Publications

2026

1. 

   Solaris: Building a Multiplayer Video World Model in Minecraft

   Georgy Savva, Oscar Michel, Daohan Lu, and 6 more authors

   Under Review, 2026

   Abs PDF Website

   Existing action-conditioned video generation models (video world models) are limited to single-agent perspectives, failing to capture the multi-agent interactions of real-world environments. We introduce Solaris, a multiplayer video world model that simulates consistent multi-view observations. To enable this, we develop a multiplayer data system designed for robust, continuous, and automated data collection on video games such as Minecraft. Unlike prior platforms built for single-player settings, our system supports coordinated multi-agent interaction and synchronized videos + actions capture. Using this system, we collect 12.64 million multiplayer frames and propose an evaluation framework for multiplayer movement, memory, grounding, building, and view consistency. We train Solaris using a staged pipeline that progressively transitions from single-player to multiplayer modeling, combining bidirectional, causal, and Self Forcing training. In the final stage, we introduce Checkpointed Self Forcing, a memory-efficient Self Forcing variant that enables a longer-horizon teacher. Results show our architecture and training design outperform existing baselines. Through open-sourcing our system and models, we hope to lay the groundwork for a new generation of multi-agent world models.

2024

1. 

   HuDOR: Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewards

   Irmak Guzey, Yinlong Dai, Georgy Savva, and 2 more authors

   ICRA 2025, 2024

   Abs PDF Website

   Training robots directly from human videos is an emerging area in robotics and computer vision. While there has been notable progress with two-fingered grippers, learning autonomous tasks without teleoperation remains a difficult problem for multi-fingered robot hands. A key reason for this difficulty is that a policy trained on human hands may not directly transfer to a robot hand with a different morphology. In this work, we present HUDOR, a technique that enables online fine-tuning of the policy by constructing a reward function from the human video. Importantly, this reward function is built using object-oriented rewards derived from off-the-shelf point trackers, which allows for meaningful learning signals even when the robot hand is in the visual observation, while the human hand is used to construct the reward. Given a single video of human solving a task, such as gently opening a music box, HUDOR allows our four- fingered Allegro hand to learn this task with just an hour of online interaction. Our experiments across four tasks, show that HUDOR outperforms alternatives with an average of 4× improvement. Code and videos are available on our website https://object-rewards.github.io/.