AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFrontierMath Erd\H{o}s
arXiv:2609.25050v1 Announce Type: cross Abstract: We introduce FrontierMath Erd\H{o}s (FME), a benchmark of 68 Erd\H{o}s problems that are open as of August 2026. To solve a task in FME, AI systems must resolve (prove or…
- arXiv cs.AIresearchLLM-Driven Training-free Location-Attribute Synergic Fusion: A Closed-Loop Paradigm for Dual-source Encrypted POIs and LULC Mapping
arXiv:2609.25051v1 Announce Type: cross Abstract: Dual-source encrypted points of interest (DSEP), POIs from two encrypted coordinate systems, suffer from intertwined location and attribute uncertainties, including nonli…
- arXiv cs.AIresearchLatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay
arXiv:2609.25053v1 Announce Type: cross Abstract: Can one language model hand its live memory to another without the receiver rereading the context? We demonstrate useful persistent hybrid-state transfer across one archi…
- arXiv cs.AIresearchPhysics-guided deep metric learning with continuous time embeddings for open-world radar pulse de-interleaving
arXiv:2609.25057v1 Announce Type: cross Abstract: Radar pulse de-interleaving is a foundational Electronic Support Measures (ESM) task that aims to separate chronologically interleaved pulse streams from multiple non-coo…
- arXiv cs.AIresearchFederating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach
arXiv:2609.25082v1 Announce Type: cross Abstract: Quantum machine learning (QML) is increasingly recognized as one of the most promising near-term applications of quantum computing, viewed as a next-frontier candidate be…
- arXiv cs.AIresearchYou've Seen Enough: Quality-Constrained Image Coding for Machines
arXiv:2609.25108v2 Announce Type: replace-cross Abstract: Visual data is increasingly consumed by machine-vision systems rather than by human observers. Image Coding for Machines (ICM) compresses images assuming the main…
- arXiv cs.AIresearchRachel: A general-purpose language model directs and revises retrosynthetic routes
arXiv:2609.25118v1 Announce Type: cross Abstract: Retrosynthetic planning advances through decisions that reshape the remaining chemical problem: a locally plausible disconnection can leave precursors whose chemoselectiv…
- arXiv cs.AIresearchWILSON - Multi-magnification composites as a foundation for patient-level pathology analysis and diagnostic text generation
arXiv:2609.25123v2 Announce Type: replace-cross Abstract: Pathologists examine tissue sections across multiple magnifications and slides, integrating morphological information to establish a diagnosis. In contrast, most…
- arXiv cs.AIresearchThe Probabilistic Structure of Large Language Models
arXiv:2609.25134v1 Announce Type: cross Abstract: This paper presents a probabilistic perspective on large language models (LLMs), developed with the aim of bringing together, in a single self-contained account, tools th…
- arXiv cs.AIresearchStable Unsupervised Continual Chunking with Sheaf SyncMap
arXiv:2609.25143v1 Announce Type: cross Abstract: Unsupervised Continual chunking is a fundamental problem in machine learning and neuroscience, where the goal is to identify groups of states that frequently co-occur in…
- arXiv cs.AIresearchBrain-Inspired Hierarchical Modularity for General Continual Learning
arXiv:2609.25146v1 Announce Type: cross Abstract: Continual learning, the ability to learn from sequential experience while retaining and adapting prior knowledge, is central to intelligent systems operating in changing…
- arXiv cs.AIresearchTowards Sustainable Magnetic Resonance Imaging: Insights from long-term, high-resolution energy recordings across an entire scanner fleet
arXiv:2609.25150v1 Announce Type: cross Abstract: Magnetic resonance imaging (MRI) is among the most energy-intensive diagnostic modalities in healthcare, yet its energy consumption and the factors influencing it remain…
- arXiv cs.AIresearchExposing Blind Spots in Deep Imbalanced Regression Evaluation
arXiv:2609.25152v1 Announce Type: cross Abstract: Deep Imbalanced Regression (DIR) addresses a common failure mode of regression models: target distributions are highly non-uniform, causing models to perform best in dens…
- arXiv cs.AIresearchBenchmarking Neural Defend ARCAS 1B: A Foundational Multimodal Deepfake Detection Model
arXiv:2609.25154v1 Announce Type: cross Abstract: AI-generated imagery evolves faster than benchmark-specific detector evaluations, making a single score an incomplete account of generalization. This paper evaluates Neur…
- arXiv cs.AIresearchMitigating Sequential Reappearance in Diffusion Data-Point Unlearning
arXiv:2609.25166v2 Announce Type: replace-cross Abstract: Diffusion data-point unlearning is typically evaluated immediately after each deletion, even though subsequent requests may repeatedly update the same model. We i…
- arXiv cs.AIresearchMulti-Term Fourier Graph Neural Network with Sample Relationship Learning for Enhanced Remaining Useful Life Prediction
arXiv:2609.25179v1 Announce Type: cross Abstract: Predicting the remaining useful life (RUL) is essential for effective predictive maintenance. Spatio-Temporal Graph Neural Networks (ST-GNNs), which can model both tempor…
