AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchHardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts
arXiv:2610.02241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures allow frontier language models to scale to trillions of parameters, but their deployment is constrained by massive memory footprint…
- arXiv cs.AIresearchToward Controlling Biology with Language:Offline Learning of Prompt-Conditioned Interventions for Cells, Organoids, and Biobots
arXiv:2610.02247v1 Announce Type: cross Abstract: Artificial intelligence increasingly serves as a natural-language interface to complex technical systems, letting people accomplish sophisticated tasks by describing what…
- arXiv cs.AIresearchCounterfactual Predictions in Scientific Emulators Without Controlled Experiments
arXiv:2610.02252v1 Announce Type: cross Abstract: Many scientific questions require reasoning about what was never observed: What if the conditions, interventions, or history had been different? Models can predict accura…
- arXiv cs.AIresearchOvercoming Challenges of Interpretive Structural Modeling with Large Language Models
arXiv:2610.02254v1 Announce Type: cross Abstract: Interpretive Structural Modeling (ISM) is a well-known process for multi-criteria decision making. The success of ISM over other methodologies is its ability to model cau…
- arXiv cs.AIresearchDiffusion-Based Synthetic Data Pretraining for Enhancing Activity Recognition
arXiv:2610.02292v1 Announce Type: cross Abstract: Human activity recognition (HAR) is increasingly important for healthcare, well-being, and daily monitoring ap- plications, for which detecting alimentary activities such…
- arXiv cs.AIresearchEditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling
arXiv:2610.02298v1 Announce Type: cross Abstract: 3D editing methods are usually tested on a single edit, yet an asset is built through a long sequence of revisions, each of which must implement the requested change whil…
- arXiv cs.AIresearch$\Psi$-Resilience: Model-Free Feature Importance from 1D Topological Signals
arXiv:2610.02299v1 Announce Type: cross Abstract: We introduce $\Psi$-Resilience, a model-free feature importance method that derives explanations directly from the data itself via 1D topological signals. Our method cons…
- arXiv cs.AIresearchSlow-Fast Multi-Teacher On-Policy Distillation for Capability Preservation
arXiv:2610.02324v1 Announce Type: cross Abstract: Foundation multimodal large language models are designed to support a broad spectrum of capabilities across diverse domains. Multi-teacher on-policy distillation (MOPD) p…
- arXiv cs.AIresearchLexicographic Multi-Objective On-Policy Distillation
arXiv:2610.02359v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) usually optimizes answer correctness, yet useful language-model behavior also requires high-quality reasoning and co…
- arXiv cs.AIresearchAutomating the Application of HCI Principles: Skills for On-Demand UI Construction, the Human-AI Space to Think, and the Future of HCI
arXiv:2610.02369v1 Announce Type: cross Abstract: Human-computer interaction (HCI) is in the middle of a transition: large language models can now generate functional user interfaces (UIs) on demand from natural-language…
- arXiv cs.AIresearchNetwork-in-the-Loop at Scale: GPU-Batched 5G Simulation for Massively Parallel Robot Learning
arXiv:2610.02370v1 Announce Type: cross Abstract: Massively parallel GPU simulators train multi-robot policies in thousands of environments, and many fleets use private Fifth-Generation (5G) networks, where each robot's…
- arXiv cs.AIresearchHop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM
arXiv:2610.02373v1 Announce Type: cross Abstract: GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that determine how retrieval i…
- arXiv cs.AIresearchEviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision
arXiv:2610.02375v1 Announce Type: cross Abstract: Dento-maxillofacial cone-beam CT (CBCT) reports may contain dozens of tooth-specific, anatomical, and spatial findings from a single 3D scan. Learning to generate such re…
- arXiv cs.AIresearchThe Surprising Effectiveness of Shared Memory in Looped Transformers
arXiv:2610.02383v1 Announce Type: cross Abstract: Looped Transformers apply the same layers several times per token, adding compute to improve quality without more parameters. Each recursion, however, writes its own key-…
- arXiv cs.AIresearchEfficient Neural Field Learning via Adaptive Coverage and Focused Sampling
arXiv:2610.02410v1 Announce Type: cross Abstract: Implicit neural representations (INRs) provide a flexible framework for modeling high-dimensional continuous fields, but their training is often inefficient due to unifor…
- arXiv cs.AIresearchMitigating Private Data Leakage in LLMs with Whiteout
arXiv:2610.02418v1 Announce Type: cross Abstract: Modern large language models (LLMs) are trained on massive, largely unfiltered datasets, including content scraped from nearly every accessible website and user inputs. A…
