activity
20242026
collaborators

7 papers

cs.AI2026

MemWM: Memory-Augmented Text-Based World Model

Yujun Wang, Tao Zhang, Jinhe Bi +9

World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can sti…

cs.LG2025

Consistency Training Helps Stop Sycophancy and Jailbreaks

Alex Irpan, Alexander Matt Turner, Mark Kurzeja +2

An LLM's factuality and refusal training can be compromised by simple changes to a prompt. Models often adopt user beliefs (sycophancy) or satisfy inappropriate requests which are…

cs.RO2025

Towards Embodiment Scaling Laws in Robot Locomotion

Bo Ai, Liu Dai, Nico Bohlinger +7

Cross-embodiment generalization underpins the vision of building generalist embodied agents for any robot, yet its enabling factors remain poorly understood. We investigate embodim…

cs.RO2025

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Embodiment Collaboration, Abby O'Neill, Abdul Rehman +291

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, thi…

cs.AI2025

An Approach to Technical AGI Safety and Security

Rohin Shah, Alex Irpan, Alexander Matt Turner +27

Artificial General Intelligence (AGI) promises transformative benefits but also presents significant risks. We develop an approach to address the risk of harms consequential enough…

cs.RO2025

Generating Robot Constitutions & Benchmarks for Semantic Safety

Pierre Sermanet, Anirudha Majumdar, Alex Irpan +2

Until recently, robotics safety research was predominantly about collision avoidance and hazard reduction in the immediate vicinity of a robot. Since the advent of large vision and…