Siqiao Huang
@KnightNemo_
Junior undergrad, Yao class @Tsinghua_Uni . Current intern @mldcmu. I'm interested in ML & Robotics.
🎥 Video diffusion models achieve stunning visual fidelity, powered by pretraining on massive internet-scale video datasets. But they’re not interactive—they don’t respond to actions or support causal rollout. 🤔 Can we harness their generative power to build autoregressive,…
🤖Can a humanoid robot carry a full cup of beer without spilling while walking 🍺? Hold My Beer ! Introducing Hold My Beer🍺: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control Project: lecar-lab.github.io/SoFTA/ See more details below👇
Guys, take a moment to look at this, this is worth some serious thoughts.
Stare at policy improvement and diffusion guidance, and you may notice a suspicious similarity... We lay out an equivalence between the two, formalizing a simple technique (CFGRL) to improve performance across-the-board when training diffusion policies. arxiv.org/abs/2505.23458
World Models already had their "Rich Sutton can't fit into the workshop room" moment! AI is truly accelerating at an immense speed. x.com/pabbeel/status…
Learning about World Models, Understanding, Modeling and Scaling at @iclr_conf this morning proved not quite realistic! Shouldn’t the organizers have guessed this would be pretty popular in 2025?
Thank @_akhaliq for sharing Vid2World, our work on crafting video diffusion models to interactive world models! Project Page: knightnemo.github.io/vid2world/
Vid2World Crafting Video Diffusion Models to Interactive World Models
Thrilled to present our new work at #ICRA2025 !
🚨 New work at #ICRA2025! Robust Robot Walker 🐾 We enable quadruped robots to pass tiny traps (bars, pits, poles) using only proprioception – no cameras, no depth! Catch us at Thursday 16:55pm in Room 305! 🔗 robust-robot-walker.github.io
🚀Excited to announce Dream 7B (Diffusion reasoning model): the most powerful open diffusion large language model to date.
Our relighting work is accepted to #ICLR2025. Paper: openreview.net/pdf?id=u1cQYxR… Code: github.com/lllyasviel/IC-… Demo: huggingface.co/spaces/lllyasv… We impose consistent light (IC-Light) transport during training. This consistency allows for stable and scalable illumination learning, and…