- arXiv cs.AIresearchFrom Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health
arXiv:2609.25186v1 Announce Type: cross Abstract: The rising global prevalence of mental health conditions, together with longstanding barriers in traditional healthcare, such as limited resources, high cost, stigma, and…
- arXiv cs.AIresearchGroundedGEO: Auditing the Evidence Gap in Generative Search Rankings
arXiv:2609.25189v1 Announce Type: cross Abstract: Generative search systems rank products and services for consequential decisions, and publishers can cheaply make candidate text look relevant. Yet evidence status is not…
- arXiv cs.AIresearchHow Children Design and Reason about Trustworthy AI Chatbots
arXiv:2609.25244v5 Announce Type: replace-cross Abstract: Children increasingly interact with AI chatbots, making trust calibration essential to AI literacy. Prior research has examined children's trust in AI mainly as u…
- arXiv cs.AIresearchGeometric and Semantic Coupling for Interaction Understanding in 3D Scenes
arXiv:2609.25247v2 Announce Type: replace-cross Abstract: Understanding interaction in a 3D scene requires recovering movable parts, their motion, and where they can be operated. These quantities are related, and their p…
- arXiv cs.AIresearchVLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models
arXiv:2609.25376v1 Announce Type: cross Abstract: Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interaction between layer…
- arXiv cs.AIresearchPICPIs: Prediction-Interval-Conditional Prediction Intervals
arXiv:2609.25388v2 Announce Type: replace-cross Abstract: A classical question in statistics is which observable quantities to condition on when drawing inferences about unobservable targets. For conformal prediction in…
- arXiv cs.AIresearchDeep Reinforcement Learning on Item-Compatibility Graphs for One-Dimensional Bin Packing
arXiv:2609.25397v1 Announce Type: cross Abstract: The one-dimensional bin packing problem (1D-BPP) is a classical NP-hard combinatorial optimization problem with applications ranging from logistics and manufacturing to c…
- arXiv cs.AIresearchLightweight Ranking Heads: Accelerating Multi-Task Experimentation in Production Recommender Systems
arXiv:2609.25433v1 Announce Type: cross Abstract: Modern production-scale recommender systems rely on complex, multi-task ranking models. Introducing new prediction tasks into these massive systems often causes bottlenec…
- arXiv cs.AIresearchA Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization
arXiv:2609.25471v1 Announce Type: cross Abstract: Semi-supervised federated learning (SSFL) trains models on clients' unlabeled data using a teacher to generate pseudo-labels, with a small labeled seed dataset on the ser…
- arXiv cs.AIresearchTerminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining
arXiv:2609.25482v1 Announce Type: cross Abstract: Large language model (LLM) pretraining conventionally returns the raw final iterate. This couples two design choices: the learning-rate schedule that generates the parame…
- arXiv cs.AIresearchRGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models
arXiv:2609.25492v1 Announce Type: cross Abstract: Large vision-language models (VLMs) can be efficiently deployed under stringent memory and latency constraints through post training quantization (PTQ). However, most PTQ…
- arXiv cs.AIresearchUniversal Fractal Natural Language Decision Map: Real-Time Edge Triage Across Heterogeneous Domains
arXiv:2609.25498v2 Announce Type: replace-cross Abstract: Deploying Large Language Models for runtime operational triage incurs prohibitive latency (>100-500 ms), high VRAM requirements (>4-8 GB), and excessive energy di…
- arXiv cs.AIresearchHill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training
arXiv:2609.25510v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can improve solutions to verifiable scientific and algorithmic problems by spending additional computation at test time. Recent syste…
- arXiv cs.AIresearchWest-WRF AI 2-km: High-Resolution Prediction of Integrated Vapor Transport and Precipitation
arXiv:2609.25512v1 Announce Type: cross Abstract: We introduce a stretched-grid artificial intelligence (AI) weather forecasting model with 2-km resolution over the western United States and part of the Northeast Pacific…
- arXiv cs.AIresearchCompressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference
arXiv:2609.25537v1 Announce Type: cross Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing latency, energy consumpt…
- arXiv cs.AIresearchA JEPA Recipe for Tabular Foundation Models
arXiv:2609.25541v1 Announce Type: cross Abstract: Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeCun, 2022; Assran e…
- arXiv cs.AIresearchDefaultGNN: A Dual-Perspective GNN Framework for Predicting Corporate Default from Buyer-Seller Transaction Networks
arXiv:2609.25542v1 Announce Type: cross Abstract: Corporate default prediction is a core problem in financial risk management, yet traditional credit models rely heavily on financial statements that are often sparse or u…
- arXiv cs.AIresearchIndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models
