AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchOn The Robustness-Resolution Tradeoff In Temporal Quantization Of Event Streams
arXiv:2609.22295v2 Announce Type: replace-cross Abstract: Event pipelines often discretize asynchronous timestamps before learning. This step looks harmless, but its stability depends directly on temporal resolution. We…
- arXiv cs.AIresearchVisual Graph Reasoning via Knowledge Compilation
arXiv:2609.22327v1 Announce Type: cross Abstract: Visual graph reasoning requires answering graph-theoretic questions directly from graph images, where graph topology and state are conveyed visually rather than given in…
- arXiv cs.AIresearchArtificial Neural Networks as Surrogate Models in Black Box Optimization
arXiv:2609.22329v1 Announce Type: cross Abstract: Black-Box Optimization (BBO) is often applied in several engineering fields and can utilize an advancement of numerical measure- ments and simulation technologies. It dea…
- arXiv cs.AIresearchAffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation
arXiv:2609.22332v3 Announce Type: replace-cross Abstract: Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act. Action-labe…
- arXiv cs.AIresearchDimensionality reduction for AI based hyperspectral image classification based on XAI
arXiv:2609.22333v1 Announce Type: cross Abstract: This research addresses the challenge of limited material recycling in wood recycling processes by leveraging artificial intelligence (AI)-based dimensionality reduction.…
- arXiv cs.AIresearchResist, Update, Reject: Preference Optimization Installs a Prior-Dependent Reliability Switch
arXiv:2609.22359v1 Announce Type: cross Abstract: An aligned model asked to hold its answer against a manipulative source must still update on a reliable one and reject an unreliable one: resistance, reliable-update, and…
- arXiv cs.AIresearchForecasting Brain Tracer Distribution from Pre-Contrast MRI: A Comparison of Direct Regression and Flow Matching
arXiv:2609.22377v2 Announce Type: replace-cross Abstract: Intrathecal contrast-enhanced MRI shows how a tracer injected into the cerebrospinal fluid spreads through the brain, but requires repeated scans over 24--48\,h.…
- arXiv cs.AIresearchMarsRecon: Self-Supervised and Multimodal Surface Representations for Mars
arXiv:2609.22379v1 Announce Type: cross Abstract: High-resolution orbital imagery offers a rich record of the Martian surface, but sparse geological labels limit supervised representation learning. We present MarsRecon,…
- arXiv cs.AIresearchContextual Causality with Large Language Models: A Survey
arXiv:2609.22409v1 Announce Type: cross Abstract: Understanding contextual causality is critical for large language models (LLMs), as it enables them to accurately identify causal relations in specific situations and sup…
- arXiv cs.AIresearchToward Personalized Sleep Guidance from Wearable Data Using Language Models
arXiv:2609.22463v2 Announce Type: replace-cross Abstract: Sleep monitoring using wearable data has shown promise for personal health, yet large language model (LLM)-based summarization and question answering remain insuf…
- arXiv cs.AIresearchFRAMES: Failure Recovery And Monitoring of Embodied Skills for Humanoid Loco-Manipulation
arXiv:2609.22538v1 Announce Type: cross Abstract: Large language model (LLM) planners can decompose natural-language instructions and select reusable robot skills, but choosing the correct skill does not guarantee succes…
- arXiv cs.AIresearchThe Ups and Downs of Backprop Weights
arXiv:2609.22554v2 Announce Type: replace-cross Abstract: Backpropagation (BP) has driven the remarkable success of modern deep learning by enabling large hierarchical networks to learn complex functions end-to-end. Yet…
- arXiv cs.AIresearchDo Student LLMs Inherit OOD Robustness? Invariance-Weighted Distillation for Reliable Knowledge Transfer
arXiv:2609.22566v1 Announce Type: cross Abstract: Knowledge distillation (KD) aims to compress high-performance teacher LLMs into lightweight students. However, distilled students often exhibit substantial performance de…
- arXiv cs.AIresearchBeyond the Leaderboard: Counterfactual Diagnosis of End-to-End and VLA Driving Policies Under Domain Shift
arXiv:2609.22582v1 Announce Type: cross Abstract: End-to-end and vision-language-action (VLA) driving policies are compared by leaderboard rank, but a rank reports an outcome, not the behaviour behind it, so it predicts…
- arXiv cs.AIresearchSEABED: SouthEast Asian Benchmark for Evaluating Audio Reasoning
arXiv:2609.22586v1 Announce Type: cross Abstract: Modern audio-language models are no longer judged only on what words they can transcribe, but on whether they can reason over what they hear: recovering meaning that live…
