Weixi Feng

Weixi Feng (冯蔚熙)

I am an Applied Scientist at Amazon AGI, working on text-to-video model pre-training. I obtained my Ph.D. in CS from the UCSB NLP group, where I was advised by Prof. William Wang. I have also interned at NVIDIA Research, Adobe Research, and Amazon.

I have spent wonderful years in Beijing, Hong Kong, and SoCal, and I am now based in Mountain View, CA.

Email: weixif565 at gmail dot com

Email / CV (Outdated) / Google Scholar / GitHub / Twitter / LinkedIn

Photo credit: Ting Lu

News

May, 2025. Joined Amazon AGI as an Applied Scientist working on text-to-video foundation model pre-training.

Jan. 13th, 2025. Just released BlobGEN-Vid, my latest internship work with NVIDIA. Check it out below!

Research

My research interests lie at the intersection of vision and language. I am broadly interested in visual generative models and controllable image/video generation.

Publication

	TC-Bench: Benchmarking Temporal Compositionality in Conditional Video Generation Weixi Feng, Jiachen Li, Michael Saxon, Tsu-Jui Fu, Wenhu Chen, William Yang Wang ACL 2025 Findings Proceedings / Preprint / Project page / Code&data
	BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representation Weixi Feng, Chao Liu, Sifei Liu, William Yang Wang, Arash Vahdat, Weili Nie CVPR 2025 Preprint / Project page / Code (coming soon) / Demo Video
	MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos Xuehai He, Weixi Feng, Kaizhi Zheng, Yujie Lu, Wanrong Zhu, Jiachen Li, Yue Fan, Jianfeng Wang, Linjie Li, Zhengyuan Yang, Kevin Lin, William Yang Wang, Lijuan Wang, Xin Eric Wang ICLR 2025 Preprint / Project page / Code & Data
	T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback Jiachen Li, Weixi Feng, Tsu-Jui Fu, Xinyi Wang, Sugato Basu, Wenhu Chen, William Yang Wang NeurIPS 2024 Preprint / Project page / Code
	Reward Guided Latent Consistency Distillation Jiachen Li, Weixi Feng, Wenhu Chen, William Yang Wang TMLR 2024 (Featured Certification) Preprint / Project page / Code
	Discriminative Diffusion Models as Few-shot Vision and Language Learners Xuehai He, Weixi Feng, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Eric Wang TMLR 2024 Preprint / Code
	VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View Raphael Schumann, Wanrong Zhu, Weixi Feng, Tsu-Jui Fu, Stefan Riezler William Yang Wang, AAAI 2024 Preprint / Paper / Code
	LayoutGPT: Compositional Visual Planning and Generation with Large Language Models Weixi Feng, Wanrong Zhu, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Xuehai He, Sugato Basu, Xin Eric Wang, William Yang Wang * equal contribution NeurIPS 2023 Preprint / Project page / Code
	EDIS: Entity-Driven Image Search over Multimodal Web Content Siqi Liu, Weixi Feng, Tsu-Jui Fu, Wenhu Chen, William Yang Wang * equal contribution EMNLP 2023 Main Preprint / Code
	Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis Weixi Feng, Xuehai He, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, Xin Eric Wang, William Yang Wang ICLR 2023 OpenReview / Preprint / Project page / Code
	Neuro-Symbolic Procedural Planning with Commonsense Prompting Yujie Lu, Weixi Feng, Wanrong Zhu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, William Yang Wang ICLR 2023 (Spotlight) OpenReview / Preprint / Code
	ULN: Towards Underspecified vision-and-Language Navigation Weixi Feng, Tsu-Jui Fu, Yujie Lu, William Yang Wang EMNLP 2022 Main Abstract in 2nd Unimplicit Workshop, NAACL, 2022 Proceedings / Preprint / Code
	CPL: Counterfactual Prompt Learning for Vision and Language Models Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Eric Wang EMNLP 2022 Main Proceedings / Preprint / Code