AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSoft Geometric Inductive Bias for Object Centric Dynamics
arXiv:2512.15493v2 Announce Type: replace-cross Abstract: Physical systems are naturally parameterized in terms of geometric entities and their transformations. While exact equivariance can be a powerful inductive bias,…
- arXiv cs.AIresearchFasterPy: An LLM-based Code Execution Efficiency Optimization Framework
arXiv:2512.22827v3 Announce Type: replace-cross Abstract: Code often suffers from performance bugs. These bugs necessitate the research and practice of code optimization. Traditional rule-based methods rely on manually d…
- arXiv cs.AIresearchSB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints
arXiv:2512.23770v4 Announce Type: replace-cross Abstract: In safety-critical domains, reinforcement learning (RL) systems must satisfy strict, zero-cost safety constraints while achieving meaningful task performance. Exi…
- arXiv cs.AIresearchVulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search
arXiv:2512.25065v3 Announce Type: replace-cross Abstract: Systems resource management tasks rely primarily on hand-designed heuristics. However, growing hardware heterogeneity and workload diversity require heuristics sp…
- arXiv cs.AIresearchDeep Delta Learning
arXiv:2601.00417v5 Announce Type: replace-cross Abstract: Transformer residual streams are updated by addition. A sufficiently expressive residual block can represent content replacement, but the residual update itself h…
- arXiv cs.AIresearchNC-Bench: An LLM Benchmark for Evaluating Conversational Competence
arXiv:2601.06426v3 Announce Type: replace-cross Abstract: Existing LLM benchmarks evaluate what models say, such as whether answers are correct, faithful, or helpful, but they do not test whether models produce the right…
- arXiv cs.AIresearchUntangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs
arXiv:2601.10257v2 Announce Type: replace-cross Abstract: When LLMs judge moral dilemmas, do they reach different conclusions in different languages, and if so, why? Two factors could drive such differences: the language…
- arXiv cs.AIresearchContextual Distributionally Robust Optimization with Causal and Continuous Structure
arXiv:2601.11016v3 Announce Type: replace-cross Abstract: We propose a framework for contextual distributionally robust optimization (DRO) that considers the causal and continuous structure of the underlying distribution…
- arXiv cs.AIresearchA Scalable Entity-Based Framework for Auditing Bias in Large Language Models
arXiv:2601.12374v3 Announce Type: replace-cross Abstract: Existing approaches to bias evaluation in large language models (LLMs) trade ecological validity for statistical control, relying either on artificial prompts tha…
- arXiv cs.AIresearchMGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation
arXiv:2601.21225v5 Announce Type: replace-cross Abstract: Large language models have made substantial progress in mathematical reasoning. However, benchmark development for multilingual evaluation has lagged behind Engli…
- arXiv cs.AIresearchHypersolid: Emergent Vision Representations via Short-Range Repulsion
arXiv:2601.21255v3 Announce Type: replace-cross Abstract: A central problem in self-supervised learning is preventing representation collapse. Most methods avoid it through global mechanisms, such as contrastive expansio…
- arXiv cs.AIresearchDenoising Time Matters:Diverse Generation in Diffusion Language Models
arXiv:2601.22629v3 Announce Type: replace-cross Abstract: Diffusion language models (Diffusion-LMs) generate text through iterative denoising, exposing a temporal structure that is largely absent from autoregressive deco…
- arXiv cs.AIresearchPlain Transformers are Surprisingly Powerful Link Predictors
arXiv:2602.01553v4 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Network…
- arXiv cs.AIresearchVLM-Guided Experience Replay
arXiv:2602.01915v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have enabled powerful semantic and multimodal reasoning capabilities, creating n…
- arXiv cs.AIresearchMolLangData: A Large-Scale Dataset for Molecular Structure-Language Description via a Rule-Regularized Method
arXiv:2602.02320v5 Announce Type: replace-cross Abstract: Molecular function is largely determined by structure. Accurately aligning molecular structure with natural language is therefore essential for enabling large lan…
- arXiv cs.AIresearchPoly-attention: a general scheme for higher-order self-attention
arXiv:2602.02422v2 Announce Type: replace-cross Abstract: The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent w…
- arXiv cs.AIresearchAll-Atom GPCR-Ligand Dynamics Simulation via a Residual Latent Flow Mode
