@riadoshi21

CS PhD @Stanford🌲 | @UCBerkeley alum. Robot learning & embodied AI

riadoshi.github.io
Joined November 2018
  • Tweets85
  • Following313
  • Followers1K
13Media
In language models, turning a generative model into a critic is simple: pass in the output and prompt for a score. Robot policies can't do this - they output physical actions & there's no built-in vocabulary to predict scores. So when it comes to RL on robot policies, we typically train a separate critic from sparse rewards - blind to everything the policy learned from the actions in the pretraining data. We think this has it backwards - can a critic learn from those actions the way the policy does? (1/n)
11
40
8
257
35,131
Ria Doshi retweeted
Kushal@kushalk_Oct 19
Precise assembly is an important benchmark for robotics. Standard industrial automation fails to generalize, but robot learning struggles with contacts. In this work, we extract force signals from proprioception and generalize well beyond the training distribution. Check it out!
Antonia Bronars
@BronarsToniOct 19
Every robot already carries contact sensors: its own joints. When a robot touches something, its joints drift slightly off their commands, and the encoders pick it up. Legged robots and humanoids already leverage this signal to walk blind - but is it enough for blind precise assembly? We find that it is! Our policies can insert pegs, mesh gears, and thread nuts using only the robot's joint positions - no camera, no tactile, and no object poses. And the peg policy works zero-shot in the real world! 🧵 w/ my amazing co-first author @younghyo_park, and advised by @kushalk_ and @pulkitology.
2
3
30
1,538
Ria Doshi retweeted
samrat@samratsahoo_Oct 16
Teleoperators collecting data to fine-tune VLAs are spending valuable time demonstrating actions robots already know how to do. TANDEM combines task and motion planning (TAMP) with human teleoperation only as needed, reducing human effort. (1/8)
5
21
2
58
4,482
Ria Doshi retweeted
Satvik Sharma
@satviks107Oct 13
Want to know how well agents can really control robots directly? In RoboARCade, we systematically evaluate and diagnose frontier agents controlling robots directly using tens of thousands of dollars’ worth of agent trajectories. RoboARCade contains diverse, precise, and long-horizon tasks. Paper, code, assets and every trace are out today. roboarcade.org
10
42
9
171
16,958
Mobile manipulation policies can break from base pose errors of just a few cm, which are common after navigation. Can we get pose generalization without additional demos? Introducing MobileVISTA: collect demos at one base pose, get a policy that works from many 🧵👇 Website: sdwistreich.github.io/mobile… Paper: arxiv.org/abs/2610.07511
12
18
4
91
7,405
Ria Doshi retweeted
Tyler Lum@tylerlum23Oct 7
Human fingers move in coordinated patterns. Can those patterns help robots explore? Excited to share EigenDEXplore! 🤖✋ Key idea: add exploration noise along directions learned from human hand motion, while leaving robots free to discover motions of their own See @harshgupta's 🧵
Harsh Gupta
@HarshGuptaOct 7
Per-joint Gaussian noise is a terrible way to explore a 20+ DoF hand We introduce EigenDEXplore, which explores along coordinated patterns from human hand motion, while keeping full control of every joint Better learning, from tool use 🔨 to reorientation 🔄 to bimanual 👐
3
15
45
2,631
Ria Doshi retweeted
samrat@samratsahoo_Oct 2
Task and motion planning (TAMP) excels at multi-step, semantic, and geometric reasoning. VLAs excel at deformable object manipulation, which TAMP can't do. Can one VLA do both? DATAFARM fine-tunes VLAs on TAMP demos aligned to the pre-training distribution. (1/9)
3
27
5
91
16,050
Robots need memory 🧠: remembering where your favorite cup is or which drawer is locked. How can a robot remember across large spaces, interactions, & fine-grained detail? Introducing MessyMem (accepted to #CoRL2026 🚀): Learning-from-Doing Memory for Mobile Manipulation. 🧵
3
26
7
131
19,077
Excited to share our work on a model for mapping molecules to olfactory receptors to perception, out today! Check out the link in thread ⬇️
Kevin K. Yang 楊凱筌@KevinKaichuangSep 2
Out today in Cell Systems: the final version of our work on biologically-inspired models for predicting how molecules smell! With @SeyoneC and @jdthamores
6
16
4
83
8,495
Why do Vision-Language-Action (VLA) models still struggle with contact-rich manipulation? 🤖 Excited to share our new paper: Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them. 🧵 (1/8)
4
36
9
248
35,069
Ria Doshi retweeted
RoboPapers
@RoboPapersJul 28
Full episode dropping soon! Geeking out with @riadoshi21 @leto__jean on CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy chorus-model.github.io/ Co-hosted by @micoolcho @DJiafei
1
4
1
14
5,800
Ria Doshi retweeted
Emily Jin@emilyzjinJul 10
During long-horizon task planning, a robot must decide what to do, while ensuring each action is geometrically feasible. To this end, we propose 𝗽𝗹𝗮𝗻𝗻𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗶𝗻𝘁𝗲𝗿𝗹𝗲𝗮𝘃𝗲𝗱 𝘃𝗶𝘀𝗶𝗼𝗻-𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝘀.
