Ph.D. Student @uwcse @uw_robotics
Washington, USA
Joined August 2022
- Tweets128
- Following1.5K
- Followers701
- Likes648
Entong Su retweeted
🤖 Introducing RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild!
We ran 5,699 real-world robot comparisons across 124 sites, evaluating 5 VLA policies and 3 frontier AI agents.
What did we learn about the state of robot foundation models and agentic models? 🧵⬇️
#robotics #ai #benchmarking #evaluation #foundationmodels #agents
Introducing RoboColosseum
An open robot eval initiative by @huggingface @BitRobotNetwork @eaic_sg @DJiafei
Access:
- 100+ robots (@UnitreeRobotics G1s, @LeRobotHF SO-101s, YAMs, Franka and more)
- 140+ in-the-wild scenes
- Open rollout data
- 10,000 FREE eval hrs
Thread ↓
Entong Su retweeted
The first RoboColosseum results are in.
We tested five robot models and three frontier AI agents across 124 real-world sites.
Here’s what researcher @YiruHelenWang found about what today’s models can do and where they struggle ↓
Entong Su retweeted
Excited to share the first paper of my undergrad, Q-OIL, which we’ll be presenting at #CoRL2026 in Austin!
Interventions provide a natural source of feedback for robots to learn from in the real world. But, humans intervene suboptimally, which needs to be accounted for in both simulation benchmarking and algorithms.
We analyze human intervention data and measure intervention suboptimality in both timing and execution. Thus, rather than using interventions as supervision, we use them as soft exploration guidance.
(1/8)
Entong Su retweeted
We’re introducing ToyBlocks, an open simulated tabletop for controlled experiments in robot learning.
It enables robotics researchers to experimentally control training data & models, run targeted evals, & trace failures to their causes. 🧵
github.com/allenai/ToyBlocks
Entong Su retweeted
1/5 FlexiTac has been accepted to the CoRL 2026 Demo Track, and today we’re releasing FlexiTac-Gen! 🧵
Try it: flexitac.github.io/flexitac-…
Over the past two years, we’ve received many requests to customize FlexiTac for different robots. With help from AI agents, we built a tool that makes it easy to design your own sensor and export the files for fabrication.
A simple piece of tactile hardware to help move your research forward. See you at CoRL!
Entong Su retweeted
Excited to share OpenRoboKit, our series of open-source robotics projects! 🤖
- RoboKit for fast, scalable optimization & simulation github.com/openrobokit/robok…
Our RoboKit paper has been accepted for a spotlight at #CORL2026
- RetargetingKit for motion transfer & teleoperation github.com/openrobokit/retar…
- GraspKit for end-to-end grasping github.com/openrobokit/grasp…
Website: openrobokit.com
Check the video (sound on 🎵) for a 16-hour grasping time-lapse in beautiful San Diego, plus a quick look at dexterous retargeting and robot simulation.
Entong Su retweeted
Introducing RoboColosseum
An open robot eval initiative by @huggingface @BitRobotNetwork @eaic_sg @DJiafei
Access:
- 100+ robots (@UnitreeRobotics G1s, @LeRobotHF SO-101s, YAMs, Franka and more)
- 140+ in-the-wild scenes
- Open rollout data
- 10,000 FREE eval hrs
Thread ↓
Entong Su 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)
Super exciting to see D&A in action on our RFS robot manipulation videos! 🤖🔥 Really cool to see the robot behaviors analyzed and visualized in this way. Awesome work! 🚀
Want to turn any VLM into a better reward model for robotics? (yes, even Astra)
Introducing D&A: decoupling description and assessment improves any VLM family for zero-shot robot rewards.
D&A scales with improvements across GPT, Gemini, Claude, Qwen, ...
It enables zero-shot RL and filtered IL, improves code-as-policies via rich language feedback, and achieves SOTA on three benchmarks.
Website: weirdlabuw.github.io/dna
Entong Su retweeted
Want to turn any VLM into a better reward model for robotics? (yes, even Astra)
Introducing D&A: decoupling description and assessment improves any VLM family for zero-shot robot rewards.
D&A scales with improvements across GPT, Gemini, Claude, Qwen, ...
It enables zero-shot RL and filtered IL, improves code-as-policies via rich language feedback, and achieves SOTA on three benchmarks.
Website: weirdlabuw.github.io/dna
Entong Su retweeted
❓I keep coming back to this: what tactile representation does manipulation need?
We introduce PanoTac: A dense three-axis Tactile Sensor.
In the demo, the robot reorients and inserts a tube, then wiggles the stopper free while the tube sits loosely in the rack. The right side show the tactile signals that helps robot detect when the stopper releases and when to switch from wiggling to lifting. (1/7)
Entong Su retweeted
Introducing DreamFAR, a world model trained from scratch using only robot data, without internet pretraining. It supports:
🎮 Real-time teleoperation
⏱️ Minutes of long-horizon rollout
🧩 Generalization across 1,000+ tasks
yimingdou.com/DreamFAR
🧵 (1/8)
Entong Su retweeted
We introduce RoboSkills: a minimal, low-cost skillset for agentic robotics 🤖
It supports diverse robotics workflows, such as learning cat’s cradle 🧶 from a human video (Real2Sim) and transferring multi-person motion to characters and humanoids 💃 (Motion Generation).
