AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
2657
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. TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale 2026-07-15 · ARXIV
  2. The Seriality Gap in Video Diffusion Models 2026-07-15 · ARXIV
  3. Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution 2026-07-15 · ARXIV
  4. Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data 2026-07-14 · ARXIV
  5. PHINN-EEG: Topological Time-Series Analysis of Dream-State EEG -- Dynamic Betti Curves for Dream Content Classification and Topology-Conditioned Neural Signal Synthesis 2026-07-13 · ARXIV
  6. UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks 2026-07-10 · ARXIV
  7. Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning 2026-07-09 · ARXIV
  8. ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation 2026-07-08 · ARXIV
  9. From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model 2026-07-07 · ARXIV
  10. Distributed Attacks in Persistent-State AI Control 2026-07-03 · ARXIV
  11. Measuring the Gap Between Human and LLM Research Ideas 2026-07-02 · ARXIV
  12. Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision 2026-07-01 · ARXIV
  13. VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes 2026-06-30 · ARXIV
  14. DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand 2026-06-29 · ARXIV
  15. DanceOPD: On-Policy Generative Field Distillation 2026-06-26 · ARXIV
  16. Learning Action Priors for Cross-embodiment Robot Manipulation 2026-06-25 · ARXIV
  17. InSight: Self-Guided Skill Acquisition via Steerable VLAs 2026-06-24 · ARXIV
  18. AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection 2026-06-23 · ARXIV
  19. How Transparent is DiffusionGemma? 2026-06-19 · ARXIV
  20. Native Active Perception as Reasoning for Omni-Modal Understanding 2026-06-18 · ARXIV
  21. Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement 2026-06-17 · ARXIV
  22. The Value Axis: Language Models Encode Whether They're on the Right Track 2026-06-16 · ARXIV
  23. Gaze Heads: How VLMs Look at What They Describe 2026-06-15 · ARXIV
  24. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments 2026-06-12 · ARXIV
  25. Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models 2026-06-11 · ARXIV
  26. When to Align, When to Predict: A Phase Diagram for Multimodal Learning 2026-06-10 · ARXIV
  27. OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics 2026-06-09 · ARXIV
  28. How reliable are LLMs when it comes to playing dice? 2026-06-08 · ARXIV
  29. TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning 2026-06-05 · ARXIV
  30. STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations 2026-06-04 · ARXIV
  31. Neuron Populations Exhibit Divergent Selectivity with Scale 2026-06-03 · ARXIV
  32. Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling 2026-06-02 · ARXIV
  33. Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models 2026-06-01 · ARXIV
  34. Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software 2026-05-29 · ARXIV
  35. PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective 2026-05-28 · ARXIV
  36. Algorithmic Monocultures in Hiring 2026-05-27 · ARXIV
  37. MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research 2026-05-26 · ARXIV
  38. SkillOpt: Executive Strategy for Self-Evolving Agent Skills 2026-05-25 · ARXIV
  39. Tokenisation via Convex Relaxations 2026-05-22 · ARXIV
  40. Variance Reduction for Expectations with Diffusion Teachers 2026-05-21 · ARXIV
  41. Atoms of Thought: Universal EEG Representation Learning with Microstates 2026-05-20 · ARXIV
  42. DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention 2026-05-19 · ARXIV
  43. IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation 2026-05-18 · ARXIV
  44. EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation 2026-05-15 · ARXIV
  45. WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data 2026-05-14 · ARXIV
  46. AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward 2026-05-13 · ARXIV
  47. ELF: Embedded Language Flows 2026-05-12 · ARXIV
  48. LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling 2026-05-11 · ARXIV
  49. ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation 2026-05-08 · ARXIV
  50. Taming Outlier Tokens in Diffusion Transformers 2026-05-07 · ARXIV