Fei Zhao

Hiiamein's activity

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

upvoted a paper 5 days ago

Vela: User Behavior as Supervision Sparks LLM Intelligence

Paper • 2610.14709 • Published 9 days ago • 87

upvoted a paper 19 days ago

ROSS: Relearning from Self-Generated Rollouts through Selective Supervision

Paper • 2609.35954 • Published 21 days ago • 54

upvoted 3 papers 20 days ago

Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents

Paper • 2609.33772 • Published 22 days ago • 36

CompoWorld: Compositional Environment Scaling for General Agents

Paper • 2609.33665 • Published 22 days ago • 42

Learning to Learn from Context: Synthetic Training from Perturbed Public Documents

Paper • 2609.33642 • Published 22 days ago • 35

upvoted a paper about 1 month ago

Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

Paper • 2609.02998 • Published Sep 2 • 19

upvoted a paper about 2 months ago

D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation

Paper • 2608.24987 • Published Aug 25 • 28

upvoted a paper 8 months ago

QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search

Paper • 2602.09901 • Published Feb 10 • 6

upvoted 2 papers 9 months ago

Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training

Paper • 2602.00747 • Published Jan 31 • 9

Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors

Paper • 2601.15625 • Published Jan 22 • 9

upvoted a paper 11 months ago

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services

Paper • 2511.07070 • Published Nov 10, 2025 • 20

upvoted a paper about 1 year ago

RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services

Paper • 2507.10605 • Published Jul 13, 2025 • 8

upvoted a paper over 1 year ago

GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets

Paper • 2504.19898 • Published Apr 28, 2025 • 5

upvoted 2 collections about 2 years ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 43 items • Updated Mar 2 • 738

Qwen2

Collection

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 37 items • Updated Mar 2 • 376