AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFactorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding
arXiv:2610.23935v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference through parallel verification of tokens proposed by a drafter. Diffusion drafters further parallelize prop…
- arXiv cs.AIresearchBeyond Prediction: A Component-Level Study of Concept Recovery in In-Context Learning
arXiv:2610.23936v1 Announce Type: cross Abstract: In-context learning (ICL) enables language models to make accurate predictions from demonstrations, but prediction success alone does not reveal the extent to which the u…
- arXiv cs.AIresearchSECURE-AI: Multi-Signal Uncertainty Quantification for Trustworthy Acoustic Cough Detection
arXiv:2610.23937v1 Announce Type: cross Abstract: Acoustic models for cough detection achieve high accuracy on curated benchmarks but fail silently in deployment, where speech, environmental noise, and audio unlike the t…
- arXiv cs.AIresearchPeekKV: The First Content Token Already Knows Which Heads Matter
arXiv:2610.23939v1 Announce Type: cross Abstract: The size of the KV cache grows linearly with context length, making it a major memory bottleneck in LLM serving. Motivated by recent progress in identifying the functiona…
- arXiv cs.AIresearchA Group-Aware Comparative Study of Classical Machine Learning and Deep Learning Methods for Sensor-Based Human Activity Recognition
arXiv:2610.23941v1 Announce Type: cross Abstract: Human Activity Recognition (HAR) using wearable or smartphone inertial sensors is commonly evaluated with both classical machine learning and deep learning methods. Howev…
- arXiv cs.AIresearchCrowdH-Edit: Reference-Guided Instruction-Based Synthetic Hajj Crowd Image Generation for Crowd Counting
arXiv:2610.23945v1 Announce Type: cross Abstract: The scarcity of domain-specific annotated images remains a major limitation for developing computer-vision systems for Hajj crowd analysis. Existing crowd-counting datase…
- arXiv cs.AIresearchREAP: Learning General Rearrangement Heuristics from Motion-Planner Feedback
arXiv:2610.23973v1 Announce Type: cross Abstract: Robotic rearrangement tasks require planning sequences of actions that fulfill high-level specifications while also being geometrically feasible. Symbolic abstractions ma…
- arXiv cs.AIresearchHow Much Can We Prune? Exploring the Performance Limits of Visual Token Pruning
arXiv:2610.23974v1 Announce Type: cross Abstract: Visual token pruning is increasingly used to reduce the memory and inference costs of vision-language models. Existing work has largely focused on designing method-specif…
- arXiv cs.AIresearchLLM Evolutionary Search Strategies Should be Compared by Tokens
arXiv:2610.23977v1 Announce Type: cross Abstract: LLM evolutionary search is currently evaluated by counting proposals (candidate programs). We demonstrate this metric hides the true cost of search, and redo the comparis…
- arXiv cs.AIresearchSituHOI: Scalable Capture of Scene-Situated Full-Body Human-Object Interaction
arXiv:2610.23980v2 Announce Type: replace-cross Abstract: Modeling human-object interaction (HOI) in real environments requires jointly representing whole-body motion, manipulated objects, and scene geometry, yet existin…
- arXiv cs.AIresearchIWOO: Wave Optics Optimizer Improved with Hybrid Strategies for Numerical Optimization and Engineering Applications
arXiv:2610.23994v1 Announce Type: cross Abstract: The Wave Optics Optimizer (WOO) incorporates optical diffraction and interference into numerical optimization and has shown competitive performance in benchmarks and engi…
- arXiv cs.AIresearchspora: A Unified Multimodal Dataset and Platform for Spatial Proteomics
arXiv:2610.24002v1 Announce Type: cross Abstract: Spatial proteomics (SP) captures the molecular composition and spatial organization of tissues at single-cell resolution, opening a direct view of the cellular ecosystems…
- arXiv cs.AIresearchPACE: Pareto-Adaptive Compression for Efficient Native MLLMs
arXiv:2610.24005v3 Announce Type: replace-cross Abstract: Native multimodal large language models (native MLLMs) jointly encode visual and linguistic sequences within a unified autoregressive Transformer, emerging as a p…
- arXiv cs.AIresearchTWIN-MoE: Two-stage Intra-Expert Imputation Network for Incomplete Multimodal Learning
