AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
arXiv:2609.30199v2 Announce Type: replace Abstract: Scientific discovery begins where known problems end. There, AI systems must engage in exploration: framing hypotheses, designing experiments, and iterating on the resu…
- arXiv cs.AIresearchAD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
arXiv:2609.30264v2 Announce Type: replace Abstract: Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A…
- arXiv cs.AIresearchCaliPPer: quantifying, predicting and improving AI model performance for binding prediction
arXiv:2606.07258v1 Announce Type: cross Abstract: Binding prediction models accelerate therapeutic antibody and TCR discovery, but their performance on new datasets is unpredictable, often leading to low discovery rates.…
- arXiv cs.AIresearchHybrid Variational Quantum-Classical Framework with Adaptive Weighting and Efficiency Assessment
arXiv:2609.28491v1 Announce Type: cross Abstract: Hybrid quantum-classical neural networks have emerged as a promising approach for leveraging quantum computing in machine learning while mitigating current hardware limit…
- arXiv cs.AIresearchAI in Science: Early Insights
arXiv:2609.28504v2 Announce Type: replace-cross Abstract: Scientific progress is a key driver of economic growth and prosperity. There is great excitement - but also concerns - about the impacts of AI on science, but so…
- arXiv cs.AIresearchCrossScale-GLIO: Topology-Preserving Vision-Language Alignment of MRI and Whole-Slide Histopathology for Diffuse Glioma
arXiv:2609.28524v1 Announce Type: cross Abstract: Magnetic resonance imaging and histopathology observe the same glioma at radically different scales. We present CrossScale-GLIO, a visual multimodal framework that repres…
- arXiv cs.AIresearchSMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion
arXiv:2609.28553v1 Announce Type: cross Abstract: Drug toxicity prediction is critical for reducing late-stage attrition in drug discovery, yet remains challenging due to severe class imbalance, scaffold-based generaliza…
- arXiv cs.AIresearchSpeculative Evaluation of Stochastic LLMs
arXiv:2609.28560v1 Announce Type: cross Abstract: Evaluating a stochastic large language model is costly: benchmark scores estimate expected performance from randomized rollouts, yet uniform repetition ignores sharp diff…
- arXiv cs.AIresearchWhen Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages
arXiv:2609.28565v1 Announce Type: cross Abstract: Post hoc explanation methods such as SHAP and LIME are widely used to interpret text classifiers, but their visualizations are mainly designed for left-to-right languages…
- arXiv cs.AIresearchAuditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning
arXiv:2609.28581v1 Announce Type: cross Abstract: Reinforcement-learning (RL) policies are often distributed as opaque neural checkpoints, while training logs show that a run occurred without explaining what the policy l…
- arXiv cs.AIresearchSGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models
arXiv:2609.28582v1 Announce Type: cross Abstract: The recent emergence of Time Series Foundation Models (TSFMs) has significantly advanced multi-step forecasting performance, enabling accurate predictions over extended f…
- arXiv cs.AIresearchNumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees
arXiv:2609.28587v1 Announce Type: cross Abstract: Large language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these interfaces do not di…
- arXiv cs.AIresearchLearning to Discover Interesting Mathematics
arXiv:2609.28603v1 Announce Type: cross Abstract: Recently, Large Language Models (LLMs) have been increasingly able to solve advanced mathematical problems, including many that have been open for decades. This opens the…
- arXiv cs.AIresearchUO-FIE: Combining Exact-Label Supervision with Graded Utility for Factivity Inference
arXiv:2609.28605v1 Announce Type: cross Abstract: The Factivity Inference Evaluation 2026 (FIE2026) classifies Chinese context-hypothesis pairs into nine ordered factivity intervals. Its evaluation metric rewards both ex…
- arXiv cs.AIresearchThe Fellowship of the Query: Learning Retrieval Actions
arXiv:2609.28653v1 Announce Type: cross Abstract: Retrieval-augmented question answering requires control decisions about when to decompose a question, search, reformulate, extract evidence, synthesize facts, verify prog…
- arXiv cs.AIresearchBeyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies
arXiv:2609.28670v1 Announce Type: cross Abstract: Graph-based world models have recently emerged as a means of learning transitions over relational state representations. However, existing approaches are largely limited…
- arXiv cs.AIresearchAn Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection
arXiv:2609.28703v1 Announce Type: cross Abstract: Hate speech on social media poses serious risks to social harmony, mental well-being, and public safety, making its timely and accurate detection essential for content mo…
- arXiv cs.AIresearchTemporal Learning for End-Effector Position Estimation under Aerodynamic Disturbances in Aerial Continuum Manipulation
