Publications (84)
A note on zero-sum Ramsey numbers of complete graphs
Cheng Chi, Jialin He, Fuhong Ma
For a graph with , the zero-sum Ramsey number is the least integer such that every labeling of the edges of by elements of contains a c…
Optimal implementation delay of taxation with trade-off for Lévy risk Processes
Wenyuan Wang, Xueyuan Wu, Cheng Chi
In this paper we consider two problems on optimal implementation delay of taxation with trade-off for spectrally negative Lévy insurance risk processes. In the first case, we assu…
XSkill: Cross Embodiment Skill Discovery
Mengda Xu, Zhenjia Xu, Cheng Chi +2
Human demonstration videos are a widely available data source for robot learning and an intuitive user interface for expressing desired behavior. However, directly extracting reusa…
The Turán number of the Cartesian product of a star and an edge
Xiamiao Zhao, Xin Cheng, Cheng Chi +3
Let denote the cycle of length , be a star with edges. And let be the graph consisting of copies of sharing one fixed edge. Equivalently, $B_t=K_…
PaperBot: Learning to Design Real-World Tools Using Paper
Ruoshi Liu, Junbang Liang, Sruthi Sudhakar +4
Paper is a cheap, recyclable, and clean material that is often used to make practical tools. Traditional tool design either relies on simulation or physical analysis, which is ofte…
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
Shifeng Zhang, Cheng Chi, Yongqiang Yao +2
Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In t…
Selective Refinement Network for High Performance Face Detection
Cheng Chi, Shifeng Zhang, Junliang Xing +3
High performance face detection remains a very challenging problem, especially when there exists many tiny faces. This paper presents a novel single-shot face detector, named Selec…
SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics
Mengzhen Liu, Enshen Zhou, Cheng Chi +6
Active perception and manipulation are crucial for robots to interact with complex scenes. Existing methods struggle to unify semantic-driven active perception with robust, viewpoi…
GICI-LIB: A GNSS/INS/Camera Integrated Navigation Library
Cheng Chi, Xin Zhang, Jiahui Liu +3
Accurate navigation is essential for autonomous robots and vehicles. In recent years, the integration of the Global Navigation Satellite System (GNSS), Inertial Navigation System (…
GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion
Cheng Chi, Shuran Song
This paper tackles the task of category-level pose estimation for garments. With a near infinite degree of freedom, a garment's full configuration (i.e., poses) is often described…
MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
Zehua Fan, Junjie He, Wenxuan Song +14
World action models (WAMs) built on video generation backbones are a rising recipe for robot learning, yet remain confined to tabletop manipulation. Mobile manipulation demands sim…
On a conjecture of Kolokolnikov on algebraic connectivity
Cheng Chi, Junjie Wang, Jiaxin Zheng
For a graph , let be the second smallest eigenvalue of the Laplacian matrix of , also known as the algebraic connectivity. Algebraic connectivity plays an important ro…
DiffChip: Thermally Aware Chip Placement with Automatic Differentiation
Giuseppe Romano, Aakrati Jain, Nima Dehmamy +2
Chiplets are modular integrated circuits that can be combined to form a larger system, offering flexibility and performance enhancements. However, their dense packing often leads t…
The Turán number for the edge blow-up of trees: the missing case
Cheng Chi, Long-Tu Yuan
The edge blow-up of a graph is the graph obtained from replacing each edge of it by a clique of the same size where the new vertices of the cliques are all different. Wang, Hou, Li…
Don't overfit the history -- Recursive time series data augmentation
Amine Mohamed Aboussalah, Min-Jae Kwon, Raj G Patel +2
Time series observations can be seen as realizations of an underlying dynamical system governed by rules that we typically do not know. For time series learning tasks, we need to u…
A Deep Reinforcement Learning Framework For Column Generation
Cheng Chi, Amine Mohamed Aboussalah, Elias B. Khalil +2
Column Generation (CG) is an iterative algorithm for solving linear programs (LPs) with an extremely large number of variables (columns). CG is the workhorse for tackling large-sca…
PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
