AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition
arXiv:2610.39265v1 Announce Type: cross Abstract: Multi-image composition (MICo) is a critical yet challenging capability for large-scale image editing models, where consistency degrades rapidly as the number of referenc…
- arXiv cs.AIresearchWorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining
arXiv:2610.39278v1 Announce Type: cross Abstract: Predicting future physical states stands as a central challenge in embodied intelligence. Existing video world models leave 3D dynamics implicit, action-based formulation…
- arXiv cs.AIresearchThere Is No Free Lunch in RLVR: Every pass@1 Gain Has a pass@k Price
arXiv:2610.39295v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) makes a language model solve more problems on the first try and fewer when given many tries: it raises pass@1 while…
- arXiv cs.AIresearchLearning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference
arXiv:2610.39305v1 Announce Type: cross Abstract: Probabilistic graphical models (PGMs) compactly encode structured joint distributions, but Most Probable Explanation (MPE), which finds the highest-probability assignment…
- arXiv cs.AIresearchTelling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe
arXiv:2610.39331v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly prompted with personas, such as "You have low vision", to stand in for people in user studies. We ask whether a persona mak…
- arXiv cs.AIresearchRetroChessBench: A Benchmark for Reconstructing and Proving Chess Histories
arXiv:2610.39341v1 Announce Type: cross Abstract: Frontier language models such as GPT 6 Astra have contributed to research mathematics, demonstrating substantial reasoning capabilities. Yet serious reasoning failures pe…
- arXiv cs.AIresearchSemantic Mismapping in Generalized Category Discovery: Evaluation and Mitigation
arXiv:2610.39356v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to perform old-category recognition and novel-category discovery in the same unlabeled set. Early methods address both objective…
- arXiv cs.AIresearchCord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models
arXiv:2610.39372v1 Announce Type: cross Abstract: The decoding order of masked diffusion language models (dLLMs) can substantially affect generation quality, yet common decoders typically apply the same reveal rule throu…
- arXiv cs.AIresearchWhat Makes Medical Examination Items Difficult? Using Large Language Models to Explore Patterns Associated With Empirical Item Difficulty
arXiv:2610.39373v1 Announce Type: cross Abstract: Research on medical item difficulty has largely focused on prediction rather than on identifying interpretable patterns associated with empirical difficulty. This study u…
- arXiv cs.AIresearchUMI-Live for In-The-Wild Bimanual Robotics Data Collection
arXiv:2610.39385v1 Announce Type: cross Abstract: Universal Manipulation Interface (UMI) devices allow human experts to demonstrate tasks for robot learning without teleoperating physical robots. Using these demonstratio…
- arXiv cs.AIresearchSymKL: A Unified Representation-Space Measure of Signal Degradation
arXiv:2610.39403v1 Announce Type: cross Abstract: Quantifying degradation between a pristine signal and its degraded observation is fundamental to signal processing, yet existing full-reference measures are inherently mo…
- arXiv cs.AIresearchSafe Multi-Objective Reinforcement Learning: Zero Constraint Violation and Primal-Averaging Convergence
arXiv:2610.39409v1 Announce Type: cross Abstract: Many applications of multi-objective reinforcement learning (MORL) require policies that balance conflicting objectives while satisfying safety constraints. We study safe…
- arXiv cs.AIresearchFDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss
arXiv:2610.39423v1 Announce Type: cross Abstract: Formula-Driven Supervised Learning (FDSL) enables vision pre-training without real images, but existing methods cast pre-training as classification on discretized labels,…
- arXiv cs.AIresearchSparse Fine-Tuning for Parameter-Efficient Adversarial Training
arXiv:2610.39455v1 Announce Type: cross Abstract: Deep neural networks achieve strong performance across many tasks but remain vulnerable to adversarial perturbations. Adversarial training (AT) is one of the most effecti…
- arXiv cs.AIresearchIntegrating Heterogeneous Echocardiography AI Outputs in Language Space: Learnable Late Fusion with a Supervised LLM
arXiv:2610.39464v1 Announce Type: cross Abstract: View- and target-specific echocardiography AI models capture useful but complementary information and may not achieve sufficient predictive performance in isolation. A le…
- arXiv cs.AIresearchRaincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference
arXiv:2610.39562v1 Announce Type: cross Abstract: Multi-turn conversations with multimodal large language models (MLLMs) reuse input context, but long multimodal inputs increase time to first token (TTFT). Query-aware ha…
- arXiv cs.AIresearchGenerative artificial intelligence prompting strategies among Chinese university students across academic tasks
arXiv:2610.39571v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) is increasingly embedded in university learning, yet effective human-GenAI interaction depends not only on access to these tool…
- arXiv cs.AIresearchRed-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin
arXiv:2610.39590v1 Announce Type: cross Abstract: As large language models (LLMs) become more widespread in Africa, their safety in low-resource languages remains largely untested since most red-teaming work focuses on E…
- arXiv cs.AIresearchData Provenance and Ethics in the Curricula of U.S. Health AI Education Programs
arXiv:2610.39606v1 Announce Type: cross Abstract: Failures of deployed clinical artificial intelligence (AI) systems have often originated in how their training data were generated. Whether the programs that train the he…
- arXiv cs.AIresearchIntrinsic Distribution Matching
arXiv:2610.39633v1 Announce Type: cross Abstract: One-step and few-step text-to-image generation must accurately render the details specified in the prompt despite limited opportunities for refinement. Distribution match…
- arXiv cs.AIresearchWhere Do Vision Language Models Fail at 3D Reasoning?
arXiv:2610.39639v1 Announce Type: cross Abstract: Vision-language models can get individual judgments right while struggling to recover and consistently use the exact properties of a 3D object. To characterize this gap,…
- arXiv cs.AIresearchRebuilding a Field's Open-Problem Catalog from the Literature: A Two-Layer Knowledge Graph, and Why Status Must Stay Proposed
arXiv:2610.39641v1 Announce Type: cross Abstract: A research field records its open problems in surveys, keynotes and community reports. Those are prose, written every few years, and nobody can ask them who works on a pr…
- arXiv cs.AIresearchEvent-SAMA: Language-Grounded Video Object Segmentation on Neuromorphic Event Streams
arXiv:2610.39676v1 Announce Type: cross Abstract: Event cameras offer microsecond temporal resolution, high dynamic range and no motion blur, but referring video object segmentation (RVOS) lacks event-stream datasets and…
- arXiv cs.AIresearchThe Importance of Speech Genre for End-of-Turn Detector Training
arXiv:2610.39742v1 Announce Type: cross Abstract: End-of-turn (EoT) detection has been studied mostly through features, models, and modalities, while the speech genre of the training data has drawn far less attention. We…
- arXiv cs.AIresearchMulti-output LSTM soft sensors for industrial anaerobic co-digestion using LSTM-beta-VAE generative data augmentation
arXiv:2610.39768v1 Announce Type: cross Abstract: Anaerobic digestion (AD) requires close monitoring of key process variables, including pH, the ratio of volatile organic acids to alkaline buffer capacity and biogas prod…
- arXiv cs.AIresearchAligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding
arXiv:2610.39835v1 Announce Type: cross Abstract: Medical diagnostic reasoning requires verifiable links between visual evidence and clinical knowledge, yet current medical vision language models are aligned with objecti…
- arXiv cs.AIresearchSHPRR: An Algorithm for Pure Exploration under Constrained Regret
arXiv:2610.39837v1 Announce Type: cross Abstract: Best Arm Identification (BAI) conventionally measures the cost of experimentation by the number of samples collected. In many operational settings, however, the cost of e…
- arXiv cs.AIresearchExploring the Potential of Symbolic Regression in Precision Livestock Farming
arXiv:2610.39839v1 Announce Type: cross Abstract: The ability to predict farrowing time in pigs is crucial for optimal farm management and ensuring piglet survival. This study investigates the potential of explainable ar…
- arXiv cs.AIresearchIncorporating Machine-Others: An Enactive Exploration of Human-LLM Interactions
arXiv:2610.39869v1 Announce Type: cross Abstract: New concepts based in interactional thinking are required to understand how humans are changed by relating to LLMs. Standard theories of technological impact upon users'…
- arXiv cs.AIresearchTuring LLM Post-Training: Calibrated Distillation and Efficient Dynamic-MoE Execution
arXiv:2610.39876v2 Announce Type: replace-cross Abstract: We study post-training for dynamically routed mixture-of-experts (MoE) models, focusing on integrating independently optimized specialists while keeping consolida…
- arXiv cs.AIresearchCovFedAvg: Local Low-Loss Curves and Federated Model Selection
arXiv:2610.39902v1 Announce Type: cross Abstract: Clients observing different parts of a prediction task may learn locally equivalent models with incompatible behavior outside their observed support. We study whether red…
- arXiv cs.AIresearchPrompts and probabilities in the linguistic assessment of language models: Evidence from semantic focus-sensitivity
arXiv:2610.39923v1 Announce Type: cross Abstract: As language models (LMs) have improved, an increasingly common means of evaluating their linguistic competence is through explicit prompting (e.g., "Which sentence is mor…
- arXiv cs.AIresearchSpectral Invariant Fusion and Refinement for Domain Generalized Semantic Segmentation
arXiv:2610.39926v1 Announce Type: cross Abstract: Domain generalized semantic segmentation is challenging because it requires accurate dense prediction on unseen domains without any access to target-domain data during tr…
- arXiv cs.AIresearchWhen to spend privacy: optimal allocation in private learning
arXiv:2610.39954v1 Announce Type: cross Abstract: Privacy accounting bounds the cumulative privacy cost of Differentially Private Stochastic Gradient Descent but does not determine how to allocate a fixed budget across i…
- arXiv cs.AIresearchMind The Gap (MTG-AD): Dataset and Fine-grained Evaluation for End-to-End Inline Audio Descriptions
