AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs
arXiv:2610.18141v1 Announce Type: new Abstract: Omnimodal large language models (OLLMs) are susceptible to cross-modal hallucinations under audio-visual interference. We find that, for a substantial fraction of incorrect…
- arXiv cs.AIresearchRadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving
arXiv:2610.18143v1 Announce Type: new Abstract: Prefix reuse improves LLM inference by sharing the KV cache of common prompt prefixes. This helps only if the scheduler can execute a matched branch in the current worker r…
- arXiv cs.AIresearchBack to the Future: Reverse-Consequence Modeling for Long-Horizon Particle Dynamics
arXiv:2610.18168v1 Announce Type: new Abstract: Accurate prediction of object trajectories is fundamental to mechanical understanding and robotic control. However, autoregressive models inherently suffer from cumulative…
- arXiv cs.AIresearchQORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction
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. Existing methods ba…
- arXiv cs.AIresearchConsider, Then Choose: Order-Invariant Decisions in System One Models
arXiv:2610.18233v1 Announce Type: new Abstract: System One models answer typed questions in a single forward pass and promise the same answer for the same input. For choice questions, this promise fails: the answer depen…
- arXiv cs.AIresearchA dataset of formalised theorem statements from the Annals of Mathematics
arXiv:2610.18301v1 Announce Type: new Abstract: Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires datasets of formal statements that are both hard and trus…
- arXiv cs.AIresearchEfficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction
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 cs.AIresearchComplex materials engineering via Provenance Action Graphs: potential, structure and demonstration
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 cs.AIresearchThe Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion
arXiv:2610.18445v1 Announce Type: new Abstract: Automating AI research creates a positive feedback loop between software capability and research effort. We study a stochastic realisation of this loop in which independent…
- arXiv cs.AIresearchThinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence
arXiv:2610.18447v3 Announce Type: replace Abstract: World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they supp…
- arXiv cs.AIresearchThe Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale
arXiv:2610.18511v1 Announce Type: new Abstract: Buildings cause nearly 40\% of carbon emissions in the US. Of total building emissions, HVAC systems are responsible for approximately 40-60\% and account for 15\% of globa…
- arXiv cs.AIresearchInput-Conditioned Search for Efficient Test-Time Scaling of Recursive Reasoners
arXiv:2610.18547v2 Announce Type: replace Abstract: People often tackle difficult problems by thinking more deeply or exploring more possibilities. Similarly, recursive reasoners, which reason by repeatedly applying a le…
- arXiv cs.AIresearchRethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection
arXiv:2610.18566v2 Announce Type: replace Abstract: Large language model (LLM) routers reduce serving cost by choosing which model to call and how many output tokens to grant it for each query. Existing routers rank mode…
- arXiv cs.AIresearchConfiguring RAG Systems: What Breaks, Where Originates, and How to Fix
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 cs.AIresearchOrder-Consistent Latent Geometry for Reliable Short-Horizon Planning in World Models
arXiv:2610.18570v1 Announce Type: new Abstract: Latent planners often rank candidate action sequences by terminal Euclidean distance to a goal latent. Exact agreement with transition distance would make this score ideal,…
- arXiv cs.AIresearchCompare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling
arXiv:2610.18583v1 Announce Type: new Abstract: Sampling-based test-time scaling enhances LLM reasoning by aggregating multiple reasoning paths for the same query. Existing methods use answer frequencies or path confiden…
- arXiv cs.AIresearchBeyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces
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. Self-consistency (SC) im…
- arXiv cs.AIresearchTo Align or Not To Align: Check Your COMPASS Before You Train
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. Howe…
- arXiv cs.AIresearchUnlocking Token Rewards via Training-Free Reward Attribution
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. Our core idea is t…
- arXiv cs.AIresearchJeva: System One Models from First Principles
arXiv:2610.18773v2 Announce Type: replace Abstract: System one models like Jev enable direct, low-latency decision-making. Yet recent open-source practice of predicting an answer from serialized text does not, by itself,…
- arXiv cs.AIresearchRead the Room Before Your Model Generates
arXiv:2610.18820v3 Announce Type: replace Abstract: Large language models (LLMs) generally rely on sampling temperature to regulate the amount of randomness in their outputs. Mainstream methods for selecting temperature…
- arXiv cs.AIresearchMFG: Multi-turn Feedback Guided Molecular Optimization
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 cs.AIresearchAesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
arXiv:2610.18860v1 Announce Type: new Abstract: Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet…
- arXiv cs.AIresearchSubgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learning
