Senior Research Scientist @ NVIDIA | PhD in Robotics @ CMU
Seattle, WA
Joined March 2009
- Tweets32
- Following105
- Followers514
- Likes139
Jenai Xuning Yang retweeted
🚀 Flexible test-time scaling with a 4B model and just 8K-token context windows!
One of my favorite things about 🪽 Hermes is how many simple but powerful ideas come together to tackle a much broader challenge:
How do we teach a small model an understudied agentic capability and inadequately measured by existing benchmarks?
In our case, that capability is contextual reasoning: knowing when and how to delegate, what to preserve in compact reasoning summaries, and how to continue reasoning from them.
🚀 We gave a 4B model with an 8K context window more test-time compute. Instead of improving, it got worse.
Scaling across context windows requires more than inline reasoning. It takes contextual reasoning: knowing how to delegate, preserve reasoning in compact summaries, and continue reasoning from them.
(1/10)
Jenai Xuning Yang retweeted
🎓 On-policy distillation has a teacher problem. SCOUT fixes it.
Then irony? OPD lets students learn from reasoning paths they actually visit. But their teachers must provide feedback on paths they rarely take themselves.
As these paths grow longer, even strong teachers struggle to provide reliable supervision.
Our idea is simple: Why not let the teacher and student learn together?
Jenai Xuning Yang retweeted
Introducing MILO, a step toward recursively self-improving agents for long-horizon, reasoning-intensive problems! 🧬
TL;DR: MILO evolves harnesses, but also the search process that discovers better harnesses.
It beats Claude Code and Codex on Terminal-Bench, outperforms methods like GEPA and Meta-Harness, and that's not all! It also discovers tighter upper bounds on three open math problems.
🧵👇
Jenai Xuning Yang retweeted
Excited to share that VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation has been accepted to #CoRL2026! 🎉🤖
VoLo explores agentic robotics for long-horizon, open-vocabulary tasks, where a VLM acts as the robot’s brain with memory to reason, plan, monitor, detect failures, recover, and orchestrate tools—including VLA/WAMs, vision models, and action primitives.
We also introduce RoboVoLo, a high-fidelity simulation benchmark with 126 tasks spanning common sense, memory/state tracking, complex references, and world knowledge, together with detailed diagnosis of current system limitations.
This work was done during my internship at @nvidia @NVIDIAAI @NVIDIARobotics. Huge thanks to all collaborators @HugoHadfield1, Alexander Zook, @mikacuy, @luke_ch_song, @erwincoumans, @xuningy, Faisal Ladhak, @BirchfieldStan, Jonathan Tremblay, and @robovalts!
🔗 Project: chicychen.github.io/VoLo/
💻 Code: github.com/NVlabs/VoLoAgent
📊 RoboVoLo Benchmark: github.com/NVlabs/RoboVoLo
Looking forward to discussions at CoRL 2026 — hope to meet many of you in person!
#CoRL2026 #AgenticRobotics #Robotics #EmbodiedAI #RobotLearning #PhysicalAI #NVIDIA
Jenai Xuning Yang retweeted
CPT is an important bridge between academic and industrial research.
I have benefited from it on both sides: as a graduate student, learning how frontier research is done in industry, and now as an industry researcher, working with graduate students to advance fundamental research.
Weakening that bridge would hurt both academia and industry.
ICE just published a new memo (BCM 2608-01) targeting international students. It effectively blocks universities from authorizing CPT internships that are not strictly mandatory for every student to graduate.
Even though internships in CS are not technically required for a degree, they greatly benefit both employers and students. They help students get familiar with the U.S. professional system. They also give American employers early access to a vital talent pipeline from top American universities.
This policy change cuts U.S. employers off from vital STEM talent pipelines and tells the world’s brightest minds to go elsewhere. This is terrible for our national interest and global competitiveness.
We need to retain top talent, not criminalize academic internships.
Jenai Xuning Yang retweeted
We have just open sourced Droid+, a really simple and easy way to drive the Droid hardware system using modern web technologies and very few dependencies! I hope people find it useful! github.com/NVlabs/DroidPlus
Jenai Xuning Yang retweeted
The next wave of robot foundation models is here. ⚡
World-Action Models are emerging as a powerful new approach for physical AI, combining pretrained scene dynamics with action generation.
Learn more ➡️ nvda.ws/43C1abm
Jenai Xuning Yang retweeted
Cosmos3 (post-trained on DROID) surpassed strong VLA & WAM baselines to rank #1 on RoboLab
All the compute FLOPs invested during the massive Cosmos3 pre-training and mid-training contribute to unlocking a better robot foundation model.😄
🎉 We added 2 SOTA WAMs to the RoboLab Leaderboard 🎉
Current leaders on RoboLab-120 (specific instr.):
🥇Cosmos3-Nano-Policy (39.7%)
🥈π0.5 (28.1%)
🥉DreamZero (28.1%)
→ See full results at: research.nvidia.com/labs/srl…
→ All policy clients available at: github.com/NVlabs/RoboLab/
Jenai Xuning Yang retweeted
a new form of greeting has dropped: see you at icml🇰🇷
1/1 accepted to ICML. more details soon
Jenai Xuning Yang retweeted
We are still far from zero-shot policy deployment on new tasks
Evaluation is a critical bottleneck in building robot foundation models. Check out our latest work RoboLab, led by @xuningy, which addresses this exact challenge.
Its a high-fidelity simulation environment for testing these models. A truly generalist policy should be able to complete these tasks zero-shot, and this benchmark highlights exactly how far we still have to go. More info 👇
Jenai Xuning Yang retweeted
Generalist robot policies need a benchmark that works across any robot and any policy. 🦾
Introducing RoboLab, a high‑fidelity simulation benchmark built on NVIDIA Isaac and Omniverse to evaluate generalist robot policies in diverse, photoreal, physics‑based environments.
Coming soon to the NVIDIA Isaac Lab‑Arena roadmap for large‑scale, robotic policy evaluation. 📖 nvda.ws/47RbOgX
#NationalRoboticsWeek