AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchGAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting
arXiv:2610.37598v1 Announce Type: cross Abstract: Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong perfor…
- arXiv cs.AIresearchMoI-Bench: A Benchmark for Image Generation and Editing on Mobile Devices
arXiv:2610.37599v1 Announce Type: cross Abstract: Developing on-device image models requires considering practical user needs, task types and device resource constraints. However, existing benchmarks provide limited guid…
- arXiv cs.AIresearchBeyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence
arXiv:2610.37605v1 Announce Type: cross Abstract: For audio-language models, an answer change after a local sound-event edit can reflect a response to the event's class, sensitivity to waveform rewriting, or both. We com…
- arXiv cs.AIresearchVideoLVR: Latent Visual Reasoning over Grounded Video Evidence
arXiv:2610.37613v1 Announce Type: cross Abstract: Chain-of-thought reasoning has substantially advanced video understanding in multimodal large language models (MLLMs). However, language-based reasoning traces do not pro…
- arXiv cs.AIresearchMuonGS: Pretraining LLMs with Relaxed Weight-Norm Control
arXiv:2610.37647v1 Announce Type: cross Abstract: Weight decay and explicit weight-norm constraints improve optimizer performance in language model pretraining, yet a unified understanding of why such control helps and h…
- arXiv cs.AIresearchCan LLMs Uncover Hidden Physical Laws through Free Exploration?
arXiv:2610.37649v1 Announce Type: cross Abstract: Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (L…
- arXiv cs.AIresearchAttention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops
arXiv:2610.37656v1 Announce Type: cross Abstract: Relations compose through the entity they share - Alice is Bob's mother and Bob is Carol's father, so Alice is Carol's grandmother - and the order matters, since a father…
- arXiv cs.AIresearchThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
arXiv:2610.37666v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of…
- arXiv cs.AIresearchHoneycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
arXiv:2610.37668v1 Announce Type: cross Abstract: Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resourc…
- arXiv cs.AIresearchEpsilon-Identifiability of Causal Quantities
arXiv:2301.12022v2 Announce Type: replace Abstract: Identifying the effects of causes and causes of effects is vital in virtually every scientific field. Often, however, the needed probabilities may not be fully identifi…
- arXiv cs.AIresearchData-Driven Maintenance Optimization: Aligning Prognostic Learning with Decision Objective
arXiv:2506.19698v2 Announce Type: replace Abstract: Estimation error in machine learning prognostic models can propagate into poor maintenance decisions. We study a data-driven predictive maintenance problem coupling hea…
- arXiv cs.AIresearchDifficulty-Estimated Policy Optimization
arXiv:2602.06375v2 Announce Type: replace Abstract: Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relativ…
- arXiv cs.AIresearchOptimal Experiments for Partial Causal Effect Identification
arXiv:2605.06993v3 Announce Type: replace Abstract: Causal queries are often only partially identifiable from observational data, and experiments that could tighten the resulting bounds are typically costly. We study the…
- arXiv cs.AIresearchCLEAR: Coupling Local Evidence with Affective Representations for Multimodal Emotion Recognition in Conversation
arXiv:2605.18547v2 Announce Type: replace Abstract: In video calls and livestreamed discussions, recognizing speakers' emotions helps identify emotionally salient segments and supports fine-grained video content analysis…
- arXiv cs.AIresearchHOLogicBench: Evaluating Higher-Order Logical Reasoning in LLMs
arXiv:2606.23238v3 Announce Type: replace Abstract: Existing LLM logical-reasoning benchmarks largely focus on object-level inference under fixed predicates and rules, leaving higher-order reasoning over rules and polici…
- arXiv cs.AIresearchLISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
arXiv:2607.19358v2 Announce Type: replace Abstract: Long chain-of-thought (CoT) reasoning models such as DeepSeek-R1 keep lengthening their inference chains under test-time scaling, yet standard self-attention incurs qua…
- arXiv cs.AIresearchWavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation
arXiv:2607.21628v3 Announce Type: replace Abstract: Simulation-to-reality translation must bridge the appearance gap between synthetic and real domains while preserving structural and semantic consistency. Conditioning-b…
- arXiv cs.AIresearchScalableRAG: High-Quality RAG with Exact Corpus Operations at Minimal Ingestion Cost
arXiv:2607.25135v2 Announce Type: replace Abstract: RAG systems face a capability-cost gap: lightweight retrievers locate evidence but expose no operands for exact corpus-level operations (counts, intersections, aggregat…
