AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchscHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data
arXiv:2610.15117v1 Announce Type: cross Abstract: To evaluate whether a compact bidirectional state-space autoencoder improves joint classification of species, cell type, and disease state from single-nucleus RNA-sequenc…
- arXiv cs.AIresearchShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer
arXiv:2610.15124v1 Announce Type: cross Abstract: Foundation models need to support diverse inference budgets, yet training a separate model for each budget duplicates pretraining effort. Elastic models train several nes…
- arXiv cs.AIagentsRIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition
arXiv:2610.15127v1 Announce Type: cross Abstract: Traffic sign recognition plays a crucial role in the development of autonomous cars to reduce the accident rate and promote road safety. It has been a necessity to addres…
- arXiv cs.AIresearchTo Defer or Not to Defer? Online Learning with LLMs and Congested Experts
arXiv:2610.15128v1 Announce Type: cross Abstract: Modern AI systems increasingly combine large language models (LLMs) with human experts, using the LLM to handle routine queries while deferring uncertain cases for expert…
- arXiv cs.AIresearchUDHRBench: Benchmarking Human Rights in Large Language Models
arXiv:2610.15179v1 Announce Type: cross Abstract: Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally recognized human righ…
- arXiv cs.AIresearchExploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models
arXiv:2610.15207v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass safety align…
- arXiv cs.AIagentsPANINI-DR: Controlled Deep Research through Generative Semantic Workspaces
arXiv:2610.15208v2 Announce Type: replace-cross Abstract: Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. As investigat…
- arXiv cs.AIresearchFramework for an AI-Ready ARPES Community Database
arXiv:2610.15236v1 Announce Type: cross Abstract: Condensed matter stands to gain profoundly from widespread adoption of artificial intelligence (AI). However, its current means of data organization impedes this endeavor…
- arXiv cs.AIagentsEvolvAttack: Backdooring self Evolving VLM Agents
arXiv:2610.15244v1 Announce Type: cross Abstract: Self-evolving mechanisms let vision-language model (VLM) agents continually adapt through evolving memory, but they also allow malicious behavior to emerge only after dep…
- arXiv cs.AIagentsSequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning
arXiv:2610.15258v1 Announce Type: cross Abstract: We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them. Agents reason in an executable SMT-LIB…
- arXiv cs.AIresearchLeHami: Symplectic Latent Dynamics for World Models
arXiv:2610.15267v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) learn world models directly in latent space, but unconstrained autoregressive predictors may contract the latent distribu…
- arXiv cs.AIresearchGeoBridge: Evolving Transferable Decoder Topologies for Geometric Vision
arXiv:2610.15280v2 Announce Type: replace-cross Abstract: Depth estimation and Gaussian reconstruction share a need for multi-scale feature processing, yet use different prediction interfaces and training objectives. Whe…
- arXiv cs.AIresearchNorth or South? Diagnosing LLMs' Understanding of North Korean Language, Society, and Knowledge
arXiv:2610.15282v1 Announce Type: cross Abstract: Large Language Models (LLMs) have made substantial progress in multilingual question answering, yet their ability to understand low-resource sociolinguistic contexts rema…
- arXiv cs.AIresearchProtein Crystallization Segmentation and Classification Using Subordinate Color Channel in Fluorescence Microscopy Images
arXiv:2610.15286v1 Announce Type: cross Abstract: The accuracy of detecting protein crystals for fluorescence microscopy images is very critical for high throughput and automated systems. Although the trace fluorescent l…
- arXiv cs.AIresearchCo-DSL: Human-LLM Co-design of Reusable Spatial Concepts for Layout Generation
arXiv:2610.15290v1 Announce Type: cross Abstract: We present Co-DSL, a framework in which users and LLMs co-design reusable spatial concepts for layout generation. In the first stage, our system allows users to create a…
- arXiv cs.AIresearchHGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Models
arXiv:2610.15297v1 Announce Type: cross Abstract: Recently, AutoRegressive Visual Generation (ARVG) models have emerged as a competitive paradigm for high-quality image synthesis. However, their substantial computational…
- arXiv cs.AIresearchWisdomNet: trustable machine learning toward error-free classification
arXiv:2610.15299v1 Announce Type: cross Abstract: Misclassification is a critical problem in many machine learning applications. Since even the classifier models with high accuracy (e.g., > 95%) still introduce some misc…
