Browse

AI News

26288 items — filtered, classified, deduplicated

arXiv cs.AI Research & Papers
Representing Higher-Order Networks: A Survey of Graph-Based Frameworks
arXiv cs.AI Research & Papers
Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
arXiv cs.AI Research & Papers
Formally Verifying Analog Neural Networks Under Process Variations Using Polynomial Zonot…
arXiv cs.AI Research & Papers
Mask-Based Priors Are More Persistent than Query-Key Initializations
arXiv cs.AI Research & Papers
Uncertainty-Aware Simulation-Based Inference for Operations Research with Large Language …
arXiv cs.AI Research & Papers
CockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent Coc…
arXiv cs.AI Research & Papers
CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Mode…
arXiv cs.AI Research & Papers
Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Age…
arXiv cs.AI Research & Papers
Latent Thought Credit: Multi-Answer Credit Assignment for Latent Reasoning
arXiv cs.AI Research & Papers
Computing with Agentic Oracles
arXiv cs.AI Research & Papers
Ekova: A Personality-Support Agent for Self-Discovery Dialogue
arXiv cs.AI Research & Papers
Why Does the Future Branch? Identifiable Closure Tests for Stochastic Physical World Mode…
arXiv cs.AI Research & Papers
LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Lay…
arXiv cs.AI Research & Papers
PolymerGPT: Multi-property Optimization with a Decoder-Based GPT Model for Generative Pol…
arXiv cs.AI Research & Papers
Anticipatory Digital Twins for Online Head-and-Neck Adaptive Proton Therapy via Foundatio…
arXiv cs.AI Research & Papers
Asymmetric Generative Recommendation via Kronecker Residual Bridge and Multi-Faceted Hier…
arXiv cs.AI Research & Papers
Belief-Contraction-Driven Active Inverse Source Localization and Characterization
arXiv cs.AI Research & Papers
Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time
arXiv cs.AI Research & Papers
Agentic Stage-One Stellarator Optimization: Autonomous Multi-Objective Search for Finite-…
arXiv cs.AI Research & Papers
Nova: An End-to-End MLIR Compiler for Deep Learning
arXiv cs.AI Research & Papers
Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation
arXiv cs.AI Research & Papers
Credit the Right Box: Marginal Contribution Assignment for Structured Visual Perception
arXiv cs.AI Research & Papers
Dual-Resolution Attention-Gated Deep Learning with Ordinal Regression for Diabetic Retino…
arXiv cs.AI Research & Papers
ARGen: Affect-Reinforced Generative Augmentation towards Vision-based Dynamic Emotion Per…
arXiv cs.AI Research & Papers
Control Under Compression: Reliability Frontiers for Tool-Using Agents
arXiv cs.AI Research & Papers
AiFlow: Token-Native Reactive Orchestration with Bounded Backpressure for Streaming LLM A…
arXiv cs.AI Research & Papers
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
arXiv cs.AI Research & Papers
AST: Adaptive, Seamless, and Training-Free Precise Speech Editing
arXiv cs.AI Research & Papers
Similarity Weighted Aggregation with Global Differential Privacy for Federated Brain Lesi…
arXiv cs.AI Research & Papers
Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers