AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSentryVLA: Uncertainty-Guided Action Selection and State Monitoring for Vision-Language-Action Robotic Control
arXiv:2604.16677v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models have emerged as generalist robotic controllers that map visual observations and language instructions to continuous actions. H…
- arXiv cs.AIresearchDoes "Do Differentiable Simulators Give Better Policy Gradients?" Give Better Policy Gradients?
arXiv:2604.18161v2 Announce Type: replace-cross Abstract: In policy gradient reinforcement learning, access to a differentiable model enables 1st-order gradient estimation that accelerates learning compared to relying so…
- arXiv cs.AIresearchSemantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring
arXiv:2604.18835v2 Announce Type: replace-cross Abstract: We propose a scalable, multifactorial experimental framework that systematically probes LLM sensitivity to subtle semantic changes in pairwise document comparison…
- arXiv cs.AIresearchProbing Visual Planning in Image Editing Models
arXiv:2604.22868v2 Announce Type: replace-cross Abstract: Visual planning represents a crucial facet of human intelligence, especially in tasks that require complex spatial reasoning and navigation. Yet, in machine learn…
- arXiv cs.AIresearchGPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
arXiv:2604.25370v3 Announce Type: replace-cross Abstract: The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never b…
- arXiv cs.AIresearchRepetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling
arXiv:2604.28075v3 Announce Type: replace-cross Abstract: Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for high-resou…
- arXiv cs.AIresearchMissingness-Conditioned Spatio-Temporal Fusion for Human Activity Recognition from Low-Quality Wearable Sensor Data
arXiv:2605.00913v2 Announce Type: replace-cross Abstract: Body-worn sensor networks capture human activities through complementary views, where nodes, modalities, and axes partially describe the underlying motion. In rea…
- arXiv cs.AIresearchSignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages
arXiv:2605.01720v4 Announce Type: replace-cross Abstract: Large-scale sign language resources usually pair RGB videos with text and support recognition, translation, and generation. However, RGB frames contain background…
- arXiv cs.AIresearchA Semantic Autonomy Framework for VLM-Integrated Indoor Mobile Robots: Hybrid Deterministic Reasoning and Cross-Robot Adaptive Memory
arXiv:2605.02525v2 Announce Type: replace-cross Abstract: Semantic indoor navigation requires robots to connect human instructions with spatial destinations, execute missions and retain useful operational experience. Thi…
- arXiv cs.AIresearchWhy Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
arXiv:2605.04971v2 Announce Type: replace-cross Abstract: Weight matrices in deep networks exhibit geometric continuity---principal singular vectors of adjacent layers point in similar directions. While this property has…
- arXiv cs.AIresearchBatMIL: Geometry-Embedding State Space Model for Whole-Slide Image Representation
arXiv:2605.05164v2 Announce Type: replace-cross Abstract: Accurate analysis of histopathological images is critical for disease diagnosis and treatment planning. Whole-slide images (WSIs), which digitize tissue specimens…
- arXiv cs.AIresearchOmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning
arXiv:2605.06728v2 Announce Type: replace-cross Abstract: Large language models can reason over biological knowledge, but they are not naturally equipped to work with quantitative omics measurements. Existing approaches…
- arXiv cs.AIresearchMathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators
arXiv:2605.07600v2 Announce Type: replace-cross Abstract: Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, cannot identify w…
- arXiv cs.AIresearchNeural Information Causality: A Random-Access Capacity Law for Representation Learning
arXiv:2605.09316v2 Announce Type: replace-cross Abstract: How can a learned representation remain useful when the question it must answer is chosen only after encoding? Preserving information is essential, but does not b…
- arXiv cs.AIresearchMicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attributed Property Graph
arXiv:2605.10120v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) show remarkable potential for scientific reasoning, yet their performance in specialized domains such as microscopy remai…
- arXiv cs.AIresearch$\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin
