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 :)
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
Kallol Saha ✈️ CoRL '26 retweeted
A Case for Paper Grading Boards (Or: A Plea for More Proposals to Radically Reform Peer Review)
tomsilver.github.io/blog/202…
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)
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 🧵👇
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/
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)
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)
Kallol Saha ✈️ CoRL '26 retweeted
How fast can you plan motions for 8 arms visiting 40 welding targets in one workcell?
Introducing cuArms: multi-agent planning meets GPU acceleration to generate coordinated motion plans in seconds, without task-specific training.
cuarms.github.io/
Kallol Saha ✈️ CoRL '26 retweeted
Life update: I recently graduated from CMU RI, and last year I went through the academic faculty job market in robot learning. I was fortunate to receive a lot of help and support from many people throughout the process.
Compared to industry job applications, there are relatively few resources available online about the faculty application process. So I decided to open-source all of my application materials from last year here:
docs.google.com/document/d/1…
I hope these materials can be helpful to others who are considering pursuing an academic career!
Kallol Saha ✈️ CoRL '26 retweeted
How your robot moves depends on what it’s driving over, especially when moving at >10m/s over loose gravel or ice 🚙💨
What if dynamics models could be conditioned on exactly the terrain they expect to drive over? Introducing SpatialBEV!
Accepted at #CoRL2026 🤠
0/7
Kallol Saha ✈️ CoRL '26 retweeted
🌍 Excited to share T2-z: Test-Time Optimization of Environment Latents for Robotic World Models!
Same observation, same action, different environments → different outcomes.
How can world models adapt to hidden environmental factors like friction, mass, or physical rules?
💡 T2-z conditions world models on optimizable environment latents.
T2-z directly optimizes the conditioning latents through world prediction, without supervision of what these factors are, what values they take, or how many factors exist.
📊 Meaningful latent structure emerges purely through world prediction! For compounded environmental factors (mass × friction), PCA of the learned latents reveals a two-dimensional structure that closely reflects the underlying factor distribution, despite the model never knowing how many factors are present or what they represent.
🤖 Across 7 simulated settings and 4 real-world robotic tasks, T2-z:
•Reduces object prediction error from 15.20 to 7.00 (54% reduction).
•Improves action success from 33.73% to 72.96% (+39.23 percentage points).
🌐 Project: t2-z-latent-optimization.git…
📄 Paper: arxiv.org/abs/2610.22364
💻 Code: github.com/T2-z-latent-optim…
Collab with Chenyuan, @RavenHuang4 @YunfanJiang @wenlong_huang @davheld @vitorguizilini @yuewang314 @drfeifei @jiajunwu_cs , leo and @YejinChoinka
Kallol Saha ✈️ CoRL '26 retweeted
Can we make dexterous robots compliant without sacrificing precise control?
Excited to introduce FOMO-Dex: Force-Modulated Dexterity! 🖐️
FOMO-Dex brings force-aware compliance to dexterous teleoperation, enabling robots to pick up thin cards and chips 🃏, cut paper 🔪, turn nuts 🔩, and use screwdrivers 🪛.
These force-aware demonstrations also train better autonomous policies!
🎥 Videos & paper: yingyuan0414.github.io/fomo-…
🧵👇 (1/8)
Kallol Saha ✈️ CoRL '26 retweeted
AI can increasingly make progress on open problems like Navier-Stokes. Yet defining a new problem still relies on human research taste.
Introducing ScholarCatalyst, a benchmark built from AI researchers’ firsthand accounts of what inspired their work.
Kallol Saha ✈️ CoRL '26 retweeted
How can robots keep learning once deployed in the messy, ever-changing real world?
Excited to announce our #CoRL2026 workshop on “Robot Learning at Deployment”!
We’ll explore how robots can continually adapt and improve under real-world constraints. 🧵
Kallol Saha ✈️ CoRL '26 retweeted
Boo! 👻 GHOST has been accepted to #RSS2026!
Can we learn manipulation skills from human video (without action retargeting)?
Yes! GHOST learns generalizable manipulation skills by training a hierarchical policy with an embodiment-agnostic sub-goal predictor + embodiment-specific controller.
🧵(1/7)
Kallol Saha ✈️ CoRL '26 retweeted
Excited to be at #ICRA2026 in Vienna this week 🇦🇹 -- I'll be presenting SCOUT as a spotlight talk at the Rigorous Robot Perception workshop on June 01 at VIP Lounge C, and SceneComplete as an Oral talk today (June 02 at TuAT3.5).
Kallol Saha ✈️ CoRL '26 retweeted
As a planning+learning researcher, I’m really excited about KinDER. It clarifies planning (especially TAMP) for outsiders, defines key open challenges for the field, and creates a common ground to compare & combined planning+learning approaches. (1/n)
Meet KinDER — a stress test for robot physical reasoning. All 13 methods failed 😈
🌎 25 environments
♾️ Infinite tasks
🏋️ Gymnasium API
⚒️ Over 20 parameterized skills
🪧 Human demonstrations
📊 13 baselines (planning and learning)
From @Princeton @CMU_Robotics @ICatGT @CambridgeMLG @nvidia @MIT_CSAIL
🧵 1/n
Kallol Saha ✈️ CoRL '26 retweeted
🚀 #ICLR2026 Oral 💥
How can we design world models that capture object interactions directly from pixels?
Introducing Latent Particle World Models-the first end-to-end self-supervised, object-centric world model, trained from videos, supporting action/img/lang conditioning.
1/n



























