Chuanruo Ning

PhD student at Cornell working on leveraging 3D vision for robot manipulation.
Previously at Peking University

[Yunhao Cao @QuantummCookie]

Introducing Unified Motion-Action (UMA) Model, a robot foundation model that uses 3D object motion as a shared interface for heterogeneous robot learning. UMA treats motion and action as co-evolving variables, enabling knowledge transfer across data sources and versatile inference. 🧵 1/n

[Qianxu Wang @helloqxwang]

Introducing KITE 🪁, a paradigm that transfers the interaction intent instead of joint-space actions across structurally different manipulators. Deploying on a new robot needs only its kinematics model (URDF), no new task demonstrations. 🧵1/8

[Kushal @kushalk_]

Teleoperation is slow, expensive, and difficult to scale. So how can we train our robots instead?

Introducing X-Sim: a real-to-sim-to-real framework that trains image-based policies 1) learned entirely in simulation 2) using rewards from human videos.

https://t.co/5yt2iTFYF4

[Chuanruo Ning @TritiumAc]

Check out our paper and project page for more information.

Prompting with the Future: Open-World Model Predictive Control with Interactive Digital Twins
📄 https://t.co/THRpinMhZb
🌐 https://t.co/VrGeMMiyUC
💻 https://t.co/s8gHqp5G5l

Huge thanks to my advisors: @KuanFang and @weichiuma

[Chuanruo Ning @TritiumAc]

How can robots solve tasks that demand both semantic and physical reasoning, like playing real-world Angry Birds, without tons of data?

We introduce Prompting with the Future: an MPC framework that fuses a pretrained VLM with an interactive digital twin for grounded, open-world motion planning.
🌐 https://t.co/VrGeMMiyUC

[Chuanruo Ning @TritiumAc]

By explicitly modeling dynamics with an interactive digital twin, our method significantly outperforms baselines that directly prompt or fine-tune the VLM to handle both semantics and physics.

[Zhihan Yang @zhihanyang_]

📢Thrilled to share our new paper: Esoteric Language Models (Eso-LMs)

> 🔀Fuses autoregressive (AR) and masked diffusion (MDM) paradigms
> 🚀First to unlock KV caching for MDMs (65x speedup!)
> 🥇Sets new SOTA on generation speed-vs-quality Pareto frontier

How? Dive in👇 [🧵1/13]

📜Paper: https://t.co/KJzjaXPJY0
📘Blog: https://t.co/azyr050fNr
💻Code: https://t.co/CkFl3DXpnz

Project co-led with @ssahoo_

[Oliver Li @oliveraochongli]

🤯 GPT-4o knows H&M left Russia in 2022 but still recommends shopping at H&M in Moscow.

🤔 LLMs store conflicting facts from different times, leading to inconsistent responses. We dig into how to better update LLMs with fresh facts that contradict their prior knowledge.

🧵 1/6 Our Paper: “Memorization vs. Reasoning: Updating LLMs with New Knowledge”

Contributions:
🏗️ Knowledge Update Playground (KUP) – a dataset & pipeline to simulate real-world fact changes
🚅 Memory-Conditioned Training (MRT)– a simple continued-pretraining method to inject and recall new facts

[Chuanruo Ning @TritiumAc]

@stand_still_aca cooooool！