Zhiding Yu

@ZhidingYu

Working to make machines understand the world like human beings. Words are my own.

Santa Clara

chrisding.github.io

Replies Reposts Media

Pinned
Zhiding Yu
@ZhidingYu
Jul 27
Better multimodal models need better spatial data. Today we’re open-sourcing LocateAnything-Data — a high-quality, training-ready spatial data collection with 12M images, 138M queries, and 785M annotations spanning multi-object detection, referring expression grounding, physical
1
Zhiding Yu
@ZhidingYu
Jun 5
We are presenting Fast-ThinkAct at 10:45am this morning at Poster #469. Welcome to drop by and discuss!
Fu-En (Fred) Yang
@FuEnYang1
Feb 23
🚀 Excited to share that our paper Fast-ThinkAct has been accepted to #CVPR2026! 🎉 Efficient Vision-Language-Action reasoning via verbalizable latent planning — enabling embodied agents to think fast internally without lengthy textual reasoning. ⚡ Achieves 9.3× faster
Zhiding Yu
@ZhidingYu
Jun 4
Super fun stuff just keeps popping up!
Noctus
@noctus91
Jun 2
Spent some time testing @NVIDIAAI LocateAnything 3B model . Point at an object, a button, a piece of text just describe it in words and it locates it instantly. The combination of grounding, OCR, and UI understanding in a model this size genuinely surprised me. The fact
Zhiding Yu
@ZhidingYu
Jun 4
This was so fast! Yes we were planning to do similar stuff : ) Nice work!
stevibe
@stevibe
Jun 3
I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System
00:00
1
Zhiding Yu
@ZhidingYu
Jun 1
LocateAnything is trending top on Hugging Face Models, together with PiD and many awesome models from NVIDIA. A remarkable moment for NVIDIA and teams!
clem 🤗
@ClementDelangue
Jun 1
So much great work lately from Nvidia, the "King of American Open-source AI"! - Crossed 1,000 total public repositories on @huggingface (820 models, 249 datasets & 57 spaces) & almost 60,000 followers - Current #1 trending model on HF with LocateAnything and #5 trending with PiD