Banghua Zhu's picture

Banghua Zhu

banghua

·

https://banghua.me

AI & ML interests

Foundation models, reinforcement learning, statistics, information theory

Recent Activity

updated a dataset 2 days ago

banghua/DL-DPO-Dataset

published a dataset 2 days ago

banghua/DL-DPO-Dataset

updated a model 3 days ago

banghua/Qwen2.5-GRPO

View all activity

Organizations

banghua's activity

upvoted a collection 8 months ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 46 items • Updated Apr 28 • 618

upvoted a paper 12 months ago

From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

Paper • 2406.11939 • Published Jun 17, 2024 • 8

upvoted a collection about 1 year ago

Starling

2 items • Updated Mar 20, 2024 • 7

upvoted 6 papers almost 2 years ago

Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons

Paper • 2301.11270 • Published Jan 26, 2023 • 2

Online Learning in Stackelberg Games with an Omniscient Follower

Paper • 2301.11518 • Published Jan 27, 2023 • 1

Jump-Start Reinforcement Learning

Paper • 2204.02372 • Published Apr 5, 2022 • 1

Doubly Robust Self-Training

Paper • 2306.00265 • Published Jun 1, 2023 • 1

On Optimal Caching and Model Multiplexing for Large Model Inference

Paper • 2306.02003 • Published Jun 3, 2023 • 1

Fine-Tuning Language Models with Advantage-Induced Policy Alignment

Paper • 2306.02231 • Published Jun 4, 2023 • 2