15 papers
Robot Learning with Visual Predicted Force
Haonan Chen, Feiyang Wu, Yuxiang Ma +11
Force-aware manipulation typically relies on specialized force or tactile sensors. We show that force-aware manipulation can instead be achieved through visual force prediction fro…
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…
Ordered Action Tokens for Visuomotor Policy Learning
Chaoqi Liu, Yue Zhao, Haonan Chen +4
Action tokenization maps continuous robot action chunks to discrete tokens and has become an important interface for modern visuomotor policies. Existing approaches either rely on…
Masked Visual Actions for Unified World Modeling
Hadi Alzayer, Wenlong Huang, Haonan Chen +8
Video models absorb rich priors over how the visual world moves, interacts, and responds to contact, making them promising substrates for robotic world modeling. The central challe…
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
Haoyu Chen, Kaichen Zhou, Hang Hua +11
Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency only while t…
B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations
Xiaoshen Han, Haoyu Xiong, Haonan Chen +4
In this work, we present B-spline Policy (BSP), an action representation designed for accelerating robot manipulation policies. Rather than predicting discrete-time action chunks,…
ArchEval: Measuring AI Agents as Computer Architects
Chenyu Wang, Zishen Wan, Jeffrey Ma +8
Computer architecture has long used benchmarks to make progress measurable. LLM agents create a different measurement problem: success is not merely writing code or tuning paramete…
Structured 4D Latent Predictive Model for Robot Planning
Zhiyi Li, Peilin Wu, Xiaoshen Han +2
Video predictive models are emerging as a powerful paradigm in robotics, offering a promising path toward task generalization, long-horizon planning, and flexible decision-making.…
You Only Touch Once: 6-DoF Object Pose Estimation from Single Tactile Contact
Pengfei Ye, Yuxiang Ma, Haonan Chen +5
Accurate 6-DoF object pose estimation is fundamental to robotic manipulation, yet vision-based methods often fail under occlusion, poor lighting, and reflective or transparent surf…
CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation
Haonan Chen, Yuxiang Ma, Stephen Tian +7
Long-horizon, contact-rich complex manipulation tasks, such as seating a GPU into a PCIe slot, demand both millimeter high precision and out-of-the-box generalization to new tasks.…
AgentDSE: Reasoning-Augmented Architectural Design Space Exploration
Chenyu Wang, Jiahe Caroline Shi, David Kong +4
Traditional architectural design space exploration (DSE) is highly inefficient, typically requiring tens of thousands of simulator evaluations across various optimization methods.…
OAT: Ordered Action Tokenization
Chaoqi Liu, Xiaoshen Han, Jiawei Gao +3
Autoregressive policies offer a compelling foundation for scalable robot learning by enabling discrete abstraction, token-level reasoning, and flexible inference. However, applying…
SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models
Haowen Liu, Shaoxiong Yao, Haonan Chen +4
Vision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities. However, they lack a grounded understanding of physical dynamics. This limitation…
Video Replanning via Latent Embedding Refinement and Rejection-Based Sampling
Po-Chen Ko, Yu Chan, Jiayuan Mao +7
Video planning has emerged as a flexible framework for robot manipulation, in which a generative model predicts a video of task completion, and a downstream module translates the p…
Multi-Modal Manipulation via Multi-Modal Policy Consensus
Haonan Chen, Jiaming Xu, Hongyu Chen +7
Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation is often suboptimal: dominant modalit…