Shivam Sood

PhD @ MARMoT Lab @NUSingapore, Prev @CarnegieMellon, @IITKgp

[Derek Tan Ming Siang @derektan1995]

🔍 How can we steer pretrained VLAs beyond dominant failure modes in OOD scenarios?

We uncover distinct test-time scaling laws 📈 for steering approaches under success and failure states.

This motivates 𝐑𝐋²-𝐕𝐋𝐀💫, an adaptive RL compositional steering framework.

🧵 👇

[Yash Jangir @off_jangir]

🤖 What would LMArena for robotics look like?

Introducing RobotArena ∞

We turn real videos into simulated environments and evaluate robot policies at scale using VLM scoring + human preferences

A scalable benchmark for robot generalists
🔗 https://t.co/E74fjWvlG3
Details 🧵👇

[Shivam Sood @sood__shivam]

@dAmineKharrat @ChongZitaZhang We were testing our sim-to-real pipeline's limits first. This test was a 'deep squat' motion trained with beyondmimic.

[Dvij Kalaria @DvijKalaria]

❓How can humanoids learn to squat and open a drawer?
Reward-tuning for every such whole-body task is infeasible.

🚀Meet DreamControl: robots "dream" how people move and manipulate objects in varied scenarios, practice using them in simulation, and then act naturally in the real-world.

🌐 https://t.co/tCt026UAGy 1/n

[Ashish Kapoor @akapoor_av8r]

The power of generative models — now embodied in humanoids.

Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction.

Diffusion + RL → natural whole-body skills on real robots.

DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as ––
Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks

Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware.

Trained purely in simulation, deployed on the @UnitreeRobotics G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness.

We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud

This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously.

Paper: https://t.co/sTnYZHKPNd
Blog: https://t.co/Sm4OFRqBKb

1/n

[Shivam Sood @sood__shivam]

Viser looks really neat (Isaac Gym policy evaluation)
https://t.co/L5tPulexT3