arXiv:2610.39955v1 Announce Type: cross Abstract: Audio descriptions (AD) are essential for making visual media accessible to blind and low-vision (BLV) users. While Multimodal Large Language Models (MLLMs) offer a scala…
- arXiv cs.AIresearchAccumulating Pruning Constraints: New Exact Polynomial-Space Algorithms for Max 2-SAT
arXiv:2610.39992v1 Announce Type: cross Abstract: We present deterministic polynomial-space algorithms that solve Max 2-SAT on $n$ variables exactly in time $\Ostar(2^{(1-\gamma)n})$, for a fixed $\gamma>0$, on several c…
- arXiv cs.AIresearchHEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization
arXiv:2610.40023v1 Announce Type: cross Abstract: Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective comb…
- arXiv cs.AIresearchUPPAAi: Towards LLM-Assisted Modeling, Verification, Analysis and Synthesis
arXiv:2610.40042v1 Announce Type: cross Abstract: For more than three decades, UPPAAL has supported the modelling and analysis of real-time and cyber-physical systems. Yet building a suitable model, formalising the inten…
- arXiv cs.AIresearchEPC-RawDC: Equivariant Physics Constrained 3D Diffusion with Raw Data Consistency for CBCT to CT Image Synthesis
arXiv:2610.40046v1 Announce Type: cross Abstract: Cone beam computed tomography (CBCT) is widely used for image guided and adaptive radiotherapy, but scatter, noise, reconstruction artifacts, and inaccurate Hounsfield un…
- arXiv cs.AIresearchRethinking Pre-pretraining
arXiv:2610.40051v1 Announce Type: cross Abstract: We report that allocating compute to synthetic pre-pretraining (PPT) never outperforms pure natural-language training in our compute-matched experiments. This holds acros…
- arXiv cs.AIresearchOne Vector or Many? Clustered Optimal-Transport Steering under Quantization
arXiv:2610.40055v1 Announce Type: cross Abstract: Activation steering changes what a language model generates by editing its hidden states at inference time. Its most common form adds one vector, the difference of class…
- arXiv cs.AIresearchLocalizing Concepts in Visual Autoregressive Models
arXiv:2610.40061v1 Announce Type: cross Abstract: Understanding the internal routing of visual concepts is crucial for the safe and controllable adaptation of generative models. While concept localization has been widely…
- arXiv cs.AIresearchLearning Safe Flow Matching Robot Policies from Binary Feasibility Oracles
arXiv:2610.40075v1 Announce Type: cross Abstract: Robot foundation models increasingly rely on flow-based action generation for general-purpose manipulation, yet the generated actions are not guaranteed to satisfy physic…
- arXiv cs.AIresearchUpcycling Language Models for Multiple Specialized Domains
arXiv:2610.40091v1 Announce Type: cross Abstract: Effective multi-domain adaptation of large language models requires prioritizing relevant domain knowledge while minimizing interference from irrelevant domains. Existing…
- arXiv cs.AIresearchEscaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning
arXiv:2610.40130v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning remains challenging in stochastic long-horizon settings, where compounding value estimation errors hinder reliable goal re…
- arXiv cs.AIresearchFARE: Factor-Aware Retrieval with Error-Guided Fusion for Retail Forecasting
arXiv:2610.40160v1 Announce Type: cross Abstract: Retail sales forecasting underpins inventory planning, yet promotions and calendar events reshape short-term demand. Although each factor usually has historical occurrenc…
- arXiv cs.AIresearchEventSeeColor: Learning to Reconstruct Color from Monochrome Events
arXiv:2610.40166v1 Announce Type: cross Abstract: Event cameras capture visual brightness changes under challenging lighting conditions. However, traditional event-based image reconstruction targets grayscale intensity a…
- arXiv cs.AIresearchUnderstanding axial attention in TSFMs through single location regression
arXiv:2610.40188v1 Announce Type: cross Abstract: Recent advances in Time Series Foundation Models (TSFMs) increasingly rely on axial attention mechanisms, but despite their empirical success, the theoretical properties…
- arXiv cs.AIresearchLatent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI
arXiv:2610.40280v1 Announce Type: cross Abstract: Decoding sensory-evoked functional magnetic resonance imaging (fMRI) data is a central analytical tool in cognitive neuroscience. Here we ask whether self-supervised lear…
- arXiv cs.AIresearchOnly Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets
arXiv:2610.40287v1 Announce Type: cross Abstract: Large language model serving is limited by facility power. Energy per token determines how many tokens a datacenter can serve, while a latency target bounds how quickly e…