27 citations · 86 across the 44 of their papers we have counts for
48 papers
Higher-Order Action Supervision Makes A Strong Policy Class
Peng Cheng, Yunxian Hou, Zhi Zhou +3
Modern data-driven decision-making methods, such as imitation learning (IL) and reinforcement learning (RL), have achieved great success in solving many complex tasks. However, the…
ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
Dongxiu Liu, Haoyi Niu, Peng Cheng +5
In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time…
Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL
Ruiming Liang, Yi Zhong, Yizhen Yuan +6
Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases. As a result, multi-reward reinfo…
X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
Miracle Kang, Lights Shi, Lucy Liang +10
Modern Vision-Language-Action (VLA) models must bridge pretrained vision-language reasoning and precise continuous robot control. Existing action tokenizers discretize actions prim…
LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models
Rongxu Cui, Zongzheng Zhang, Jingrui Pang +11
Despite the impressive manipulation capabilities of Vision-Language-Action (VLA) models, their operational safety under strict constraints remains largely unverified. To address th…
World Value Models for Robotic Manipulation
Zhihao Wang, Jianxiong Li, Yu Cui +4
Generalist value models play a pivotal role in scaling robotic policy learning from large-scale, mixed-quality data. Mathematically, accurate value estimation demands deep temporal…
Horizon Adaptive Offline Policy Learning via Value Stitching
Kexin Zheng, Xianyuan Zhan, Xintao Yan
Learning accurate value functions plays a decisive role for reinforcement learning (RL) agents to solve long-horizon, complex tasks. Conventional temporal-difference (TD) learning…
Demystifying Action Space Design for Robotic Manipulation Policies
Yuchun Feng, Jinliang Zheng, Zhihao Wang +5
The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learn…
Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving
Yinan Zheng, Tianyi Tan, Bin Huang +11
Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving autonomous driving tasks. However, the…
Unraveling the Hidden Dynamical Structure in Recurrent Neural Policies
Jin Li, Yue Wu, Mengsha Huang +3
Recurrent neural policies are widely used in partially observable control and meta-RL tasks. Their abilities to maintain internal memory and adapt quickly to unseen scenarios have…
Dichotomous Diffusion Policy Optimization
Ruiming Liang, Yinan Zheng, Kexin Zheng +9
Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inf…
Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling
Tianyi Tan, Yinan Zheng, Ruiming Liang +6
Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this chall…
X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
Jinliang Zheng, Jianxiong Li, Zhihao Wang +12
Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To…
PhysiAgent: An Embodied Agent Framework in Physical World
Zhihao Wang, Jianxiong Li, Jinliang Zheng +6
Vision-Language-Action (VLA) models have achieved notable success but often struggle with limited generalizations. To address this, integrating generalized Vision-Language Models (…
Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
Pengxiang Li, Yinan Zheng, Yue Wang +6
End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages…
Efficient Robotic Policy Learning via Latent Space Backward Planning
Dongxiu Liu, Haoyi Niu, Zhihao Wang +6
Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introd…
Skill Expansion and Composition in Parameter Space
Tenglong Liu, Jianxiong Li, Yinan Zheng +4
Humans excel at reusing prior knowledge to address new challenges and developing skills while solving problems. This paradigm becomes increasingly popular in the development of aut…
Diffusion-Based Planning for Autonomous Driving with Flexible Guidance
Yinan Zheng, Ruiming Liang, Kexin Zheng +8
Achieving human-like driving behaviors in complex open-world environments is a critical challenge in autonomous driving. Contemporary learning-based planning approaches such as imi…
Universal Actions for Enhanced Embodied Foundation Models
Jinliang Zheng, Jianxiong Li, Dongxiu Liu +7
Training on diverse, internet-scale data is a key factor in the success of recent large foundation models. Yet, using the same recipe for building embodied agents has faced noticea…
Are Expressive Models Truly Necessary for Offline RL?
Guan Wang, Haoyi Niu, Jianxiong Li +3
Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL…
Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning
Jianxiong Li, Zhihao Wang, Jinliang Zheng +8
Multimodal task specification is essential for enhanced robotic performance, where \textit{Cross-modality Alignment} enables the robot to holistically understand complex task instr…
xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing
Haoyi Niu, Qimao Chen, Tenglong Liu +5
Reusing pre-collected data from different domains is an appealing solution for decision-making tasks, especially when data in the target domain are limited. Existing cross-domain p…
Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
Liyuan Mao, Haoran Xu, Xianyuan Zhan +2
One important property of DIstribution Correction Estimation (DICE) methods is that the solution is the optimal stationary distribution ratio between the optimized and data collect…
Instruction-Guided Visual Masking
Jinliang Zheng, Jianxiong Li, Sijie Cheng +6
Instruction following is crucial in contemporary LLM. However, when extended to multimodal setting, it often suffers from misalignment between specific textual instruction and targ…