Zineng Tang

@ZinengTang

PhD in @Berkeley_ai and @BerkeleyNLP. Previously @UNCNLP and @MSFTResearch.

Berkeley, CA

zinengtang.github.io

Joined February 2019

590 Following

1,758 Followers

Replies Reposts Media

Zineng Tang
@ZinengTang
Oct 3
Come hang out at our #COLM2026 workshop on Oct 9! LSEI asks how LMs can learn by interacting w/ the world and other agents! We’ve got an exciting speaker lineup and plenty to discuss. Bring your questions & hot takes! 🔥 📍 Hilton SF Union Sq, 15&16 🔗 …arning-situated-interaction.github.io
1
Zineng Tang
@ZinengTang
Sep 18
Check out our paper at COLM 2026. We make (world-model based) controller language-instructable. It needs no manual labels with rollouts + our pos-hoc annotation method. The result is a flexible controller interface that any VLM/human can plug into. zinengtang.github.io/instruct-to-act
Zineng Tang
@ZinengTang
Jun 5
Excited to announce LSEI @ COLM 2026: Workshop on Learning from Situated and Embodied Interaction, happening in San Francisco on Oct 9! We study how interaction can serve as a learning signal for language models. Deadline: June 23, 2026 CFP: …arning-situated-interaction.github.io (1/2)
1
Zineng Tang
@ZinengTang
Jun 6, 2025
Excited to share our new work! DOVE 🕊️: a dynamic vision encoder that adapts token count to image complexity. Fewer tokens, same fidelity—outperforming fixed-length AEs tokenizer on classification & VLM tasks! Arxiv: arxiv.org/abs/2506.03643 Web: dove-encoder.github.io/dove-encoder/ #AI #CV
1
Zineng Tang
@ZinengTang
Mar 20, 2025
We are thrilled to announce TULIP! 🌷 tulip-berkeley.github.io A state of the vision language encoders coupled with generative model for stronger representation learning.
Long Lian and 2 others
7