- arXiv cs.AIresearchGeometry-Aware Time Reparameterization for Flow-Map Distillation
arXiv:2610.02427v1 Announce Type: cross Abstract: Flow-map distillation enables one- and few-step generation by learning finite-time transitions of a pretrained generative ODE. We investigate whether changing the teacher…
- arXiv cs.AIresearchLearning Style, Forgetting Semantics: A Case Study of SFT and RFT on Classification Tasks
arXiv:2610.02437v1 Announce Type: cross Abstract: Why does supervised fine-tuning (SFT) lead to more forgetting than reinforcement fine-tuning (RFT), even when all teacher demonstrations are semantically correct? We stud…
- arXiv cs.AIresearchAre you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval
arXiv:2610.02438v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance in code generation, where success depends on both recalling relevant algorithmic knowledge and reasoning…
- arXiv cs.AIresearchCounterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs
arXiv:2610.02444v1 Announce Type: cross Abstract: Large language models often solve a theorem forward yet fail to disprove a closely related false one: a falsification gap that supervised fine-tuning does not close and c…
- arXiv cs.AIresearchFinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms
arXiv:2610.02455v1 Announce Type: cross Abstract: Multi-party financial chatrooms are vital for sales-and-trading professionals, but their complexity makes manual recovery of missed trades infeasible: each Request for Qu…
- arXiv cs.AIresearchFrom Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders
arXiv:2610.02486v1 Announce Type: cross Abstract: Typed decision models answer schema-constrained questions about a text in one forward pass and return probabilities meant to be thresholded. We ask whether biomedical sen…
- arXiv cs.AIresearchCompound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents
arXiv:2610.02503v1 Announce Type: cross Abstract: Deploying compound AI systems reliably and safely requires understanding failure modes that emerge at component boundaries, not within individual models. Cascading errors…
- arXiv cs.AIresearchMulti-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning
arXiv:2610.02505v1 Announce Type: cross Abstract: Policy gradient methods for on-policy reinforcement learning (RL) can become unstable when expensive, scarce target-domain data yield noisy gradient estimates. We address…
- arXiv cs.AIresearchIGNITE Tokamak World Model Architecture
arXiv:2610.02515v1 Announce Type: cross Abstract: We introduce IGNITE, a generative world foundation model for fusion plasma behavior simulation trained in a self-supervised manner from over a decade of unlabeled experim…
- arXiv cs.AIresearchStudent-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers
arXiv:2610.02516v1 Announce Type: cross Abstract: Zero-shot classifiers are useful for routing user requests to specialized LLM tasks, but scoring every request against a large candidate set is expensive: a zero-shot NLI…
- arXiv cs.AIresearchInstance-Dependent Regret for CMDPs with Step-Wise Constraints
arXiv:2610.02520v1 Announce Type: cross Abstract: We study online learning in episodic tabular constrained Markov decision processes with step-wise safety constraints. In such a setting, the constraints induce a safe sub…
- arXiv cs.AIresearchCriticHack: Evaluating Visual Rewards Under Robot Policy Optimization
arXiv:2610.02527v1 Announce Type: cross Abstract: Learned visual reward models are increasingly used to optimize robot policies, yet a reward model can score an execution that acts on the wrong object as highly as one th…
- arXiv cs.AIresearchOut of Sync, Out of Sight: Phantom State Attacks against IIoT Intrusion Detection
arXiv:2610.02552v1 Announce Type: cross Abstract: Machine learning-based intrusion detection systems (IDS) are critical for securing Industrial Internet of Things (IIoT) environments. Most adversarial research against th…
- arXiv cs.AIresearchDAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative Rendering
arXiv:2610.02567v1 Announce Type: cross Abstract: Diffusion transformers (DiTs) generate high-fidelity images from text and image conditions, but their outputs carry large variance and their faithfulness to a desired tar…
- arXiv cs.AIresearchImproving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting
arXiv:2610.02571v2 Announce Type: replace-cross Abstract: As AI-assisted programming becomes increasingly mainstream, the environmental impact of AI-generated software has emerged as an important consideration. This moti…
- arXiv cs.AIresearchHow Causality Bridges the Semantic Gap
arXiv:2610.02594v1 Announce Type: cross Abstract: Numerical measurements capture how a system behaves, but often leave the meanings of its variables unspecified. Some variables are measured but never labeled, and others…
- arXiv cs.AIresearchEquivariant Flow Matching for Electron Density Prediction
arXiv:2610.02651v1 Announce Type: cross Abstract: Machine learning surrogates for density functional theory (DFT) have been increasingly used to reduce the cost of first-principles calculations. In this arena, predicting…