arXiv:2610.24014v1 Announce Type: cross Abstract: Recent Mixture-of-Experts (MoE) approaches address missing modalities either by routing each missingness pattern to a dedicated expert, which scales poorly as the number…
- arXiv cs.AIresearchAnalysis of Binary O-type Star Systems Using Recurrent Neural Networks
arXiv:2610.24015v1 Announce Type: cross Abstract: This work presents an initial analysis of the estimation of effective temperature and surface gravity for simulated O-type binary systems using a recurrent neural network…
- arXiv cs.AIresearchLLM Evolution in a Simple Simulated Market
arXiv:2610.24033v1 Announce Type: cross Abstract: Arguments that AI systems will evolve in harmful ways are largely made in the abstract. We provide a concrete empirical example. We simulate simple markets consisting of…
- arXiv cs.AIresearchClient-Aware Security Adaptive Early Exit Vision Transformers for Heterogeneous Federated Learning
arXiv:2610.24036v1 Announce Type: cross Abstract: Federated learning (FL) trains a shared model across data-owning clients without centralizing raw data, but client data difficulty and compute budgets can differ. We stud…
- arXiv cs.AIresearchBLANC: Adaptive Temporal Scheduling for Sign Language Production
arXiv:2610.24109v1 Announce Type: cross Abstract: Sign language production (SLP) aims to synthesize expressive signing motion from written text. Modeling signing motion presents two key temporal challenges. First, fine-g…
- arXiv cs.AIresearchGraph-Regularized Synthetic Control for Stable Counterfactual Estimation under Donor Redundancy
arXiv:2610.24113v1 Announce Type: cross Abstract: Synthetic control methods estimate counterfactual outcomes by weighting untreated donor units to match a treated unit before treatment. In recent applications, however, t…
- arXiv cs.AIresearchPrefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers
arXiv:2610.24123v1 Announce Type: cross Abstract: Prefix-tuning is a parameter-efficient fine-tuning method for large language models (LLMs) that steers model outputs by prepending task-specific prefix representations to…
- arXiv cs.AIresearchOn the Selectivity of Generative Models in Structure-Based Drug Design
arXiv:2610.24124v1 Announce Type: cross Abstract: Designing small-molecule drugs that selectively bind to a target protein while avoiding unintended interactions with other proteins is essential for reducing side effects…
- arXiv cs.AIresearchThe Weight of Teamwork: Does Communication Structure Help LLM Scientists Search for Scientific Laws?
arXiv:2610.24131v1 Announce Type: cross Abstract: Team performance is often reported as one delivered score, even though that score is produced in two stages: a system generates candidate answers and a selection rule ret…
- arXiv cs.AIresearchFrom Spectrograms to Shallow Speech SSL: Audio-Frontend Design for Generator-Disjoint and Low-Latency Audio--Visual Deepfake Detection
arXiv:2610.24138v1 Announce Type: cross Abstract: Video-mediated conversational systems rely on synchronized speech and facial video, making audio--visual input integrity important for reliable perception. We study audio…
- arXiv cs.AIresearchlepidoptera: A Domain-Agnostic Engine for Causal Simulation with Mixed Variable Types, Vine Copula Dependence, and Individual-Level Counterfactual Propagation
arXiv:2610.24147v1 Announce Type: cross Abstract: lepidoptera is an open-source R and Python package for simulation from structural causal models with heterogeneous variable types. The package is built around a typed mec…
- arXiv cs.AIresearchBootstrap Stochastic Interpolant Tree for Inference-time Search Under Sparse Reward
arXiv:2610.24185v1 Announce Type: cross Abstract: Tree-based samplers offer a compelling alternative for scalable inference-time search, bypassing the per-step reward and gradient dependencies that introduce systematic b…
- arXiv cs.AIresearchTowards an Intelligent Decision Engine for Smart Contract Deployment
arXiv:2610.24198v1 Announce Type: cross Abstract: Layer 2 (L2) blockchain solutions emerged in recent years, predominantly in the Ethereum ecosystem, as a viable option for scaling a main blockchain network (L1). However…
