AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchTopology-Stratified Materials Discovery with A Flow-Based Generative Model
arXiv:2609.26547v1 Announce Type: cross Abstract: Accurate generation of crystal structures is the foundation to the discovery of high-performance materials for extreme-environment applications, such as aerospace, additi…
- arXiv cs.AIresearchReceptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models
arXiv:2609.26579v1 Announce Type: cross Abstract: A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In parallel, work on soc…
- arXiv cs.AIresearchHierarchical GNNs for power flow: letting physics shape the hierarchy
arXiv:2609.26603v3 Announce Type: replace-cross Abstract: Hierarchical latent communication improves the generalization of a power-flow model, shared across three grids, to new operating scenarios. The module exchanges i…
- arXiv cs.AIresearchGreedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference
arXiv:2609.26621v1 Announce Type: cross Abstract: Greedy decoding from large language models is commonly treated as deterministic. We show it is not precision-invariant: the same model, prompt, and decoding algorithm pro…
- arXiv cs.AIresearchCapable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
arXiv:2609.26637v1 Announce Type: cross Abstract: The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-sour…
- arXiv cs.AIresearchA Spectral Theory of Grokking: Weight Decay induces Feature Learning
arXiv:2609.26679v1 Announce Type: cross Abstract: In grokking an early fit to the training data separates from a much later improvement in generalization. During this delay, training can move from a fixed neural tangent…
- arXiv cs.AIresearchBeyond Repeated Sampling: Learning Search Policies for LLM Reasoning
arXiv:2609.26704v1 Announce Type: cross Abstract: Large language models increasingly tackle hard reasoning problems by spending more test-time compute, yet the dominant strategy remains naive repeated sampling: draw many…
- arXiv cs.AIresearchTrain Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning
arXiv:2609.26708v1 Announce Type: cross Abstract: Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathematical and code reas…
- arXiv cs.AIresearchTraceVIC: Causal Reasoning over Code Evolution for Identifying Vulnerability-Inducing Commits
arXiv:2609.26711v2 Announce Type: replace-cross Abstract: Software vulnerabilities are often discovered long after they are introduced, making it difficult to identify the vulnerability-inducing commit (VIC) responsible…
- arXiv cs.AIresearchThe Sirens' Song: When Proximal Background Context Overshadows Distant Evidence
arXiv:2609.26718v1 Announce Type: cross Abstract: Long-context LLMs focus on retrieving distant evidence from extensive context, yet existing work has largely focused on overcoming distance alone. In this work, we identi…
- arXiv cs.AIresearchMetrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen
arXiv:2609.26749v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to the automated repair of C/C++ security vulnerabilities, and compile rate is a commonly reported proxy for progres…
- arXiv cs.AIresearchFleXray: Universal Clinical X-ray Segmentation
arXiv:2609.26756v2 Announce Type: replace-cross Abstract: X-ray is medicine's most widely used imaging modality, yet remains among its least quantitative. Unlike volumetric modalities like CT or MRI, X-ray collapses 3D a…
- arXiv cs.AIresearchSpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
arXiv:2609.26780v2 Announce Type: replace-cross Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said…
- arXiv cs.AIresearchStable Marriage Problems with Ties and Incomplete Preferences: An Empirical Comparison of ASP, SAT, ILP, CP, and Local Search Methods
arXiv:2108.05165v3 Announce Type: replace Abstract: We study a variation of the Stable Marriage problem, where every man and every woman express their preferences as preference lists which may be incomplete and contain t…
- arXiv cs.AIresearchDecidable Reasoning About Time in Finite-Domain Situation Calculus Theories
arXiv:2402.03164v3 Announce Type: replace Abstract: Representing time is crucial for cyber-physical systems and has been studied extensively in the situation calculus. The most commonly used approach represents time by a…
- arXiv cs.AIresearchGlucose-ML: A collection of longitudinal diabetes datasets for development of robust AI solutions
arXiv:2507.14077v2 Announce Type: replace Abstract: Artificial intelligence (AI) algorithms are a critical part of state-of-the-art digital health technology for diabetes management. Yet, access to large high-quality dat…
