Zuowu Shi

RL4LLM4AI's activity

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

upvoted 4 papers about 6 hours ago

T-DIG: Text-Conditioned Diversity for Image Generation

Paper • 2610.29003 • Published 8 days ago • 3

Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation

Paper • 2610.26030 • Published 9 days ago • 28

PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds

Paper • 2610.34921 • Published 3 days ago • 3

ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

Paper • 2610.34283 • Published 4 days ago • 364

upvoted a paper 13 days ago

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Paper • 2610.21601 • Published 14 days ago • 225

upvoted a paper 22 days ago

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

Paper • 2610.08448 • Published 23 days ago • 111

upvoted 3 papers about 2 months ago

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published Sep 3 • 114

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

Paper • 2609.04199 • Published Sep 3 • 273

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 94

upvoted 2 papers 5 months ago

Geometry-Aware Image Flow Matching

Paper • 2605.25294 • Published May 24 • 7

DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning

Paper • 2605.25604 • Published May 25 • 49

upvoted a paper about 1 year ago

VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models

Paper • 2509.19803 • Published Sep 24, 2025 • 85