Wenhu Chen [陈文虎 in Chinese]
Researcher in Artificial Intelligence
Email: hustchenwenhu [at] gmail [dot] com
Google Scholar / CV (updated in July 25) / Github / Twitter
Biography
Wenhu Chen is an AI researcher. He obtained the Canada CIFAR AI Chair Award in 2022. He worked at Google DeepMind from 2021 to 2025, where he contributed to the Gemini multimodel and evaluation efforts. Before that, he obtained his PhD from the CS department of the University of California, Santa Barbara. His research interest lies in natural language processing, deep learning, and multimodal learning. He aims to design models that handle complex reasoning scenarios, such as math problem-solving and knowledge grounding. He is also interested in building more powerful multimodal models to bridge different modalities. He won the prestigious Golden Jubilee Research Excellence Award at the University of Waterloo in 2025. He received the Area Chair Award in AACL-IJCNLP 2023, the Best Paper Honorable Mention in WACV 2021, and the UCSB CS Outstanding Dissertation Award in 2021.Research Interest
My research interest covers the following aspects:- Reasoning
- Information Retrieval
- Benchmarks and Evaluation
- Generative AI
Research Highlights
You might have heard of me because of the following work I conducted.1. Natural Language Processing (LLMs)
- Program-of-Thoughts: A prompting strategy to use tools to solve complex reasoning tasks
- MAmmoTH/MAmmoTH2/General Reasoner: Advancing reasoning model to solve complex reasoning tasks
- OpenCoderInterpreter/AceCoder: Advanced coding language models for complex tasks
2. Multimodal Understanding (Image & Video)
- MuRAG/UniIR/MagicLens/VLM2Vec/VLM2Vec-V2: the framework to enable unified and compositional multimodal information retrieval
- Mantis/MAmmoTH-VL/MAmmoTH-VL2: advanced vision-language models with better reasoning skills
- VL-Rethinker/Pixel-Reasoner: advanced vision-language models with better reasoning skills
3. Multimodal Generation (Image & Video)
- Re-Imagen/SuTI/Kosmos-G/Instruct-Imagen: the most effective and efficient and controllable image generation models
- T2V-Turbo/T2V-Turbo-v2: efficient text-to-video generation models
- MagicBrush/OmniEdit/AnyV2V: powerful image and video editing models
4. Benchmarks & Evaluation
- MMMU/MMLU-Pro/TheoremQA/MEGA-Bench:: the commonly used language model and vision-language model evaluation suite
- TabFact/HybridQA/OTT-QA: Table and text reasoning evaluation benchmarks
5. Others
- MERT/ChatMusician/YuE: Foundation models for understanding and composing music
- MAP-Neo/Fine-FineWeb: Fully open-source language models with high-quality pre-training datasets
- KB-BINDER/TableCoT/StructLM: Grounding foundation models on structured knowledge
- TheoremExplainAgent: Building agents for composing education videos
TIGER Lab
I direct the Text and Image GEnerative Research (TIGER) lab. My lab is focused on studying different generative models in different modalities including text, images, videos and music. We are committed to building powerful state-of-the-art models for various domains. Our lab is always looking for talented and self-motivated students.
Awards
- 2025: Math Golden Jubilee Award
- 2024: CVPR Best Paper Finalist
- 2023: AACL-IJCNLP23 Area Chair Award
- 2022: Canada CIFAR AI Chair
- 2021: UCSB CS Outstanding Dissertation Award
- 2021: WACV21 Best Student Paper Honorable Mention
- 2018: Tencent Rhino-Bird Award
- 2016: IDEA Research Grant
Fundings
- CIFAR AI Chair Funding: Accessing Diverse Web Knowledge with Natural Language Interface (2022 - 2027)
- NSERC Discovery Fund: Building Semiparametric Models to Decouple Knowledge from Computation (2023 - 2028)
- Mitacs Accelerate Fund: Question Answering over Long Clinical Documents (2024 - 2026)
- CIFAR AI Catalyst Fund: Generating Images with Multimodal Instruction (2024 - 2026)
- National Research Council Canada - AI4D Funding: Accelerating Scientific Discovery with Foundation Models (2024 - 2026)
- National Research Council Canada - New Beginning Funding: Building More Efficient Visual Generative Models (2025 - 2026)