- arXiv cs.AIresearchUltra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy
arXiv:2509.00961v3 Announce Type: replace Abstract: Active learning is a general learning mechanism shared by artificial and human learners. Whether AI can teach humans such a strategy that transfers across domains is an…
- arXiv cs.AIresearchNavigating Taxonomic Expansions of Entity Sets Driven by Knowledge Bases
arXiv:2512.16953v3 Announce Type: replace Abstract: Recognizing similarities among entities is central to both human cognition and computational intelligence. Within this broader landscape, Entity Set Expansion is one pr…
- arXiv cs.AIresearchNIMO Controller: a self-driving laboratory orchestrator based on the Model Context Protocol
arXiv:2605.15227v2 Announce Type: replace Abstract: Self-driving laboratories (SDLs) are attracting increasing attention as a means of accelerating scientific discovery; however, developing SDL software remains technical…
- arXiv cs.AIresearchExecution Realism and Reproducibility in LLM-Based Trading Systems: A Systematic Scoping Review and Evidence Audit
arXiv:2606.08285v3 Announce Type: replace Abstract: Execution realism remains weakly standardized in research on large-language-model-based trading systems, limiting comparison and reproduction across backtests, simulati…
- arXiv cs.AIresearchAccelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation
arXiv:2606.24369v3 Announce Type: replace Abstract: Reinforcement learning (RL) has become a dominant post-training paradigm, driving the emergence of high-performance RL systems such as veRL for autoregressive large lan…
- arXiv cs.AIresearchEnhancing Fitness Intelligence through Domain-Specific LLM Post-Training
arXiv:2607.02118v2 Announce Type: replace Abstract: Scientific Fitness Coaching (SFC) is typically delivered by human professionals, making it costly and inaccessible to many. While recent advances in Large Language Mode…
- arXiv cs.AIresearchVeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based Verification
arXiv:2607.20474v2 Announce Type: replace Abstract: Natural language interfaces can greatly benefit the accessibility and usability of optimization modeling, and recent advances in large language models (LLMs) show promi…
- arXiv cs.AIresearchWhere Does Neural Advantage Arise in Continuous-Time Dynamic Graph Prediction?
arXiv:2608.06765v3 Announce Type: replace Abstract: Aggregate performance on continuous-time dynamic graphs (CTDGs) combines, in a single score, the portion attributable to known temporal regularities and the additional…
- arXiv cs.AIresearchPTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks
arXiv:2608.07066v2 Announce Type: replace Abstract: Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonl…
- arXiv cs.AIresearchPerfReasoning: How Well Do LLMs Reason on Hardware Performance?
arXiv:2609.04476v3 Announce Type: replace Abstract: Performance modeling is central to hardware design and software optimization, yet constructing these models requires structured reasoning about computation, data reuse,…
- arXiv cs.AIresearchBenchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation
arXiv:2609.11115v4 Announce Type: replace Abstract: Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluations, locate their benchmark datasets and code, a…
- arXiv cs.AIresearchPotential of Artificial Intelligence Algorithms for Identification of Relevant Diagnostic and Prognostic Biomarkers of Early-Stage Liver Cancer
arXiv:2609.15638v2 Announce Type: replace Abstract: This study explores the use of deep learning and explainable artificial intelligence to diagnose hepatocellular carcinoma (HCC) and define effective biomarkers across f…
- arXiv cs.AIresearchDA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration
arXiv:2311.04799v3 Announce Type: replace-cross Abstract: Pretraining language models is still a challenge for many researchers due to its substantial computational costs. As such, there is growing interest in developing…
- arXiv cs.AIresearchHighway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
arXiv:2412.02520v5 Announce Type: replace-cross Abstract: Connected automated vehicles (CAVs) equipped with adaptive cruise control (ACC) create new opportunities for highway congestion mitigation. Traditional practice r…
- arXiv cs.AIresearchFedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning
arXiv:2502.16396v2 Announce Type: replace-cross Abstract: Federated learning systems are increasingly threatened by data poisoning attacks, where malicious clients compromise global models by contributing tampered update…
- arXiv cs.AIresearchBigO(Bench): Can LLMs Generate Code with Controlled Time and Space Complexity?
