AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDemystifying the Unreasonable Effectiveness of Greedy Alignment Methods
arXiv:2604.17207v2 Announce Type: replace-cross Abstract: Greedy AI alignment methods based on Bradley-Terry reward-model fitting and KL-regularized Alignment are remarkably effective in both offline and online preferenc…
- arXiv cs.AIresearchLearning Evidence Highlighting for Frozen LLMs
arXiv:2604.22565v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evidence Emphas…
- arXiv cs.AIresearchSGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation
arXiv:2604.22825v2 Announce Type: replace-cross Abstract: Large segmentation foundation models such as the Segment Anything Model (SAM) have reshaped promptable segmentation in natural images, and recent efforts have ext…
- arXiv cs.AIresearchDRAGON: A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
arXiv:2604.25231v2 Announce Type: replace-cross Abstract: Diagram question answering (DQA) requires models to interpret structured visual representations such as charts, maps, infographics, circuit schematics, and scient…
- arXiv cs.AIresearchVUDA: Enabling Controlled Spatial Sharing of Graphics and Compute on NVIDIA GPUs
arXiv:2605.01352v2 Announce Type: replace-cross Abstract: Graphics and compute increasingly share a single GPU in embodied AI simulators, AI-enabled games, and VR systems. Running these workloads concurrently can improve…
- arXiv cs.AIresearchQuery-Dependent Use of Generated Descriptions for Reliable Visual Question Answering
arXiv:2605.01733v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) hallucinate objects that are not present, and a growing line of work tries to curb this by feeding the model its own generated capti…
- arXiv cs.AIresearchFederated Semi-Supervised Graph Neural Networks with Prototype-Guided Pseudo-Labeling for Privacy-Preserving Gestational Diabetes Mellitus Prediction
arXiv:2605.01810v2 Announce Type: replace-cross Abstract: Gestational Diabetes Mellitus (GDM) is a high-prevalence pregnancy complication that requires accurate early risk stratification to reduce maternal and fetal morb…
- arXiv cs.AIresearchRoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
arXiv:2605.03821v2 Announce Type: replace-cross Abstract: Existing robot video world models are typically trained with low-level objectives such as reconstruction and perceptual similarity, which are poorly aligned with…
- arXiv cs.AIresearchDemystifying Manifold Constraints in LLM Pre-training
arXiv:2605.04418v2 Announce Type: replace-cross Abstract: The recent success of matrix optimizers (e.g., Muon) suggests that specific normalization of momentum, such as orthogonalization and row-wise normalization, benef…
- arXiv cs.AIresearchTwo-Stage Learned Decomposition for Scalable Routing on Multigraphs
arXiv:2605.05389v2 Announce Type: replace-cross Abstract: Most neural methods for Vehicle Routing Problems (VRPs) are limited to Euclidean settings or simple graphs. In this work, we instead consider multigraphs, where p…
- arXiv cs.AIresearchOne Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent
arXiv:2605.05630v3 Announce Type: replace-cross Abstract: Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a sing…
- arXiv cs.AIresearchSymDrift: One-Shot Generative Modeling under Symmetries
arXiv:2605.06140v3 Announce Type: replace-cross Abstract: Generative modeling of physical systems, such as molecules, requires learning distributions that are invariant under global symmetries, such as rotations in three…
- arXiv cs.AIresearchWhen to Trust Imagination: Adaptive Action Execution for World Action Models
arXiv:2605.06222v3 Announce Type: replace-cross Abstract: World Action Models (WAMs) jointly predict future visual observations and actions, but typically execute a fixed number of actions before replanning, regardless o…
- arXiv cs.AIresearchAre We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
arXiv:2605.06643v2 Announce Type: replace-cross Abstract: Despite the growing popularity of Multimodal Domain Generalization (MMDG) for enhancing model robustness, it remains unclear whether reported performance gains re…
- arXiv cs.AIresearchUniPool: Learning Expert-to-Layer Ownership from Brief Global Access
arXiv:2605.06665v2 Announce Type: replace-cross Abstract: Most Mixture-of-Experts (MoE) transformers preassign each expert to one layer for the whole of training. We study whether a brief global-access phase can learn a…
- arXiv cs.AIresearchEnabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning
arXiv:2605.06724v2 Announce Type: replace-cross Abstract: Denoising electroencephalogram (EEG) is an inherently challenging task, since neural activity is not only subtle but also inseparable from spectrally overlapping…