- arXiv cs.AIresearchHard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection
arXiv:2608.02343v2 Announce Type: replace Abstract: Many operational problems are constrained sequential decision processes with combinatorial action spaces and interdependent constraints. Mixed-integer linear programs (…
- arXiv cs.AIresearchValidating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge
arXiv:2608.29249v3 Announce Type: replace Abstract: The online culinary ecosystem is increasingly populated by recipe content generated, modified, or summarized by LLMs. Although often convincing, such outputs may contai…
- arXiv cs.AIresearchWhen Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation
arXiv:2609.12718v2 Announce Type: replace Abstract: Hallucinations can undermine clinician trust in LLMs, making it important that evaluation methods capture clinically relevant errors. Rubric-based evaluation has become…
- arXiv cs.AIresearchInferring Inference
arXiv:2310.03186v4 Announce Type: replace-cross Abstract: Patterns of microcircuitry in the cerebral cortex suggest that the brain has an array of repeated canonical computational units. However, neural representations a…
- arXiv cs.AIresearchDyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors
arXiv:2311.17098v4 Announce Type: replace-cross Abstract: Achieving constant accuracy in object detection is challenging due to the inherent variability of object sizes. One effective approach to this problem involves op…
- arXiv cs.AIresearchFairness Definitions in Language Models Explained
arXiv:2407.18454v4 Announce Type: replace-cross Abstract: Language Models (LMs) have demonstrated exceptional performance across various Natural Language Processing (NLP) tasks. Despite these advancements, LMs can inheri…
- arXiv cs.AIresearchShe Works, He Works: A Curious Exploration of Gender Bias in AI-Generated Imagery
arXiv:2407.18524v2 Announce Type: replace-cross Abstract: She Works, He Works is an interdisciplinary project that combines feminist visual theory, AI critique, and artistic practice to examine gender representation in A…
- arXiv cs.AIresearchHateSense: Hierarchical Sentiment Analysis Framework for Hate Speech Detection: Implementing Binary and Multiclass Classification Strategy
arXiv:2411.05819v2 Announce Type: replace-cross Abstract: Hate speech detectors must separate hateful posts from the far more common offensive but non-hateful ones, and two popular ideas for doing so are hierarchical (co…
- arXiv cs.AIresearchThe Price of Failure Risk: Clipped Barrier Policy Gradients with Convex Regularization
arXiv:2411.19193v4 Announce Type: replace-cross Abstract: In many control problems, actions consume a resource budget, such as a wear allowance, and the probability of exhausting it within a given horizon must stay below…
- arXiv cs.AIresearchSmart Surveillance: Deep Learning and Hybrid Approaches for Dynamic Scene Analysis, Object Detection and Motion Tracking
arXiv:2412.05331v4 Announce Type: replace-cross Abstract: Event-triggered recording reduces the footage a surveillance camera must store, but the trigger decides how much idle video is kept, how many events are missed, a…
- arXiv cs.AIresearchCorrecting Before Adapting: Gradient Correction for Federated Adaptive Optimization
arXiv:2502.02727v4 Announce Type: replace-cross Abstract: Client-drift compensation methods mitigate the impact of data heterogeneity in federated learning (FL). While drift correction is well studied for stochastic grad…
- arXiv cs.AIresearchAnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection
arXiv:2502.09254v3 Announce Type: replace-cross Abstract: Graph anomaly detection (GAD) aims to identify abnormal nodes that differ from the majority of the nodes in a graph, which has been attracting significant attenti…
- arXiv cs.AIresearchAn Embarrassingly Simple Data Selection Strategy for Million-Scale Multi-Modal Instruction-Tuning
arXiv:2503.13383v2 Announce Type: replace-cross Abstract: Recent research demonstrates that pretrained large language models (LLMs) require minimal but carefully curated data for instruction-tuning. Building on LLMs, mul…
- arXiv cs.AIresearchIn-Context Learning for MIMO Turbo Receivers
arXiv:2505.06175v2 Announce Type: replace-cross Abstract: Multiple-input multiple-output (MIMO) turbo receivers iteratively exchange information between a soft-input soft-output detector and a decoder. Traditional implem…
- arXiv cs.AIresearchOn the Reliability and Stability of Selective Methods in Malware Classification Tasks
arXiv:2505.22843v4 Announce Type: replace-cross Abstract: The performance figures of modern drift-adaptive malware classifiers appear promising, but does this translate to genuine operational reliability? The standard ev…
