AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchBeyond Pattern Matching in 3D MLLMs: Part-Level Functional Reasoning for Generalizable Recognition
arXiv:2610.32262v1 Announce Type: cross Abstract: 3D MLLMs recognize objects via pattern matching, which fails when geometrically similar objects require functional reasoning to disambiguate (e.g., dresser vs. wardrobe).…
- arXiv cs.AIresearchTokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs
arXiv:2610.32264v1 Announce Type: cross Abstract: Finding which phenomena occur in a tokamak discharge, and when, is often a manual task. Previous efforts at labeling events have been task-specific, each with its own cor…
- arXiv cs.AIresearch"Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs
arXiv:2610.32281v1 Announce Type: cross Abstract: Negation occurs in every language, yet its surface realization differs drastically. Despite this, multilingual large language models (LLMs) translate negation robustly, r…
- arXiv cs.AIresearchComplementing DINO Features with Image Structure for Part Discovery
arXiv:2610.32293v1 Announce Type: cross Abstract: Self-supervised Vision Transformers (ViTs) like DINO encode rich semantics, enabling training-free segmentation of objects from the background and discovery of their part…
- arXiv cs.AIresearchChoreoStudio: Planning What, When, and Who in Music-Driven Group Choreography
arXiv:2610.32325v1 Announce Type: cross Abstract: Music-driven group dance generation must decide not only how each dancer moves, but also what formation the group should form, when it should change, and who should execu…
- arXiv cs.AIagents4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents
arXiv:2610.32332v1 Announce Type: cross Abstract: Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicti…
- arXiv cs.AIresearchData-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring
arXiv:2610.32334v1 Announce Type: cross Abstract: Pre-trained code models are exposed to backdoor poisoning, in which crafted training samples make the model misbehave on a trigger. A capable attacker minimizes the numbe…
- arXiv cs.AIresearchTENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection
arXiv:2610.32337v1 Announce Type: cross Abstract: In unsupervised multivariate time series anomaly detection (MTSAD), local variation can inflate reconstruction and forecasting errors, making observation-space discrepanc…
- arXiv cs.AIresearchPASTA: Prompt-Aware Annealed Diffusion Sampling
arXiv:2610.32390v1 Announce Type: cross Abstract: While Diffusion models produce high-quality images, real-world visual design requires intentionally preserving clean regions for headlines, logos, or UI elements. Existin…
- arXiv cs.AIresearchCycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images
arXiv:2610.32423v1 Announce Type: cross Abstract: Recent advances in Vision-Language Models (VLMs) have significantly improved Visual Question Answering (VQA) performance, yet their reasoning over structured content such…
- arXiv cs.AIagentsDecoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation
arXiv:2610.32443v1 Announce Type: cross Abstract: Pre-consultation medical dialogues are essential for collecting comprehensive patient information, but are costly to obtain at scale due to privacy and ethical constraint…
- arXiv cs.AIresearchDIGOM: Disentangled Interaction Graphs for Outcome prediction in Multimodal healthcare
arXiv:2610.32451v1 Announce Type: cross Abstract: Multimodal healthcare data contain relational information that extends beyond individual patient observations. Effective clinical outcome prediction therefore requires no…
- arXiv cs.AIresearchAutoMIL: Automated Multiple Instance Learning for Whole-Slide Image Classification
arXiv:2610.32452v1 Announce Type: cross Abstract: Developing multiple instance learning pipelines for the classification of whole-slide images involves many interdependent design decisions and expertise in both pathology…
- arXiv cs.AIagentsBeyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation
arXiv:2610.32453v1 Announce Type: cross Abstract: AI agents can inspect code and run tests to support smart contract security. SlowMist reports about $38.6 billion in losses across the broader blockchain ecosystem. Exist…
- arXiv cs.AIresearchEfficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF)
arXiv:2610.32486v1 Announce Type: cross Abstract: Deploying Vision-Language Models for video anomaly detection confronts a fundamental constraint. Their semantic reasoning demands computational budgets incompatible with…
- arXiv cs.AIresearchMusicTwins: Training Audio-Language Models to Listen like Their Persona
arXiv:2610.32495v1 Announce Type: cross Abstract: People differ in how they perceive music, what associations they make with it, what they like about it, and how they respond to it. Computational models intended to simul…
- arXiv cs.AIresearchAnalysing Austrian Parliamentary Speeches by Predicting Party Affiliations
arXiv:2610.32515v1 Announce Type: cross Abstract: This paper examines speech characteristics of the Austrian National Council members (CMs). We introduce analysis methodology based on a fine-tuned BERT-Model which assign…
