AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchNeither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)
arXiv:2610.01533v1 Announce Type: new Abstract: Existing work on Semantic IDs (SIDs) for generative recommendation treats SID construction as a representation learning problem: encode items into a quantised latent space…
- arXiv cs.AIresearchThe AI Assessment Sandbox Configurator: A Framework to Support Technical Assessment in AI Regulatory Sandboxes
arXiv:2610.01539v1 Announce Type: new Abstract: The EU's Artificial Intelligence Act requires all Member States to establish AI Regulatory Sandboxes (AIRS) by August 2027: supervised environments bringing together nation…
- arXiv cs.AIresearchFedLore: Communication and Memory Efficient Federated Learning via Shared Gradient Low-Rank Projection
arXiv:2610.01620v1 Announce Type: new Abstract: Federated training of foundation models is constrained by client memory and communication costs. LoRA-based methods reduce these costs through low-rank adapters, but their…
- arXiv cs.AIresearchMeasuring the Stability Assumption Behind Action Chunking
arXiv:2610.01626v1 Announce Type: new Abstract: Action chunking improves the performance of policies learned by behavioural cloning, and several mechanisms have been proposed to explain why, including temporal consistenc…
- arXiv cs.AIresearchCoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement
arXiv:2610.01710v1 Announce Type: new Abstract: Visual grounding localizes an object described by language with a bounding box. Most multimodal grounding models compress target identification, spatial reasoning, and boun…
- arXiv cs.AIresearchvFedProtoQNAS: Prototype-Guided Personalized Quantum Neural Architecture Search for Virtual Federated Learning
arXiv:2610.01718v1 Announce Type: new Abstract: Quantum federated learning (QFL) has emerged as a promising approach for collaboratively training compact quantum neural networks (QNNs) over distributed private data on re…
- arXiv cs.AIresearchTopK-Guided: Adaptive, Budget-Aware Activation Sparsity for Efficient LLM Inference
arXiv:2610.01763v1 Announce Type: new Abstract: Activation sparsity speeds up large language model (LLM) inference by setting unimportant activations to zero so that the corresponding computations can be skipped. Existin…
- arXiv cs.AIresearchRealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
arXiv:2610.01780v3 Announce Type: replace Abstract: An AI companion that talks with someone for months should come to understand them. It should know who they are, remember what they said, and recognize when something fr…
- arXiv cs.AIresearchQ-Learning for Reachability in MEC-Free MDPs
arXiv:2610.01781v1 Announce Type: new Abstract: Reinforcement learning (RL) for reachability specifications is fundamental to sequential decision-making. Prior work establishes asymptotic convergence to optimal policies,…
- arXiv cs.AIresearchLineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification
arXiv:2610.01800v1 Announce Type: new Abstract: Time series captioning is a fundamental step in time series understanding and can also serve as the bridge between signal and natural language. Supervised fine-tuning (SFT)…
- arXiv cs.AIresearchAI-assisted mitotic counting improves reproducibility and efficiency across multiple tumour types
arXiv:2610.01813v1 Announce Type: new Abstract: Mitotic counting is an important component of tumour grading, diagnosis and prognostic assessment across several tumour types, but manual assessment is time-consuming and s…
- arXiv cs.AIresearchOn the Divergence of Accuracy and Mechanism Consistency in Time Series World Models
arXiv:2610.01842v1 Announce Type: new Abstract: A time series world model (TSWM) predicts a controlled system's state from its observed history and planned actions and exogenous inputs. Current approaches build forecaste…
- arXiv cs.AIresearchTemporal-Difference Learning for Dragonchess
arXiv:2610.01845v1 Announce Type: new Abstract: Our research investigates how two adaptive AI methods, evolutionary transfer learning and TD(lambda), perform in the three-dimensional chess environment Dragonchess. The ga…
- arXiv cs.AIresearchAVSD-Scenes: A Dataset for Audio-Visual Description of Urban Scenes
arXiv:2610.01861v1 Announce Type: new Abstract: Natural language descriptions can provide rich semantic representations of audio-visual urban scenes, yet datasets that jointly describe both auditory and visual informatio…
- arXiv cs.AIresearchRethinking Knowledge Retrieval for Generation: A Survey on RAG Architectures and Applications
arXiv:2610.01936v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across natural language tasks but remain fundamentally limited by their static knowled…
- arXiv cs.AIresearchCounterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage
arXiv:2610.01963v1 Announce Type: new Abstract: Emergency department (ED) triage is a high-stakes prioritization task in which demographic, socioeconomic, and system-context information may improperly influence acuity as…
- arXiv cs.AIresearchCan AI Oversight Be Zero Knowledge?
