Shaofei Cai

phython96's activity

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

authored 3 papers about 17 hours ago

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

Paper • 2509.22601 • Published Sep 26, 2025 • 29

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published about 1 month ago • 242

SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents

Paper • 2512.22322 • Published 6 days ago • 34

upvoted 2 papers 2 days ago

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published about 1 month ago • 242

SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents

Paper • 2512.22322 • Published 6 days ago • 34

upvoted a paper about 2 months ago

Revisiting Multimodal Positional Encoding in Vision-Language Models

Paper • 2510.23095 • Published Oct 27, 2025 • 20

upvoted 4 papers 3 months ago

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13, 2025 • 176

Training-Free Group Relative Policy Optimization

Paper • 2510.08191 • Published Oct 9, 2025 • 44

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

Paper • 2509.22601 • Published Sep 26, 2025 • 29

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26, 2025 • 184

authored a paper 5 months ago

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

Paper • 2507.23698 • Published Jul 31, 2025 • 10

commented 2 papers 5 months ago

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

Paper • 2507.23698 • Published Jul 31, 2025 • 10 •

4

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

Paper • 2507.23698 • Published Jul 31, 2025 • 10 •

4

updated a collection 5 months ago

ROCKET

Collection

ROCKET is the research series that explores vision-based goal specification methods. • 12 items • Updated Sep 21, 2025 • 2

upvoted a paper 5 months ago

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

Paper • 2507.23698 • Published Jul 31, 2025 • 10

commented a paper 5 months ago

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

Paper • 2507.23698 • Published Jul 31, 2025 • 10 •

4

authored 3 papers 6 months ago

Edge-featured Graph Neural Architecture Search

Paper • 2109.01356 • Published Sep 3, 2021

Open-World Skill Discovery from Unsegmented Demonstrations

Paper • 2503.10684 • Published Mar 11, 2025 • 5

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

Paper • 2507.01925 • Published Jul 2, 2025 • 39

upvoted a paper 6 months ago

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

Paper • 2507.01925 • Published Jul 2, 2025 • 39