1 code implementation • 9 Apr 2024 • Jiayi Pan, Yichi Zhang, Nicholas Tomlin, Yifei Zhou, Sergey Levine, Alane Suhr
We show that domain-general automatic evaluators can significantly improve the performance of agents for web navigation and device control.
1 code implementation • 29 Feb 2024 • Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar
In this paper, we develop a framework for building multi-turn RL algorithms for fine-tuning LLMs, that preserves the flexibility of existing single-turn RL methods for LLMs (e. g., proximal policy optimization), while accommodating multiple turns, long horizons, and delayed rewards effectively.
1 code implementation • 7 Dec 2023 • Sihan Xu, Yidong Huang, Jiayi Pan, Ziqiao Ma, Joyce Chai
We show that when the initial sample is known, a special variance schedule reduces the denoising step to the same form as the multi-step consistency sampling.
Ranked #1 on Text-based Image Editing on PIE-Bench
2 code implementations • 6 Dec 2023 • Jiayi Pan, Chengcan Wang, Kaifu Zheng, Yangguang Li, Zhenyu Wang, Bin Feng
Our results show that, with SmoothQuant+, the Code Llama-34B model can be quantized and deployed on a A100 40GB GPU, achieving lossless accuracy and a throughput increase of 1. 9 to 4. 0 times compared to the FP16 model deployed on two A100 40GB GPUs.
1 code implementation • 31 Oct 2023 • Yichi Zhang, Jiayi Pan, Yuchen Zhou, Rui Pan, Joyce Chai
Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world.
1 code implementation • 14 Jun 2023 • Ziqiao Ma, Jiayi Pan, Joyce Chai
The ability to connect language units to their referents in the physical world, referred to as grounding, is crucial to learning and understanding grounded meanings of words.
1 code implementation • 9 Mar 2023 • Jiayi Pan, Glen Chou, Dmitry Berenson
We evaluate our approach on three existing LTL/natural language datasets and show that we can translate natural language commands at 75\% accuracy with far less human data ($\le$12 annotations).
1 code implementation • 22 Oct 2022 • Yichi Zhang, Jianing Yang, Jiayi Pan, Shane Storks, Nikhil Devraj, Ziqiao Ma, Keunwoo Peter Yu, Yuwei Bao, Joyce Chai
These reactive agents are insufficient for long-horizon complex tasks.
1 code implementation • 10 Jan 2022 • Donald Loveland, Jiayi Pan, Aaresh Farrokh Bhathena, Yiyang Lu
While edge deletion is a common method used to promote fairness in GNNs, it fails to consider when data is inherently missing fair connections.
no code implementations • 28 Nov 2021 • Jiayi Pan, Heye Zhang, Weifei Wu, Zhifan Gao, Weiwen Wu
To improve image quality from sparse-view data, a Multi-domain Integrative Swin Transformer network (MIST-net) was developed in this article.