诗雨 梁

isaacmartinbj's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 11 hours ago

SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference

Paper • 2606.31145 • Published 8 days ago • 7

upvoted a paper 3 days ago

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Paper • 2606.08671 • Published 15 days ago • 43

upvoted a paper 13 days ago

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Paper • 2606.17162 • Published 23 days ago • 176

upvoted a paper 18 days ago

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Paper • 2606.18023 • Published 22 days ago • 209

upvoted 2 papers 19 days ago

Looped World Models

Paper • 2606.18208 • Published 22 days ago • 477

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published 21 days ago • 139

upvoted a paper 20 days ago

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published 22 days ago • 76

upvoted 5 papers 26 days ago

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

Paper • 2606.08063 • Published Jun 6 • 82

From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning

Paper • 2606.07190 • Published Jun 5 • 35

InterleaveThinker: Reinforcing Agentic Interleaved Generation

Paper • 2606.13679 • Published 27 days ago • 82

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Paper • 2606.11926 • Published 28 days ago • 126

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published about 1 month ago • 486

upvoted 4 papers about 1 month ago

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Paper • 2606.02437 • Published Jun 1 • 237

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Paper • 2605.30263 • Published May 28 • 59

Less is More: Early Stopping Rollout for On-Policy Distillation

Paper • 2605.27028 • Published May 26 • 15

VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis

Paper • 2605.22570 • Published May 21 • 24