Research Scientist @GoogleDeepMind | PhD @Stanford
Stanford, California
Joined July 2013
- Tweets25
- Following235
- Followers153
- Likes84
Min Woo Sun retweeted
Excited to share DR-GEM, a self-supervised computational framework for dimensionality reduction and clustering, and its application to single-cell and spatial transcriptomics. nature.com/articles/s41467-0…
Congrats to the team! @christineyyeh, who spearheaded this study, @DixianZhu, and @minwsun.
Here is a quick overview of the paper 👇 (1/11)
Min Woo Sun retweeted
Frontier vision-language models can give convincing answers to biomedical questions—yet they often can’t tell what they’re looking at.
The MMBU benchmark at #ECCV26 showed this clearly: models frequently get the answer right while failing to identify the modality, body part, or stain.
Now, we’re challenging teams to tackle this perception bottleneck in biomedical AI.
3 tracks. $100K+ in compute and prizes. Oct 1–Dec 31.
📅 Good news: registration has been extended through September 30, so there’s still time to join!
Thanks to @gxl_ai, @AnthropicAI, @StanfordAILab, @na2uqi, and @biohub for supporting the challenge!
#MedicalAI #MultimodalAI #ComputerVision
Min Woo Sun retweeted
Introducing Gemini 3.8 Flash, another jump in Gemini's agentic + coding capabilities, and our 3rd updated Flash model in only 6 weeks...
This model has been a ton of fun to work with, excited to see what you all think!
1/ Excited to share our new work: “Accelerating Scientific Research with Gemini in the Real-World.”
We extend the AI Co-Scientist into an execution-grounded research system spanning ideation → experimentation → paper writing, and validate it across materials science, biology, and computer science. 🧵
Grateful to everyone who made this work possible. It was a privilege to contribute alongside such an amazing group of collaborators.
@SRSchmidgall , @_shaw_marth, Lin Yang, @valentinlievin, Jingyun Yang , Yuchen Zhuang, @timstro, Alex Bijamov, @minwsun, @apalepu13, Justin Chen, David Steiner, @JShreibati, @ckbjimmy, Yilin Zhao, Xingjian Hu, Nicholas Zahn, Sadhya Garg, Julia Kirby, Yuxiang Gan, Jiaoli Li, @divy93t, @AziziShekoofeh, David Racz, @Mysiak, @vivnat, @ChenglinWu3, @tdanino, @KeranRong, @harryhaozhewang, @benoitschilling, Yong Cheng, @quocleix, and @taotu831
8/ What I find most exciting is the direction this points toward: AI systems that don’t just reason about science, but can iteratively interact with experiments, code, measurements, and human experts.
7/ We evaluated these mechanisms in a double-blind study with 30 domain experts and 450 independent reviews.
The reliability modules reduced severe result hallucinations and plagiarism relative to the ablated baseline, while the safety system refused 98.7% of hazardous prompts.
6/ An important part of autonomous science is not just capability, but scientific reliability.
We therefore added mechanisms that explicitly penalize hallucination/plagiarism and verify manuscript claims against raw experimental execution logs before finalization.
5/ In computer science, we pushed autonomy further.
Given only a research directive, Co-Scientist autonomously designed and iterated an inference-time scaling architecture, Agent_H, which outperformed six frontier models on length-adjusted HealthBench Hard & Professional.
4/ In biology, Co-Scientist built a vision-based system to predict emergent E. coli swarming morphologies at unseen inducer concentrations from sparse experimental images.
The predictions showed quantitative concordance with subsequent wet-lab measurements across most evaluated morphology metrics.
3/ In materials science, Co-Scientist helped design CVD synthesis protocols tailored to a custom lab setup.
This included a safer precursor route for a 2D layered material with characteristics consistent with Ti₃C₂Tₓ MXene, as well as single-attempt growth of monolayer MoS₂, MoSe₂, and WS₂.
2/ A central question for AI-for-science is:
Can an AI system move beyond hypothesis generation to interface with real-world experiments and empirical feedback?
Here, we explore that spectrum, from human-executed wet-lab experiments to fully autonomous computational research.
Incredible work by @valentinlievin, @SRSchmidgall, @timstro, Alex Bijamov and the @GoogleDeepMind @GoogleResearch team! So proud to be part of this project before officially starting my RS role in a few weeks!
Medical training begins in textbooks, but clinical competence is forged through practice. We introduce ResidencyRL: a multi-turn online RL method to train health agents in simulation, and demonstrate significant gains on top of frontier systems. arxiv.org/abs/2608.07418
ALT Paper visual abstract
Min Woo Sun retweeted
Introducing MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research #CVPR2025
✅ 1k multimodal reasoning VQAs testing MLLMs for science
🧑🔬 Biology researchers manually created the questions
🤖 RefineBot: a method for fixing QA language shortcuts
🧵
Min Woo Sun retweeted
🚨Large video-language models LLaVA-Video can do single-video tasks.
But can they compare videos?
Imagine you’re learning a sports skill like kicking: can an AI tell how your kick differs from an expert video?
🚀 Introducing "Video Action Differencing" (VidDiff), ICLR 2025
🧵
Min Woo Sun retweeted
Biomedical datasets are often confined to specific domains, missing valuable insights from adjacent fields. To bridge this gap, we present BIOMEDICA: an open-source framework to extract and serialize PMC-OA.
📄Paper: lnkd.in/dUUgA6rR
🌐Website: lnkd.in/dnqZZW4M
Min Woo Sun retweeted
Among the most impressive aspect of the Llama 3.1 release is the accompanying research paper! Close to 100 pages of deep knowledge-sharing on LLMs like we havn't seen very often recently
What a treat!
It covers everything, pretrainining data, filtering, annealing, synthetic data, scaling laws, infrastructures, parallelism, training recipees, post-training adaptation, tool-use, benchmarking, inference strategies, quantization, vision, speech, videos...
Mind-blown! Maybe the single paper you can read today to join the field of LLM from zero right to the frontier
Read it here and feel the open-science ai.meta.com/research/publica…
