Gengsheng Li

RyukiRi's activity

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

upvoted 2 papers 1 day ago

EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment

Paper • 2610.14609 • Published 5 days ago • 53

Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation

Paper • 2609.23697 • Published 15 days ago • 5

authored 4 papers 7 days ago

Rubric-based On-policy Distillation

Paper • 2605.07396 • Published May 8 • 41

Visual-Advantage On-Policy Distillation for Vision-Language Models

Paper • 2605.21924 • Published May 21 • 1

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

Paper • 2604.02288 • Published Apr 2 • 32

R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training

Paper • 2602.13103 • Published Feb 16 • 1

upvoted 4 papers 7 days ago

Visual-Advantage On-Policy Distillation for Vision-Language Models

Paper • 2605.21924 • Published May 21 • 1

R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training

Paper • 2602.13103 • Published Feb 16 • 1

Data-Free On-Policy Distillation: How Far Can We Go Without External Data?

Paper • 2609.14193 • Published 14 days ago • 12

nanoMuse: An Open-Source Personal Agent for Every Device You Own

Paper • 2610.08699 • Published 9 days ago • 114

upvoted a collection about 1 month ago

Open-MOPD: Multi-Teacher On-Policy Distillation

Collection

Open-MOPD 3B family: MixSFT, math/code/IF RL teachers, the final on-policy-distilled student, and training/evaluation data. • 6 items • Updated Aug 18 • 5

upvoted 2 papers about 2 months ago

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Paper • 2602.12125 • Published Feb 12 • 70

Trust Region Policy Distillation

Paper • 2607.04751 • Published Jul 6 • 35

upvoted a paper 2 months ago

Continual Learning in Transition

Paper • 2608.06216 • Published Aug 6 • 27

upvoted 2 papers 3 months ago

CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition

Paper • 2607.25294 • Published Jul 28 • 47

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

Paper • 2604.02288 • Published Apr 2 • 32

upvoted 2 papers 5 months ago

Rubric-based On-policy Distillation

Paper • 2605.07396 • Published May 8 • 41

Group-in-Group Policy Optimization for LLM Agent Training

Paper • 2505.10978 • Published May 16, 2025 • 24

upvoted 2 papers 6 months ago

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

Paper • 2603.25562 • Published Mar 26 • 18

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published Apr 14 • 116