arXiv:2609.28716v1 Announce Type: cross Abstract: This paper investigates temporal neural networks for \mbox{end-effector} position \mbox{estimation} of an aerial continuum manipulator (ACM) operating under aerodynamic e…
- arXiv cs.AIresearchTechnical Manual for Toolkit for Confidence-Corpus Consistency, Corpus Absorption and Rule Learning via Fine-Tuning on a Fabricated Corpus
arXiv:2609.28747v2 Announce Type: replace-cross Abstract: This manual documents version 2.0.0 of an open toolkit for fine-tuning small causal language models on fabricated and rule-governed arithmetic corpora and measuri…
- arXiv cs.AIresearchKathDB-FAO: Synthesized Query Plans in a Multimodal DBMS
arXiv:2609.28761v1 Announce Type: cross Abstract: We design, implement, and evaluate KathDB-FAO, a new query evaluation subsystem for our KathDB multimodal DBMS. KathDB-FAO takes as input a query in natural language (NL)…
- arXiv cs.AIresearchDrGait: Biomechanically Grounded Visual Reasoning for Interpretable Clinical Gait Analysis
arXiv:2609.28796v1 Announce Type: cross Abstract: Current automated gait analysis for clinical applications relies on uninterpretable black-box classifiers. Although Vision-Language Models (VLMs) offer strong reasoning c…
- arXiv cs.AIresearchA Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations
arXiv:2609.28806v1 Announce Type: cross Abstract: Full-duplex dialogue systems, which listen while speaking, must distinguish a completed turn from a pause within a turn and an interruption that requests a turn from a br…
- arXiv cs.AIresearchKeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalization
arXiv:2609.28818v1 Announce Type: cross Abstract: Generalization in robotic manipulation requires policies to perform tasks across diverse unseen object instances that vary in shape, size, and pose. However, conventional…
- arXiv cs.AIresearchM$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease
arXiv:2609.28836v1 Announce Type: cross Abstract: While various multimodal methods combining imaging and tabular data for Alzheimer's disease (AD) diagnosis were proposed, they are often limited in generalization across…
- arXiv cs.AIresearchBroadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputs
arXiv:2609.28879v1 Announce Type: cross Abstract: Audio-language models can produce confident answers unsupported by the audio, motivating uncertainty estimates that identify unreliable responses. We compare probability-…
- arXiv cs.AIresearchRobots That Take Initiative: A Framework for Building and Evaluating Proactive Robots
arXiv:2609.28910v1 Announce Type: cross Abstract: Effective robot assistance beyond narrow roles and repetitive tasks requires robots to be proactive - to decide what needs to be done rather than waiting to be told. Whil…
- arXiv cs.AIresearchCross-Country Code-Mixing for Generative Recommendation
arXiv:2609.28972v1 Announce Type: cross Abstract: Cross-country recommendation on modern e-commerce platforms is typically deployed with disjoint user and item ID spaces across markets, removing the shared anchors that c…
- arXiv cs.AIresearchCrossSafe: Towards Cross-Embodiment Latent Safety Filters
arXiv:2609.28984v2 Announce Type: replace-cross Abstract: Cross-embodiment learning has shown that a single model, such as a vision-language-action (VLA) model, can learn state representations and manipulation skills tha…
- arXiv cs.AIresearchDesign and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots
arXiv:2609.29043v1 Announce Type: cross Abstract: General Purpose Service Robot (GPSR) tasks, as defined in the RoboCup@Home benchmark, require robots to interpret diverse natural language commands and generate multi-ste…
- arXiv cs.AIresearchThe Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning
arXiv:2609.29045v1 Announce Type: cross Abstract: Open-weight LLMs give downstream users control over the inference stack, but this flexibility can undermine post-release guarantees that sensitive knowledge has been modi…
- arXiv cs.AIresearchEmpath: Tracing Multi-Level Emotion Dynamics in Crisis Counseling Dialogues
arXiv:2609.29056v1 Announce Type: cross Abstract: Emotion dynamics are critical for understanding crisis-support conversations, yet most computational work treats emotion as static utterance-level labels. We introduce EM…
- arXiv cs.AIresearchEIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection
arXiv:2609.29064v1 Announce Type: cross Abstract: The proliferation of photorealistic AI-generated images demands robust detection methods that generalize across diverse generative models. While existing approaches targe…
- arXiv cs.AIresearchCan Classical Semantic-Extractive Summarization Be Evaluated in Hindi? A Replication Study
arXiv:2609.29090v1 Announce Type: cross Abstract: We replicate the distributional-semantics extractive summarisation method of Mohd, Jan and Shah (2020) and adapt it to Hindi, substituting a Devanagari-appropriate compon…
- arXiv cs.AIresearchDAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models
arXiv:2609.29092v1 Announce Type: cross Abstract: Vision-based legged locomotion methods assume clean depth at training time and rely on hand-tuned post-processing filters at deployment. However, filter parameters are ra…
