AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRuby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition
arXiv:2609.27289v1 Announce Type: cross Abstract: Conventional Japanese automatic speech recognition (ASR) is supervised by an orthographic transcript, although the same written form can correspond to different lexical r…
- arXiv cs.AIresearchBeyond the Illusion of Power: Calibrating Quasi-Experiments in Observational IS
arXiv:2609.27299v1 Announce Type: cross Abstract: Information systems (IS) researchers increasingly use quasi-experimental methods such as difference-in-differences (DiD) and instrumental variables (IV) to recover causal…
- arXiv cs.AIresearchMulti-View Fusion for Encrypted C2 Detection: A Leakage-Controlled Measurement Study of Evaluation Pitfalls
arXiv:2609.27311v1 Announce Type: cross Abstract: Command-and-control (C2) traffic increasingly hides within TLS, so defenders now apply machine learning to traffic metadata. Many studies assume that combining two metada…
- arXiv cs.AIresearchTurning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning
arXiv:2609.27312v1 Announce Type: cross Abstract: Robots deployed for competitive tasks must outmaneuver their opponents without sacrificing safety. Existing approaches, including safe reinforcement learning (RL), train…
- arXiv cs.AIresearchEvolving Inspectable O-RAN Slicing xApps with LLMs
arXiv:2609.27337v1 Announce Type: cross Abstract: Open RAN (O-RAN) slicing xApps must adapt resource allocations to changing channel conditions and traffic demands while meeting service-level agreements (SLAs). Deep rein…
- arXiv cs.AIresearchConstraint-Driven Context Engineering: Designing Domain Interfaces for AI Systems
arXiv:2609.27354v1 Announce Type: cross Abstract: Generative AI systems are increasingly deployed to address domain problems. These systems operate under technical, regulatory, institutional, and normative constraints th…
- arXiv cs.AIresearchQuantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction
arXiv:2609.27355v2 Announce Type: replace-cross Abstract: Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post-training com…
- arXiv cs.AIresearchGeometry-Conditioned Visual Place Recognition in Natural Environments
arXiv:2609.27370v1 Announce Type: cross Abstract: Visual Place Recognition (VPR) in natural environments remains challenging due to repetitive vegetation, sparse distinctive landmarks, and substantial appearance and view…
- arXiv cs.AIresearchNeither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models
arXiv:2609.27372v1 Announce Type: cross Abstract: Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by completeness of the prior…
- arXiv cs.AIresearchPlanned Test-Time Scaling with Coordinated Reasoning Paths
arXiv:2609.27374v1 Announce Type: cross Abstract: Test-time scaling with parallel branches is widely adopted to improve performance on challenging reasoning tasks. The predominant approach, repeated sampling, draws branc…
- arXiv cs.AIresearchPsychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models
arXiv:2609.27378v1 Announce Type: cross Abstract: End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipulation. We formalize…
- arXiv cs.AIresearchForget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech
arXiv:2609.27399v1 Announce Type: cross Abstract: Recent zero-shot text-to-speech (ZS-TTS) systems can reproduce a speaker's voice with high fidelity from only a few seconds of reference speech, raising concerns over una…
- arXiv cs.AIresearchWhat Looks Like a Capability Limit in Vision-Language Models Is a Readout Limit
arXiv:2609.27408v1 Announce Type: cross Abstract: Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate. That convention is treated as neutral. We…
- arXiv cs.AIresearchQuantum Reinforcement Learning for Cost and Delay Tradeoffs in Quantum Cloud Orchestration
arXiv:2609.27446v1 Announce Type: cross Abstract: Quantum cloud computing, delivered through the quantum-as-a-service (QaaS) model, provides access to quantum computing resources. However, applying uniform time-based pri…
- arXiv cs.AIresearchBEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models
arXiv:2609.27450v1 Announce Type: cross Abstract: Vision-language-action (VLA) models handle long-horizon manipulation, yet success hinges on a few precision-critical phases where millimeter-scale errors undo all prior p…
- arXiv cs.AIresearchKairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs
arXiv:2609.27467v1 Announce Type: cross Abstract: Long-term autonomy in human-populated environments requires anticipating whether and how people will move at times a robot has not yet observed. Existing representations…
- arXiv cs.AIresearchPassing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound
arXiv:2609.27489v1 Announce Type: cross Abstract: This paper introduces Passing, an interactive audiovisual installation that generates an endless journey from a single continuous monorail-window recording by reconstruct…