arXiv:2605.10981v2 Announce Type: replace-cross Abstract: Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(…
- arXiv cs.AIresearchScaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
arXiv:2605.12049v2 Announce Type: replace-cross Abstract: Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent biological constraint…
- arXiv cs.AIresearchCoherence-Guided Pyramid Self-Contrastive Disentanglement for Ultrasound Imaging via Single-Shot Test-Time Training
arXiv:2605.12567v3 Announce Type: replace-cross Abstract: The inherent electronic noise, side lobes, and speckle noise complicate clinical interpretation of ultrasound images. Conventional denoising methods rely on expli…
- arXiv cs.AIresearchWhere and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning
arXiv:2605.15464v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capability of language models, since model-generated answers can be…
- arXiv cs.AIresearchContinuous Diffusion Scales Competitively with Discrete Diffusion for Language
arXiv:2605.18530v3 Announce Type: replace-cross Abstract: While diffusion has drawn considerable recent attention from the language modeling community, continuous diffusion has appeared less scalable than discrete approa…
- arXiv cs.AIresearchStableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video
arXiv:2605.18553v2 Announce Type: replace-cross Abstract: Recovering world space 4D motion of two interacting hands from egocentric video is a fundamental capability for supervising robot policy learning, where wrist tra…
- arXiv cs.AIresearchDivide et Calibra: Multiclass Local Calibration via Vector Quantization
arXiv:2605.21060v2 Announce Type: replace-cross Abstract: Accurate and well-calibrated Machine Learning (ML) models are mandatory in high-stakes settings, yet effective multiclass calibration remains challenging: global…
- arXiv cs.AIresearchThe Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
arXiv:2605.21856v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evalua…
- arXiv cs.AIresearchAn Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation
arXiv:2605.24155v2 Announce Type: replace-cross Abstract: Effective skills-aware talent recommendation must balance behavioral transition patterns, trajectory-sensitive adaptation, and inspectable occupation-level criter…
- arXiv cs.AIresearchLearning Faithful Reasoning Processes with Spatio-Temporal Latent Dynamics for Large Language Models
arXiv:2605.26893v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning has significantly enhanced the reasoning capabilities of large language models (LLMs). However, existing reinforcement learning m…
- arXiv cs.AIresearchPrompt PerturbAItions: Mechanisms of LLM Response Inconsistencies
arXiv:2605.30913v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in conversational settings where user phrasing ranges from polite to casual to toxic, yet less is known abo…
- arXiv cs.AIresearchCrazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX
arXiv:2606.01478v3 Announce Type: replace-cross Abstract: High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing robots' capabilities. While aerial robotics simulators have evolve…
- arXiv cs.AIresearchModeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation
arXiv:2606.02552v2 Announce Type: replace-cross Abstract: Despite advances in depth estimation, flying points remain a persistent failure mode: near object boundaries, depth estimators often predict spurious 3D points in…
- arXiv cs.AIresearchPRISM: PRior-guided Imagination Sampling in world Models
arXiv:2606.07974v2 Announce Type: replace-cross Abstract: Latent world models learn representations that enable them to predict how actions change the environment - a capability we call physical intuition. We find that t…
- arXiv cs.AIresearchLaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
arXiv:2606.15768v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot…
- arXiv cs.AIresearchBayesian Anytime Pareto Set Identification for Multi-Objective Multi-Armed Bandits
arXiv:2606.18785v2 Announce Type: replace-cross Abstract: Identifying Pareto optimal solutions is critical to support multi-objective decision-making. In this work, we present Top-Two Pareto Front Thompson Sampling (TTPF…
- arXiv cs.AIresearchSURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization
arXiv:2606.24259v2 Announce Type: replace-cross Abstract: Fine-tuned encoders deployed across heterogeneous NLP tasks face three compounding problems: mismatched inductive biases, class-imbalance corruption of feature st…
- arXiv cs.AIresearchDiagnosing and Mitigating Context Rot in Long-horizon Search
