ByteDance KeyBank Center, Bellevue, WA.
10655 NE 4th St
Bellevue, WA 98004
Welcome to my homepage. I am Quanzeng You. Currently, I am a research scientist at ByteDance working on Computer Vision. Before that, I am a researcher at Microsoft Azure Computer Vision Science Group.
I received my Ph.D. degree from Department of Computer Science, University of Rochester. My Ph.D. advisor is Prof. Jiebo Luo. I am broadly interested in computer vision, deep learning and multimedia content understanding.
news
| Mar 08, 2024 | InfiMM-HD is ON: A Leap Forward in High-Resolution Multimodal Understanding. |
|---|---|
| Jan 18, 2024 | InfiMM models are released at HuggingFace InfiMM. This is another open-source reproduction based on Flamingo architecture. We held the top position on the MMMU leaderboard at the time of our submission (Jan 1 2024).  |
| Jan 18, 2024 | Check out our findings on Visual Instruction Fine-tuning: COCO is “ALL” You Need for Visual Instruction Fine-tuning |
| Jan 11, 2024 | Our survey on MLLM Reasoning is available online: A Comprehensive Survey on Emerging Trends in Multimodal Reasoning |
| Dec 04, 2023 | InfiMM-Eval is ON: Complex Open-ended Reasoning Evaluation for MLLMs. |