AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWhen Does Equivariance Help? Canonical Alignment in Neural Fluid Surrogates
arXiv:2605.18816v2 Announce Type: replace-cross Abstract: Neural surrogates can accelerate computational fluid dynamics (CFD) simulations by orders of magnitude, but practical deployment in engineering and healthcare app…
- arXiv cs.AIresearchMLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
arXiv:2605.21954v2 Announce Type: replace-cross Abstract: Video temporal grounding (VTG), which localizes the start and end times of a queried event in an untrimmed video, is a key test of whether multimodal large langua…
- arXiv cs.AIresearchLearning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
arXiv:2605.21988v2 Announce Type: replace-cross Abstract: Video large language models (Video LLMs) can achieve strong video-QA accuracy without reliably tracking spatiotemporal dynamics. A model may answer a motion quest…
- arXiv cs.AIresearchAnytime Training with Schedule-Free Spectral Optimization
arXiv:2605.23061v2 Announce Type: replace-cross Abstract: Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availab…
- arXiv cs.AIresearchXWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms
arXiv:2605.23348v3 Announce Type: replace-cross Abstract: AI power demand is growing at an unprecedented rate while power grids are often ailing and struggle to keep up. Grid expansion comes with high capital expenditure…
- arXiv cs.AIresearchOne-Forcing: Towards Stable One-Step Autoregressive Video Generation
arXiv:2605.23458v2 Announce Type: replace-cross Abstract: Recent advances in autoregressive diffusion-based video generation have substantially improved the quality of real-time video synthesis. However, most existing me…
- arXiv cs.AIresearchEviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
arXiv:2605.29670v2 Announce Type: replace-cross Abstract: Schema linking is a difficult and important step in large-scale Text-to-SQL, where systems must identify a compact yet sufficient schema context from large and am…
- arXiv cs.AIresearchMulti-Legal-Bench: When the Answer Is in the Input. Label Leakage in Legal Benchmarks Built from Court Registries
arXiv:2605.29738v3 Announce Type: replace-cross Abstract: Court registries publish millions of decisions with structured metadata, which makes them an attractive source of labelled legal benchmarks: the court type, the f…
- arXiv cs.AIresearchNo More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
arXiv:2605.30120v4 Announce Type: replace-cross Abstract: Multi-vector retrieval (MVR) models, exemplified by ColBERT, have established new benchmarks in retrieval accuracy by preserving fine-grained token-level interact…
- arXiv cs.AIresearchShared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models
arXiv:2605.31220v3 Announce Type: replace-cross Abstract: Confidence estimation (CE), i.e. quantifying the reliability of a model's prediction, has attracted great interest in the context of large language models (LLMs).…
- arXiv cs.AIresearchBitsMoE: Cost-Aware Bit Allocation in Spectral Space for MoE LLM Quantization
arXiv:2606.00079v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) large language models incur substantial memory costs due to their large expert parameter counts. Mixed-precision quantization reduces the…
- arXiv cs.AIresearchCan Predicted Dynamics Exist in the Physical World?
