Self-Evolving Search Index
Paper • 2609.19656 • Published • 46
Bingzheng Wei
Bingzheng
AI & ML interests
None yet
Recent Activity
upvoted a paper about 24 hours ago
Self-Evolving Search Index upvoted a paper 1 day ago
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent HarnessOrganizations
None yet
upvoted a paper about 24 hours ago
upvoted 6
papers 1 day ago
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Paper • 2609.20519 • Published • 95
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Paper • 2609.20511 • Published • 96
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Paper • 2609.19969 • Published • 139
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Paper • 2609.14857 • Published • 209
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
Paper • 2609.18708 • Published • 65
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
Paper • 2609.19134 • Published • 82
upvoted a paper 3 days ago
upvoted 3
papers 4 days ago
upvoted 8
papers 5 days ago
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Paper • 2609.13285 • Published • 77
AI for Games in the Foundation Model Era
Paper • 2609.16679 • Published • 145
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models
Paper • 2609.14973 • Published • 171
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Paper • 2609.14858 • Published • 239
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Paper • 2609.06986 • Published • 367
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
Paper • 2609.13356 • Published • 256
Atria Dawn: The Dawn of Agentic Superintelligence
Paper • 2609.15818 • Published • 420
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Paper • 2609.11638 • Published • 691
upvoted a paper 6 days ago