AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSetGRPO: Calibrating Grader-Induced Policy Optimization
arXiv:2610.36807v1 Announce Type: cross Abstract: Rubric-based reinforcement learning uses fine-grained grader feedback to train large language models on open-ended tasks, but grader randomness can alter GRPO updates in…
- arXiv cs.AIresearchTAPESTRY: A Single Backbone for Video Generation and Robot Control
arXiv:2610.36823v1 Announce Type: cross Abstract: Pretrained video generation models encode rich priors about physical interactions, but leveraging them for robot control typically requires either resource-intensive vide…
- arXiv cs.AIresearchWhen All Rollouts Fail: Policy-Compatible Joint Decoding for Hard-Problem Reasoning
arXiv:2610.36849v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) derives its learning signal from binary rewards via on-policy exploration and becomes a powerful paradigm for improv…
- arXiv cs.AIresearchActiveAlign: Aligning Egocentric Manipulation via Active Perception
arXiv:2610.36859v1 Announce Type: cross Abstract: Real-to-Sim-to-Real (Real2Sim2Real) enables structured world representations for planning, interpretability, and safe execution. Most existing approaches rely on passive…
- arXiv cs.AIresearchAdaGround: Token-Normalized Adaptive Zooming with Verifier-in-the-Loop Refinement for GUI Grounding
arXiv:2610.36874v1 Announce Type: cross Abstract: GUI grounding on high-resolution screens fails mostly on small targets, and zooming in is a common training-free remedy. However, most existing zooming pipelines do not m…
- arXiv cs.AIresearchDeveloping a Speech Language Model for Basque
arXiv:2610.36911v1 Announce Type: cross Abstract: Although the recent development of LLMs has paved the way for multi-modal interaction, minority languages face difficulties keeping pace. This work presents the first ope…
- arXiv cs.AIresearchSelf-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models
arXiv:2610.36948v1 Announce Type: cross Abstract: A large language model maintains conversational content in an external storage that is outside the model and grows as the dialogue continues. This work assumes an environ…
- arXiv cs.AIresearchDCKV: Learned Transform Coding of the Prompt KV Cache in Hybrid Language Models
arXiv:2610.36950v1 Announce Type: cross Abstract: Hybrid language models keep a key-value (KV) cache only in their few full-attention layers, but this cache is still the part of a prompt's state that grows with the promp…
- arXiv cs.AIresearchDense Representation Learning and Differentiable Shape Modeling for Spine Landmark Detection
arXiv:2610.36951v1 Announce Type: cross Abstract: Spine landmark detection from spinal X-ray is a key step for estimating spine deformation severity, for building biomechanical models, and for pre-operative planning. We…
- arXiv cs.AIresearchPailitaoMMSearch2.0 Technical Report: Scaling Generative Retrieval to Unified End-to-End Multimodal Search
arXiv:2610.36958v1 Announce Type: cross Abstract: Generative retrieval models have been increasingly adopted in search and recommendation systems. However, industrial generative retrieval models are commonly specialized…
- arXiv cs.AIresearchAdvancement or Acceleration? How Data Curation Improves LLM Training
arXiv:2610.36983v1 Announce Type: cross Abstract: While data curation is widely credited with improving large language model training, a basic question remains unresolved: does curation expand what a model can ultimately…
- arXiv cs.AIresearchLearnPrunerV2: Learnable Progressive Token Pruning for Vision-Language Models
arXiv:2610.36986v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable multimodal capabilities but suffer from prohibitive computational overhead due to the massive number of visual…
- arXiv cs.AIresearchEvaluating Priority Dispatch for Premium Membership in On-demand Taxi-sharing
arXiv:2610.37011v1 Announce Type: cross Abstract: In this paper, we analyze the dispatch-level feasibility of introducing premium membership into an on-demand taxi-sharing service using a sequential optimal insertion met…
- arXiv cs.AIresearchV-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models
arXiv:2610.37019v1 Announce Type: cross Abstract: Embedding-level scaling expands the capacity of language models through lookup-based memory rather than by increasing model depth, width, or dense computation. Extending…
- arXiv cs.AIresearchCrop Yield Prediction Using Regression Models: A Comparative Evaluation of Model Performance
arXiv:2610.37022v1 Announce Type: cross Abstract: Reliable crop-yield prediction can support agricultural planning and resource allocation. This study evaluates five regression models for predicting crop yield from envir…
- arXiv cs.AIresearchInterpretable Deep Learning Models for Breast Cancer Diagnosis Using Medical Imaging
arXiv:2610.37026v1 Announce Type: cross Abstract: Deep learning shows promise for breast cancer diagnosis, but limited interpretability hinders clinical adoption. We benchmark ten ImageNet-pretrained models (ResNet50, VG…
- arXiv cs.AIresearchZooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception
arXiv:2610.37037v1 Announce Type: cross Abstract: Multimodal perception forms the foundation of multimodal intelligence. In particular, spatial perception and multimodal long-context understanding are two pivotal tasks t…
- arXiv cs.AIresearchExploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization
arXiv:2610.37058v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) typically relies on preference pairs generated from diverse model pools and ranked by an external LLM judge. The recently proposed de…
- arXiv cs.AIresearchEnergyCal: Taming Loss Spikes in Muon-Family Optimizers for Sparse MoE Training
arXiv:2610.37062v1 Announce Type: cross Abstract: Sparse mixture-of-experts (MoE) language-model training can exhibit large loss spikes with Muon-family optimizers. We introduce EnergyCal, a lightweight rule that attenua…
- arXiv cs.AIresearchLearning to Look Beyond Screens: Transferable Visual Observation from GUI Grounding
arXiv:2610.37093v1 Announce Type: cross Abstract: Visual perception is evolving from passive recognition toward active, task-oriented observation. We investigate GUI grounding as a scalable source of spatial supervision…
- arXiv cs.AIresearchHardware-Matched Spiking Neural Networks for Real-Time Purkinje Cell Spike Classification
arXiv:2610.37104v1 Announce Type: cross Abstract: Distinguishing Purkinje cell (PC) simple spikes (SSs) from complex spikes (CSs) is key to studying cerebellar function. PC recordings commonly rely on wired headstages, w…
- arXiv cs.AIresearchA First-Step Bias Restores Lost Diversity in Diffusion Model Distillation
arXiv:2610.37110v1 Announce Type: cross Abstract: Distribution-matching distillation enables high-quality image generation in only a few denoising steps. However, distilled student models often map different initial nois…
- arXiv cs.AIresearchMRI-to-CT Translation of Spinal Images via Anatomy-Guided Pseudo-Pairing and Adversarial Diffusion
arXiv:2610.37134v1 Announce Type: cross Abstract: Magnetic Resonance Imaging (MRI) is routinely used to diagnose spinal disorders, but surgical planning often requires Computed Tomography (CT) for better visualization of…
- arXiv cs.AIresearchWhat the Primary Lund Plane Omits: A Model-Stitching Diagnosis of a Jet-Tagger Representation Gap
arXiv:2610.37137v1 Announce Type: cross Abstract: Lund-plane and Particle Transformer (ParT) jet taggers can differ in performance because one representation is weaker, or because a weaker downstream computation reads an…
- arXiv cs.AIresearchGenerative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks
arXiv:2610.37139v1 Announce Type: cross Abstract: Equilibrium Propagation (EqProp) offers a biologically grounded and hardware-aligned alternative to backpropagation for training Hopfield Networks. However, its behavior…
- arXiv cs.AIresearchBeyond Parameter Protection: Fisher-Shaped EWC for Replay-Free Continual Learning
arXiv:2610.37145v1 Announce Type: cross Abstract: In replay-free continual learning, Elastic Weight Consolidation (EWC) uses Fisher information matrix (FIM) to protect acquired knowledge by penalizing changes to historic…
- arXiv cs.AIresearchGCSR-OCC: Geometry Calibration and Semantic Routing for Open-Vocabulary Occupancy Prediction
arXiv:2610.37149v1 Announce Type: cross Abstract: Open-vocabulary 3D occupancy prediction represents scene geometry and semantics in a unified voxel grid, enabling recognition beyond predefined categories. One approach r…
- arXiv cs.AIresearchRetrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution
arXiv:2610.37215v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies demonstrate remarkable semantic generalization, yet remain highly vulnerable to out-of-distribution (OOD) visual shifts during execu…
- arXiv cs.AIresearchWhen Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning
arXiv:2610.37239v2 Announce Type: replace-cross Abstract: Multi-relational graph detectors learn from clean data how much to trust each relation, but an adversary pays a different price to manipulate each relation and ea…
- arXiv cs.AIresearchAligning Large Language Models for Safety in African Languages: A Case Study of Hausa
arXiv:2610.37245v1 Announce Type: cross Abstract: Safety alignment research for large language models (LLMs) remains concentrated on high-resource languages, leaving open how existing alignment methods perform in low-res…
- arXiv cs.AIresearchA Lightweight Attention-Based CNN with Saliency-Map Interpretability for Skin Cancer Detection
arXiv:2610.37314v1 Announce Type: cross Abstract: Skin cancer is among the most prevalent and life threatening forms of cancer worldwide. Early and accurate diagnosis significantly improves patient survival rates. Howeve…
- arXiv cs.AIresearchWCC: A Learning-Based Framework for Deciding When to Apply Cooperative Coevolution in Large-Scale Optimization
arXiv:2610.37329v1 Announce Type: cross Abstract: Cooperative Coevolution (CC) and Non-Decomposition Algorithms (NDAs) are two primary approaches for large-scale global optimization (LSGO). Although both have achieved su…
- arXiv cs.AIresearchCoS-VQ: Coordinated Shared-Scale Vector Quantization for Large Language Models