arXiv:2606.00089v3 Announce Type: replace-cross Abstract: Can learned state-action proposals exist in the physical world? Before executing a proposed action sequence, a robot can inspect empirical variation and disagreem…
- arXiv cs.AIresearchContext-aware tokenization for Cross-subject Emotion Decoding from EEG
arXiv:2606.00884v2 Announce Type: replace-cross Abstract: In cross-subject EEG emotion decoding, neighboring windows can inform the representation of a target window, but they contain both background variation and sustai…
- arXiv cs.AIresearchKnowledge-Intensive Video Generation
arXiv:2606.01285v2 Announce Type: replace-cross Abstract: Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce knowledge-inten…
- arXiv cs.AIresearchQuantifying and Mitigating Domain Shift in Peach Leaf Damage Classification: Attention Mechanisms and Fine-Tuning Strategies
arXiv:2606.02045v3 Announce Type: replace-cross Abstract: Deep learning models for crop damage assessment are typically trained and validated on curated public imagery, yet their behaviour when deployed in real orchards…
- arXiv cs.AIresearchConTraIRL: Factorized Contrastive Abstractions for Transferable IRL
arXiv:2606.03017v2 Announce Type: replace-cross Abstract: Reward transfer in Inverse Reinforcement Learning (IRL) is unreliable when policies must generalize to unseen combinations of environment dynamics and task goals.…
- arXiv cs.AIresearchFrom 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members
arXiv:2606.03876v2 Announce Type: replace-cross Abstract: With the growing prevalence of modern ubiquitous computing technologies, multi-modal tracking systems hold promise for providing timely awareness and reassurance…
- arXiv cs.AIresearchChannel-Preserving Representation Alignment for EEG-to-Music Reconstruction
arXiv:2606.04040v2 Announce Type: replace-cross Abstract: Reconstructing naturalistic music from EEG requires extracting music-specific information from weak signals distributed across electrodes. Existing spectrogram re…
- arXiv cs.AIresearchLarge Language Models Hack Rewards, and Society
arXiv:2606.04075v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal re…
- arXiv cs.AIresearchDual Advantage Fields
arXiv:2606.04188v2 Announce Type: replace-cross Abstract: Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide…
- arXiv cs.AIresearchHearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
arXiv:2606.06833v3 Announce Type: replace-cross Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription deci…
- arXiv cs.AIresearchDefending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
arXiv:2606.07970v2 Announce Type: replace-cross Abstract: Malicious finetuning attacks pose a major safety threat against open-weight large language models (LLMs). However, existing alignment-stage defenses provide limit…
- arXiv cs.AIresearchSci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems
arXiv:2606.08034v2 Announce Type: replace-cross Abstract: Symbolic benchmarks have emerged as a key approach to assess model robustness under minor modifications to STEM-related questions. However, existing symbolic benc…
- arXiv cs.AIresearchStarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling
arXiv:2606.15197v3 Announce Type: replace-cross Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimization modeling…
- arXiv cs.AIresearchWasserstein Convergence of ODE-Based Samplers in Decentralized Diffusion Model via Velocity Field Decomposition
arXiv:2606.15835v2 Announce Type: replace-cross Abstract: Diffusion models have achieved impressive empirical success in generative tasks, and their convergence theory is now relatively well understood. Motivated by priv…
- arXiv cs.AIresearchWhat Should a Streaming Video Model Remember?
arXiv:2606.16353v2 Announce Type: replace-cross Abstract: Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory…
- arXiv cs.AIresearchWhen Does Depth Matter For In-Context Learning? Adaptive Inference in Deep Transformers
arXiv:2606.16694v2 Announce Type: replace-cross Abstract: Transformers perform computations through many successive attention and feedforward blocks, allowing them to learn complex correlations between a large collection…
- arXiv cs.AIresearchDRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution
arXiv:2606.18307v2 Announce Type: replace-cross Abstract: Data selection for instruction tuning is usually studied for efficiency, reaching strong performance with a fraction of the training data. We ask whether data sel…
- arXiv cs.AIresearchWhen to Commit and When to Defer: Maturing Markov Decision Processes under Refining Information and Expiring Opportunities
arXiv:2606.18820v2 Announce Type: replace-cross Abstract: Sequential decisions often become better informed as action opportunities expire. We introduce Maturing Markov Decision Processes (MMDPs), a structured subclass o…
- arXiv cs.AIresearchOneCanvas: 3D Scene Understanding via Panoramic Reprojection
arXiv:2606.19253v2 Announce Type: replace-cross Abstract: Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets…
- arXiv cs.AIresearchOnly Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
arXiv:2606.22681v2 Announce Type: replace-cross Abstract: Multi-hop question answering remains challenging for Retrieval-Augmented Generation (RAG) because existing approaches either propagate errors across iterative ret…
- arXiv cs.AIresearchRethinking Object-Centric Representations for Video Dynamics Modeling