We also support Auto Research, Agent as Policy, and Agentic Simulation. With suitable tools and workflows, we enable cheaper models to solve complex tasks.
GitHub: github.com/openrobokit/robos…
Website: openrobokit.com/roboskills
Watch the video for more examples.
Entong Su retweeted
Context isn’t just what you put in a prompt. It’s also what stands between a robot and its goal. Robot policies in everyday environments must generalize not only across objects, but also across the spatial contexts in which they appear.
Excited to share COWBOY 🤠 (CoRL 2026) — our sim-to-real recipe for contextual whole-body manipulation. One generalist grasping policy coordinates base, arm, dexterous hand, and active vision end-to-end, adapting its motion and grasps to object and scene geometry. Trained in simulation, deployed zero-shot in the wild.
w/ @JasonJZLiu @LiuMuxinl
🧵(1/N)
Entong Su 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)
Entong Su retweeted
🤖 The RoboEval Diagnostic Bimanual Challenge is live! Track 2 at the #CoRL2026 workshop "From GPU-Accelerated Simulation to Scalable and Generalizable Real Robot Policy Learning".
Scored on behavior, not just success.
⏰ Deadline: Nov 1 (AoE)
robo-eval.github.io/challeng…
Entong Su retweeted
What does RL learn from 10 assembly tasks in a row, with sparse reward only at the very end of all 10 tasks? Traditionally, absolutely nothing!
That’s 1,125 actions over 45 seconds. Even if a random policy somehow nails each task 1% of the time, chaining all 10 happens with probability 10⁻²⁰. Worse odds than winning Powerball twice in a row.
Excited to share AlphaNIST, a single policy which achieves 98.2% success rate across all tasks, and is able to solve 10 assemblies in a row under sparse reward! Check out our website: alpha-nist.github.io.
More details in @octi_zhang ‘s thread, and some extra comments of my own below! 🧵
(1/6) From @GoogleDeepmind’s AlphaGo to AlphaZero, we saw machines find moves that reached beyond what we’d imagined for them. No one taught them those strategies. They emerged from reinforcement learning: playing, failing, and trying again under a single binary task reward for success or failure. Inspired by them, we couldn’t help but wonder: what might a robot discover if we gave it that same freedom to learn?
That question led us to AlphaNIST. Starting tabula rasa, with that same binary reward plus only a simple control cost, a single policy solves all 20 @NIST assembly tasks at a 98.2% success rate in simulation. More surprising still, AlphaNIST can complete 10 different tasks in a row, receiving that reward only once, after all 10 are done.
Just as AlphaGo’s strategies surprised its creators, AlphaNIST discovered dexterous strategies we couldn’t have come up with ourselves.
Paper: arxiv.org/abs/2610.13354
Website: alpha-nist.github.io
Entong Su retweeted
Can we scale robot learning without scaling human labor? 📈
Demonstrations, resets, failure recovery, constant supervision—collecting robot data still takes substantial human effort.
🔑 Three keys let agents take on more of the work:
1. Real2Sim2Real: Agents explore and learn in digital twins, where trial and error is safer and cheaper.
2. Autonomous Recovery: Robots learn to recover from unexpected failures instead of waiting for human resets.
3. Human-on-Demand Learning: Multiple robots run in parallel, and humans step in only when autonomous recovery falls short.
🥑 Recova brings these together to get more robot learning out of every hour of human effort.
research.nvidia.com/labs/gea…
Joint work with @anjjei, Johan Bjorck, @ZhidingYu, @yin_hongxu, @jankautz, @DrJimFan, @yukez, and @Sifei30488L.
👇 Here's how it works 🧵
Entong Su retweeted
This is the most impressive result I’ve seen in my PhD.
One policy, trained from scratch, solves all 20 NIST assembly tasks. It can even complete 10 tasks in a row, with a single binary reward only after all 10 are done.
@octi_zhang combined diverse resets from OmniReset, task sampling from SGS, and multi-task training to unlock finer dexterity and longer horizons. No extra GPUs needed: one run on the same hardware replaces 20 specialist runs.
Videos and details: alpha-nist.github.io
Proud to be part of this incredible work! More in his thread 👇
(1/6) From @GoogleDeepmind’s AlphaGo to AlphaZero, we saw machines find moves that reached beyond what we’d imagined for them. No one taught them those strategies. They emerged from reinforcement learning: playing, failing, and trying again under a single binary task reward for success or failure. Inspired by them, we couldn’t help but wonder: what might a robot discover if we gave it that same freedom to learn?
That question led us to AlphaNIST. Starting tabula rasa, with that same binary reward plus only a simple control cost, a single policy solves all 20 @NIST assembly tasks at a 98.2% success rate in simulation. More surprising still, AlphaNIST can complete 10 different tasks in a row, receiving that reward only once, after all 10 are done.
Just as AlphaGo’s strategies surprised its creators, AlphaNIST discovered dexterous strategies we couldn’t have come up with ourselves.
Paper: arxiv.org/abs/2610.13354
Website: alpha-nist.github.io
Entong Su retweeted
GPT-6 Astra unlocks a whole new level of simulation scaling! It generates diverse environments, designs and solves tasks, and deploys seamlessly across embodiments.
Below: 25 unique environments, 25 multi-step tasks, and 5 robot embodiments generated in under 24 hours with just 3 generic prompts!
🧵