3,694 items tracked: 32 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2610.17379v1 Announce Type: new Abstract: LLM-based automated heuristic design (AHD) discovers heuristics for combinatorial optimization problems (COPs), where an LLM generates candidates in an evolutionary search.
arXiv:2610.17391v1 Announce Type: new Abstract: Amazing breakthroughs in reinforcement learning have taken place.
arXiv:2610.17401v1 Announce Type: new Abstract: Incomplete field-of-view (FOV) diffusion MRI (dMRI) acquisitions compromise whole-brain white matter analysis by excluding brain regions from tractography and connectivity…
arXiv:2610.17463v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are promising for energy-efficient spatiotemporal pattern recognition at the edge, but efficient deployment and on-device adaptation require…
arXiv:2610.17473v1 Announce Type: new Abstract: Generative safety guards must classify requests correctly and return outputs that applications can parse.
arXiv:2610.17549v1 Announce Type: new Abstract: Identifying a robot task from a short instruction is sensitive to which descriptions are available for retrieval.
arXiv:2610.17610v1 Announce Type: new Abstract: Recently, the integration of generative priors has revolutionized Monocular Depth Estimation (MDE), achieving state-of-the-art (SOTA) performance with remarkably high data…
arXiv:2610.17641v1 Announce Type: new Abstract: Bias scores in language-model evaluations often conflate what a model prefers with whether it answers at all.
arXiv:2610.17665v1 Announce Type: new Abstract: Can vision-language models turn 2D observations into 3D understanding that supports precise action?
arXiv:2610.17689v1 Announce Type: new Abstract: Serverless inference is emerging as an efficient deployment model for Large Language Models (LLMs) due to its ability to elastically scale resources, improve GPU utilizatio…
arXiv:2610.17690v1 Announce Type: new Abstract: Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed trajectories, while genera…
arXiv:2610.17699v1 Announce Type: new Abstract: Single-cell RNA sequencing (scRNA-seq) enables cell-level analysis of biological heterogeneity, but learning effective representations from high-dimensional, unordered gene…
arXiv:2610.17718v1 Announce Type: new Abstract: Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence.
arXiv:2610.17900v1 Announce Type: new Abstract: Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning.
arXiv:2610.18047v1 Announce Type: new Abstract: In this paper, our goal is to represent text embeddings as sketches for three main reasons.
arXiv:2610.18089v1 Announce Type: new Abstract: AI has become increasingly helpful in scientific discovery, yet human expert review remains essential for those problems without reliable automated evaluation, posing a fun…
arXiv:2610.18095v1 Announce Type: new Abstract: AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks.
arXiv:2610.18105v1 Announce Type: new Abstract: Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems.
arXiv:2610.18126v1 Announce Type: new Abstract: Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world.
arXiv:2610.18141v1 Announce Type: new Abstract: Omnimodal large language models (OLLMs) are susceptible to cross-modal hallucinations under audio-visual interference.
arXiv:2610.18143v1 Announce Type: new Abstract: Prefix reuse improves LLM inference by sharing the KV cache of common prompt prefixes.
arXiv:2610.18198v1 Announce Type: new Abstract: Knowledge graph link prediction involving unseen entities and relations requires learning transferable reasoning patterns from observed graph structure.
arXiv:2610.18301v1 Announce Type: new Abstract: Recent progress in autoformalisation of mathematics using AI has been impressive.
arXiv:2610.18304v1 Announce Type: new Abstract: Guardrail approaches that rely on reasoning-based large language models (LLM) improve safety decisions, but come with substantial inference overhead due to the explicit rea…
arXiv:2610.18314v1 Announce Type: new Abstract: This work discusses and tests the potential of reaction graphs for material synthesis, in which events consist of reaction steps (actions) and their outputs (observations).
arXiv:2610.18445v1 Announce Type: new Abstract: Automating AI research creates a positive feedback loop between software capability and research effort.
arXiv:2610.18547v1 Announce Type: new Abstract: People often tackle difficult problems by thinking more deeply or exploring more possibilities.
arXiv:2610.18567v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for improving Large Language Model (LLM) by intertwining it with other components, such as a vector/…
arXiv:2610.18583v1 Announce Type: new Abstract: Sampling-based test-time scaling enhances LLM reasoning by aggregating multiple reasoning paths for the same query.
arXiv:2610.18606v1 Announce Type: new Abstract: Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer.
arXiv:2610.18638v1 Announce Type: new Abstract: Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tuned checkpoints.
arXiv:2610.18704v1 Announce Type: new Abstract: In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model.
arXiv:2610.18851v1 Announce Type: new Abstract: Multi-objective molecular optimization is a critical process in drug discovery that aims to modify a given molecule to simultaneously improve multiple properties while main…
arXiv:2501.06597v1 Announce Type: cross Abstract: The widespread adoption of generative AI has generated diverse opinions, with individuals expressing both support and criticism of its applications.
arXiv:2603.23784v1 Announce Type: cross Abstract: Grokking-the phenomenon where validation accuracy of neural networks on modular addition of two integers rises long after training data has been memorized-has been charac…
arXiv:2609.14421v1 Announce Type: cross Abstract: Recent advances in multimodal foundation models have intensified the need to understand how different modalities share, preserve, and complement information.
arXiv:2610.13966v1 Announce Type: cross Abstract: Predicting cellular responses to chemical and genetic perturbations is a central test for AI virtual cells, yet many single-cell models reduce each condition to an averag…
arXiv:2610.13994v1 Announce Type: cross Abstract: Flow matching learns how to transport noise toward data, but its mean prediction does not directly report the endpoint uncertainty remaining at an intermediate state.
arXiv:2610.13995v1 Announce Type: cross Abstract: Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning.
arXiv:2610.13996v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not certify the derivation be…
arXiv:2610.13998v1 Announce Type: cross Abstract: This paper proposes a hybrid reinforcement learning trading framework integrating intraday market data with transformer-based financial sentiment signals.
arXiv:2610.13999v1 Announce Type: cross Abstract: Rule decisions such as content moderation, advertising compliance, and eligibility checks combine several conditions, exemptions, and missing-information cases, and an er…
arXiv:2610.14004v1 Announce Type: cross Abstract: People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines.
arXiv:2610.14009v1 Announce Type: cross Abstract: Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established failure analysis methods transfer effectively to this setting.
arXiv:2610.14015v1 Announce Type: cross Abstract: Learning-to-rank (LTR) models can align rankings with undesignated signals when those signals appear as features or leak into training labels.
arXiv:2610.14020v1 Announce Type: cross Abstract: Self-driving laboratories (SDLs) aim to automate the full experimental loop, from scientific decision-making to physical execution.
arXiv:2610.14025v1 Announce Type: cross Abstract: Activation steering controls large language model behavior by adding a direction to hidden activations during inference.
arXiv:2610.14028v1 Announce Type: cross Abstract: Data selection for LLM fine-tuning faces two facts about real training: data pools draw from many distinct domains, and evaluation spans diverse tasks.
arXiv:2610.14029v1 Announce Type: cross Abstract: LLM-as-a-judge evaluation commonly aggregates multiple judges' decisions into a majority vote, yet this panel decision process does not guarantee that the evaluation of a…
arXiv:2610.14030v1 Announce Type: cross Abstract: Looped transformers reuse one shared block across many recurrent steps, so depth becomes a quantity that can be spent at runtime rather than a stack of distinct layers.