RoboPapers @RoboPapers
@chris_j_paxton, @micoolcho & @DJiafei geeking out weekly with authors of robotics AI papers. On YouTube / X / Spotify / Substack youtube.com/@RoboPapers Joined February 2025-
Tweets307
-
Followers6K
-
Following3
-
Likes17
Project page: allenai.org/blog/molmoact2 Code: github.com/allenai/molmoa… ArXiV: arxiv.org/pdf/2605.02881…
There are few truly open models in the world, including both weights and data. However, these models are crucial for research and development of new systems — they help us learn which data is important and help develop new capabilities for deploying robots in the real world. MolmoAct2 provides a foundation for open research into robotics. It is associated with its own open dataset, an open-data action tokenizer, and a reasoning variant which predicts depth tokens. And people have actually been using it across the community, running experiments in their own labs or homes. @hq_fang and @DJiafei tell us more. Watch Episode 87 of RoboPapers, with @micoolcho and @chris_j_paxton, now!
Full episode dropping soon! Geeking out with @hq_fang @DJiafei on MolmoAct 2: An open foundation for robots that work in the real world allenai.org/blog/molmoact2 Co-hosted by @micoolcho @chris_j_paxton
Full episode dropping soon! Geeking out with @hq_fang @DJiafei on MolmoAct 2: An open foundation for robots that work in the real world allenai.org/blog/molmoact2 Co-hosted by @micoolcho @chris_j_paxton
Project Page: opendrivelab.com/RISE/ ArXiV: arxiv.org/abs/2602.11075
Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by @jiazhi_yang2024 et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with @chris_j_paxton and @DJiafei, to learn more!
Can humanoids assemble IKEA furniture? Calling for competing teams at IROS 2026! Co-organized by @UnitreeRobotics @BitRobotNetwork @LightwheelAI etc
We’re excited to partner with BitRobot Network, Lightwheel AI, Singapore Institute of Technology and contributors like Jie Tan (Deepmind), Steve Xie (Lightwheel), Michael Cho (FrodoBots), etc. Looking forward to push the boundary of humanoid loco-manipulation in this Humanoid
Full episode dropping soon! Geeking out with @jiazhi_yang2024 on RISE: Self-Improving Robot Policy with Compositional World Model opendrivelab.com/rise/ Co-hosted by @chris_j_paxton @DJiafei
Full episode dropping soon! Geeking out with @jiazhi_yang2024 on RISE: Self-Improving Robot Policy with Compositional World Model opendrivelab.com/rise/ Co-hosted by @chris_j_paxton @DJiafei
Collecting robot data at scale is key to deploying working manipulation policies, and the team from Tutor Intelligence @tutorintel is here to tell us about how to accomplish it. Their new announcement: a massive, 100-robot “data factory,” with a behind-the-scenes look at how to build a teleoperation platform and how to make robots and policies that are useful for their customers. Tutor Intelligence is a full-stack robotics company: they build robot arms, they sell robot arms, they write the software and they train neural networks. @joshgruenstein, @JesseMMichel, @shirazkn, and Joe McCalmon, and Joe McCalmon join us to tell us more about how they scale both teleop data and human interventions from their teleoperators in order to train the policies they need. Watch Episode #85 of RoboPapers, with @chris_j_paxton and @DJiafei, to learn more!
Full episode dropping soon! Geeking out with @joshgruenstein @JesseMMichel @shirazkn Joe McCalmon on @tutorintel Co-hosted by @chris_j_paxton @DJiafei
Learning robust, general-purpose reward functions for robotics unlocks many potential applications, like on-robot reinforcement learning or dataset validation. However, there’s a question of how to actually train such reward functions. Training success/failure prediction leads to ambiguous signals partway through a demonstration — it’s hard to measure progress — making the method unsuitable for reinforcement learning, among other things. Predicting progress, on the other hand, does not give a good way of using failure data. So why not do both? Robometer combines both progress and preference supervision, resulting in a stable, scalable, and highly general reward learning approach. @aliangdw @yigitkkorkmaz and @Jesse_Y_Zhang join us to tell us more. Watch Episode #84 of RoboPapers, with Chris Paxton and Jiafei Duan today!
Can't wait to push the boundary of dexterous manipulation with our collaborators: Nippon Origami Association @BitRobotNetwork @LightwheelAI @SharpaRobotics @sanatem @hq_fang @Noriaki_Hirose @gao_young
Interested to learn more? Register for our info sessions here: robotic-origami-challenge.github.io
3 of us @micoolcho @chris_j_paxton @DJiafei are super excited to help organize the Robotic Origami Competition at IROS (Sept 2026), along with @BitRobotNetwork @SharpaRobotics @LightwheelAI @hq_fang @sanatem @Noriaki_Hirose @gao_young Calling for teams!
