aligning large language models (LLMs) with human privacy preferences requires capturing individuals' disclosure boundaries beyond general privacy norms. However, a gap…
arXiv:2608.12719v1 Announce Type: cross Abstract: Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized task center to…
arXiv:2512.13325v2 Announce Type: replace-cross Abstract: Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing control over data when it…
arXiv:2603.00048v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in sensitive applications including psychological support, healthcare, and high-stakes decision-making.…
arXiv:2608.12842v1 Announce Type: new Abstract: Model merging has recently attracted significant attention as a promising paradigm for constructing unified multi-task models without requiring additional retraining.…
arXiv:2608.13520v1 Announce Type: cross Abstract: We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity}…