arXiv:2602.03902v2 Announce Type: replace-cross Abstract: G-protein-coupled receptors (GPCRs), which are targeted by over one-third of approved drugs, undergo intricate conformational transitions to transduce signals. Wh…
- arXiv cs.AIresearchUnveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
arXiv:2602.05548v4 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), particularly GRPO, has become the standard for eliciting LLM reasoning. However, its efficiency in explorat…
- arXiv cs.AIresearchPreventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity
arXiv:2602.13486v3 Announce Type: replace-cross Abstract: Federated low-rank adaptation (FedLoRA) has facilitated communication-efficient and privacy-preserving fine-tuning of foundation models for downstream tasks. In p…
- arXiv cs.AIresearchReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
arXiv:2602.15983v5 Announce Type: replace-cross Abstract: Large language models (LLMs) can translate natural-language problem descriptions into optimization code, but the code is prone to silent failures: it executes and…
- arXiv cs.AIresearchCodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
arXiv:2602.17684v3 Announce Type: replace-cross Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit te…
- arXiv cs.AIresearchDon't stop me now: How Validation Criteria Affect Checkpoint Selection and Early Stopping
arXiv:2602.22107v2 Announce Type: replace-cross Abstract: Checkpoint selection is a standard component of neural network training, yet the validation criterion used to select a checkpoint is often chosen heuristically. M…
- arXiv cs.AIresearchEfficient Token-Level Policy Optimization for Masked Diffusion Models via Velocity Alignment
arXiv:2603.01563v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) successfully aligns autoregressive models in rigorous domains like mathematical reasoning and code generatio…
- arXiv cs.AIresearchPhysics-Informed Neural Networks with Architectural Physics Embedding for Large-Scale Wave Field Reconstruction
arXiv:2603.02231v2 Announce Type: replace-cross Abstract: Large-scale wave field reconstruction requires precise solutions but faces challenges with computational efficiency and accuracy. The physics-based numerical meth…
- arXiv cs.AIresearchFarther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
arXiv:2603.03415v3 Announce Type: replace-cross Abstract: In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs of increasing difficulty, quantified a…
- arXiv cs.AIresearchA theoretical model of dynamical grammatical gender shifting based on set-valued set function
arXiv:2603.03510v3 Announce Type: replace-cross Abstract: This study investigates the diverse characteristics of nouns, focusing on both semantic (e.g., countable/uncountable) and morphosyntactic (e.g., masculine/feminin…
- arXiv cs.AIresearchSalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models
arXiv:2603.04410v3 Announce Type: replace-cross Abstract: While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hindering their mainstr…
- arXiv cs.AIresearchConcept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
arXiv:2603.08309v3 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically m…
- arXiv cs.AIresearchRubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning
arXiv:2603.09160v2 Announce Type: replace-cross Abstract: Dense image captioning is critical for vision-language pretraining and for text-to-image generation, but scaling expert-quality annotations is prohibitively expen…
- arXiv cs.AIresearchAdaptive Weighted h-Transform Sampling for Coarse-Guided Visual Generation
arXiv:2603.12057v3 Announce Type: replace-cross Abstract: Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applic…
- arXiv cs.AIresearchHO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
arXiv:2603.14773v3 Announce Type: replace-cross Abstract: Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and spli…
- arXiv cs.AIresearchFlashSampling: Fast and Memory-Efficient Exact Sampling
arXiv:2603.15854v3 Announce Type: replace-cross Abstract: Sampling from a categorical distribution is mathematically simple, but in large-vocabulary decoding, it often triggers extra memory traffic and extra kernels afte…
- arXiv cs.AIresearchIndexRAG: Index-Time Reasoning for Multi-Hop Retrieval-Augmented Generation
arXiv:2603.16415v2 Announce Type: replace-cross Abstract: Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either t…
- arXiv cs.AIresearchCompDiff enables fair and zero shot medical image generation across demographic intersections through compositional diffusion