arXiv:2610.37336v1 Announce Type: cross Abstract: Large language models (LLMs) require substantial memory, motivating low-bit weight quantization for efficient deployment. Existing vector quantization (VQ) methods often…
- arXiv cs.AIresearchChannel Selection for Mixture-of-Experts Decoding Needs No Calibration Data
arXiv:2610.37386v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are bottlenecked by loading routed-expert weights from memory during interactive decoding at small batch sizes. Because most intermediate…
- arXiv cs.AIresearchJEPA-Inspired Latent Field Prediction for Sparse-Pilot MIMO-OFDM Channel Reconstruction
arXiv:2610.37391v1 Announce Type: cross Abstract: Accurate acquisition of full channel state information (CSI) is essential for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) wirele…
- arXiv cs.AIresearchLearning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling
arXiv:2610.37393v1 Announce Type: cross Abstract: Robot policy evaluation often relies on a binary success signal for task completion. In real-world deployment, however, desired execution behaviors are also defined by qu…
- arXiv cs.AIresearchBayes-Adaptive MDPs for Rollout Allocation to Enhance GRPO Training
arXiv:2610.37429v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has demonstrated strong performance in LLM post-training. However, it allocates a uniform rollout budget to every training quest…
- arXiv cs.AIresearchRepresenting the Unseen: Rethinking Visual Imagination for Spatial Reasoning
arXiv:2610.37437v1 Announce Type: cross Abstract: Visual world models increasingly support spatial reasoning by generating RGB views of unobserved states. However, RGB has become the default interface largely because it…
- arXiv cs.AIresearchPerceptRL: Making Visual Perception Rewardable in MLLMs from Answers to Interactions
arXiv:2610.37471v1 Announce Type: cross Abstract: Fine-grained visual perception remains a bottleneck during post-training of multimodal large language models (MLLMs), as perceptual errors can constrain gains from reason…
- arXiv cs.AIresearchHow Reliable Is Individualized Functional-Network Attribution in Resting-State fMRI Cognitive Prediction in ADNI?
arXiv:2610.37472v1 Announce Type: cross Abstract: Individualized attribution estimates which functional networks drive a model prediction for a given subject and is often proposed as an interpretable resting-state fMRI (…
- arXiv cs.AIresearchHGPRGDel: GPR-Aware Learning and Ranking for Growth-Coupled Gene Deletion Design
arXiv:2610.37478v1 Announce Type: cross Abstract: Designing microbial strains for growth-coupled production, in which cellular growth is linked to the synthesis of a target compound through genetic interventions, is a fu…
- arXiv cs.AIresearchFollow the Gradient: Tracing Safety Degradation Back to Training Data
arXiv:2610.37481v1 Announce Type: cross Abstract: Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training example looks harmful. Because this safety-degrading da…
- arXiv cs.AIresearchOrthogonal and Parametrized Multi-Attribute Steering of LLMs
arXiv:2610.37517v2 Announce Type: replace-cross Abstract: Activation steering offers an effective and efficient way to modify an LLM's behavior at inference time. However, it remains unclear how to apply steering such th…
- arXiv cs.AIresearchThe Structure Gap: When More Data Cannot Replace Structured Reasoning
arXiv:2610.37523v1 Announce Type: cross Abstract: A persistent belief in modern AI is that sufficiently large learners trained on sufficiently much data can make explicit domain knowledge optional. This paper examines a…
- arXiv cs.AIresearchWhich Hand Was Late? Diagnosis for Robot Failure Recovery in Bimanual Tool Use
arXiv:2610.37533v1 Announce Type: cross Abstract: Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successfu…
- arXiv cs.AIresearchGroundControl: Satellite-Conditioned Multi-View Diffusion for Reconstruction-Free Novel View Synthesis
arXiv:2610.37545v1 Announce Type: cross Abstract: Multi-view or video diffusion models have recently emerged as state-of-the-art approaches for novel-view synthesis from sparse image collections. While they can produce h…
- arXiv cs.AIresearchWhen, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies
arXiv:2610.37547v1 Announce Type: cross Abstract: Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or…
- arXiv cs.AIresearchKinematic Constraint-Referenced Evaluation for Articulated Object Manipulation
arXiv:2610.37550v1 Announce Type: cross Abstract: Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We int…
- arXiv cs.AIresearchWhen uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance
arXiv:2610.37561v1 Announce Type: cross Abstract: Background. Selective prediction systems improve the safety of clinical artificial intelligence by deferring ambiguous cases to human experts while automating high-confid…
- arXiv cs.AIresearchREGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation
arXiv:2610.37584v2 Announce Type: replace-cross Abstract: Personalized recommendation depends on learning semantic and collaborative relations among items from online content and user interactions. Generative recommendat…