SeanWang0027 PRO

SeanWang0027

·

https://haojinw0027.github.io/

AI & ML interests

LLM Post-Training

Recent Activity

published a model 7 days ago

CL-From-Nothing/rl_warm_up_code_rose_sft_25K_1_7B_SFT-parquet_qwen3-1.7b-base-code-10k-sft_epoch_1_mask_lr1e-5

updated a model 7 days ago

CL-From-Nothing/rl_warm_up_code_rose_sft_25K_1_7B_SFT-parquet_qwen3-1.7b-base-code-10k-sft_epoch_1_mask_lr1e-5

published a dataset 8 days ago

CL-From-Nothing/code_rose_sft_25K_1_7B_SFT

View all activity

Organizations

upvoted a paper about 1 month ago

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models

Paper • 2605.20177 • Published May 19 • 10

upvoted a paper 3 months ago

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Paper • 2603.24472 • Published Mar 25 • 57

upvoted 2 papers 5 months ago

Residual Context Diffusion Language Models

Paper • 2601.22954 • Published Jan 30 • 36

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Paper • 2602.01058 • Published Feb 1 • 45