arXiv:2610.01995v1 Announce Type: new Abstract: AI systems increasingly produce outputs from confidential data, such as a fitness-for-duty assessment from medical records or the predicted properties of a drug candidate f…
- arXiv cs.AIresearchCounting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries
arXiv:2610.02005v1 Announce Type: new Abstract: A multi-LLM \emph{council} lets several large language models (LLMs) deliberate on a question and return an answer together with a confidence estimate. As these systems bec…
- arXiv cs.AIresearchAtoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering
arXiv:2610.02014v1 Announce Type: new Abstract: The rapid maturation of artificial intelligence (AI) and machine learning (ML) has catalyzed a profound shift in how chemical engineering problems are formulated, analyzed,…
- arXiv cs.AIresearchSPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL
arXiv:2610.02023v1 Announce Type: new Abstract: While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making immersive authoring…
- arXiv cs.AIresearchHydroJEV: A one-second, training-free screen for cyber-attack and fault attribution in water distribution networks
arXiv:2610.02048v1 Announce Type: new Abstract: When a SCADA alarm is raised in a water distribution network, operators must decide quickly whether it reflects a cyberattack, a physical fault, a normal transient or a fau…
- arXiv cs.AIresearchExternal Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing
arXiv:2610.02066v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly serve as foundational reasoning engines, their tendency to hallucinate remains a critical vulnerability. While recent internal…
- arXiv cs.AIresearchCausal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval
arXiv:2610.02070v3 Announce Type: replace Abstract: Memory-augmented large language models must decide which memories to retain, and recent systems do so by estimating each memory's effect on task performance. However, t…
- arXiv cs.AIresearchHomomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints
arXiv:2610.02074v1 Announce Type: new Abstract: Privacy-preserving machine learning presents significant deployment challenges on the cloud for intelligent systems with confidential data. Fully Homomorphic Encryption (FH…
- arXiv cs.AIresearchA Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification
arXiv:2610.02116v1 Announce Type: new Abstract: A comparative explainability framework is presented to audit DeBERTa-v3 under zero-shot classification of medical abstracts. The work addresses the disagreement problem in…
- arXiv cs.AIresearchVISTA: A Visual Harness for Reasoning in an Interactive World
arXiv:2610.02200v1 Announce Type: new Abstract: We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive envir…
- arXiv cs.AIresearchScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
arXiv:2610.02202v1 Announce Type: new Abstract: What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an…
- arXiv cs.AIresearchNew Snake-in-the-Box Records via Snakepit Surgery and Learned Construction
arXiv:2607.15270v3 Announce Type: cross Abstract: The snake-in-the-box problem asks for a longest induced path in the hypercube graph $Q_n$. We find a length-191 snake in dimension $n=9$, the lowest dimension where the m…
- arXiv cs.AIresearchSTATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets
arXiv:2610.00003v1 Announce Type: cross Abstract: Vision models pretrained for frame-level appearance often struggle to infer hidden physical properties from motion. We study center-of-mass (CoM) localization for opaque,…
- arXiv cs.AIresearchOn-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and Confidence
arXiv:2610.00007v1 Announce Type: cross Abstract: Named-entity recognition (NER) is increasingly wanted on-device (no API, low latency, data kept local). The practitioner's question is not the leaderboard but which model…
- arXiv cs.AIresearchBounded-Fidelity Sim-as-Demo-Stage: Mocap Handoff for Governance Benchmarks
arXiv:2610.00008v1 Announce Type: cross Abstract: Sim-to-real research pursues physics fidelity as a primary objective: simulators are judged by how closely they reproduce real-world contact dynamics. For governance benc…
- arXiv cs.AIresearchSpatial Lifting for Dense Prediction
arXiv:2610.00017v1 Announce Type: cross Abstract: We present Spatial Lifting (SL), a novel methodology for dense prediction tasks. SL operates by lifting standard inputs, such as 2D images, into a higher-dimensional spac…
- arXiv cs.AIresearchSW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials
arXiv:2610.00050v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) represent a paradigmatic shift in deep learning by replacing fixed node activations with learnable univariate functions on edges, offeri…
- arXiv cs.AIresearchAsk a Language Model for Lottery Numbers: Concentration in Repeated Six-of-49 Outputs
arXiv:2610.00052v1 Announce Type: cross Abstract: We evaluate six language-model configurations on requests for six distinct random integers from 1-49. Across 1,200 attempted calls using four English prompt variants, 1,1…
- arXiv cs.AIresearchThe First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating
arXiv:2610.00054v1 Announce Type: cross Abstract: Reading an LLM judge's verdict from the logits of its first generated token is cheap, requires no generation, and is exactly what constrained decoding and likelihood-scor…
- arXiv cs.AIresearchPushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing
arXiv:2610.00063v1 Announce Type: cross Abstract: Instance-billed serverless platforms charge for CPU and memory over the lifetime of a warm instance, making idle inference state a direct serving cost. We present billing…
- arXiv cs.AIresearchProbabilistic Plan Legibility with Off-the-shelf Planners
arXiv:2610.00065v1 Announce Type: cross Abstract: Legible planning is the creation of plans that best disambiguate their goals from a set of other candidates from an observer's perspective. In this paper we propose a met…
- arXiv cs.AIresearchA Framework for Egocentric and Exocentric Procedural Understanding via Temporal Segmentation and Semantic Abstraction
arXiv:2610.00069v1 Announce Type: cross Abstract: Long-horizon ego/exo data contains rich procedural evidence, but are redundant, noisy, and costly to process or retain. We propose a compact framework that converts conti…
- arXiv cs.AIresearchLegal text classification in Korean sexual offense cases: from traditional machine learning to large language models with XAI insights
arXiv:2610.00087v1 Announce Type: cross Abstract: The advancement of natural language processing (NLP) has expanded AI-based text classification in the legal domain. However, accurately classifying legal documents remain…
- arXiv cs.AIresearchMulti-Behavioral Evolved Substrates Through Neuromodulation and Activation Selection
arXiv:2610.00148v1 Announce Type: cross Abstract: Open-ended artificial life systems must acquire diverse competencies from a single evolving genotype. Biological brains combine neuromodulation, which reconfigures circui…
- arXiv cs.AIresearchPer-Node Activation Function Evolution in Indirectly Encoded Substrates: Solvability, Limits, and Emergent Diversity
arXiv:2610.00149v1 Announce Type: cross Abstract: Biological neurons achieve computational diversity through specialized types: tonic, bursting, adapting, and fast-spiking cells coexist within the same circuit. Artificia…
- arXiv cs.AIresearchWhen the AI Leaves the Tailorshop: Measuring What an LLM Advisor Leaves Behind in Complex Problem Solving
arXiv:2610.00163v1 Announce Type: cross Abstract: Complex problem solving depends on acting effectively and understanding how a system works. AI advice may support these outcomes unequally. Two preregistered experiments…
- arXiv cs.AIresearchFour Ways to Grow a Classifier and Why One of Them Cannot Learn
arXiv:2610.00180v2 Announce Type: replace-cross Abstract: Constructive classifiers add structure while they train: a level to a tree, a unit to a hidden layer, a split at a leaf. This paper asks what each of four such gr…
- arXiv cs.AIresearchWhite Men Without Degrees Receive the Lowest Ratings from Large Language Models
arXiv:2610.00185v1 Announce Type: cross Abstract: White men without an undergraduate degree receive the lowest average ratings among eight gender-race-education groups in controlled large-language-model evaluations of cr…
- arXiv cs.AIresearchShatterQuant: Breaking Uniform Precision with Block-Wise Mixed-Precision on a Systolic Transformer Hardware Accelerator
arXiv:2610.00207v1 Announce Type: cross Abstract: Due to limited support for intra-tensor heterogeneous precision in conventional accelerators, neural network quantization remains largely restricted to per-tensor precisi…
- arXiv cs.AIresearchUseful to Whom? The Easy-versus-Coverage Boundary Moves with the Learner
arXiv:2610.00221v2 Announce Type: replace-cross Abstract: Is the same data equally useful to every learner? The question is whether the value of a training sample belongs to the sample or arises in its interaction with t…
- arXiv cs.AIresearchPartial AUC Maximization from Positive-unlabeled Data
arXiv:2610.00284v1 Announce Type: cross Abstract: The partial area under the receiver operating characteristic curve (pAUC) is an important performance metric for binary classification that summarizes true positive rates…
- arXiv cs.AIresearchMulti-Jurisdictional Legal Identity Assurance for Capability Gating: A Design-Science Proposal for Tiered, Reusable Identity Assurance of Natural, Juridical, and Machine Entities
arXiv:2610.00287v1 Announce Type: cross Abstract: Identity assurance is the cost a digital system pays for dishonesty and uncertainty: it exists to make acts attributable when not everyone can be trusted at their word. A…
- arXiv cs.AIresearchLENS-GRF: Permutation-Invariant Lesion Evidence Network with Gated Residual Fusion for Acne Severity Grading and Multi-Rater Clinical Oracle Analysis
arXiv:2610.00294v1 Announce Type: cross Abstract: Automated acne severity grading requires both whole-face context and fine-grained lesion evidence. We propose LENS-GRF (Lesion Evidence Network with Set-Transformer and G…
- arXiv cs.AIresearchCertainty Is Not Just Correctness: Rethinking Token-Level Certainty in LLM Reasoning
arXiv:2610.00296v1 Announce Type: cross Abstract: Token-level certainty is widely used as a proxy for correctness in LLM training and inference. However, the performance of certainty-based methods depends both on the inf…