- arXiv cs.AIresearchLandmark-Free and Scale-Blind Multi-View Registration of Preoperative Liver Models to Intraoperative Surfaces
arXiv:2610.24218v1 Announce Type: cross Abstract: Augmented-reality guidance in laparoscopic liver resection requires aligning preoperative 3D liver models from CT/MRI with intraoperative surfaces. Monocular reconstructi…
- arXiv cs.AIresearchAnalyzing Repetition and Interference Effects in Memory-Constrained User Simulators
arXiv:2610.24232v1 Announce Type: cross Abstract: User simulators can help evaluate and train AI systems to interact with humans at scale. To do so, evaluation of user simulators must measure behavioral parity with peopl…
- arXiv cs.AIresearchEncoder-Free Multimodal LLMs Learn Implicit Encoders
arXiv:2610.24239v1 Announce Type: cross Abstract: We empirically analyze two recently proposed encoder-free multimodal LLMs, Gemma-4 12B and Inkling-Small. Unlike previous multimodal LLMs, these models do not use modalit…
- arXiv cs.AIresearchTowards Reinforcement Learning for Space Robotics: Fast Training and Reliable Real-World Transfer
arXiv:2610.24241v1 Announce Type: cross Abstract: This work demonstrates the use of a fast simulation-based training framework to learn control policies using reinforcement learning. The hardware requirements are minimal…
- arXiv cs.AIresearchLearning Administrative Boundary-Aware Location Encoders via Reverse Geocoding
arXiv:2610.24306v2 Announce Type: replace-cross Abstract: Location encoders learn compact representations of latitude--longitude coordinates for downstream geospatial prediction tasks. Existing approaches are pretrained…
- arXiv cs.AIresearchIndirect Influences of Artificial Intelligence Advice on Complex Sepsis Treatment Decisions
arXiv:2610.24313v1 Announce Type: cross Abstract: Sepsis is a major public health concern, and many sepsis patients die due to ineffective hemodynamic management. Artificial intelligence could support hemodynamic decisio…
- arXiv cs.AIresearchMorpheus-2.0: Multiscale Probabilistic Forecasting with Dual-Axis Attention
arXiv:2610.24321v1 Announce Type: cross Abstract: A universal forecaster is trained once and applied everywhere, so it must serve tasks whose schemas, forecast horizons, and temporal resolutions all differ. The number of…
- arXiv cs.AIresearchWhat Matters for NVFP4 Training? A Comparative Study of Low-Precision Pretraining Recipes
arXiv:2610.24343v1 Announce Type: cross Abstract: Training large language models directly in 4-bit floating-point (FP) formats promises substantial improvements in throughput and energy efficiency. While some recipe desi…
- arXiv cs.AIresearchKoi: Evidence-Guided, Self-Calibrating Planning for Multi-Cloud, Heterogeneous LLM Inference Fleets
arXiv:2610.24355v1 Announce Type: cross Abstract: Deploying a large language model (LLM) requires choosing the right accelerator, parallelization strategy, engine configuration, and replica count amongst ~140 other varia…
- arXiv cs.AIresearchTactix: Towards a Programmable Strategy Interface for Flexible SAT Solving
arXiv:2610.24369v1 Announce Type: cross Abstract: Modern SAT solvers combine a rich repertoire of proof rules with sophisticated strategies that determine when and how to apply them. Often, the internal implementations a…
- arXiv cs.AIresearchZeroDSS: Semantic Segmentation from Class Names Alone
arXiv:2610.24405v1 Announce Type: cross Abstract: Semantic segmentation depends heavily on real images with pixel-level annotations, making dense supervision a major obstacle to deployment in new domains. We study task-s…
- arXiv cs.AIresearchLong Listening Thoughts: Eliciting Open Auditory Reasoning with Deliberative Perception and Cognitive Refinement
arXiv:2610.24409v1 Announce Type: cross Abstract: We introduce Long Listening Thoughts (LLT), a framework for constructing post-training datasets that improves audio reasoning by pairing deliberate perceptual grounding w…
- arXiv cs.AIresearchWhen Opposite Premises Translate Identically: A Source-Conditioned Diagnostic for Multilingual Commonsense Items
arXiv:2610.24428v1 Announce Type: cross Abstract: Multilingual reasoning comparisons depend on translated premises preserving the relations in their English sources. Automatic translation scores can rank source-target pa…
- arXiv cs.AIresearchDo 3D Large Language Models Really Use 3D Evidence?