- arXiv cs.AIresearchSeeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act
arXiv:2609.22588v1 Announce Type: cross Abstract: Vision-language models (VLMs) perform strongly on visual question answering benchmarks, yet often make decisions that contradict visual evidence they have already identif…
- arXiv cs.AIresearchPreserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation
arXiv:2609.22603v3 Announce Type: replace-cross Abstract: Summarization ships in countless production systems, making model selection a routine decision that depends on measuring summary quality. Existing metrics struggl…
- arXiv cs.AIresearchFrom Documented Strengths to Force Limits: Material-Informed Robotic Insertion for Construction Assembly
arXiv:2609.22609v1 Announce Type: cross Abstract: Insertion is a fundamental operation in robotic construction assembly, where variations in material properties and assembly conditions make it difficult to select contact…
- arXiv cs.AIresearchHIGenNTO: Scalable Humanoid Interaction Generation via Noise-Space Trajectory Optimization
arXiv:2609.22611v1 Announce Type: cross Abstract: Humanoid robots can acquire complex skills by imitating kinematic humanoid motion references, yet reliable references for contact-rich interactions remain difficult to ob…
- arXiv cs.AIresearchMath2Visual-X: A Modular Framework for Pedagogically Aligned Lower-Primary Math Visuals Generation
arXiv:2609.22647v1 Announce Type: cross Abstract: Visual representations can help lower-primary learners understand Math Word Problems, but generating classroom-usable visuals remains difficult. Existing symbolic systems…
- arXiv cs.AIresearchLLaDA-PRM: A Bidirectional Step-Level Reasoning Evaluator
arXiv:2609.22700v1 Announce Type: cross Abstract: Step-level reasoning evaluators are commonly based on autoregressive language models, whose causal attention restricts each step representation to the problem, previous s…
- arXiv cs.AIresearchAnalyzing Public Discourse on Urbanism: Topic Clustering, Sentiment Analysis and Retrieval-Augmented Generation using YouTube Comments
arXiv:2609.22705v1 Announce Type: cross Abstract: Online discourse about urban issues - walkability, cycling infrastructure, public transit, housing density, and street safety - is voluminous but unstructured, and existi…
- arXiv cs.AIresearchBeyond Raw Engagement: A Counterfactual Observability Framework for Recommender Systems at Netflix
arXiv:2609.22747v1 Announce Type: cross Abstract: Understanding the performance of large-scale recommender systems remains an underexplored challenge, especially for content creators and model developers. The raw engagem…
- arXiv cs.AIresearchParameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant
arXiv:2609.22770v2 Announce Type: replace-cross Abstract: We study a parameterized hybrid ranker that fuses a dense embedding list and a sparse lexical list. The method has a small, explicit parameter vector: a dense pri…
- arXiv cs.AIresearchParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding
arXiv:2609.22771v1 Announce Type: cross Abstract: Recent advances in Audio LLMs have achieved human-level speech recognition, yet existing systems struggle to capture paralinguistic aspects such as speaker traits, expres…
- arXiv cs.AIresearchDiagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation
arXiv:2609.22793v1 Announce Type: cross Abstract: LLM-based machine translation evaluation can closely match human judgments, but in practice it remains largely diagnostic, with the signals rarely translating into direct…
- arXiv cs.AIresearchAlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation
arXiv:2609.22796v1 Announce Type: cross Abstract: Dialectal Arabic machine translation (MT) remains challenging despite recent progress in Arabic language technologies, particularly because effective translation requires…
- arXiv cs.AIresearchCommonsense-Grounded Path Planning from Abstract Instructions
arXiv:2609.22813v1 Announce Type: cross Abstract: We present \emph{commonsense ranked search} (CoRS), a novel path planner that turns an abstract instruction into a route that follows commonsense. While existing methods…
- arXiv cs.AIresearchSatOV: Restoring Spatial Priors for Training-Free Open-Vocabulary Segmentation in Remote Sensing Imagery
arXiv:2609.22834v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVS) of remote sensing imagery is a challenging pixel-level task requiring strong generalization and adaptation to the spatial char…
- arXiv cs.AIresearchSame Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?
