🚨Introducing DISCO🪩: Distilled Tree Search over Continuous Actions (Best Paper Finalist🏆 at #CoRL2026)

DISCO combines learned policies with Monte-Carlo Tree Search (MCTS) over continuous actions for long-horizon manipulation tasks.

A thread 🧵👇

A Case for Paper Grading Boards (Or: A Plea for More Proposals to Radically Reform Peer Review)

tomsilver.github.io/blog/2026/reth…

Back in ~Dec 2025, I really wanted to work on mobile manipulation, but robots were either too expensive or not performant enough.

So we built our own!

Excited to finally share something I’ve had so much fun working on:

1. Pixel: a co-designed full stack system for learning Pixel-UMI: environment aware whole body manipulation without robot data.

w/ @JasonJZLiu

(1/N)

Kallol shows the world (what I consider) the right way to combine planning and learning with DISCO!

PS - catch his oral talk if you want to see him show (what I consider) the world the right way to do presentations as well (thanks to @vincesitzmann 👀)

Thrilled to share that our paper DISCO: Distilled Tree Search over Continuous Actions has been selected as a 𝐂𝐨𝐑𝐋 𝟐𝟎𝟐𝟔 𝐁𝐞𝐬𝐭 𝐏𝐚𝐩𝐞𝐫 𝐀𝐰𝐚𝐫𝐝 𝐅𝐢𝐧𝐚𝐥𝐢𝐬𝐭! 🏆 Congrats to @_ksaha 🎉

Can robots learn to plan for the long horizon without expensive search at Monte Carlo Tree Search in simulation and iteratively distills its discoveries into a policy that can execute directly, without search at test time. We demonstrate strong performance on long-horizon object packing and stacking, including real-world transfer!

📍 Catch us in Austin!
🎤 Oral: Nov 10, 11:00–11:30 AM | Hilton Austin (Session O6)
📌 Poster: Nov 10, 5:00–6:30 PM | JW Marriott Austin (Session P2, Poster #176)

🔗 distilled-search.github.io

Does more human video always improve robot learning? 👀

Excited to introduce H2RBench, our #CoRL2026 work—a Real2Sim benchmark for evaluating human-to-robot transfer methods.

🧵 (1/9)

Can learning to grasp teach a robot to use tools? 🤖🖐️

Introducing our #CoRL2026 paper:
“From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation”
We turn grasp data into pretraining for autonomous tool use.

🎥 Project & videos: yingyuan0414.github.io/grasp2dexterit…
🧵👇 (1/9)

Check out our website, paper and codebase for more details!
We also built an interactive game🎮 to demonstrate the DISCO algorithm. Can you find more plans than DISCO?👀

Website: distilled-search.github.io
Paper: arxiv.org/abs/2610.25785
Code: github.com/kallol-saha/DI…

If you are attending CoRL, do visit our Oral Talk and Poster Session:

🎤 Oral: Nov 10, 11:00–11:30 AM | Hilton Austin (Session O6)
📌 Poster: Nov 10, 5:00–6:30 PM | JW Marriott Austin (Session P2, Poster #176)

See you in Austin!🍻

For the past year, I’ve been very excited about bringing the AlphaGo recipe to robot learning. I’m deeply grateful to my advisors, Prof. Maxim Likhachev and Prof. @davheld, and my collaborators @yining_hong, @ambermli, and @YejinChoinka for supporting me every step of the way!!

Check out our website, paper and codebase for more details!
We also built an interactive game🎮 to demonstrate the DISCO algorithm. Can you find more plans than DISCO?👀

Website: distilled-search.github.io
Paper: arxiv.org/abs/2610.25785
Code: github.com/kallol-saha/DI…