JieSun(SII)

Sunshine279

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

upvoted a paper 2 days ago

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

upvoted a paper 8 days ago

PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents

View all activity

Organizations

Papers 2

arxiv:2601.11044

arxiv:2506.03690

models 4

Sunshine279/gammaPO-mistral-7b-instruct-v0.2

7B • Updated Jun 29, 2025 • 18

Sunshine279/gammaPO-llama-3-8b-instruct

8B • Updated Jun 29, 2025 • 21

Sunshine279/gammaPO-qwen-2.5-7b-instruct

8B • Updated Jun 29, 2025 • 3 • 2

Sunshine279/gammaPO-gemma-2-9b-it

9B • Updated Jun 29, 2025 • 14 • 1

datasets 2

Sunshine279/qwen_ultrafeedback_binarized_flip0.2

Updated Jul 15, 2025 • 38

Sunshine279/qwen_ultrafeedback_binarized

Updated Jul 14, 2025 • 64