Yifan Wang's picture

1 3 1

Yifan Wang

AmberYifan

·

AI & ML interests

None yet

Recent Activity

published a model 1 day ago

AmberYifan/Qwen3-4B-MATH-GRPO-len-control-tuned-test

published a model 2 days ago

AmberYifan/Qwen3-4B-MATH-GRPO-len-control-tuned

published a model 3 days ago

AmberYifan/Qwen3-4B-OpenR1Math-MARL-structure-v2

View all activity

Organizations

authored a paper 10 days ago

LLMs Can Get "Brain Rot"!

Paper • 2510.13928 • Published 15 days ago • 21

authored 2 papers 22 days ago

Cascade Reward Sampling for Efficient Decoding-Time Alignment

Paper • 2406.16306 • Published Jun 24, 2024

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

Paper • 2510.02341 • Published Sep 27 • 2

authored a paper 23 days ago

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

Paper • 2504.02193 • Published Apr 3