- arXiv cs.AIresearchUncheatable Eval: Dynamic Compression-Based Evaluation of Language Models
arXiv:2609.27510v1 Announce Type: cross Abstract: Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and undermining the relia…
- arXiv cs.AIresearchNV-Reason-CT: 3D Visual Language Model for CT Analysis
arXiv:2609.27511v2 Announce Type: replace-cross Abstract: We present NV-Reason-CT, a generative vision--language model for chest and abdominal CT combining native 3D visual encoding with radiologist-guided reasoning. The…
- arXiv cs.AIresearchPhyMo: A Physical-Field Modality for Multimodal AI4Physics
arXiv:2609.27554v1 Announce Type: cross Abstract: Multimodal learning is emerging as a powerful paradigm for AI for Physics (AI4Physics), where predicting physical systems requires the joint interpretation of heterogeneo…
- arXiv cs.AIresearchTNLearn: An Open Source Python Package for Task-based Neurons
arXiv:2609.27564v1 Announce Type: cross Abstract: The brain does not rely on a single type of neuron to perform all kinds of tasks; instead, it designs different neurons for different tasks. The concept of task-based neu…
- arXiv cs.AIresearchDCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment
arXiv:2609.27572v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as a key paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing reward systems, such…
- arXiv cs.AIresearchHidden not Deleted: How Networks Suppress Entangled Features
arXiv:2609.27593v1 Announce Type: cross Abstract: Concept erasure methods that operate via linear projection assume that features occupy separable subspaces. We show this assumption fails under dense superposition: when…
- arXiv cs.AIresearchWhen Context Misleads: In-context Learning with Jurisdiction in Large Language Models
arXiv:2609.27603v2 Announce Type: replace-cross Abstract: In-Context Learning (ICL) has become a cornerstone of modern LLM deployment. However, existing ICL post-training methods have a critical blind spot: they excel at…
- arXiv cs.AIresearchCan Jev Judge Radiology Reports? Evaluating a System One Model for Clinical Factuality
arXiv:2609.27607v1 Announce Type: cross Abstract: An AI-generated radiology report can resemble a physician's report while omitting an abnormality, adding an unsupported finding, or reversing its presence. Measuring thes…
- arXiv cs.AIresearchInGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation
arXiv:2609.27620v1 Announce Type: cross Abstract: Modern text-to-image (T2I) models generate high-quality images from arbitrary user prompts, yet they can just as easily produce not-safe-for-work (NSFW) content. Conventi…
- arXiv cs.AIresearchLearning Local Heterogeneity and Cross-Region Context for Large-Scale Traffic Forecasting
arXiv:2609.27637v1 Announce Type: cross Abstract: Traffic flow forecasting is essential to intelligent transportation systems. Large-scale traffic forecasting requires jointly modeling local spatial dependencies and cros…
- arXiv cs.AIresearchInternW0: A Foundational Physical World Model for Efficient Real-World Interactions
arXiv:2609.27656v1 Announce Type: cross Abstract: Physical intelligence requires more than predicting how the world may evolve: predictions must remain actionable as the world continues to change. We introduce InternW0,…
- arXiv cs.AIresearchFLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
arXiv:2609.27657v1 Announce Type: cross Abstract: Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion d…
- arXiv cs.AIresearchThe Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA
arXiv:2609.27669v1 Announce Type: cross Abstract: Small language models (SLMs) are increasingly paired with knowledge graphs (KGs), yet end-to-end KG question answering conflates graph access, search, navigation, reasoni…
- arXiv cs.AIresearchAI-Driven Neural Surrogates for In Silico Design of Cognitive-Affective Neuromodulation Targets
arXiv:2609.27729v1 Announce Type: cross Abstract: In neuropsychiatry, the primary goal is often not only to decode brain activity but to change it, for example to lessen a negative affective bias or an overly salient mem…
- arXiv cs.AIresearchInfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies
arXiv:2609.27734v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies often rely strongly on the camera viewpoints seen during training, causing substantial performance degradation when deployed from un…
- arXiv cs.AIresearchHard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives
arXiv:2609.27758v1 Announce Type: cross Abstract: Safety alignment in large language models is trained primarily in English, and recent work reports that the underlying harmfulness representation survives translation: En…
- arXiv cs.AIresearchBackdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning
arXiv:2609.27760v2 Announce Type: replace-cross Abstract: Federated learning enables distributed training without requiring clients to share their raw data. However, its reliance on the integrity of the client-submitted…