arXiv:2503.15242v3 Announce Type: replace-cross Abstract: We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with s…
- arXiv cs.AIresearchAdaptive Helpfulness-Harmlessness Alignment with Preference Vectors
arXiv:2504.20106v4 Announce Type: replace-cross Abstract: Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, whi…
- arXiv cs.AIresearchTEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action
arXiv:2505.01583v2 Announce Type: replace-cross Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLMs). We propose…
- arXiv cs.AIresearchOV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots
arXiv:2506.11585v3 Announce Type: replace-cross Abstract: We introduce OV-MAP, a novel approach to open-world 3D mapping for mobile robots by integrating open-features into 3D maps to enhance object recognition capabilit…
- arXiv cs.AIresearchTowards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
arXiv:2508.20443v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data…
- arXiv cs.AIresearchData Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
arXiv:2510.09655v3 Announce Type: replace-cross Abstract: We propose a system for marking sensitive or copyrighted texts to detect their use in fine-tuning large language models under black-box access with statistical gu…
- arXiv cs.AIresearchProvable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits
arXiv:2510.10730v3 Announce Type: replace-cross Abstract: We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonli…
- arXiv cs.AIresearchPOPI: Personalizing LLMs via Optimized Natural Language Preference Inference
arXiv:2510.17881v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a…
- arXiv cs.AIresearchMetamodel-Guided Model Generation with Layered Constraints
arXiv:2510.25890v4 Announce Type: replace-cross Abstract: Large language models (LLMs) enable natural-language interaction in engineering modeling, but generated models may violate structural constraints, domain rules, o…
- arXiv cs.AIresearchSTAR-VAE: A Scalable Latent-Variable Transformer for Controllable Molecular Generation
arXiv:2511.02769v2 Announce Type: replace-cross Abstract: Many molecular Transformers lack probabilistic latent variables for posterior inference and latent interpolation. We introduce STAR-VAE, a SELFIES-encoded, Transf…
- arXiv cs.AIresearchFinding Kissing Numbers with Game-theoretic Reinforcement Learning
arXiv:2511.13391v5 Announce Type: replace-cross Abstract: Since Isaac Newton first studied the Kissing Number Problem in 1694, determining the maximal number of non-overlapping spheres around a central sphere has remaine…
- arXiv cs.AIresearchTowards Synergistic Teacher-AI Interactions with Generative Artificial Intelligence
arXiv:2511.19580v2 Announce Type: replace-cross Abstract: Generative artificial intelligence (GenAI) is increasingly used in education, posing significant challenges for teachers adapting to these changes. GenAI offers u…
- arXiv cs.AIresearchRadiance-Field Guided Pretraining: Scaling Localization Models with Unlabeled Wireless Signals
arXiv:2512.07309v2 Announce Type: replace-cross Abstract: Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing.…
- arXiv cs.AIresearchA Multimodal Large Language Model-Driven Framework for Context-Aware UAV Emergency Landing Site Selection
arXiv:2602.01163v2 Announce Type: replace-cross Abstract: Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, temporary structures)…
- arXiv cs.AIresearchSWE-Universe: Scale Real-World Verifiable Environments to Millions
arXiv:2602.02361v2 Announce Type: replace-cross Abstract: We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitH…
- arXiv cs.AIresearchDiscovering Data Manifold Geometry through Geometric Properties
arXiv:2602.02611v2 Announce Type: replace-cross Abstract: A prevailing paradigm in modern representation learning is the map-first approach, in which a representation map is learned from reconstruction, embedding, or tas…
- arXiv cs.AIresearchFMMD: A multimodal multidisciplinary dataset of open peer reviews from F1000Research
arXiv:2602.14285v2 Announce Type: replace-cross Abstract: Automated scholarly paper review (ASPR) has entered the coexistence phase with traditional peer review, where artificial intelligence (AI) systems are increasingl…
- arXiv cs.AIresearchReal Money, Fake Models: Deceptive Model Claims in Shadow APIs
arXiv:2603.01919v3 Announce Type: replace-cross Abstract: Access to frontier large language models (LLMs), such as GPT-5 and Gemini-2.5, is often hindered by high pricing, payment barriers, and regional restrictions. The…
- arXiv cs.AIresearchSpectral Overfitting in Noisy Linear Probing of Pretrained Representations
arXiv:2603.02293v3 Announce Type: replace-cross Abstract: Frozen pretrained features are often treated as a safe interface for downstream learning: only a small linear readout is trained, while the backbone is fixed. We…