arXiv:2603.16551v4 Announce Type: replace-cross Abstract: Medical image generators trained on imbalanced data can fail at demographic intersections absent from training. We introduce CompDiff, which encodes age, sex and…
- arXiv cs.AIresearchWhen Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removal
arXiv:2603.20433v2 Announce Type: replace-cross Abstract: While Large Audio-Language Models (LALMs) have been shown to exhibit degraded instruction-following capabilities, their ability to infer task patterns from in-con…
- arXiv cs.AIresearchBenchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF
arXiv:2603.21359v2 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently exhibit performance biases against regional dialects of low-resource languages. However, frameworks to quantify these disp…
- arXiv cs.AIresearchP^2O: Joint Policy and Prompt Optimization
arXiv:2603.21877v4 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but is suffer from advantage collapse: when all rollouts of a…
- arXiv cs.AIresearchThe Model Says Walk: Measuring whether LLMs Condition on Hidden Constraints
arXiv:2603.29025v4 Announce Type: replace-cross Abstract: Asked whether to walk or drive to a car wash 50 m away, most language models say walk, forgetting that the car has to be there. Such failures are usually measured…
- arXiv cs.AIresearchAromaGen: Interactive Generation of Rich Olfactory Experiences with Multimodal Language Models
arXiv:2604.01650v4 Announce Type: replace-cross Abstract: Smell's connections with food, memory, and social experience have motivated researchers to bring olfaction into interactive systems. Multimodal AI opens new possi…
- arXiv cs.AIresearchAn Inspectable LLM Council for Multi-Model Research Answer Aggregation
arXiv:2604.02923v5 Announce Type: replace-cross Abstract: Long-form research questions often require a single answer that combines details, reconciles conflicting estimates, and retains qualifications spread across sever…
- arXiv cs.AIresearchHow Does "English (US)" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline
arXiv:2604.04204v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly embedded in educational, professional, and public infrastructure, yet widely used platforms expose "English (US)" as…
- arXiv cs.AIresearchRelative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment
arXiv:2604.04410v2 Announce Type: replace-cross Abstract: Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human pr…
- arXiv cs.AIresearchEffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution Feedback
arXiv:2604.05137v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can generate functionally correct programs that differ substantially in execution efficiency. Existing inference-time optimization me…
- arXiv cs.AIresearchAn Imperfect Verifier is Good Enough: Learning with Noisy Rewards
arXiv:2604.07666v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is widely used for post-training Large Language Models, but practical verifiers can make errors. We study ho…
- arXiv cs.AIresearchHiFloat4 Format for Language Model Pre-training on Ascend NPUs
arXiv:2604.08826v2 Announce Type: replace-cross Abstract: Training large foundation models at low numerical precision is one of the most promising directions for reducing the compute and memory cost of modern AI. Recent…
- arXiv cs.AIresearchFastGrasp: Learning-based Whole-Body Control Method for Fast Dexterous Grasping with Mobile Manipulators
arXiv:2604.12879v2 Announce Type: replace-cross Abstract: Fast dexterous grasping while a mobile base remains in motion requires coordinated whole-body control and rapid adaptation to physical contact. We propose FastGra…
- arXiv cs.AIresearchLightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
arXiv:2604.13010v3 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is an effective post-training paradigm for large language models but requires a live teacher server throughout training, resulting in…
- arXiv cs.AIresearchUniRect-CoT: Enhancing Generation in Unified Multimodal Models via Reflective Rectification with Inherent Understanding
arXiv:2604.13540v2 Announce Type: replace-cross Abstract: Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable capabilit…
- arXiv cs.AIresearchMambaSL: Exploring Single-Layer Mamba for Time Series Classification
arXiv:2604.15174v3 Announce Type: replace-cross Abstract: Despite recent advances in state space models (SSMs) such as Mamba across various sequence domains, research on their standalone capacity for time series classifi…
- arXiv cs.AIresearchWhy Fine-Tuning Encourages Hallucinations and How to Fix It
arXiv:2604.15574v3 Announce Type: replace-cross Abstract: Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through super…