- arXiv cs.AIresearchStarRTT: An End-to-End Real-Time Framework for Blind Zone-Free RTT Prediction in Starlink LEO Satellite Networks
arXiv:2610.32540v1 Announce Type: cross Abstract: Low Earth Orbit (LEO) satellite mega-constellations such as Starlink require frequent handovers due to high orbital velocities, resulting in substantial Round-Trip Time (…
- arXiv cs.AIagentsTool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance
arXiv:2610.32555v1 Announce Type: cross Abstract: LLM agents increasingly rely on external tools exposed via the Model Context Protocol (MCP), yet current benchmarks assume tools respond correctly and on time, leaving ag…
- arXiv cs.AIresearchInterpretable Singing Emotion Recognition Using Acoustic and Vocal Technique Features
arXiv:2610.32629v1 Announce Type: cross Abstract: Singing emotion recognition relies predominantly on deep learning models that achieve strong performance but offer limited insight into the vocal characteristics driving…
- arXiv cs.AIresearchEditJev: System One Routing for Image Editing Models
arXiv:2610.32635v1 Announce Type: cross Abstract: Instruction-based image editing models exhibit pronounced sample-specific performance variation: different models can produce substantially different results for the same…
- arXiv cs.AIagentsCan AI Agents Help Robotic Engineers? Lessons from Two Focus Days in Industry
arXiv:2610.32636v1 Announce Type: cross Abstract: Software developers increasingly use AI agents that execute multi-step programming tasks on their own. However, it is unclear if and how this transfers to robotic enginee…
- arXiv cs.AIresearchInferSlice: A Reference Architecture for SLO-driven LLM Inference over a Telco Wide-Area Network
arXiv:2610.32638v1 Announce Type: cross Abstract: LLM inference is increasingly deployed as a core service for enterprise and interactive applications, but sovereignty, compliance, latency and resource-locality requireme…
- arXiv cs.AIresearchSemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric Correspondences
arXiv:2610.32663v1 Announce Type: cross Abstract: We introduce SemGeo-Gen, an unsupervised method for generating approximate cross-instance semantic-geometric supervision from weakly aligned 3D object collections. Our go…
- arXiv cs.AIagentsConditional Neural Processes for Self-Supervised Goal Discovery in Action Imitation
arXiv:2610.32688v1 Announce Type: cross Abstract: Inspired by infants' ability to learn novel tasks by imitating others, in this work we evaluate to what extent Conditional Neural Processes can autonomously learn represe…
- arXiv cs.AIresearchSP-Guide: Enhancing Aerial Vision-Language Navigation with Spatial Priors
arXiv:2610.32697v1 Announce Type: cross Abstract: Aerial vision-language navigation (AVLN) requires a UAV to reach a language-described target from partial egocentric observations while reasoning over large outdoor scene…
- arXiv cs.AIresearchOntology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications
arXiv:2610.32725v1 Announce Type: cross Abstract: The rapid expansion of scientific literature far outpaces the speed of manual curation, creating a fundamental bottleneck in extracting structured knowledge from scientif…
- arXiv cs.AIresearchPlayerEmbed: Learning Behavioral Fingerprint Representations from Raw Input Sequences
arXiv:2610.32727v1 Announce Type: cross Abstract: Raw player input sequences in video games contain fine-grained behavior, but are high-dimensional and noisy, which makes large-scale analytics challenging. To address thi…
- arXiv cs.AIresearchInternal Discrepancy for Contrastive Learning: Generalization Bounds and Downstream Behaviors
arXiv:2610.32729v1 Announce Type: cross Abstract: Contrastive learning has emerged as a popular paradigm for training representation models. While prior studies pursue more practical and less restrictive assumptions to e…
- arXiv cs.AIresearchAdaptive World-Models for Anomaly Recognition (AWARE): A Framework for Robot Dynamics Prediction and Introspection
arXiv:2610.32742v1 Announce Type: cross Abstract: Unrecognized anomalies in critical infrastructure can rapidly cascade into catastrophic physical or operational failures. Current anomaly detection approaches often rely…
- arXiv cs.AIagentsSemantic Representation for Agentic Self-Play in Automated Laboratories
arXiv:2610.32755v1 Announce Type: cross Abstract: Navigating complex, high-dimensional biological search spaces necessitates scalable physical and computational intelligence to explore beyond local optima through iterati…
- arXiv cs.AIresearchClean-label Poisoning Attack and Defense Game for Federated Learning in Vehicular Networks
arXiv:2610.32765v1 Announce Type: cross Abstract: This paper studies interactions between clean-label poisoning attack and defense in vehicular networks using federated learning (FL). Basic Safety Message (BSM) classific…
- arXiv cs.AIresearchOn-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