Cheng Chi, Shifeng Zhang, Junliang Xing +3
Pedestrian detection in crowded scenes is a challenging problem, because occlusion happens frequently among different pedestrians. In this paper, we propose an effective and effici…
UniDA3D: A Unified Domain-Adaptive Framework for Multi-View 3D Object Detection
Hongjing Wu, Cheng Chi, Jinlin Wu +3
Camera-only 3D object detection is critical for autonomous driving, offering a cost-effective alternative to LiDAR based methods. In particular, multi-view 3D object detection has…
RoboBrain 2.0 Technical Report
BAAI RoboBrain Team, Mingyu Cao, Huajie Tan +50
We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in…
Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation
Huajie Tan, Peterson Co, Yijie Xu +9
Long-horizon robotic manipulation is increasingly important for real-world deployment, requiring spatial disambiguation in complex layouts and temporal resilience under dynamic int…
PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing
Yuheng Ji, Yuyang Liu, Huajie Tan +15
Current robotic evaluation is still largely dominated by binary success rates, which collapse rich execution processes into a single outcome and obscure critical qualities such as…
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Cheng Chi, Fangyun Wei, Han Hu
Existing object detection frameworks are usually built on a single format of object/part representation, i.e., anchor/proposal rectangle boxes in RetinaNet and Faster R-CNN, center…
PIGEON: VLM-Driven Object Navigation via Points of Interest Selection
Cheng Peng, Zhenzhe Zhang, Xiaobao Wei +7
Object navigation in unseen indoor environments requires agents to perform semantic search under partial observability. Vision-language models (VLMs) provide strong semantic-spatia…
From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
Sining Ang, Yuguang Yang, Chenxu Dang +8
Vision-Language-Action (VLA) driving augments end-to-end (E2E) planning with language-enabled visual backbones, yet it remains unclear how vision-language models (VLMs) differ from…
Cloth Funnels: Canonicalized-Alignment for Multi-Purpose Garment Manipulation
Alper Canberk, Cheng Chi, Huy Ha +4
Automating garment manipulation is challenging due to extremely high variability in object configurations. To reduce this intrinsic variation, we introduce the task of "canonicaliz…
RoboNinja: Learning an Adaptive Cutting Policy for Multi-Material Objects
Zhenjia Xu, Zhou Xian, Xingyu Lin +4
We introduce RoboNinja, a learning-based cutting system for multi-material objects (i.e., soft objects with rigid cores such as avocados or mangos). In contrast to prior works usin…
Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection
Enshen Zhou, Qi Su, Cheng Chi +5
Automatic detection and prevention of open-set failures are crucial in closed-loop robotic systems. Recent studies often struggle to simultaneously identify unexpected failures rea…
End-to-end multi-channel speaker extraction and binaural speech synthesis
Cheng Chi, Xiaoyu Li, Yuxuan Ke +4
Speech clarity and spatial audio immersion are the two most critical factors in enhancing remote conferencing experiences. Existing methods are often limited: either due to the lac…
Robust Extrinsic Self-Calibration of Camera and Solid State LiDAR
Jiahui Liu, Xingqun Zhan, Cheng Chi +2
This letter proposes an extrinsic calibration approach for a pair of monocular camera and prism-spinning solid-state LiDAR. The unique characteristics of the point cloud measured r…
Convergence of Symbiotic Communications and Blockchain for Sustainable and Trustworthy 6G Wireless Networks
Haoxiang Luo, Gang Sun, Cheng Chi +2
Symbiotic communication (SC) is known as a new wireless communication paradigm, similar to the natural ecosystem population, and can enable multiple communication systems to cooper…
Relational Learning for Joint Head and Human Detection
Cheng Chi, Shifeng Zhang, Junliang Xing +3
Head and human detection have been rapidly improved with the development of deep convolutional neural networks. However, these two tasks are often studied separately without consid…
Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation
Huajie Tan, Sixiang Chen, Yijie Xu +12
The primary obstacle for applying reinforcement learning (RL) to real-world robotics is the design of effective reward functions. While recently learning-based Process Reward Model…
Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey
Shuanghao Bai, Wenxuan Song, Jiayi Chen +15
Embodied intelligence has witnessed remarkable progress in recent years, driven by advances in computer vision, natural language processing, and the rise of large-scale multimodal…
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Embodiment Collaboration, Abby O'Neill, Abdul Rehman +291
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, thi…
RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration
Huajie Tan, Cheng Chi, Xiansheng Chen +21
The proliferation of collaborative robots across diverse tasks and embodiments presents a central challenge: achieving lifelong adaptability, scalable coordination, and robust sche…
RefineFace: Refinement Neural Network for High Performance Face Detection
Shifeng Zhang, Cheng Chi, Zhen Lei +1
Face detection has achieved significant progress in recent years. However, high performance face detection still remains a very challenging problem, especially when there exists ma…
Occlusion-robust Deformable Object Tracking without Physics Simulation
Cheng Chi, Dmitry Berenson
Estimating the state of a deformable object is crucial for robotic manipulation, yet accurate tracking is challenging when the object is partially-occluded. To address this problem…
From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance
Zhe Li, Cheng Chi, Yangyang Wei +7
Natural language offers a natural interface for humanoid robots, but existing language-guided humanoid locomotion pipelines remain cumbersome and untrustworthy. They typically deco…
ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data
Zeyi Liu, Cheng Chi, Eric Cousineau +3
Audio signals provide rich information for the robot interaction and object properties through contact. This information can surprisingly ease the learning of contact-rich robot ma…
Towards Cross-View Point Correspondence in Vision-Language Models
Yipu Wang, Yuheng Ji, Yuyang Liu +10
Cross-view correspondence is a fundamental capability for spatial understanding and embodied AI. However, it is still far from being realized in Vision-Language Models (VLMs), espe…
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
Enshen Zhou, Jingkun An, Cheng Chi +8
Spatial referring is a fundamental capability of embodied robots to interact with the 3D physical world. However, even with the powerful pretrained vision language models (VLMs), r…
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Alexander Khazatsky, Karl Pertsch, Suraj Nair +98
The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. Ho…
RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation
Shihan Wu, Xuecheng Liu, Shaoxuan Xie +81
Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware hete…
JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
Yihan Lin, Jiawei He, Shifeng Bao +6
Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployment cost. Existing latent WAM…
A solution to Frankl and Kupavskii's conjecture concerning ErdÅs-Kleitman matching problem
Cheng Chi, Yan Wang
For integers , let be the maximum size of a family with no pairwise disjoint members. The study of determining is clo…
LassoFlexNet: Flexible Neural Architecture for Tabular Data
Kry Yik Chau Lui, Cheng Chi, Kishore Basu +1
Despite their dominance in vision and language, deep neural networks often underperform relative to tree-based models on tabular data. To bridge this gap, we incorporate five key i…
Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
Shuanghao Bai, Jing Lyu, Wanqi Zhou +9
Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representati…
TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
Yi Han, Enshen Zhou, Shanyu Rong +6
Vision-Language Models (VLMs) have shown remarkable capabilities in spatial reasoning, yet they remain fundamentally limited to qualitative precision and lack the computational pre…
Reshaping Action Error Distributions for Reliable Vision-Language-Action Models
Shuanghao Bai, Dakai Wang, Cheng Chi +8
In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies. Most existing VLA framewor…
Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
Cheng Chi, Zhenjia Xu, Siyuan Feng +5
This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot's visuomotor policy as a conditional denoising diffusion process. We benchmar…
Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain
Yulin Luo, Chun-Kai Fan, Menghang Dong +19
Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a central challenge. Recent embodied systems often follow a dual-system paradigm, w…
New Extremal Ranges and Constructions of the ErdÅs--Kleitman Problem
Cheng Chi, Yan Wang
For integers , let denote the maximum size of a family with no pairwise disjoint members. The problem of determining ,…
RALTPER: A Risk-Aware Local Trajectory Planner for Complex Environment with Gaussian Uncertainty
Cheng Chi
In this paper, we propose a novel Risk-Aware Local Trajectory Planner (RALTPER) for autonomous vehicles in complex environments characterized by Gaussian uncertainty. The proposed…
Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
Gangwei Xu, Haotong Lin, Hongcheng Luo +11
This paper presents Pixel-Perfect Depth, a monocular depth estimation model based on pixel-space diffusion generation that produces high-quality, flying-pixel-free point clouds fro…
DextAIRity: Deformable Manipulation Can be a Breeze
Zhenjia Xu, Cheng Chi, Benjamin Burchfiel +3
This paper introduces DextAIRity, an approach to manipulate deformable objects using active airflow. In contrast to conventional contact-based quasi-static manipulations, DextAIRit…
Learning to Think Fast and Slow for Visual Language Models
Chenyu Lin, Cheng Chi, Jinlin Wu +2
When faced with complex problems, we tend to engage in slower, more deliberate thinking. In contrast, for simple questions we give quick, intuitive responses. This dual-system thin…
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
Cheng Chi, Zhenjia Xu, Chuer Pan +5
We present Universal Manipulation Interface (UMI) -- a data collection and policy learning framework that allows direct skill transfer from in-the-wild human demonstrations to depl…
Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics
Enshen Zhou, Yibo Li, Jingkun An +12
Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spa…
Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds
Yun Wang, Cheng Chi, Xin Yang
Scene flow estimation, which predicts the 3D motion of scene points from point clouds, is a core task in autonomous driving and many other 3D vision applications. Existing methods…
Uni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving Scenarios
Zikang Yuan, Yuechuan Pu, Hongcheng Luo +7
Ensuring the safety of autonomous vehicles necessitates comprehensive simulation of multi-sensor data, encompassing inputs from both cameras and LiDAR sensors, across various dynam…
Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Control
Yifan Hou, Zeyi Liu, Cheng Chi +5
Compliance plays a crucial role in manipulation, as it balances between the concurrent control of position and force under uncertainties. Yet compliance is often overlooked by toda…
RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration
Huajie Tan, Xiaoshuai Hao, Cheng Chi +13
The dawn of embodied intelligence has ushered in an unprecedented imperative for resilient, cognition-enabled multi-agent collaboration across next-generation ecosystems, revolutio…
GOMPSNR: Reflourish the Signal-to-Noise Ratio Metric for Audio Generation Tasks
Lingling Dai, Andong Li, Cheng Chi +3
In the field of audio generation, signal-to-noise ratio (SNR) has long served as an objective metric for evaluating audio quality. Nevertheless, recent studies have shown that SNR…
Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives
Shuanghao Bai, Wenxuan Song, Jiayi Chen +14
Recent advances in vision, language, and multimodal learning have substantially accelerated progress in robotic foundation models, with robot manipulation remaining a central and c…
Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving
Lijun Zhou, Hongcheng Luo, Zhenxin Zhu +34
This report presents a unified technical system addressing the two core capabilities of world models for autonomous driving: world representation and world generation. For world re…
VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation
Haoran Zhang, Shuanghao Bai, Wanqi Zhou +6
Robotic grasping is one of the most fundamental tasks in robotic manipulation, and grasp detection/generation has long been the subject of extensive research. Recently, language-dr…
On zero-sum Ramsey numbers of cycles and wheels