- arXiv cs.AIresearchEidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA
arXiv:2609.27784v1 Announce Type: cross Abstract: Semi-structured documents are ubiquitous in scientific reports, financial statements, and technical manuals. Question answering over such documents requires simultaneous…
- arXiv cs.AIresearchEvaluating ADC-only deep learning pipelines for breast cancer detection and segmentation using standalone diffusion-weighted MRI
arXiv:2609.27815v1 Announce Type: cross Abstract: Dynamic contrast-enhanced (DCE) imaging is the gold standard technique for the detection and characterization of breast cancer using magnetic resonance imaging (MRI). How…
- arXiv cs.AIresearchSafe Multi-Robot Coordination via VLM-LLM Reasoning and Reachability Analysis
arXiv:2609.27816v1 Announce Type: cross Abstract: Safe coordination in heterogeneous machine-to-machine (M2M) robotic systems is challenging when robots differ in sensing capabilities, environmental awareness, and motion…
- arXiv cs.AIresearchA Non-Invasive Cloud-Based Migration Strategy for Post-Quantum Cybersecurity in Smart HVAC Systems: Architecture, Implementation, and Empirical Evaluation
arXiv:2609.27828v1 Announce Type: cross Abstract: Legacy smart HVAC controllers rely on vendor-cloud TLS secured by ECDH and RSA, both broken by Shor's algorithm, and typical 10-15 year lifespans mean today's devices rem…
- arXiv cs.AIresearchQuery Implied Generative Engine Optimization
arXiv:2609.27845v1 Announce Type: cross Abstract: The landscape of search has changed drastically with how people look for information online. Traditional search engines are being replaced by Generative Search Engines (G…
- arXiv cs.AIresearchWhat Changed? Drift Detection with Real, Virtual, and Incomparable Diagnosis
arXiv:2609.27865v1 Announce Type: cross Abstract: Sharing a deep encoder does not, by itself, fix the central confound of task-comparison scores. We show that cross-evaluated heads on a frozen shared representation inher…
- arXiv cs.AIresearchA Shared Encoder Is Not a Shared Task: Conditional Comparison for Deep Expert Pools
arXiv:2609.27866v1 Announce Type: cross Abstract: Sharing a deep encoder does not, by itself, fix the central confound of task-comparison scores. We show that cross-evaluated heads on a frozen shared representation inher…
- arXiv cs.AIresearchTopoGS: Topology-Aware Anchor Feature Aggregation for Large-Scale 3D Gaussian Splatting
arXiv:2609.27868v1 Announce Type: cross Abstract: Octree-based 3D Gaussian Splatting organizes anchors into multi-level hierarchies for level-of-detail rendering, but features at different levels are typically optimized…
- arXiv cs.AIresearchRelCheck: Dual-Evidence Spatial Grounding for VLM Hallucination Correction
arXiv:2609.27890v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) fre- quently generate text that is inconsistent with the input image. While object- and attribute-level hallucinations have recei…
- arXiv cs.AIresearchSpread and Scale: What Determines Whether Test-Time Budget Allocation Pays
arXiv:2609.27917v1 Announce Type: cross Abstract: Neural combinatorial optimization solvers generate many candidate solutions per instance and report the best one found, using the same sample budget for every instance re…
- arXiv cs.AIresearchRiemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices
arXiv:2609.27982v1 Announce Type: cross Abstract: In this paper, we are concerned with matrices formed by block-diagonal factors interleaved with fixed permutations -- a flexible family of structured matrices. This class…
- arXiv cs.AIresearchControlled Attribute-Specific Summarization of Interrogative Dialogues
arXiv:2609.28004v1 Announce Type: cross Abstract: Effective summarization of interrogative dialogues is a critical task in forensic and investigative settings, requiring high factual accuracy, coherence, and attribute-sp…
- arXiv cs.AIresearchPISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning
arXiv:2609.28022v1 Announce Type: cross Abstract: Space weather early warning depends on detecting solar wind transients in in-situ measurements at the first Sun-Earth Lagrange point (L1), before they reach Earth. Fixed…
- arXiv cs.AIresearchEvaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing
arXiv:2609.28026v1 Announce Type: cross Abstract: We investigate whether state-of-the-art large language models (LLMs) generate feedback that reflects the pedagogical practices of expert teachers in terms of feedback foc…
- arXiv cs.AIresearchTEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval
arXiv:2609.28048v1 Announce Type: cross Abstract: Modern information retrieval (IR) systems rarely represent time, yet many information needs depend on it: in clinical, journalistic, and legal search, when an event occur…
- arXiv cs.AIresearchPrompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings
arXiv:2609.28049v1 Announce Type: cross Abstract: Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is rob…