- arXiv cs.AIresearchAccuracy and Uncertainty in Machine Deception Detection (Research White Paper)
arXiv:2610.15314v1 Announce Type: cross Abstract: A deception detector is only as useful as the trust its alarms deserve. Like a polygraph, detectors that read a language model's internal activations can catch deceptive…
- arXiv cs.AIresearchAnchor-and-Harvest Curriculum: A Fully Unmasked Non-LLM Curriculum for Craftax
arXiv:2610.15328v1 Announce Type: cross Abstract: We introduce Anchor-and-Harvest Curriculum (AHC), a domain-informed, rule-based training system for Craftax-Full. AHC combines achievement-oriented tasks, harvested initi…
- arXiv cs.AIresearchZOIF: Zeroth-Order Influence Function Estimation for LLM Data Selection Using Only Forward Passes
arXiv:2610.15336v1 Announce Type: cross Abstract: Influence functions enable principled data selection for large language models (e.g., identifying influential training samples for model editing, debugging, or efficient…
- arXiv cs.AIresearchStimFlow: Synthesizing Brain Activity from Images via Stimulus-conditioned Flow Matching
arXiv:2610.15341v1 Announce Type: cross Abstract: The inherent variability of fMRI responses across trials encourages a generative view of the stimulus-to-response mapping. Prior generative encoders often operate in comp…
- arXiv cs.AIresearchAcross Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models
arXiv:2610.15343v1 Announce Type: cross Abstract: World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threats remains largely…
- arXiv cs.AIresearchCodeWalk: Generating Coding Benchmarks by Walking a Problem Graph
arXiv:2610.15345v1 Announce Type: cross Abstract: High-quality coding problems are expensive to collect. Benchmarks such as SWE-bench rely on substantial human curation, while synthetic alternatives typically rely on cos…
- arXiv cs.AIresearchGugak-VocalSet: A Multi-Genre Studio-Quality Dataset of Korean Traditional Singing with Sigimsae Annotations
arXiv:2610.15350v1 Announce Type: cross Abstract: We present Gugak-VocalSet, the first publicly available audio dataset for Korean traditional singing with dense annotations of sigimsae, a structured pitch contour system…
- arXiv cs.AIresearchSiam-ALS: An Explainable Siamese Deep Learning Framework for Early ALS Detection Using EEG and Eye-Tracking Signals
arXiv:2610.15351v1 Announce Type: cross Abstract: Amyotrophic lateral sclerosis (ALS) diagnosis remains challenging due to heterogeneous symptoms and reliance on clinical assessment, underscoring the need for objective,…
- arXiv cs.AIagentsAdversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification
arXiv:2610.15359v1 Announce Type: cross Abstract: Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations. Certified $\ell_2$ defenses…
- arXiv cs.AIresearchA Sovereign, Indic-First, Reasoning Model
arXiv:2610.15371v1 Announce Type: cross Abstract: Gnani-Evon-v3.3-30B-A3B is a long-context hybrid Mamba-Transformer mixture-of-experts model for reasoning, instruction following, and tool use in English and eight Indian…
- arXiv cs.AIresearchIn-Place Indic Tokenizer Expansion and Continual Pretraining of Nemotron-3-Nano-30B-A3B
arXiv:2610.15373v1 Announce Type: cross Abstract: We adapted Nemotron-3-Nano-30B-A3B for eight Indian languages without changing its backbone architecture. We expanded the vocabulary in place from 131,072 to 163,072 entr…
- arXiv cs.AIresearchE8 Lattice Key Quantization for Low-Bit KV-Cache Compression
arXiv:2610.15384v1 Announce Type: cross Abstract: Compressing the key-value (KV) cache is essential for serving long-context large language models (LLMs) under memory constraints. While current scalar quantization method…
- arXiv cs.AIagentsSensitivity or Criterion? Measuring and Moving When Language Models Act
arXiv:2610.15415v1 Announce Type: cross Abstract: Before an agent acts, it must decide whether action is warranted. A single accuracy cannot distinguish failure to recognize a warranted action from reluctance to act. Sig…
- arXiv cs.AIresearchPessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
arXiv:2610.15428v2 Announce Type: replace-cross Abstract: Context-based offline meta-reinforcement learning (COMRL) has advanced almost entirely through better task representations, which separate task identity from arti…
- arXiv cs.AIresearchWorld Modeling through Spectral Alignment
arXiv:2610.15429v2 Announce Type: replace-cross Abstract: How do we tell a world model what information to preserve? We study this question through the lens of spectral representation learning. We introduce SpecWM, a JEP…
- arXiv cs.AIresearchBridgeCodec: Mamba Enhanced Neural Audio Codec with Schr\"odinger Bridge at Low Bitrate