Cheng Chi, Jialin He
For an integer and a graph with , let be the least integer such that every edge-labeling contains a copy of wh…
VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models
Zirui Ge, Pengxiang Ding, Baohua Yin +16
Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge…
Extremal Families for the ErdÅs--Kleitman Problem: The Missing Constructions
Cheng Chi, Yan Wang
The paper identifies new extremal families for the Erdős–Kleitman problem by analyzing weighted constructions and confirms the Frankl–Kupavskii meta‑conjecture in many parameter ra…
Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control
Zhe Li, Cheng Chi, Yangyang Wei +9
Humans intuitively move to sound, but current humanoid robots lack expressive improvisational capabilities, confined to predefined motions or sparse commands. Generating motion fro…
MathSticks: A Benchmark for Visual Symbolic Compositional Reasoning with Matchstick Puzzles
Yuheng Ji, Huajie Tan, Cheng Chi +8
We introduce \textsc{MathSticks}, a benchmark for Visual Symbolic Compositional Reasoning (VSCR), which unifies visual perception, symbolic manipulation, and arithmetic consistency…
RoboBrain 2.5: Depth in Sight, Time in Mind
Huajie Tan, Enshen Zhou, Zhiyu Li +32
We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on…
RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion
Zhe Li, Cheng Chi, Boan Zhu +10
Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art humanoid locomotion systems rely on either…
On Zero-sum Ramsey numbers of complete bipartite graphs
Cheng Chi, Jialin He
For an integer and a graph satisfying , the zero-sum Ramsey number is the least integer such that every edge-labeling $w\colon E(K_n…
Anti-Ramsey numbers for cancellative configurations in p-graphs
Cheng Chi, Long-tu Yuan
We study edge-colorings of the complete -graph on vertices that contain no three edges of distinct colors such that the symmetric difference of and is contai…
Neural Control: Concurrent System Identification and Control Learning with Neural ODE
Cheng Chi
Controlling continuous-time dynamical systems is generally a two step process: first, identify or model the system dynamics with differential equations, then, minimize the control…
Concurrent intersection point of magnetization and magneto-conductivity curves in strongly fluctuating superconductors
Cheng Chi, Xujiang Jiang, Jiangfan Wang +2
The thermal fluctuations contribution to magnetization and magneto-conductivity of type II layered superconductor is calculated in the framework of Lawrence-Doniach model. For nume…
On three open problems in zero-sum Ramsey numbers
Cheng Chi, Jialin He, Quan Sun
Let denote the -vertex complete -uniform hypergraph. For an -uniform hypergraph and an integer , the -color Ramsey number is the least…
Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objects
Cheng Chi, Benjamin Burchfiel, Eric Cousineau +2
This paper tackles the task of goal-conditioned dynamic manipulation of deformable objects. This task is highly challenging due to its complex dynamics (introduced by object deform…
Flow as the Cross-Domain Manipulation Interface
Mengda Xu, Zhenjia Xu, Yinghao Xu +4
We present Im2Flow2Act, a scalable learning framework that enables robots to acquire real-world manipulation skills without the need of real-world robot training data. The key idea…
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
Cheng Chi, Xianqi Wang, Hongcheng Luo +9
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their pe…
Loss Function Search for Face Recognition
Xiaobo Wang, Shuo Wang, Cheng Chi +2
In face recognition, designing margin-based (e.g., angular, additive, additive angular margins) softmax loss functions plays an important role in learning discriminative features.…
Finance-Informed Neural Network: Learning the Geometry of Option Pricing
Amine M. Aboussalah, Xuanze Li, Cheng Chi +1
We propose a Finance-Informed Neural Network (FINN) for option pricing and hedging that integrates financial theory directly into machine learning. Instead of training on observed…
WIDER Face and Pedestrian Challenge 2018: Methods and Results
Chen Change Loy, Dahua Lin, Wanli Ouyang +49
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian. The challenge focuses on the problem of precise localization of human faces and bodies, and accurat…