arXiv:2609.25562v2 Announce Type: replace-cross Abstract: Open robot policies increasingly follow two paradigms: vision-language-action models (VLAs) directly map observations and instructions to actions, whereas world-a…
- arXiv cs.AIresearchRootQuantV2: Adapting a Vision Foundation Model for Root-Trait Regression from Minirhizotron Imagery
arXiv:2609.25567v1 Announce Type: cross Abstract: A lack of high-throughput phenotyping solutions for root traits in field-grown crops has severely constrained understanding and improvement of below-ground traits and pro…
- arXiv cs.AIresearchEMGBlend: Heterogeneity-Aware Self-Supervised Pretraining for Gesture and Force Decoding
arXiv:2609.25582v1 Announce Type: cross Abstract: Public surface electromyography (EMG) datasets vary widely in electrode layout, channel count, frequency support, and size. Simply mixing them for pretraining can misalig…
- arXiv cs.AIresearchDeflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus
arXiv:2609.25586v1 Announce Type: cross Abstract: Large language models increasingly support decisions where values are in tension, yet little is known about whether interacting with them changes which values users prior…
- arXiv cs.AIresearchWhat Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation
arXiv:2609.25623v2 Announce Type: replace-cross Abstract: More privileged information does not always make a better teacher. We study this tension in on-policy self-distillation (OPSD), where a self-teacher scores the st…
- arXiv cs.AIresearchAn Exploratory Replica-Overlap Probe of the Grokking Transition
arXiv:2609.25634v1 Announce Type: cross Abstract: We trained 64 independently seeded networks in four configurations, continuing each to sustained convergence or a 40,000-epoch ceiling. We then asked whether an RSB-inspi…
- arXiv cs.AIresearchWhen Quantum Meets AI: Quantum Methods for Machine Learning and Machine Learning Methods for Quantum Systems
arXiv:2609.25641v1 Announce Type: cross Abstract: This thesis studies the intersection of quantum computing and artificial intelligence in two directions: quantum methods for machine learning and machine learning methods…
- arXiv cs.AIresearchFrom Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs
arXiv:2609.25655v1 Announce Type: cross Abstract: As large language models (LLMs) scale rapidly, dense full-parameter adaptation becomes increasingly expensive, motivating sparse and modular architectures such as Mixture…
- arXiv cs.AIresearchTeaching Reinforcement Learning and Humanoid Robotics to High-School Students: An Expert-Validated Curriculum Design on a Low-Cost Open Platform
arXiv:2609.25674v1 Announce Type: cross Abstract: Lower cost open source robots and reinforcement learning (RL) simulation tools create new opportunities for precollege students to engage with contemporary robotics. Howe…
- arXiv cs.AIresearchInterpretable AI plus Handheld, Portable Retinal Photographs: A Low-Cost Glaucoma Screening Solution for West Africa
arXiv:2609.25697v1 Announce Type: cross Abstract: Purpose: To develop and evaluate an interpretable artificial intelligence (AI) framework for glaucoma screening from low-cost portable, handheld retinal fundus photograph…
- arXiv cs.AIresearchSlow Decay and Silenced Expression: Iterated Subliminal Trait Transfer in Language-Model Lineages
arXiv:2609.25721v1 Announce Type: cross Abstract: Language models are increasingly trained on the outputs of other models, forming chains that we call lineages, in which a trait present in one generation can pass to the…
- arXiv cs.AIresearchSelf-Supervised Combinatorial Optimization with Constraints via Frank-Wolfe
arXiv:2609.25728v1 Announce Type: cross Abstract: Self-supervised learning for combinatorial optimization has emerged as a promising paradigm for solving discrete optimization problems with neural networks, but a central…
- arXiv cs.AIresearchBeyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence
arXiv:2609.25735v1 Announce Type: cross Abstract: Class-balanced replay controls class frequency but does not determine the interval between successive replay appearances of a class. We study this interval, the rehearsal…
- arXiv cs.AIresearchSyndrome, Synergy, and Safety: Structured Reasoning and Knowledge-Driven Alignment for TCM Prescription Generation
arXiv:2609.25755v1 Announce Type: cross Abstract: Applying large language models to Traditional Chinese Medicine (TCM) prescription generation reveals three clinically critical gaps: models produce end-to-end mappings wi…
- arXiv cs.AIresearchVideo-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models
arXiv:2609.25773v2 Announce Type: replace-cross Abstract: HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes errors that c…
- arXiv cs.AIresearchEvaluating Accuracy and Probabilistic Reliability of Zero-Shot Time Series Foundation Models
arXiv:2609.25788v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) promise a paradigm shift toward zero-shot forecasting by eliminating task-specific training. However, existing works often overlook…
- arXiv cs.AIresearchYou Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs
arXiv:2609.25809v1 Announce Type: cross Abstract: Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly many selected per toke…