3
16
2
102
15,723
Ria Doshi retweeted
Tyler Lum@tylerlum23Jul 1
🤖 How can we teach dexterous robots to perform precise, contact-rich assembly? Introducing Play2Perfect: first learn to play with objects, then perfect the policy for tight insertion, multi-part assembly, and screwing. Sound on! 🔊 🧵👇
10
52
11
288
68,827
Ria Doshi retweeted
Aneesh Muppidi
@aneeshersJun 30
Introducing Real-time RL. In the real world, time isn't free. The environment keeps "moving" even when you're computing your next action. We show how RL agents can learn to adaptively think in real-time games. 1/🧵
17
84
17
720
78,256
How can generalist policies adapt to new challenges at deployment using skills they already have? We optimize VLA *prompt inputs* with reinforcement learning, enabling efficient real-robot adaptation on complex tasks where existing methods struggle. 🧵 semantic-action-rl.github.io
3
20
4
87
20,561
Seeing multiple, mobile robots collaborate on manipulation tasks was my dream since I started at Stanford. @riadoshi21 made it happen. CHORUS is a single decentralized VLA policy whose architecture stays fixed regardless of team size.
Ria Doshi
@riadoshi21Jun 11
🤔 Can we train one VLA policy to control multi-robot teams without any explicit communication? ✨ Introducing CHORUS: a single policy for decentralized, multi-embodiment collaboration 🧵⬇️
1
15
75
14,337
Ria Doshi retweeted
Cherie Ho@hocherie1Jun 18
How should we evaluate robots in the age of foundation models? We hosted the RSS RoboEval Workshop with folks from academia, industry, and policy to discuss this. 💪 We put together an actionable guide and insights to get you started on robot evaluations. Link below. 🧵1/N
1
10
1
24
2,767
Ria Doshi retweeted
Will Chen@verityw_Jun 12
Generalist robot policies learn many useful skills. How can we elicit relevant behaviors when faced with new tasks? We introduce Flow Reversal Steering (FRS): a way to refine coarse actions produced by semantic reasoning into similar precise ones! flow-reversal-steering.githu… 1/N
3
16
2
67
17,473
We equipped PI policies with memory! And taught our robots to do long-horizon real world tasks such as preparing the items for a recipe, cooking a grilled cheese and cleaning the kitchen!
Physical Intelligence
@physical_intMar 3
We’ve developed a memory system for our models that provides both short-term visual memory and long-term semantic memory. Our approach allows us to train robots to perform long and complex tasks, like cleaning up a kitchen or preparing a grilled cheese sandwich from scratch 👇
8
15
2
89
24,120
Ria Doshi retweeted
Tian Gao@TianGao_19Feb 16
Long-tail scenarios remain a major challenge for autonomous driving. Unusual events—like accidents or construction zones—are underrepresented in driving data, yet require semantic and commonsense reasoning grounded in control. We propose SteerVLA, a framework that uses VLM reasoning to steer a driving policy via grounded, fine-grained language instructions. Paper: arxiv.org/abs/2602.08440 Website: steervla.github.io/
5
24
6
180
71,997
Load more