Eric Space @erictian830831
0 Followers 2K Following
luonto rain @MeowLinux10745
3 Followers 115 Following
degenerative @ShermanMmm
41 Followers 4K Following
Doraku @Doraku0618
45 Followers 2K Following
tliutliu @tliutliu
8 Followers 3K Following
Zhiwei Feng ⁽̨̡ �... @Zhiwae97
46 Followers 105 Following
Jacob Ogle @jdo5v
2 Followers 105 Following
haonan chen @HaonanC05
0 Followers 39 Following
sidcode @sidcode_
854 Followers 3K Following PhDing in Robotics and AI | creating cyber-physical commons: code, culture, capital, coordination | ex @KERNEL0x https://t.co/p99leFCelp @initc3org @GoldmanSachs
Qian @Qian5jdq
0 Followers 31 Following
Wang HR BAAI @WangHR136
1 Followers 32 Following
Sanket Lokegaonkar @sanketloke94
56 Followers 843 Following Mid-training and Post-training Research Lead @Amazon Rufus. Previously @UberATG, @Bloomberg. @VT_CS alum. Opinions my own.
WeClean @wcyd_1130
7 Followers 478 Following
Ainur @nygmetainur
55 Followers 223 Following Building Humanoid Scientists | Automated 40+ cancer drug discovery methods | Genentech + Stanford spin-offs | MechE
carlolope_534 @carlolope_534
806 Followers 6K Following
Milaidy @MilaidyNow
2K Followers 201 Following Pursuing scalable world models for general intelligence @berkeley_ai.
Hanlin Wang @hanlinwang1024
199 Followers 1K Following PolyU CS PhD student LLM Agent/Reinforcement Learning/Embodied AI
brain rich @brain_rich27
1 Followers 37 Following
Teo @teodorbogoeski
0 Followers 105 Following
Frank Krimmel III @krimmelfb
113 Followers 921 Following No blue check, I refuse to pay for Elon’s AI research.
Shulin Tian @shulin_tian
229 Followers 300 Following PhD Student @MMLabNTU + ACIS Scholar @ASTARsg | Agents, Vision & Learning
Chengxuan Qian @chengxuanqian
220 Followers 1K Following Incoming CS PhD @UCSB | Multimodal GenAI & World Models
Zeratuaster @zeratuaster
3 Followers 464 Following
minghui lin @lin_minghu84883
0 Followers 9 Following
Robot Cave @RobotCaveCom
60 Followers 87 Following Robot news, automation trends, and practical robotics insights, without the hype. Humans first, robots close behind. Tracking technology that serves people.
Madsen Servius 🇭�... @madsenservius
196 Followers 3K Following Founder & CEO @doklahaiti • Computer Scientist
Greg Nelson @fractopods
20 Followers 51 Following
Mohamed ELharchaoui @Med_Elharchaoui
8 Followers 239 Following
wu bing @Bing19378
1 Followers 138 Following
Haoran (Richard) Cai @Richard_Seattle
119 Followers 778 Following Multimodal foundation model @LumaLabsAI. Previously, @AdobeResearch, @UWStat, @uwgenome.
Samet Akcay @ackaysam
1 Followers 53 Following
Tttkkk @Tttkkk16653569
0 Followers 514 Following
Basile Terver @BasileTerv987
957 Followers 302 Following Computer vision, SSL, Robotics PhD student at AMI Labs and INRIA Paris (Willow team) - Supervision : Yann LeCun and Jean Ponce. Ex Meta FAIR
Jiafei Duan @DJiafei
6K Followers 1K Following Assistant Professor at @NUScomputing| Robotics & AI PhD @uwcse| Host of @RoboPapers| Ex-@allen_ai, @NVIDIA my opinion is my alone.
Chris Paxton @chris_j_paxton
33K Followers 4K Following Mostly posting about robots. currently AI @agilityrobotics prev embodied AI @AIatMeta, @NVIDIAAI. All views my own.
Michael Cho - Rbt/Acc @micoolcho
6K Followers 3K Following I ❤️ robots, cheap hardware, steam engines, XGBoost, Liverpool FC & SG 🇸🇬 | Plane crash survivor | Building @BitRobotNetwork @frodobotsTrends for United States
You might like
