Lingfeng Sun

@ling_feng_sun

Building robots | PhD @UCBerkeley | previous: Researcher @rai_inst

Cambridge, MA

lingfeng.moe

Joined July 2024

194 Following

347 Followers

Replies Reposts Media

Pinned
Lingfeng Sun
@ling_feng_sun
Sep 28
What can GPT-6 Astra do on a humanoid when the contact gets hard? Give it the right interaction kernel. Led by @yk20wang, our team presents KPI: A Promptable Kernel for Physical Interaction on Humanoids. With our agentic system, Astra completes long-horizon, contact-rich tasks
11
Lingfeng Sun
@ling_feng_sun
Sep 26
We introduce KIWI: a modular robot-data rig built around Insta360 cameras. Voice-controlled capture. No carried computer or trackers. Ego/wrist video, training-ready motion and a 3D scene—from the same recording. 1/5
16
Lingfeng Sun
@ling_feng_sun
Sep 22
New work with @SichangSu42538 : real-world RL for long-horizon manipulation. online RL only on the bottleneck subtasks; agents write the selector, verifier and reset, rollouts need no human corrections. Humans reset only what the robot "cannot".
Sichang Su (Destiny)
@SichangSu42538
Sep 22
Your fine-tuned VLA does most of a long-horizon task, then gets stuck at a few critical steps. Don't retrain it. Don't collect more demos of what already works. Let it practice the part that fails, on the real robot. PARTS, w/ @ling_feng_sun (project lead) 🧵 1/8
Lingfeng Sun
@ling_feng_sun
Sep 1
Come and show your agents!
Haoru Xue
@HaoruXue
Aug 25
🚨 Call for live demo / paper at CoRL 2026 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽! No paper required for demo track. Due Sep 27. 🔮 The real magical power of agent is live interactive demo with the audience, which is why we provide all-out support: - Robot, compute,
Lingfeng Sun
@ling_feng_sun
Mar 4
The latest and the "last" project I led at RAI😝. Still zeroshot, no demo, no model, generalization comes from world model itself. Using novaflow with video planning to close loop is a practical way of using world models "today". More zeroshot series of works coming..stay tuned.
Jiahui Fu
@jiahuifu_carol
Mar 3
🤖 How can we enable robots to solve complex, multi-step manipulation tasks without a single demonstration or any task-specific training? Introducing NovaPlan: a hierarchical framework for zero-shot long-horizon manipulation. It unifies closed-loop video language planning with
1

Lingfeng Sun

Lingfeng Sun’s posts