arXiv:2609.22850v4 Announce Type: replace-cross Abstract: Claims about what an internal direction in an LLM represents need evidential constraints beyond an observer's prior beliefs about the system. Decodability and suc…
- arXiv cs.AIresearchDiscrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs
arXiv:2609.22851v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) utilize either continuous features or discrete tokens, yet the optimal representation paradigm for general audio understanding…
- arXiv cs.AIresearchThe Moral Check: Strategic AI Governance for the Pacing Problem
arXiv:2609.22869v1 Announce Type: cross Abstract: Technology cannot steer itself. Strategy provides that steering, establishing the rule that purpose and judgment must precede compute capital. As the frontier artificial…
- arXiv cs.AIresearchPer-Query Gating of LLM Rerankers for Multi-Hop Retrieval
arXiv:2609.22880v1 Announce Type: cross Abstract: LLM rerankers add of the order of \$0.2-0.3 per 1,000 queries and about a second of tail latency on top of a graph-augmented dense pipeline such as HippoRAG2, and on thre…
- arXiv cs.AIresearchBlock-Sparse Attention with Semantic-Geometric Decoupled Routing
arXiv:2609.22884v1 Announce Type: cross Abstract: Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling with sequence leng…
- arXiv cs.AIresearchMerge++: Universal Merge Refinement Through Data-Free Checkpoint Inversion
arXiv:2609.22886v1 Announce Type: cross Abstract: Model merging consolidates fine-tuned experts into one multi-task model without retraining. All existing data-free methods approach this problem entirely in weight space.…
- arXiv cs.AIresearchAre Coreset Selection Methods Worth Their Cost?
arXiv:2609.22894v2 Announce Type: replace-cross Abstract: Coreset selection picks a representative subset of the labeled training set to make training cheaper. However, it is usually evaluated by downstream accuracy at a…
- arXiv cs.AIresearchAVTR-1: Open Stack for Real-Time Interactive Avatars
arXiv:2609.22913v1 Announce Type: cross Abstract: Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live system must synchron…
- arXiv cs.AIresearchMeasuring Behavioural Signatures of Large Language Models through Psychometric Profiling
arXiv:2609.22934v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate human decisions and communication, yet their behavioural regularities remain difficult to characterize systematically. W…
- arXiv cs.AIresearchRewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
arXiv:2609.22947v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video r…
- arXiv cs.AIresearchA Horizon-slicing Approach to Minimum Obstacle Displacement Planning for Robot Navigation
arXiv:2609.22974v1 Announce Type: cross Abstract: In this paper, we investigate the Minimum Obstacle Displacement Planning problem from a robot motion planning perspective. The problem involves determining a feasible pat…
- arXiv cs.AIresearchDual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach
arXiv:2609.22981v1 Announce Type: cross Abstract: We present a dual-locking method for securing trained neural networks that combines key-driven index permutation with PIN-based watermarking based on Sparse Quantization…
- arXiv cs.AIresearchInterpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection
arXiv:2609.23008v1 Announce Type: cross Abstract: Multi-class open-set anomaly detection requires a model to characterize the normal acceptance domain formed by multiple heterogeneous subdistributions using only class-la…
- arXiv cs.AIresearchWatching Quantum Models Think: Hilbert-Space Interpretability in Quantum Transformer Blocks
arXiv:2609.23016v1 Announce Type: cross Abstract: Deep learning models are powerful but opaque. As quantum machine learning matures, the field faces a defining choice: build quantum models that are equally opaque, or exp…
- arXiv cs.AIresearchFrom Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
arXiv:2609.23065v3 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input--output be…
- arXiv cs.AIresearchMolSC: Leveraging Substituent Contributions to Enhance Fine-grained Molecular Understanding in LLMs
arXiv:2609.23073v1 Announce Type: cross Abstract: Recent advances in natural language processing have led to molecular Large Language Models (LLMs) with strong performance across diverse chemistry tasks. However, they st…
- arXiv cs.AIresearchNeural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
arXiv:2609.23087v1 Announce Type: cross Abstract: Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOPs, capture size an…
- arXiv cs.AIresearchWhitening Inverts the Hierarchy: What the Norm of a Whitened Embedding Measures
arXiv:2609.23117v1 Announce Type: cross Abstract: Whitening a foundation-model embedding and using its squared norm as a training-free likelihood surrogate is motivated by the observation that whitened coordinates often…
- arXiv cs.AIresearchQwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation
arXiv:2609.23139v1 Announce Type: cross Abstract: Most medical vision-language models (VLMs) excel at open-ended report generation and VQA but provide limited support for structured, fine-grained clinical perception with…
- arXiv cs.AIresearchBearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics
arXiv:2609.23152v1 Announce Type: cross Abstract: Recently proposed self-supervised audio encoders learn powerful general-purpose representations of sound scenes, yet they are spatially blind. To supply the missing spati…
- arXiv cs.AIresearchEquiSELD: Efficient training of equivariant sound event localization and detection networks
arXiv:2609.23156v1 Announce Type: cross Abstract: First-order Ambisonics (FOA) signals exhibit exact O(3) symmetry: The rotation or reflection of the FOA signal modifies the direction of arrival of the sound sources, whi…