arXiv:2610.24447v1 Announce Type: cross Abstract: Recent 3D Large Language Models (3D-LLMs) have shown strong performance on scene question answering with extensive post-training. Yet, existing benchmarks rarely evaluate…
- arXiv cs.AIresearchHumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time
arXiv:2610.24452v2 Announce Type: replace-cross Abstract: We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also specify a pose or motion…
- arXiv cs.AIresearchTree Plurality Veto: Voting in Few Rounds with Efficient Communication and Low Metric Distortion
arXiv:2610.24456v1 Announce Type: cross Abstract: We consider the metric distortion framework for voting, where $n$ voters and $m$ candidates are embedded in an unknown metric space. A voting rule selects a candidate usi…
- arXiv cs.AIresearchSENTRY: A Streaming Edge Network Trust Engine for Real-Time Audio Deepfake Detection
arXiv:2610.24468v1 Announce Type: cross Abstract: Real-time voice cloning has enabled large-scale streaming deepfake and vishing attacks, while existing Network Detection and Response (NDR) solutions rely on GPU-based po…
- arXiv cs.AIresearchWhich Long Documents Matter? A Controlled Study of Data Selection for Context Extension
arXiv:2610.24469v1 Announce Type: cross Abstract: Natural long documents are widely used for context extension, but which selection pipelines are effective remains unclear. We conduct a controlled comparison on Qwen2.5-3…
- arXiv cs.AIresearchGazeAct: A Human-Gaze-Annotated Manipulation Dataset for Attention-Regularized Policies
arXiv:2610.24507v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies must ground language instructions in the right objects, contact points, and target locations for reliable manipulation. Human gaze p…
- arXiv cs.AIresearchContrastive Hypergraph Source-free Domain Adaptive Object Detection in Adverse Weather Conditions--Extended Version
arXiv:2610.24532v1 Announce Type: cross Abstract: Adverse weather conditions such as fog, rain, snow, and low illumination introduce structured visibility degradations that severely impair object detectors trained on cle…
- arXiv cs.AIresearchFrom Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability
arXiv:2610.24556v1 Announce Type: cross Abstract: We study feature vectors: directions in a language model's activation space that correspond to human-interpretable concepts, such as honesty or deception. Existing unsupe…
- arXiv cs.AIresearchASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects
arXiv:2610.24572v1 Announce Type: cross Abstract: Automatic Speech recognition (ASR) struggles with Pathological speech due to persistent speaker-specific mismatch. In clinical and accessibility scenarios, only limited t…
- arXiv cs.AIresearchAdamPM: Memory-Efficient LLM Optimization via Moment Pooling
arXiv:2610.24598v1 Announce Type: cross Abstract: Adam is widely used for training large language models (LLMs) owing to its strong optimization performance and training stability, but its element-wise estimation for the…
- arXiv cs.AIresearchSeverity-Channel Conditioning: An Injection-Level Study for Consumer-Device Deblurring
arXiv:2610.24599v1 Announce Type: cross Abstract: Motion-deblurring models lose substantial accuracy when transferred from professional cameras to smartphone-derived imagery. This paper studies whether a severity descrip…