Haoxiang Wang's picture

Haoxiang Wang

Haoxiang-Wang

·

https://haoxiang-wang.github.io/

AI & ML interests

Machine Learning (Transfer Learning, OOD Generalization, Domain Adaptation, Meta-Learning)

Recent Activity

upvoted a paper 14 days ago

Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

commented on a paper 14 days ago

Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

upvoted a paper 3 months ago

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

View all activity

Organizations

Haoxiang-Wang's activity

upvoted a paper 14 days ago

Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

Paper • 2505.18116 • Published 18 days ago • 4

upvoted 2 papers 3 months ago

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Paper • 2503.15558 • Published Mar 18 • 49

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published Feb 26 • 84

upvoted a collection 5 months ago

Cosmos

The collection of Cosmos models • 31 items • Updated 4 days ago • 291

upvoted a paper about 1 year ago

RLHF Workflow: From Reward Modeling to Online RLHF

Paper • 2405.07863 • Published May 13, 2024 • 72

upvoted a collection about 1 year ago

Standard-format-preference-dataset

We collect the open-source datasets and process them into the standard format. • 14 items • Updated May 8, 2024 • 24

upvoted a paper over 1 year ago

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Paper • 2312.11514 • Published Dec 12, 2023 • 257