40 citations · 53 across the 14 of their papers we have counts for
19 papers
Multimodal Filesystem Memory For Long-Horizon Embodied Agents
Chloe Su, Jiahan Li, Zhenting Qi +5
Agents operating over long horizons need an effective memory that allows them to reuse their experience throughout long interactions. If the entire history of an interaction is ret…
Scaling Online Exploration for Robot Agents
Runhan Huang, Xiangcheng Zhang, Haoyu Chen +17
Robot learning has advanced by scaling demonstration datasets and model capacity; however, deploying a new robot embodiment or task typically necessitates a dedicated teleoperation…
Who Improves the Robot? Toward Physical Recursive Self-Improvement
Hai Zhou, Fan Yang, Zeyi Chen +27
Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physical RSI)…
DeepJEPA: Scaling World Models from Within
Zijian Jin, Yunbei Zhang, Yuanzhe Liu +5
World-model planners typically scale outward by rolling farther, sampling more trajectories, or optimizing longer, while assigning the same computation to every imagined transition…
LIBERO-MAX: Do Robot Policies Adapt When the World Changes?
Yunbei Zhang, Zijian Jin, Yuanzhe Liu +14
Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and committed actions reflect the previ…
DriftWorld: Fast World Modeling through Drifting
Susie Lu, Haonan Chen, Weirui Ye +1
Predictive world models enable robots to simulate the visual outcomes of their actions, but state-of-the-art diffusion-based models remain costly because generating each rollout re…
Temporal Backtracking Search for Test-time Generative Video Reasoning
Sejoon Jun, Zheng Ding, Huangyuan Su +2
While test-time scaling has revolutionized reasoning in large language models, generative video reasoning remains bottlenecked by a single-shot paradigm. We demonstrate that search…
Self-Improving Language Models with Bidirectional Evolutionary Search
Guowei Xu, Zhenting Qi, Huangyuan Su +4
Search has been proposed as an effective method for self-improving language models and agentic systems, both for post-training sample generation and for inference. However, widely…
Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning
Shaohuai Liu, Weirui Ye, Yilun Du +1
Developing generalist robots capable of mastering diverse skills remains a central challenge in embodied AI. While recent progress emphasizes scaling model parameters and offline d…
TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models
Zheng Ding, Weirui Ye
Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widesp…
Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos
Weirui Ye, Fangchen Liu, Zheng Ding +3
Simulation offers a promising approach for cheaply scaling training data for generalist policies. To scalably generate data from diverse and realistic tasks, existing algorithms ei…
Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance
Kaifeng Zhang, Zhao-Heng Yin, Weirui Ye +1
Defining reward functions for skill learning has been a long-standing challenge in robotics. Recently, vision-language models (VLMs) have shown promise in defining reward signals f…
EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data
Shengjie Wang, Shaohuai Liu, Weirui Ye +2
Sample efficiency remains a crucial challenge in applying Reinforcement Learning (RL) to real-world tasks. While recent algorithms have made significant strides in improving sample…
Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own
Weirui Ye, Yunsheng Zhang, Haoyang Weng +6
Reinforcement learning (RL) is a promising approach for solving robotic manipulation tasks. However, it is challenging to apply the RL algorithms directly in the real world. For on…
Real-time scheduling of renewable power systems through planning-based reinforcement learning
Shaohuai Liu, Jinbo Liu, Weirui Ye +8
The growing renewable energy sources have posed significant challenges to traditional power scheduling. It is difficult for operators to obtain accurate day-ahead forecasts of rene…
Seer: Language Instructed Video Prediction with Latent Diffusion Models
Xianfan Gu, Chuan Wen, Weirui Ye +2
Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals. Therefore, text-conditioned video prediction (TVP) is an essential…
Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions
Weirui Ye, Pieter Abbeel, Yang Gao
One of the most important AI research questions is to trade off computation versus performance since ``perfect rationality" exists in theory but is impossible to achieve in practic…
Planning for Sample Efficient Imitation Learning
Zhao-Heng Yin, Weirui Ye, Qifeng Chen +1
Imitation learning is a class of promising policy learning algorithms that is free from many practical issues with reinforcement learning, such as the reward design issue and the e…
Mastering Atari Games with Limited Data
Weirui Ye, Shaohuai Liu, Thanard Kurutach +2
Reinforcement learning has achieved great success in many applications. However, sample efficiency remains a key challenge, with prominent methods requiring millions (or even billi…