Haobo Yuan

PhD Student @ UC Merced

[Chen Change Loy @ccloy]

Proud to share our lab’s @MMLabNTU work Log-linear Sparse Attention (LLSA) - a trainable sparse attention mechanism that reduces attention complexity from O(N²) to O(N log N), making diffusion transformers much more efficient.

Also, special shout-out to the first author @zhouyifan1107 for presenting the poster in full costume - truly above and beyond. The level of dedication is impressive! 👏

#CVPR2026 #DiffusionModels #EfficientAI #SparseAttention

[Haobo Yuan @HarborYuan]

Sa2VA is the the first unified model for dense grounded understanding of both images and videos. It combines the SAM-2 and MLMM models to enable a wide range of image and video tasks in minimal one-shot instruction tuning.

[Haobo Yuan @HarborYuan]

Introducing our Sa2VA. 🔥

Project Page: https://t.co/6RFu459ks2
GitHub: https://t.co/4VPQxABO33
Huggingface Demo: https://t.co/yyWI7WvQXh (Feat: @huggingface @fffiloni )
We provide various ways to get a quick start. Have fun~🥳

[merve @mervenoyann]

ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license 💗

The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) for images and videos ⏯️
take a look 🧶

[Adina Yakup @AdinaYakup]

Sa2Va 🔥 a unified model for dense grounded understanding of images & videos released by Bytedance.
Model: https://t.co/yjTV7yGjiI
Paper: https://t.co/ntvcGrtJmg
✨ 1B/4B/8B
✨ Based on InternVL, used Qwen2 & 2.5, InternLM as language part.
✨ unifies text, images, and videos into a shared token space for seamless multimodal interactions

[Haobo Yuan @HarborYuan]

Our Open-Vocabulary SAM has been accepted by ECCV 2024. 🔥

Project Page: https://t.co/izru0l2he3
Code: https://t.co/I4ysfJi2V5

#ECCV

[AK @_akhaliq]

mmlab-ntu presents Open-Vocabulary SAM

Segment and Recognize Twenty-thousand Classes Interactively

paper page: https://t.co/QqODebOcPp

Open-Vocabulary SAM extends SAM's segmentation capabilities with CLIP-like real-world recognition, while significantly reducing computational costs. It outperforms combined SAM and CLIP methods in object recognition on the COCO open vocabulary benchmark

[Xiangtai Li @xtl994]

Happy to share that our survey has been accepted by T-PAMI. @HenghuiDing @HarborYuan

We present the first comprehensive survey on open-vocabulary learning: detection, segmentation, video, 3D analysis, etc.

Paper: https://t.co/uju0cI37oy

Github: https://t.co/9BivSt22uN

[Haobo Yuan @HarborYuan]

@ClementDelangue Congrats. Hugging Face🤗 is really helpful in my research.

[MrBeast @MrBeast]

I’m gonna give 10 random people that repost this and follow me $25,000 for fun (the $250,000 my X video made)

I’ll pick the winners in 72 hours

[Xiangtai Li @xtl994]

Glad to share one research work during my post-doc study with @HarborYuan @ccloy.

Name: OMG-Seg: Is One Model Good Enough For All Segmentation?

Arxiv: https://t.co/uO1UFFcRjl

Project Page: https://t.co/3tflOkGmOR

Code: https://t.co/Xji2qTcLti

Demo: https://t.co/QBkW7YWHCJ

[Haobo Yuan @HarborYuan]

Thank you @AK for sharing our work!
We are excited to introduce our Open-Vocabulary SAM, which fuses the knowledge from two foundation models (CLIP and SAM) into a unified architecture.

Website: https://t.co/08w7K1s4qU
Code: https://t.co/I4ysfJi2V5
Paper: https://t.co/sgSNvCvBup

[AK @_akhaliq]

mmlab-ntu presents Open-Vocabulary SAM

Segment and Recognize Twenty-thousand Classes Interactively

paper page: https://t.co/QqODebOcPp

Open-Vocabulary SAM extends SAM's segmentation capabilities with CLIP-like real-world recognition, while significantly reducing computational costs. It outperforms combined SAM and CLIP methods in object recognition on the COCO open vocabulary benchmark

[iSchool at Illinois @iSchoolUI]

Maintaining anonymity on the internet has become increasingly challenging. @MIT @techreview explores China's shift away from online anonymity, highlighting research conducted by #iSchoolUI PhD student @kyriezz78. Check out the full article: https://t.co/xW13oghxnK

[Chong Zhou @ChongZhou7]

Introducing EdgeSAM, the first SAM variant that can run at over 30 FPS on an iPhone 14 with minimal compromise in performance.

Code, models, and Hugging Face demo are available!

arXiv: https://t.co/kPt7fnlCvC
Project page: https://t.co/6w60RZQgnG

[Google DeepMind @GoogleDeepMind]

We’re excited to announce 𝗚𝗲𝗺𝗶𝗻𝗶: @Google’s largest and most capable AI model.

Built to be natively multimodal, it can understand and operate across text, code, audio, image and video - and achieves state-of-the-art performance across many tasks. 🧵 https://t.co/mwHZTDTBuG

[Xiangtai Li @xtl994]

Happy to achieve 500+ stars. https://t.co/XDmGcqE4uC. We will continue to update the draft on the arxiv. @HenghuiDing @wenweiz97 @HarborYuan

[Andrea Tagliasacchi @CVPR @taiyasaki]

This is how you get a 2-column (SIGGRAPH style) teaser image in #CVPR2024 (code and outcome below)

[Haobo Yuan @HarborYuan]

@encounter19972 Awesome work!!

[encounter1997 @encounter19972]

Excited to share our recent work "Object-aware Inversion and Reassembly for Image Editing"

Paper: https://t.co/q6mn33f2V6
Code: https://t.co/Kl8ox0c7Dr
Project Page: https://t.co/EKJuo3tlMW

(1/5)

[European Conference on Computer Vision #ECCV2026 @eccvconf]

#ECCV2022 paper submission deadline in a month!

https://t.co/NprCpmChMs

[Haobo Yuan @HarborYuan]

Requesting faucet funds into 0x8F9e997625c285a84fF6Dc1BB38d0574093d99ac on the #Rinkeby #Ethereum test network.

[Haobo Yuan @HarborYuan]

Requesting faucet funds into 0x8F9e997625c285a84fF6Dc1BB38d0574093d99ac on the #Rinkeby #Ethereum test network.