🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We started this moonshot project a year ago. Now we are excited to share our progress on robot learning from egocentric human data 🕶️🤲 Key idea: Egocentric human data is robot data in disguise. By bridging the kinematic, visual, and distributional gap, we can directly leverage

Model merging is tricky when model weights aren’t aligned Introducing KnOTS 🪢: a gradient-free framework to merge LoRA models. KnOTS is plug-and-play, boosting SoTA merging methods by up to 4.3%🚀 📜: arxiv.org/abs/2410.19735 💻: github.com/gstoica27/KnOTS

🤔Ever wondered why merging LoRA models is trickier than fully-finetuned ones? 🔍We explore this and discover that poor alignment b/w LoRA models lead to subpar merging. 💡The solution? KnOTS🪢— our latest work that uses SVD to improve alignment and boosts SOTA merging methods.

Congratulations! It's a proud moment for chess, a proud moment for India, a proud moment for WACA, and for me, a very personal moment of pride. Ding played a very exciting match and showed the champion he is. International Chess Federation WACA_Chess

I was winning against the World Champion 🥰

Introducing Gaze-LLE, a new model for gaze target estimation built on top of a frozen visual foundation model! Gaze-LLE achieves SOTA results on multiple benchmarks while learning minimal parameters, and shows strong generalization paper: arxiv.org/abs/2412.09586

Hang it in The Louvre — Winter Collection 😍❄️ 📸 IG/jfendipix

Run it back? ❄️

Excited to share a sneak peek into what we've been building at Yutori! What you see below is our trained model and internal prototype — multiple agents running in parallel in the background, completing tasks of varying complexity, relevant information and cues to step in being

Both academia and industry must rethink AI progress. The best teams don’t just chase scale — they explore ideas that shape the future and nurture humanity. The past few years have tested our resilience; now, we must rebuild the belief that innovation is possible at all scales.

happy to share that Gaze-LLE was accepted to #CVPR2025!

Some papers rejected due to "incremental novelty" 🫠 We as a community should emphasize less on being novel and more on being simple, interesting, and useful.

Join us at the WorldModelBench workshop at #CVPR2025 where we'll tackle systematic evaluation of World Models! Focus: benchmarks, metrics, downstream tasks, and safety. Submit papers now: worldmodelbench.github.io

🚀 Excited about how generative AI can power experimental (not just observational) audits of ML systems that reveal actionable insights into performance and bias? Join us at EMACS (Experimental Model Auditing with Controllable Synthesis) workshop #CVPR2025! sites.google.com/view/emacs2025/

Tired of switching between different AI models for different tasks? What if you could combine them instead? 🤖➕ 🚀 Excited to share our work, KnOTS — efficient model merging, which will be presented at ICLR 2025 in Singapore! 🇸🇬

Excited to announce the Artificial Social Intelligence Workshop @ ICCV 2025 #ICCV2025 Join us in October to discuss the science of social intelligence and algorithms to advance socially-intelligent AI! Discussion will focus on reasoning, multimodality, and embodiment.

We are very excited to host the Artificial Social Intelligence Workshop at #ICCV2025! We hope you'll join us there and consider submitting your work as a paper or extended abstract!

I'm at #CVPR2025—excited to connect, chat, and learn. Feel free to reach out if you want to meet up! #CVPR2025

The WorldModelBench workshop is happening tomorrow (June 12th) at #CVPR2025! We have an exciting series of talks, do attend! Place: Room 108 Time: Morning Session #NVIDIAResearch

Had the honor to present diffusion transformers at CS25, Stanford. The place is truly magical. Slides: bit.ly/dit-cs25 Recording: youtu.be/vXtapCFctTI?si… Thanks to Steven Feng for making it happen!