- arXiv cs.AIresearchDistributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis
arXiv:2610.02659v2 Announce Type: replace-cross Abstract: Modern state space models (SSMs), such as Mamba2, provide a compelling alternative to transformers by combining linear-time sequence modeling with recurrent state…
- arXiv cs.AIresearchGeneralization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional Data
arXiv:2610.02663v2 Announce Type: replace-cross Abstract: Despite the remarkable empirical success of flow-matching models, their statistical generalization guarantees remain underdeveloped. Existing analyses often impos…
- arXiv cs.AIresearchLarge Language Continuous Diffusion Models
arXiv:2610.02665v1 Announce Type: cross Abstract: Despite the success of discrete diffusion language models (dLMs) for fast parallel decoding, their non-smooth, high-dimensional space hinders trajectory steering for reas…
- arXiv cs.AIresearchTest-time Calibration Learning for Large Language Model Reasoning
arXiv:2610.02695v1 Announce Type: cross Abstract: Reliable large language models (LLMs) must not only produce accurate answers but also express confidence that faithfully reflects their probability of being correct. Such…
- arXiv cs.AIresearchMuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model Heads
arXiv:2610.02705v1 Announce Type: cross Abstract: The Muon optimizer derives its update rule for hidden linear layers by solving a local linearization of the loss penalized by the spectral norm, motivated by an RMS-stabi…
- arXiv cs.AIresearchRevisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis
arXiv:2610.02718v1 Announce Type: cross Abstract: Vision-language models such as CLIP exhibit strong semantic generalization, but remain limited in fine-grained visual perception. A recent work named KUEA presents a natu…
- arXiv cs.AIresearchTPBench: A Turning-Point Benchmark for Dialogue Compression
arXiv:2610.02736v1 Announce Type: cross Abstract: A compressor can keep the facts of a dialogue and still drop the turn that changed them. A user corrects a price, reverses a choice, or adds a constraint. We call this fa…
- arXiv cs.AIresearchCorrecting Guided Diffusion Trajectories with Spectral Alignment
arXiv:2610.02753v1 Announce Type: cross Abstract: The practical success of conditional image generation hinges on fine-grained differences in condition alignment and visual fidelity. Classifier-free guidance (CFG) is cen…
- arXiv cs.AIresearchNearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
arXiv:2610.02771v1 Announce Type: cross Abstract: We study fixed-confidence best-arm identification under strict 1-bit feedback constraints. At each round, the learner selects an arm and a query set, and receives only a…
- arXiv cs.AIresearchImproving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing
arXiv:2610.02772v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly serve as general-purpose interfaces to factual knowledge, but their parameters do not automatically reflect information that cha…
- arXiv cs.AIresearchOPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation
arXiv:2610.02781v1 Announce Type: cross Abstract: Many useful language-model tasks cannot be evaluated by exact outcome verification. Rubric-based reinforcement learning (RL) addresses this issue by scoring open-ended re…
- arXiv cs.AIresearchAdaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization
arXiv:2610.02822v1 Announce Type: cross Abstract: Temporal Domain Generalization (TDG) has emerged to address real-world streaming data with distribution shifts over time. However, existing methods are either prone to ov…
- arXiv cs.AIresearchFastOPD: On-Policy Distillation for Lightweight VLA Deployment
arXiv:2610.02832v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs high computational co…
- arXiv cs.AIresearchDistributionally Robust Survival Models under Subpopulation Shift and Outlier Contamination
arXiv:2610.02868v1 Announce Type: cross Abstract: Learning robust survival models under distribution shift is an important but challenging problem in many applications. In heterogeneous populations, a model that performs…
- arXiv cs.AIresearchConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone Evolution
arXiv:2610.02873v1 Announce Type: cross Abstract: The evolution of linguistic style in conversations is an underexplored issue in NLP. Most style-control datasets focus on sentences or assume a static style throughout, m…
- arXiv cs.AIresearchQuery-aware routing for Cross-lingual performance gains in Encoders
arXiv:2610.02875v1 Announce Type: cross Abstract: Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language performance. We inv…
- arXiv cs.AIresearchDyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs
arXiv:2610.02882v1 Announce Type: cross Abstract: Large-scale foundation models achieve strong performance across diverse tasks, but their size makes inference costly, largely due to dense matrix multiplications. Prior w…