arXiv:2606.29718v3 Announce Type: replace-cross Abstract: Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon search tasks. The concern that increasing context…
- arXiv cs.AIresearchLUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
arXiv:2607.00687v2 Announce Type: replace-cross Abstract: Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences ra…
- arXiv cs.AIresearchCausalMix: Data Mixture as Causal Inference for Language Model Training
arXiv:2607.01104v2 Announce Type: replace-cross Abstract: In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy model…
- arXiv cs.AIresearchUnbiased Alignment for Large Language Models with Noisy Preferences
arXiv:2607.03248v2 Announce Type: replace-cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimiz…
- arXiv cs.AIresearchPhysics-Informed Structure Anchoring With Capture-Aware Prototype Calibration for Cross-Environment RF Fingerprinting
arXiv:2607.09760v3 Announce Type: replace-cross Abstract: Radio frequency fingerprint identification (RFFI) exploits transmitter-specific hardware imperfections as physicallayer identity cues for Internet of Things (IoT)…
- arXiv cs.AIresearchSLAB: Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories
arXiv:2607.11725v2 Announce Type: replace-cross Abstract: Prefabricated prefinished volumetric construction (PPVC) builds room-sized modules in factories that operate as flexible job shops. A module waits 12 to 48 h afte…
- arXiv cs.AIresearchLoop the Loopies!
arXiv:2607.16051v3 Announce Type: replace-cross Abstract: We present Loopie, the most powerful open-source looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter mo…
- arXiv cs.AIresearchGTIN: A Unified Scalable Framework for Joint Event and Time Prediction in Temporal Graphs
arXiv:2607.23556v3 Announce Type: replace-cross Abstract: Temporal graphs are increasingly used to model dynamic systems across diverse domains, including social, financial, and traffic networks. Predicting both what the…
- arXiv cs.AIresearchSpectONet: A Physics-Guided Spectral Deep Operator Network for Euler-Bernoulli Beam Dynamics
arXiv:2607.25790v2 Announce Type: replace-cross Abstract: This paper proposes a novel physics-guided spectral deep operator network, termed SpectONet, for solving Euler-Bernoulli beam (EBB) vibration problems. The propos…
- arXiv cs.AIresearchTowards Practical Algorithm Selection for Unsupervised Domain Adaptation in Medical Imaging
arXiv:2607.28125v3 Announce Type: replace-cross Abstract: Numerous unsupervised domain adaptation (UDA) algorithms exist, but for clinical practice, selecting the best-suited one along with proper hyperparameters often r…
- arXiv cs.AIresearchA False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility
arXiv:2608.00583v4 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) monitors are reported by their aggregate accuracy on a pool of reward hacks. We show that this number is a false average. On Terminal Wrenc…
- arXiv cs.AIresearchCallScreenBench: Benchmarking Small Language Models as Phone Secretaries
arXiv:2608.01033v3 Announce Type: replace-cross Abstract: Language models small enough to run on a handset, quantized to a few bits, are increasingly capable of acting on their user's behalf -- which makes on-device task…
- arXiv cs.AIresearchContent-Aware Adaptive Token Pruning for Video-Language Models
arXiv:2608.03112v2 Announce Type: replace-cross Abstract: Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, lim…
- arXiv cs.AIresearchLC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
arXiv:2608.05600v2 Announce Type: replace-cross Abstract: Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE), whereas reinforcement learning (RL) requires s…
- arXiv cs.AIresearchGenotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Models
arXiv:2608.06779v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have accelerated drug discovery, particularly in the automated design of antimicrobial peptides (AMPs). However, current validation p…
- arXiv cs.AIresearchLoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes
arXiv:2608.06795v2 Announce Type: replace-cross Abstract: Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introd…
- arXiv cs.AIresearchCoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
arXiv:2608.07458v2 Announce Type: replace-cross Abstract: Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for high…
- arXiv cs.AIresearchHow Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging
arXiv:2608.12035v2 Announce Type: replace-cross Abstract: Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship. However, the…