- arXiv cs.AIresearchWildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model
arXiv:2609.29106v1 Announce Type: cross Abstract: 3D foundation models recover video cameras and geometry in one forward pass, but some of the strongest are up to scale. Joint people-scene reconstruction then requires tw…
- arXiv cs.AIresearchLess is More: Encoder-only Audio-Visual Segmentation
arXiv:2609.29121v1 Announce Type: cross Abstract: Audio-Visual Semantic Segmentation (AVSS) aims to identify, segment, and classify sound-emitting objects in video frames. Previous Transformer-based AVSS approaches large…
- arXiv cs.AIresearchTag-Aware Structured Text Translation: Towards a Systematic Understanding
arXiv:2609.29131v1 Announce Type: cross Abstract: Internet texts are replete with format tags that carry structural, semantic, and functional meaning. Current large language model (LLM)-based translation systems struggle…
- arXiv cs.AIresearchNot Every Token Is Worth Distilling: Selective Supervision for Direct-OPD
arXiv:2609.29142v2 Announce Type: replace-cross Abstract: Direct On-Policy Distillation (Direct-OPD) transfers reinforcement-learning-induced policy improvements from a small model to a larger student by using the token-…
- arXiv cs.AIresearchAI-Moderated Interviews for Market Research and Digital Twins Calibration
arXiv:2609.29143v1 Announce Type: cross Abstract: AI-moderated interviews are emerging as a scalable market-research method for generating consumer insights and building consumer "digital twins." Yet it remains unclear w…
- arXiv cs.AIresearchMed-AR: Autoregressive Vision-Language Pretraining for Long-Tailed Chest X-Ray Classification and Uncertainty-Aware Evaluation
arXiv:2609.29156v1 Announce Type: cross Abstract: Long-tailed chest X-ray classification requires visual representations that capture both common abnormalities and subtle, infrequent findings. We propose Med-AR-8B and Me…
- arXiv cs.AIresearchSpot, Separate, and Enhance: Fully Generative Approach for Audio Mixing
arXiv:2609.29169v1 Announce Type: cross Abstract: We introduce Spot, Separate, and Enhance (SSE), the first multimodal, user-guided generative model for audio remixing and enhancement. SSE enhances video content by rebal…
- arXiv cs.AIresearchFB-GDM: Fully-Bayesian Guided Diffusion Models for High-Dimensional Linear Inverse Problems via Unsupervised Variational Inference
arXiv:2609.29216v1 Announce Type: cross Abstract: Diffusion models are powerful priors for linear inverse problems, but the reference guidance methods, Diffusion Posterior Sampling (DPS) and Pseudoinverse-Guided Diffusio…
- arXiv cs.AIresearchPost-Training Leaves Behavioral Shadows on Unrelated Decisions
arXiv:2609.29233v1 Announce Type: cross Abstract: We find that language models can transfer capabilities through task-unrelated text. Post-training typically improves language models using task-specific data. Prior work…
- arXiv cs.AIresearchTOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution
arXiv:2609.29240v1 Announce Type: cross Abstract: Text image super-resolution (TSR) aims to recover visually faithful and readable text under unknown degradations. Existing diffusion-based methods typically rely on multi…
- arXiv cs.AIresearchNo More Free Lunch: Corpus Task Complexity Matters as Corpora Grow
arXiv:2609.29245v1 Announce Type: cross Abstract: Given a large corpus, the questions one might ask can vary -- from "When was the first human heart transplant?" to "What are all the contradictory claims in this literatu…
- arXiv cs.AIresearchDeep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors
arXiv:2609.29256v1 Announce Type: cross Abstract: Glaucoma is the leading cause of irreversible blindness, and timely identification of fast progressors is essential to prevent disability. Current practice estimates prog…
- arXiv cs.AIresearchTP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models
arXiv:2609.29264v1 Announce Type: cross Abstract: Artificial intelligence (AI) models are increasingly deployed through remote services, making model misappropriation a growing concern. Existing approaches, including wat…
- arXiv cs.AIresearchReasoning Instructions Can Break Answer Decoding in Vision--Language Models
arXiv:2609.29278v1 Announce Type: cross Abstract: Chain-of-thought (CoT) instructions can distort multiple-choice VLM evaluation when a scorer appends a reasoning cue but reads answer-label logits before the model genera…
- arXiv cs.AIresearchNeuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting
arXiv:2609.29317v1 Announce Type: cross Abstract: Time series analysis is fundamental in domains such as finance, healthcare, and meteorology. Real-world time series often exhibit multiscale characteristics shaped by div…
- arXiv cs.AIresearchHyperbolic Multimodal Continual Learning: A Closest-Admissible Solution
arXiv:2609.29329v1 Announce Type: cross Abstract: Existing continual-learning methods protect parameters, replayed examples, or Euclidean feature subspaces. When applied to hyperbolic multimodal models, they do not expli…