- arXiv cs.AIresearchSkip What You Can Predict: Predictive Repositioning for Policy Optimization for Efficient LLM Training
arXiv:2605.06755v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) can improve the reasoning ability of large language models, but repeatedly updating a policy on the same rol…
- arXiv cs.AIresearchOn Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
arXiv:2605.06835v2 Announce Type: replace-cross Abstract: Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is a rising int…
- arXiv cs.AIresearchMELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text
arXiv:2605.06903v2 Announce Type: replace-cross Abstract: Large language models are widely used in everyday writing, making reliable AI-generated text detection crucial for academic integrity, content moderation, and pro…
- arXiv cs.AIresearchIn-Context Credit Assignment via the Core
arXiv:2605.06920v2 Announce Type: replace-cross Abstract: We propose incentive-aligned mechanisms for in-context credit assignment: the task of assigning credit for AI-generated content among creators whose intellectual…
- arXiv cs.AIresearchBGM-IV: AI-Powered Bayesian Generative Modeling for Instrumental Variable Regression with High-Dimensional Covariates
arXiv:2605.07029v2 Announce Type: replace-cross Abstract: Instrumental-variable (IV) regression enables causal estimation under endogeneity, but modern IV problems often involve nonlinear structural effects and high-dime…
- arXiv cs.AIresearchRRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
arXiv:2605.07129v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and natural-lang…
- arXiv cs.AIresearchEncoder-Decoder Transformers: Logical Characterizations and Periodicity
arXiv:2605.07705v2 Announce Type: replace-cross Abstract: We give logical characterizations of encoder-decoder transformers, the foundational architecture for LLMs that also sees use in various settings that benefit from…
- arXiv cs.AIresearchMemory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
arXiv:2605.07721v3 Announce Type: replace-cross Abstract: Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without gen…
- arXiv cs.AIresearchGazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning
arXiv:2605.07817v2 Announce Type: replace-cross Abstract: Human visual reasoning is governed by active vision, a process where meta-cognitive control drives top-down goal-directed attention, dynamically routing foveal fo…
- arXiv cs.AIresearchOne Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
arXiv:2605.07931v4 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models can use visual prediction to anticipate future states, but dense visual features make the generative sequence grow with the nu…
- arXiv cs.AIresearchLAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment
arXiv:2605.08156v2 Announce Type: replace-cross Abstract: Zero-shot visual recognition often depends on localized parts, attributes, and textures that are diluted in global image representations. Existing training-free l…
- arXiv cs.AIresearchAIPO: Learning to Reason from Active Interaction
arXiv:2605.08401v3 Announce Type: replace-cross Abstract: Recent advances in LLMs have demonstrated strong reasoning capabilities, largely stimulated by RLVR. However, the exploration of existing RLVR algorithms remains…
- arXiv cs.AIresearchRecovering Physical Dynamics from Discrete Observations via Intrinsic Differential Consistency
arXiv:2605.08454v2 Announce Type: replace-cross Abstract: Recovering continuous-time dynamics from discrete observations is difficult because local supervision loses fidelity as the observation interval grows. We replace…
- arXiv cs.AIresearchFraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence
arXiv:2605.08820v2 Announce Type: replace-cross Abstract: Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to real-world claims, creating new challenges for verifying…
- arXiv cs.AIresearchTowards Effective Theory of LLMs: A Representation Learning Approach
arXiv:2605.09294v2 Announce Type: replace-cross Abstract: We propose Representational Effective Theory (RET), a framework for describing large language model computation in terms of learned macrostates rather than micros…
- arXiv cs.AIresearchNeural Cluster First, Route Second: Capacitated Vehicle Routing via Differentiable Optimal Transport
arXiv:2605.09301v2 Announce Type: replace-cross Abstract: The Capacitated Vehicle Routing Problem (CVRP) underpins modern last-mile logistics, where routing decisions recur over the same fixed service area, like a city.…
- arXiv cs.AIresearchPoDAR: Power-Decoupled Audio Representation for Generative Modeling
arXiv:2605.10084v2 Announce Type: replace-cross Abstract: The performance of audio latent diffusion models is primarily governed by generator expressivity and the modelability of the underlying latent space. While recent…