arXiv:2610.15453v1 Announce Type: cross Abstract: Neural audio codecs achieve remarkable performance but operate as closed ecosystems with rigidly co-trained encoderdecoder pairs, severely hindering interoperability. To…
- arXiv cs.AIagentsWhen Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems
arXiv:2610.15459v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks. Their reliance on networked protocols, remote tools, an…
- arXiv cs.AIresearchSecurity in LLM-Assisted Coding: A Systematic Literature Review
arXiv:2610.15482v1 Announce Type: cross Abstract: Large Language Models accelerate software development but introduce severe security vulnerabilities. This systematic review investigates security risks in automated codin…
- arXiv cs.AIresearchThe Imperishable Record, Forgiveness, and the Future of Criminal Justice
arXiv:2610.15499v1 Announce Type: cross Abstract: Digital technologies can preserve records of wrongdoing indefinitely, and AI can give those records continuing influence over a person's future. We describe this conditio…
- arXiv cs.AIresearchCacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff
arXiv:2610.15509v1 Announce Type: cross Abstract: KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the context again. We…
- arXiv cs.AIresearchREPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming
arXiv:2610.15513v1 Announce Type: cross Abstract: Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming methods either requ…
- arXiv cs.AIresearchSARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning
arXiv:2610.15514v1 Announce Type: cross Abstract: Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardware-agnostic speedup.…
- arXiv cs.AIresearchOceanFlow: Coherent Flow Matching for Probabilistic Ocean Modeling
arXiv:2610.15518v1 Announce Type: cross Abstract: Probabilistic ocean modeling is essential for risk-aware marine operations, climate analysis, and scientific decision-making, where downstream decisions depend on the con…
- arXiv cs.AIagentsImproving the Bounds on Approximating Weighted Maximin Share for Chores
arXiv:2610.15520v1 Announce Type: cross Abstract: We investigate the problem of allocating indivisible chores among agents with arbitrary positive weights and additive nonnegative cost functions. An allocation is said to…
- arXiv cs.AIresearchELECT: Settling Identity Before Rendering for Scalable Story Visualization
arXiv:2610.15555v1 Announce Type: cross Abstract: Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing methods typically mai…
- arXiv cs.AIagentsDynamic Conflict Clustering with Lightweight Learning and Strategic Repair for Distributed Constraint Satisfaction
arXiv:2610.15658v1 Announce Type: cross Abstract: Distributed Constraint Satisfaction Problems (DCSPs) model distributed decision-making in multi-agent systems, where agents assign values to local variables while satisfy…
- arXiv cs.AIresearchRethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning
arXiv:2610.15681v1 Announce Type: cross Abstract: Parametric Computer-Aided-Design (CAD) modeling from human intent remains challenging, particularly during the conceptual design stage, where design goals are expressed t…
- arXiv cs.AIresearchTabMosaic: Unified In-Context Diffusion for Tabular Generative Tasks
arXiv:2610.15699v1 Announce Type: cross Abstract: Generative modeling for tabular data has advanced to the point where models can synthesize realistic records, recover missing values, and generate samples conditioned on…
- arXiv cs.AIresearchRespFocus: Learning Temporal Evidence for Weakly Supervised Respiratory Sound Classification
arXiv:2610.15702v1 Announce Type: cross Abstract: Respiratory auscultation provides a low-cost means of assessing pulmonary function, yet transient crackles and sustained wheezes can be difficult to recognize in noisy cl…
- arXiv cs.AIresearchbharatSetu: a 1M x 22 bridge for indic translation
arXiv:2610.15705v1 Announce Type: cross Abstract: India's Eighth Schedule recognises 22 languages, yet parallel data is uneven across them, and many language pairs, especially among lower-resource languages such as Bodo,…
- arXiv cs.AIresearchWhat DNA Foundation Models Learn Beyond Sequence Composition
arXiv:2610.15711v1 Announce Type: cross Abstract: Do genomic foundation models (FMs) provide predictive information beyond simple sequence composition? We evaluate frozen representations from five DNA FMs against normali…
- arXiv cs.AIresearchUncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework
arXiv:2610.15724v1 Announce Type: cross Abstract: Denoising Diffusion Probabilistic Models have emerged as powerful generative priors across domains ranging from molecular design to high-resolution image synthesis. Howev…
- arXiv cs.AIagentsSkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification
arXiv:2610.15725v2 Announce Type: replace-cross Abstract: Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to unauthorized cop…