RoboPapers

Ep#70: A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation

Ep#69: MolmoSpaces, an Open Ecosystem for Embodied AI

Ep#68: DreamZero: World Action Models are Zero-Shot Policies

Ep#67: Asimov - Open Source Humanoid

Ep#66: Ordered Action Tokenization

Ep#65: VLM4VLA: Revisiting Vision-Language Models in Vision-Language-Action Models

Ep#64: Project Instinct

Ep#63: NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos

Ep#62: PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies

Evaluating robotic policies in the real world is notoriously difficult, slow, and non-reproducible, yet simulation benchmarks often fail to capture real-world performance accurately. A new approach addresses this by leveraging 3D Gaussian splatting and generative models to create scalable, low-cost simulation environme...

Ep#61: 1x World Model

Ep#60: Sim-to-Real Manipulation with VIRAL and Doorman

Humanoid loco-manipulation increasingly relies on sim-to-real reinforcement learning, yet bridging the gap between simulation and real-world deployment remains a significant challenge. The VIRAL and Doorman projects demonstrate that zero-shot, vision-based policy transfer is achievable for tasks like pick-and-place and...

Ep#59: SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies

Ep#58: RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning

Ep#57: Learning Dexterity from Human Videos with Gen2Act and SPIDER

Ep#56: GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation

Ep#55: Trace Anything: Representing Any Video in 4D via Trajectory Fields

Ep#54: MemER: Scaling Up Memory for Robot Control via Experience Retrieval

Ep#53: Semantic World Models

Ep#52: Probe, Learn, Distill: Self-improving Vision-Language-Action Models

Ep#51: Humanoid Everyday