- arXiv cs.AIresearchInvestigating Single-Block Recurrence in Vision Transformers for Image Recognition
arXiv:2605.10661v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) implement depth by stacking independently parameterized blocks, but it remains unclear how much of this parameterization is necessary a…
- arXiv cs.AIresearchWhen and How to Canonize: A Generalization Perspective
arXiv:2605.11008v3 Announce Type: replace-cross Abstract: While invariant architectures are standard for processing symmetric data, there is growing interest in achieving invariance by applying group averaging or canoniz…
- arXiv cs.AIresearchInternalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
arXiv:2605.11235v2 Announce Type: replace-cross Abstract: In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handc…
- arXiv cs.AIresearchDeep Minds and Shallow Probes
arXiv:2605.11448v2 Announce Type: replace-cross Abstract: Neural representations are not unique objects. Even when two systems realize the same downstream computation, their hidden coordinates may differ by reparameteriz…
- arXiv cs.AIresearchEvery Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
arXiv:2605.11653v2 Announce Type: replace-cross Abstract: With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such…
- arXiv cs.AIresearchEHR-RAGp: Prototype-Guided Retrieval of Longitudinal Electronic Health Records for Clinical Prediction Models
arXiv:2605.12335v2 Announce Type: replace-cross Abstract: Electronic Health Records (EHR) contain rich longitudinal patient information and are widely used in predictive modeling applications. However, effectively levera…
- arXiv cs.AIresearchCoRe-Gen: Robust Spectrum-to-Structure Generation under Imperfect Fingerprint Conditions
arXiv:2605.12980v2 Announce Type: replace-cross Abstract: Molecular structure elucidation from tandem mass spectra (MS/MS) remains challenging, particularly for de novo generation beyond database coverage. A common appro…
- arXiv cs.AIresearchWatermarking Should Be Treated as a Monitoring Primitive
arXiv:2605.13095v4 Announce Type: replace-cross Abstract: Watermarking is a primary means for providers of generative models to meet legal requirements to mark synthetic content. A watermark embeds a hidden signal into g…
- arXiv cs.AIresearchCross Modality Image Translation In Medical Imaging Using Generative Frameworks
arXiv:2605.13686v2 Announce Type: replace-cross Abstract: Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and Positron Emission Tomography (PET) provide complementary information about tissues. Medical image-…
- arXiv cs.AIresearchWhere Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
arXiv:2605.14368v2 Announce Type: replace-cross Abstract: Continuous diffusion language models require choosing a representation space in which denoising operates, yet it remains unclear which representations are most co…
- arXiv cs.AIresearchEverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
arXiv:2605.15042v2 Announce Type: replace-cross Abstract: We propose EverAnimate, an efficient post-training method for long-horizon animated video generation that preserves visual quality and character identity. Long-fo…
- arXiv cs.AIresearchGoal-Conditioned Supervised Learning for LLM Fine-Tuning
arXiv:2605.16345v2 Announce Type: replace-cross Abstract: Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into onlin…
- arXiv cs.AIresearchReducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference Supervision
arXiv:2605.16411v4 Announce Type: replace-cross Abstract: Hallucination remains a major challenge in vision-language models (VLMs), particularly when linguistically plausible responses are unsupported by visual evidence.…
- arXiv cs.AIresearchDeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
arXiv:2605.16441v2 Announce Type: replace-cross Abstract: Beat-level Electrocardiography (ECG) arrhythmia detection aims to assign an arrhythmia class to each beat in a recording, yet many existing systems treat beats as…
- arXiv cs.AIresearchFidelity Probes for Specification--Code Alignment
arXiv:2605.17246v2 Announce Type: replace-cross Abstract: Software modernization often relies on natural-language specifications recovered from an existing implementation. Incorrect or missing requirements can lead to de…
- arXiv cs.AIresearchDCFold: Efficient Protein Structure Generation with Single Forward Pass
arXiv:2605.17899v2 Announce Type: replace-cross Abstract: AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy. This state-of-the-a…
- arXiv cs.AIresearchConcise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
arXiv:2605.18202v3 Announce Type: replace-cross Abstract: Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reliability in h…