Anne Lee

@AnneLe222

1st year PhD. @berkeley_ai

Berkeley, CA

Joined March 2025

98 Following

507 Followers

Replies Reposts Media

Anne Lee
@AnneLe222
Oct 15
We are presenting COVA-SFT in BayLearn 2026! A lot of researchers are visiting this problem, and you should definitely check this dataset out!! Humans think visually, even for text-only problems. We generated a large scale public dataset to use. Paper:
arxiv.org
CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions
Chain-of-thought (CoT) reasoning has dramatically improved large language models (LLMs) by allowing them to decompose problems into intermediate steps. While CoT is widely effective for linguistic...
2
Anne Lee
@AnneLe222
Apr 13
I’m returning to Berkeley as a Ph.D. in EECS, specializing in Computer Vision! I am grateful for my mentors/family/friends who have guided me through this process. I cant wait to continue building exciting work in @berkeley_ai. Stay tuned!!
51
Anne Lee
@AnneLe222
Nov 30, 2025
We are presenting "Generate, but Verify". Our backtracking schema reduces VLM hallucinations significantly. See how we implemented this in a single VLM architecture. Visit our poster session to chat with us! 📄: arxiv.org/abs/2504.13169 @NeurIPSConf
Patrick Wu
@tsunghan_wu
Nov 29, 2025
Excited to see @deepseek_ai push the generation-verification idea to IMO-level math (insane!) We’ve been exploring the same flow earlier this year and it really cuts VLM hallucinations! NeurIPS folks, come chat at our poster: Thu Dec 4, 4:30–7:30 pm, Exhibit Hall C/D/E, #4618.
1
Anne Lee
@AnneLe222
Nov 27, 2025
Me as an undergrad, I am super fortunate to learn and work w Patrick - has so many ideas in bringing up exciting problems in AI that needs to be solved someday and this essay is amazing - check it out!
Patrick Wu
@tsunghan_wu
Nov 27, 2025
Accidentally wrote a blog post on dynamic human-AI interaction this week, sharing some tentative ideas I find interesting in this field and the connection to our REVERSE-VLM. I’ll be presenting it at NeurIPS next week. Happy to chat more at San Diego 🙂 patrickthwu.com/posts/dynamic-…
Anne Lee
@AnneLe222
Nov 2, 2025
Attending EMNLP2025 (SuZhou)! 🍀 Showing our work visual puzzles with @_dmchan , and supporting the community as a volunteer Happy to meet everyone and to make new connections! @emnlpmeeting #EMNLP2025 arxiv.org/abs/2505.23759 : An exciting dataset to test vlm capabilities
arxiv.org
Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint
Rebus puzzles, visual riddles that encode language through imagery, spatial arrangement, and symbolic substitution, pose a unique challenge to current vision-language models (VLMs). Unlike...
4

Anne Lee

Anne Lee’s posts