arXiv:2606.23436v2 Announce Type: replace-cross Abstract: Learning to decompose videos into persistent objects is a fundamental challenge in unsupervised object-centric representation learning. Despite recent progress, e…
- arXiv cs.AIresearchJuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators
arXiv:2606.28421v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) diffusion models typically require substantial computational resources and cloud infrastructure, posing significant challenges for edge deploy…
- arXiv cs.AIresearchA Gravitational Interpretation of Safety Reversion under Fine-Tuning
arXiv:2606.28525v2 Announce Type: replace-cross Abstract: Safety alignment in large language models can degrade during post-training even when neither the data nor the objective is intentionally adversarial. Alignment re…
- arXiv cs.AIresearchReal-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval
arXiv:2607.00448v3 Announce Type: replace-cross Abstract: The two-tower model is widely used in the retrieval stage of large-scale recommendation systems, where training typically relies on in-batch and/or out-of-batch n…
- arXiv cs.AIresearchFlow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition
arXiv:2607.00535v2 Announce Type: replace-cross Abstract: Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by learning long-range transport maps between noise and data. However,…
- arXiv cs.AIresearchScaling Laws for Collapse in Asynchronous GRPO
arXiv:2607.01083v3 Announce Type: replace-cross Abstract: Asynchronous reinforcement learning improves the throughput of large language model post-training by decoupling rollout generation from policy optimization, but i…
- arXiv cs.AIresearchSampling Meets Interaction: Sequentially-Controlled Multi-Particle Flow-Maps for Efficient Inference-time Search
arXiv:2607.01144v2 Announce Type: replace-cross Abstract: While generative models have enabled training-free reward alignment, existing particle-based methods are fundamentally constrained by their propensity to local ex…
- arXiv cs.AIresearchLACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
arXiv:2607.02513v2 Announce Type: replace-cross Abstract: LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlear…
- arXiv cs.AIresearchBFMT: Enhancing Search Capabilities of Tree Sampler via Bootstrap Flow-Map Tree
arXiv:2607.02915v2 Announce Type: replace-cross Abstract: The ability to efficiently navigate high-dimensional spaces to identify optimal candidates-whether designing targeted molecular structures or generating images wi…
- arXiv cs.AIresearchOne Image, No Tokens: A Controlled Study of Glyph-Based Chinese Language Modeling
arXiv:2607.03994v2 Announce Type: replace-cross Abstract: Modern language models generally represent text as sequences of discrete token embeddings, an assumption deeply rooted in current practice but rarely questioned.…
- arXiv cs.AIresearchSource-Lifted Flow Matching for Intervenable Multimodal Imitation
arXiv:2607.10206v2 Announce Type: replace-cross Abstract: Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity is largely pa…
- arXiv cs.AIresearchThe Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators
arXiv:2607.13075v2 Announce Type: replace-cross Abstract: An activation-based safety gate must distinguish harmful assistance from legitimate work on the same topic. We test whether probes trained on broad harmful-versus…
- arXiv cs.AIresearchWhat Does Model Growth Really Add? Functional Capacity Beyond Parameter Count
arXiv:2607.14571v2 Announce Type: replace-cross Abstract: Model growth adds parameters to a trained checkpoint and continues training, aiming to increase capacity while reusing the existing model instead of training from…
- arXiv cs.AIresearchTRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
arXiv:2607.16242v2 Announce Type: replace-cross Abstract: Fine-Tuning-as-a-Service (FTaaS) platforms let users perform supervised fine-tuning (SFT) on customized data, but this pipeline can erode model safety alignment.…
- arXiv cs.AIresearchCoCurve: Cross-Module Co-Pruning Curvature for Structured LLM Pruning
arXiv:2607.17568v2 Announce Type: replace-cross Abstract: Resource-constrained deployment requires sustaining large language model (LLM) capabilities as models scale under fixed memory and computation budgets. Structured…
- arXiv cs.AIresearchCriPO: Enhancing Rubric-based RL via Self-Distillation
arXiv:2607.18082v4 Announce Type: replace-cross Abstract: Rubric-based Reinforcement Learning (RL) has recently shown promise in improving Large Language Models (LLMs) on open-ended tasks. A widely recognized limitation…
- arXiv cs.AIresearchMOPDA: Mixed-Trajectory On-Policy Distillation for Language-Guided Industrial Anomaly Detection
arXiv:2607.18850v2 Announce Type: replace-cross Abstract: Large vision-language models (LVLMs) have shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretab…
- arXiv cs.AIresearchSimulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics
arXiv:2607.19389v2 Announce Type: replace-cross Abstract: As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn sign…
- arXiv cs.AIresearchConfidently Deceptive: On the Relationship Between Confidence and Deception in LLMs
arXiv:2607.20444v2 Announce Type: replace-cross Abstract: The increasing capabilities of large language models (LLMs) are being accompanied by deep-rooted risks of deceptive behaviours that cause models to produce mislea…