Yating Wu

What does a scientific figure make you wonder? 📊 When we read papers, figures often raise questions that the surrounding text helps answer. But most VLM benchmarks focus on questions answerable from the figure alone. We introduce MQUD: 1,250 inquisitive questions over 245 figures from 56 papers, annotated by original paper authors. MQUD extends Questions Under Discussion (QUD) from text to multimodal scientific discourse. Instead of asking only what is visible, MQUD asks what implicit scientific question a figure raises in context.

@kaiwei_chang Congratulations!!

I’ve recently been promoted to Full Professor at UCLA 🎉 It’s been a long journey, with many tears, laughs, and surprises along the way. When I was working on linear models 20 years ago, I couldn’t have imagined we’d be building trustworthy AI agents today. I feel incredibly fortunate and deeply grateful to my research group, mentors, collaborators, and students who have made this journey so meaningful. I still remember the moment of hooding each of my PhD students. Those are the happiest moments in my career. Many thanks as well to my family, colleagues, and friends for their support. Looking forward to the next chapter. For those interested, check out our recent work: web.cs.ucla.edu/~kwchang/ Photo: a decade after graduation

@AlexGDimakis Thank you Alex!

@YatingWu96 Great work Yating !

What does a scientific figure make you wonder? 📊 When we read papers, figures often raise questions that the surrounding text helps answer. But most VLM benchmarks focus on questions answerable from the figure alone. We introduce MQUD: 1,250 inquisitive questions over 245 figures from 56 papers, annotated by original paper authors. MQUD extends Questions Under Discussion (QUD) from text to multimodal scientific discourse. Instead of asking only what is visible, MQUD asks what implicit scientific question a figure raises in context.

[4/4] Paper: arxiv.org/abs/2604.23733 Project page: lingchensanwen.github.io/multimodal-qud/ Dataset: huggingface.co/datasets/lingc… w/@WilliamRudmanjr, Venkat Govindarajan, @AlexGDimakis, @jessyjli

[3/4] Do VLMs actually ground in the figure? Fine-tuning Qwen3.5-9B on MQUD makes generated questions more grounded in the figure and more specific to the paper’s scientific content.

[4/4] Project page: lingchensanwen.github.io/multimodal-qud/ Dataset: huggingface.co/datasets/lingc…

[3/4] Do VLMs actually ground in the figure? Fine-tuning Qwen3.5-9B on MQUD makes generated questions more grounded in the figure and more specific to the paper’s scientific content.

1k+ downloads each on the MINT empathy models since release 🔥 Encouraging to see the interest in our work! tl;dr: In multi-turn empathic dialogue, LLMs reuse the same discourse moves far more often than humans do; MINT uses RL to diversify them. Give it a try!👇 huggingface.co/hongli-zhan/MI…

New paper! 🏁 My final one from my PhD at UT Austin. 🦜LLMs sound empathic, but they keep saying the same thing over and over. Not just the same words, the same discourse moves, turn after turn. We found that LLMs repeat the same discourse moves at nearly 2x the rate of human supporters across a multi-turn conversation, and existing metrics don’t catch this. So we built MINT 🌿 (Multi-turn Inter-tactic Novelty Training), the first RL framework to optimize discourse move diversity in multi-turn empathic dialogue. +25% empathy, −26% repetition. w/ @jessyjli @_desmond_ong et al. 📄 arxiv.org/abs/2604.11742

📢 Please note a critical update to the original #EMNLP2026 Call for Papers: since EMNLP and AACL share the ARR May cycle, authors will need to explicitly select a target conference at submission time. This choice will be binding! For more details see: #paper-submission-information" target="_blank" rel="nofollow noopener">2026.emnlp.org/calls/main_con…

@MLFoundations Congratulations to Adam!

Adam Klivans Wins Test of Time Award at FOCS 2025: cs.utexas.edu/news/2025/adam…

LLMs trained to memorize new facts can’t use those facts well.🤔 We apply a hypernetwork to ✏️edit✏️ the gradients for fact propagation, improving accuracy by 2x on a challenging subset of RippleEdit!💡 Our approach, PropMEND, extends MEND with a new objective for propagation.

Language is often strategic, but LLMs tend to play nice. How strategic are they really? Probing into that is key for future safety alignment.🛟 👉Introducing CoBRA🐍, a framework that assesses strategic language. Work with my amazing advisors @jessyjli and @David_Beaver! 🧵👇

How good are LLMs at 🔭 scientific computing and visualization 🔭? AstroVisBench tests how well LLMs implement scientific workflows in astronomy and visualize results. SOTA models like Gemini 2.5 Pro & Claude 4 Opus only match ground truth scientific utility 16% of the time. 🧵

A key hypothesis in the history of linguistics is that different constructions share underlying structure. We take advantage of recent advances in mechanistic interpretability to test this hypothesis in Language Models. New work with @kmahowald and @ChrisGPotts! 🧵👇

Introducing ChartMuseum🖼️, testing visual reasoning with diverse real-world charts! ✍🏻Entirely human-written questions by 13 CS researchers 👀Emphasis on visual reasoning – hard to be verbalized via text CoTs 📉Humans reach 93% but 63% from Gemini-2.5-Pro & 38% from Qwen2.5-72B

Have that eerie feeling of déjà vu when reading model-generated text 👀, but can’t pinpoint the specific words or phrases 👀? ✨We introduce QUDsim, to quantify discourse similarities beyond lexical, syntactic, and content overlap.

@naoto_inoue_ おめでとうございます！

I have joined Apple as a senior machine learning engineer and will relocate to BayArea once the visa is issued (hopefully in a few months?).