arXiv:2610.32770v1 Announce Type: cross Abstract: On-policy self-distillation enables post-training foundation models without relying on stronger external teachers. However, existing approaches rely on ground-truth quest…
- arXiv cs.AIresearchAI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases
arXiv:2610.32780v1 Announce Type: cross Abstract: AI representation is emerging in digital democracy, assisting in voter emulation and decision-making. Large language models (LLMs) behave differently depending on the mod…
- arXiv cs.AIagentsEvery Edge Needs a Quote: Building a Quote-Grounded Knowledge Graph of Healthcare Software Adoption with Language-Model Agents
arXiv:2610.32781v1 Announce Type: cross Abstract: Hospitals regularly buy software that clinicians and patients depend on. Because these purchases are costly, hard to reverse and can affect patient care, buyers look for…
- arXiv cs.AIresearchMultiplicative vs. Additive State Coupling in Learned Optimizer Schedules
arXiv:2610.32801v1 Announce Type: cross Abstract: We learn schedules for a continuous penalty relaxation of MAX-CUT by backpropagating through an unrolled classical solver. A state-blind schedule generalizes to instances…
- arXiv cs.AIresearchPoKER: A Probability of Kill Estimation Rate Model for Air-to-Air Missiles Using Machine Learning on Stochastic Targets
arXiv:2610.32864v1 Announce Type: cross Abstract: This work introduces PoKER, a novel probabilistic model engineered to optimize missile launch effectiveness in air-to-air scenarios, specifically within Beyond Visual Ran…
- arXiv cs.AIresearchInterpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery
arXiv:2610.32866v1 Announce Type: cross Abstract: Fine-tuning on datasets of unknown origin can create a backdoor in the trained model when the data includes poisoned examples. Difficult to localise and remove, backdoors…
- arXiv cs.AIresearchGreen Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations
arXiv:2610.32891v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to optimize code for performance. This practice often assumes that improvements in execution speed naturally translate…
- arXiv cs.AIresearchYalda-Embedding: Open Development of a Competitive Persian Retrieval Model
arXiv:2610.32933v1 Announce Type: cross Abstract: Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training…
- arXiv cs.AIresearchMonetizing Intelligence: Advertising and Subscription Design on LLM Platforms
arXiv:2610.32945v1 Announce Type: cross Abstract: Large language model (LLM) platforms introducing advertising must decide how much capability ad revenue should fund and what consumers should pay to avoid ads. We study a…
- arXiv cs.AIresearchBeyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models
arXiv:2610.32948v1 Announce Type: cross Abstract: Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that addresses the mismatch between continuous measuremen…
- arXiv cs.AIresearchDexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection
arXiv:2610.32969v1 Announce Type: cross Abstract: Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperation records executable robot actions, but it requires a…
- arXiv cs.AIresearchRobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
arXiv:2610.32971v1 Announce Type: cross Abstract: Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions. Existing robust RL algori…
- arXiv cs.AIagentsSceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
arXiv:2610.32978v1 Announce Type: cross Abstract: Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-…
- arXiv cs.AIresearchMEDMKG: Benchmarking Medical Knowledge Exploitation with Multimodal Knowledge Graph
arXiv:2505.17214v2 Announce Type: replace Abstract: Medical deep learning models depend heavily on domain-specific knowledge to perform well on knowledge-intensive clinical tasks. Prior work has primarily leveraged unimo…
- arXiv cs.AIresearchExpressivity Results for Structured Argumentation Frameworks with Uncertain Rules and Premises
arXiv:2510.18631v3 Announce Type: replace Abstract: Modelling qualitative uncertainty in formal argumentation is essential both for practical applications and theoretical understanding. Yet, most existing work focuses on…
- arXiv cs.AIresearchTesting Transformer Learnability on the Arithmetic Sequence of Rooted Trees
arXiv:2512.01870v3 Announce Type: replace Abstract: We study whether a transformer network can learn the deterministic sequence of trees generated by the iterated prime factorization of the natural numbers. Each integer…
- arXiv cs.AIagentsMedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data
arXiv:2512.13297v2 Announce Type: replace Abstract: In medical data analysis, extracting deep insights from complex, multi-modal datasets is essential for improving patient care, increasing diagnostic accuracy, and optim…
- arXiv cs.AIresearchLearning to Predict, Discover, and Reason in High-Cardinality Event Sequences
arXiv:2603.16313v4 Announce Type: replace Abstract: Electronic control units (ECUs) embedded within modern vehicles generate a large number of asynchronous events known as diagnostic trouble codes (DTCs). These discrete…