Xiyang Wu's picture

4 1

Xiyang Wu

wuxiyang

AI & ML interests

Reinforcement learning, Robotics, LLM

Recent Activity

upvoted a paper 4 days ago

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

liked a model 4 months ago

zli12321/answer_equivalence_roberta-large

updated a Space 6 months ago

wuxiyang/AUTOHALLUSION

View all activity

Organizations

None yet

Papers 1

arxiv:2306.06236

spaces 1

AUTOHALLUSION

AUTOHALLUSION (EMNLP 2024 Findings)

models

None public yet

datasets

None public yet