LLMs Can Get "Brain Rot"!
Paper
•
2510.13928
•
Published
•
21
Yifan Wang PRO
AmberYifan
AI & ML interests
None yet
Recent Activity
published
a model
19 days ago
AmberYifan/Qwen2.5-7B-Instruct-wildfeedback-SPIN-iter5
published
a model
19 days ago
AmberYifan/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter5
published
a model
19 days ago
AmberYifan/Qwen2.5-7B-Instruct-wildfeedback-iterDPO-iter5
Organizations
authored
a
paper
about 1 month ago
authored
3
papers
about 2 months ago
Cascade Reward Sampling for Efficient Decoding-Time Alignment
Paper
•
2406.16306
•
Published
DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning
Paper
•
2510.02341
•
Published
•
2
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment
Paper
•
2504.02193
•
Published