AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
2659
延迟
—
最新内容
当前时间
安全连接 OPERATIONAL

03 / ARTICLE LEDGER

关联文章

按发布时间倒序

  1. ARO: A New Lens On Matrix Optimization For Large Models 2026-02-10 · ARXIV
  2. ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation 2026-02-10 · ARXIV
  3. GEBench: Benchmarking Image Generation Models as GUI Environments 2026-02-10 · ARXIV
  4. Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense 2026-02-10 · ARXIV
  5. ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling 2026-02-10 · ARXIV
  6. Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model 2026-02-10 · ARXIV
  7. MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation 2026-02-10 · ARXIV
  8. LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge 2026-02-10 · ARXIV
  9. Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion 2026-02-10 · ARXIV
  10. Emergent Misalignment is Easy, Narrow Misalignment is Hard 2026-02-10 · ARXIV
  11. Direct Soft-Policy Sampling via Langevin Dynamics 2026-02-10 · ARXIV
  12. Optimal Turkish Subword Strategies at Scale: Systematic Evaluation of Data, Vocabulary, Morphology Interplay 2026-02-09 · ARXIV
  13. Learning a Generative Meta-Model of LLM Activations 2026-02-09 · ARXIV
  14. InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning 2026-02-09 · ARXIV
  15. From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows 2026-02-09 · ARXIV
  16. Endogenous Resistance to Activation Steering in Language Models 2026-02-09 · ARXIV
  17. DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos 2026-02-09 · ARXIV
  18. DAWN: Dependency-Aware Fast Inference for Diffusion LLMs 2026-02-09 · ARXIV
  19. Agentic Uncertainty Reveals Agentic Overconfidence 2026-02-09 · ARXIV
  20. Shared LoRA Subspaces for almost Strict Continual Learning 2026-02-06 · ARXIV
  21. Pseudo-Invertible Neural Networks 2026-02-06 · ARXIV
  22. PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling 2026-02-06 · ARXIV
  23. Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory 2026-02-06 · ARXIV
  24. DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching 2026-02-06 · ARXIV
  25. DFlash: Block Diffusion for Flash Speculative Decoding 2026-02-06 · ARXIV
  26. Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference 2026-02-06 · ARXIV
  27. CommCP: Efficient Multi-Agent Coordination via LLM-Based Communication with Conformal Prediction 2026-02-06 · ARXIV
  28. Can vision language models learn intuitive physics from interaction? 2026-02-06 · ARXIV
  29. AP-OOD: Attention Pooling for Out-of-Distribution Detection 2026-02-06 · ARXIV
  30. Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity 2026-02-06 · ARXIV
  31. RRAttention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference 2026-02-06 · ARXIV
  32. Exact Recovery in the Data Block Model 2026-02-06 · ARXIV
  33. DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders 2026-02-06 · ARXIV
  34. Constrained Group Relative Policy Optimization 2026-02-06 · ARXIV
  35. Subliminal Effects in Your Data: A General Mechanism via Log-Linearity 2026-02-05 · ARXIV
  36. Rethinking the Trust Region in LLM Reinforcement Learning 2026-02-05 · ARXIV
  37. Reinforced Attention Learning 2026-02-05 · ARXIV
  38. Protein Autoregressive Modeling via Multiscale Structure Generation 2026-02-05 · ARXIV
  39. Multi-layer Cross-Attention is Provably Optimal for Multi-modal In-context Learning 2026-02-05 · ARXIV
  40. Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism 2026-02-05 · ARXIV
  41. CRoSS: A Continual Robotic Simulation Suite for Scalable Reinforcement Learning with High Task Diversity and Realistic Physics Simulation 2026-02-05 · ARXIV
  42. CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation 2026-02-05 · ARXIV
  43. Contrastive Continual Learning for Model Adaptability in Internet of Things 2026-02-05 · ARXIV
  44. Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL 2026-02-04 · ARXIV
  45. Robust Intervention Learning from Emergency Stop Interventions 2026-02-04 · ARXIV
  46. PrevizWhiz: Combining Rough 3D Scenes and 2D Video to Guide Generative Video Previsualization 2026-02-04 · ARXIV
  47. PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning 2026-02-04 · ARXIV
  48. Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing 2026-02-04 · ARXIV
  49. AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations 2026-02-04 · ARXIV
  50. Accelerating Scientific Research with Gemini: Case Studies and Common Techniques 2026-02-04 · ARXIV