Kallol Saha ✈️ CoRL '26 (@_ksaha) header
Kallol Saha ✈️ CoRL '26 (@_ksaha) profile picture

Robotics PhD @ CMU I work on integrated learning and planning

Pittsburgh, Pennsylvania, USA
Joined May 2023
Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)Photo by Kallol Saha ✈️ CoRL '26 (@_ksaha)
🚨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 🧵👇
6
29
3
140
8,519
Kallol Saha ✈️ CoRL '26 retweeted
Excited to share that our work πR² (pi-r2-flow.github.io/) won 🏆 Best Paper Award 🏆 at the CoRL 2026 Workshop on Efficient Foundation Models for Real-Time Embodied AI! Many thanks to @shubhtuls who guided me in this project, and all the organizers of the workshop :)
6
8
97
4,002
Kallol Saha ✈️ CoRL '26 retweeted
Ever wondered how robots can learn task representations from unstructured human language? Today at #CoRL2026, I'm presenting my first-ever paper 🎉: Flexible Language-Guided Representation Editing for Adaptive Robot Behavior. Come say hi at Poster #37! 🧵1/8
1
5
11
571
I'm at #CoRL2026 and will be talking about DISCO at the Hilton Austin ballroom at 11-11:30 AM today! I will also be at poster no. 176 (2nd floor JW Marriott) - come chat! 👋 There will also be an official livestream here: youtube.com/live/uPXoJm-L3YY…
🚨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 🧵👇
1
14
495
Kallol Saha ✈️ CoRL '26 retweeted
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 mobile manipulation. 2. Pixel-UMI: environment aware whole body manipulation without robot data. w/ @JasonJZLiu (1/N)
26
55
24
346
41,840
Kallol Saha ✈️ CoRL '26 retweeted
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 👀)
🚨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 🧵👇
1
4
265
Kallol Saha ✈️ CoRL '26 retweeted
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 deployment? DISCO uses 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/
10
17
2
204
10,520
Kallol Saha ✈️ CoRL '26 retweeted
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)
2
12
2
54
2,750
Kallol Saha ✈️ CoRL '26 retweeted
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/grasp… 🧵👇 (1/9)
5
19
1
86
3,926
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/DISCO
1
1
265
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!🍻
2
234
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!!
1
1
110
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/DISCO
1
78