- arXiv cs.AIresearchDoubly Robust Alignment for Large Language Models
arXiv:2506.01183v3 Announce Type: replace-cross Abstract: This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promis…
- arXiv cs.AIresearchRole-Augmented Intent-Driven Generative Search Engine Optimization
arXiv:2508.11158v3 Announce Type: replace-cross Abstract: Generative search engines (GSEs), which combine large language models (LLMs) with retrieval-augmented generation (RAG), are reshaping how users access Web informa…
- arXiv cs.AIresearchHow K-12 Teachers Adapt Generative AI to Local Classroom Demands: Cultural Distance Between GenAI Defaults and Everyday Teaching Practices
arXiv:2509.10780v2 Announce Type: replace-cross Abstract: Generative AI (GenAI) is entering K-12 classrooms, but its default culture does not always fit local teaching. Existing accounts either treat this misfit as macro…
- arXiv cs.AIresearchMultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
arXiv:2510.07328v3 Announce Type: replace-cross Abstract: Medical decision systems increasingly rely on data from multiple sources to ensure reliable and unbiased diagnosis. However, existing multimodal learning models f…
- arXiv cs.AIresearchSemantic World Models
arXiv:2510.19818v2 Announce Type: replace-cross Abstract: Planning with world models offers a powerful paradigm for robotic control. Conventional approaches train a model to predict future frames conditioned on current f…
- arXiv cs.AIresearchSELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting
arXiv:2512.03620v2 Announce Type: replace-cross Abstract: Safeguarding the Intellectual Property (IP) of Large Language Models (LLMs) against model theft represents a critical challenge in contemporary AI research. Altho…
- arXiv cs.AIresearchCounting Clues: A Lightweight Probabilistic Baseline Can Match an LLM
arXiv:2512.12868v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel on multiple-choice clinical diagnosis benchmarks, yet it is unclear how much of this performance reflects underlying probabilis…
- arXiv cs.AIresearchSkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping
arXiv:2512.13494v2 Announce Type: replace-cross Abstract: Large language models (LLM) have achieved remarkable performance across a wide range of tasks. However, their substantial parameter sizes pose significant challen…
- arXiv cs.AIresearchTS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
arXiv:2512.15773v2 Announce Type: replace-cross Abstract: Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. Existin…
- arXiv cs.AIresearchReach-Avoid Differential game with Reachability Analysis for UAVs: A decomposition approach
arXiv:2512.22793v2 Announce Type: replace-cross Abstract: Reach-avoid (RA) games have significant applications in security and defense, particularly for unmanned aerial vehicles (UAVs). These problems are inherently chal…
- arXiv cs.AIresearchForeground-Aware Dataset Distillation via Dual-Path Patch Selection
arXiv:2601.02727v2 Announce Type: replace-cross Abstract: In this paper, we propose a foreground-aware dataset distillation method that performs content-adaptive dual-path patch selection. With the rising computational c…
- arXiv cs.AIresearchThe Fake Friend Dilemma: Relational Trust and the Political Economy of Conversational AI
arXiv:2601.03222v4 Announce Type: replace-cross Abstract: As conversational AI systems become a larger part of the media landscape, they raise questions about whose interests they serve and the risks they may pose to use…
- arXiv cs.AIresearchBeyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation
arXiv:2601.12401v4 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex huma…
- arXiv cs.AIresearchSQuID: A Benchmark for Quantitative Spatial Reasoning on Satellite Imagery
arXiv:2601.13401v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) describe satellite images fluently but struggle with the quantitative spatial reasoning that remote sensing (RS) analysts perform ro…
- arXiv cs.AIresearchA swap-adversarial framework for domain generalization in pre- and post-stimulation Parkinsonian state classification
arXiv:2602.10528v3 Announce Type: replace-cross Abstract: We propose a novel swap-adversarial framework that mitigates high inter-subject variability and the high-dimensional low-sample-size problem in electrocorticograp…
- arXiv cs.AIresearchMIDAS: Mosaic Input-Specific Differentiable Architecture Search
arXiv:2602.17700v2 Announce Type: replace-cross Abstract: Differentiable Neural Architecture Search (NAS) provides efficient, gradient-based methods for automatically designing neural networks, yet its adoption remains l…
- arXiv cs.AIresearchPreconditioned Flow Matching
arXiv:2603.02337v3 Announce Type: replace-cross Abstract: Flow matching (FM) learns vector fields by regressing stochastic velocity targets along intermediate distributions $p_t$. We identify a geometric optimization bot…