Yihong Sun

CS PhD student @Cornell | Ugrad @JohnsHopkins

[Yihong Sun @YihongSun_]

📢 Excited to share our latest #NeurIPS2025 work on tracking and understanding object transformations!

🔗: https://t.co/UR3pLVwiet

Come chat with us on Friday 12/5, 11AM-2PM, at Poster #4703!

[Bharath Hariharan @BharathHarihar3]

Continuing with NeurIPS: On Friday (12/5, 11AM-2PM, #4703), @YihongSun_ will be presenting our #NeurIPS2025 work on tracking objects through state changes.

[Albert Tseng @tsengalb99]

Excited to announce our #AISTATS📜on training LLMs with MXFP4! We use stoch. rounding and random Hadamard transforms (all fast on HW) to get low-variance, unbiased gradient estimates with MXFP4 GEMMs. We get a ~30% speedup over FP8 with almost no PPL gap!

https://t.co/UiVCRMXlsS

[Yihong Sun @YihongSun_]

📢 Excited to share our latest work: Video Creation by Demonstration!

arXiv: https://t.co/WRihWGSm0j

Check out our results here: https://t.co/GhYNisIjyn

[Ting Liu @_tingliu]

Introducing our latest work Video Creation by Demonstration, a novel video creation experience.

Paper: https://t.co/YZFCLKj5aM
Project: https://t.co/o9inp7qScE
Huggingface: https://t.co/Lg5h7kvr70

[Yihong Sun @YihongSun_]

Happy to get feedback and questions! For more details, please check out our paper! See you on Friday 10/4 at Poster Session 7, #73! 😃

Huge thanks to my advisor, @BharathHarihar3! This wouldn’t have been possible without your support!
(7/n)

[Yihong Sun @YihongSun_]

📢Excited to share our latest @eccvconf work MOD-UV on learning object detectors from unlabeled videos only!

🔗: https://t.co/QdmVsTpfeG

I will give a talk at Wild3D workshop (cc: @weichiuma) on Monday 9/30 and come chat with us on Friday 10/4 at Poster Session 7, #73!

[Yihong Sun @YihongSun_]

Results: We obtain significant improvements over previous unsupervised object detection methods across multiple datasets & metrics, with notable improvements in Box AR by 6.6 on Waymo Open, 5.9 on nuScenes, and 8.2 on KITTI compared to CutLER.
(6/n)

[Jieneng Chen @jieneng_chen]

Thanks @arankomatsuzaki for sharing our #CVPR2024 ViTamin work!

Collaborated with @yucornetto1, Xiaohui Shen, @YuilleAlan and Liang-Chieh Chen

TLDR: We design a scalable vision model in the vision-language era, advancing the limits for VLMs and multi-modal LLMs!

[Gemmechu Hassena @GemmechuHassena]

Excited to share our work, ObjectCarver! Given multiview images and click points on one image, ObjectCarver decomposes scenes into separate objects, providing high-quality 3D surfaces while handling occlusion and close-contact objects. (1/6)
website: https://t.co/vi5UVkUMBc