arXiv:2407.12703v5 Announce Type: cross Abstract: Fine-tuning pre-trained language models (PLMs) has recently shown a potential to improve knowledge graph completion (KGC). However, most PLM-based methods focus solely on…
- arXiv cs.AIresearchEmoXpt: Analyzing Emotional Variances in Human Comments and LLM-Generated Responses
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. This study investigat…
- arXiv cs.AIresearchLatent Algorithmic Structure Precedes Grokking: A Mechanistic Study of ReLU MLPs on Modular Arithmetic
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 cs.AIresearchDependency, Compression, and Synergy: A Unified Information-Theoretic View of Multimodal Learning
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. Mutual Infor…
- arXiv cs.AIresearchMRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction
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 cs.AIresearchPosterior Flow Matching
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. Thi…
- arXiv cs.AIresearchGameSmith: Scaling Zero-Sum Self-Play with Synthesised Games
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. Exis…
- arXiv cs.AIresearchSplicing Hints into Reasoning Traces: Learning from Demonstrator Failures
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 cs.AIresearchSharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models
arXiv:2610.13997v1 Announce Type: cross Abstract: Concept representations in diffusion models drift across network depth and denoising time, yet existing sparse autoencoders offer only per-block or per-timestep dictionar…
- arXiv cs.AIresearchEnhanced Trading Systems with Intelligent Market Analysis
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. The system extr…
- arXiv cs.AIresearchSemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions
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 cs.AIresearchPreSO: Privileged Representation Isolation for On-Policy Self-Distillation
arXiv:2610.14001v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning with verifiable r…
- arXiv cs.AIresearchShowing versus Doing: Teaching by Demonstration
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. In contrast, teaching by demo…
- arXiv cs.AIresearchWhat Can Language Models Inherit from Solomonoff Induction? Limits, Attainable Properties, and What Served Conditionals Reveal
arXiv:2610.14007v1 Announce Type: cross Abstract: A familiar line of reasoning runs as follows: language models are flexible approximators trained under a strictly proper loss, so scale brings them closer to Solomonoff i…
- arXiv cs.AIresearchWhen Log Parsing Removes What Matters: Detecting Failures in Distributed GPU Workloads
arXiv:2610.14009v2 Announce Type: replace-cross Abstract: Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established anomaly detection methods transfer effectively to this…
- arXiv cs.AIresearchPhysics-Informed State Space Models for Day-Ahead Photovoltaic Power Forecasting
arXiv:2610.14014v1 Announce Type: cross Abstract: Accurate day-ahead photovoltaic (PV) power forecasting requires both strong temporal modeling and adherence to physical PV system constraints. Purely data-driven models o…
- arXiv cs.AIresearchBias Robustness of Genetic Multi-Criteria Sorting versus Learned Rankers under Proxy Skew and Label Contamination
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. We compare label-free genet…
- arXiv cs.AIresearchBarycentric Anchored Weight Search for Robust Model Merging
arXiv:2610.14017v1 Announce Type: cross Abstract: We propose Barycentric Anchored Search, a post-hoc weight-space procedure for improving fine-tuned vision models under distribution shift without additional gradient trai…
- arXiv cs.AIresearchRoboHarness: A Simple Harness Outperforms VLA and World Action Models
arXiv:2610.14018v2 Announce Type: replace-cross Abstract: The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world. One stra…
- arXiv cs.AIresearchLabInstruct: Benchmarking Situated Instructional Video Generation for Lab Procedures
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. Ideally, AI-generated plans could be c…
- arXiv cs.AIresearchOPMD: On-Policy Mechanism Distillation Beyond Output Supervision
arXiv:2610.14022v1 Announce Type: cross Abstract: On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains confined to the output…
- arXiv cs.AIresearchContrastive Covariance Subspaces for Activation Steering
arXiv:2610.14025v1 Announce Type: cross Abstract: Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, that direction must be…
- arXiv cs.AIresearchPick the Mixture, Not the Samples: Combinatorial Data Selection for LLMs
arXiv:2610.14028v2 Announce Type: replace-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. As a resul…
- arXiv cs.AIresearchCan We Trust This Evaluation? Instance-Level Reliability of LLM-as-a-Judge
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 cs.AIresearchRotate the Loop: Blockwise Conformality for Looped Transformers
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. T…
- arXiv cs.AIresearchPLDiv: Measuring Dataset Diversity and Semantic Collapse via Persistence Landscapes
arXiv:2610.14031v1 Announce Type: cross Abstract: Modern data pipelines increasingly combine human-created and human-curated data with AI-generated data for model training and evaluation. As datasets grow, they often add…
- arXiv cs.AIresearchA Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning
arXiv:2610.14041v1 Announce Type: cross Abstract: Inverse Reinforcement Learning (IRL) is classically solved using Lagrangian optimisation, by jointly optimising a primal-dual problem with gradient descent to obtain the…