Publications (24)
GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction
Ge Sun, Sheng Wang, Lei Zhu +2
Accurate prediction of pedestrian trajectories is crucial for improving the safety of autonomous driving. However, this task is generally nontrivial due to the inherent stochastici…
DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies
Shivam Sood, Ge Sun, Peizhuo Li +1
Optimal Control for legged robots has gone through a paradigm shift from position-based to torque-based control, owing to the latter's compliant and robust nature. In parallel to t…
LHPF: Look back the History and Plan for the Future in Autonomous Driving
Sheng Wang, Yao Tian, Xiaodong Mei +5
Decision-making and planning in autonomous driving critically reflect the safety of the system, making effective planning imperative. Current imitation learning-based planning algo…
Learning-based Hierarchical Control: Emulating the Central Nervous System for Bio-Inspired Legged Robot Locomotion
Ge Sun, Milad Shafiee, Peizhuo Li +3
Animals possess a remarkable ability to navigate challenging terrains, achieved through the interplay of various pathways between the brain, central pattern generators (CPGs) in th…
HeLoM: Hierarchical Learning for Whole-Body Loco-Manipulation by a Hexapod Robot
Xinrong Yang, Peizhuo Li, Hongyi Li +8
In nature, animals often need to move/manipulate objects comparable in weight/size to their own bodies. Compared to grasping and carrying, pushing provides a more straightforward a…
MGTraj: Multi-Granularity Goal-Guided Human Trajectory Prediction with Recursive Refinement Network
Ge Sun, Jun Ma
Accurate human trajectory prediction is crucial for robotics navigation and autonomous driving. Recent research has demonstrated that incorporating goal guidance significantly enha…
Flexible Imputation of Incomplete Network Data
Ge Sun, Weisheng Zhang
Sampled network data are widely used in empirical research because collecting complete network information is costly. However, empirical analyses based on sampled networks may lead…
SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learning
Peizhuo Li, Hongyi Li, Ge Sun +7
Despite recent advances in learning-based controllers for legged robots, deployments in human-centric environments remain limited by safety concerns. Most of these approaches use p…
Enhancing Campus Mobility: Achievements and Challenges of Autonomous Shuttle "Snow Lion''
Yingbing Chen, Jie Cheng, Sheng Wang +15
The rapid evolution of autonomous vehicles (AVs) has significantly influenced global transportation systems. In this context, we present ``Snow Lion'', an autonomous shuttle meticu…
Attention-Based Functional-Group Coarse-Graining: A Deep Learning Framework for Molecular Prediction and Design
Ming Han, Ge Sun, Juan J. de Pablo
Machine learning (ML) offers considerable promise for the design of new molecules and materials. In real-world applications, the design problem is often domain-specific, and suffer…
DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving
Sheng Wang, Ge Sun, Fulong Ma +5
Evaluating and training autonomous driving systems require diverse and scalable corner cases. However, most existing scene generation methods lack controllability, accuracy, and ve…
FALCON: Actively Decoupled Visuomotor Policies for Loco-Manipulation with Foundation-Model-Based Coordination
Chengyang He, Ge Sun, Yue Bai +3
We present FoundAtion-model-guided decoupled LoCO-maNipulation visuomotor policies (FALCON), a framework for loco-manipulation that combines modular diffusion policies with a visio…
The Athenian Academy: A Seven-Layer Architecture Model for Multi-Agent Systems
Lidong Zhai, Zhijie Qiu, Lvyang Zhang +5
This paper proposes the "Academy of Athens" multi-agent seven-layer framework, aimed at systematically addressing challenges in multi-agent systems (MAS) within artificial intellig…
Legged Robots for Object Manipulation: A Review
Yifeng Gong, Ge Sun, Aditya Nair +5
Legged robots can have a unique role in manipulating objects in dynamic, human-centric, or otherwise inaccessible environments. Although most legged robotics research to date typic…
Bound states and the collective dynamics of Distant Quantum Emitters coupled to a chiral waveguide
Meng Qian Wu, Ge Sun, Jing Lu +1
We consider two two-level quantum emitters (QEs) with separations on the order of the wavelength which are chirally coupled to a one-dimensional (1D) waveguide, and the electromagn…
Cavity Modified Oscillating Bound States with a -type giant emitter in a linear waveguide
Ge Sun, Ya Yang, Jing Li +2
We study a system composed by a three-level giant atom (3GA), a waveguide initially in the vacuum state, and a single-mode cavity. The 3GA-cavity system is in a strong-coupling reg…
Emergent Oscillating bound states in a semi-infinite linear waveguide with a point-like -type quantum emitter driven by a classical field
YuPing He, Ge Sun, Jing Li +3
An oscillating bound state is a phenomenon where excitations mediated by the continuum modes oscillate persistently. Although it is generated by the superposition of two bound stat…
Prediction of Diblock Copolymer Morphology via Machine Learning
Hyun Park, Boyuan Yu, Juhae Park +4
A machine learning approach is presented to accelerate the computation of block polymer morphology evolution for large domains over long timescales. The strategy exploits the separ…
Resonator-assisted single-photon frequency convertion in a conventional waveguide with a giant V-type atom
Ge Sun, Hongzheng Wu, Jing Lu +1
We propose a scheme to achieve efficient frequency conversion for a single photon propagating in a 1D conventional waveguide by exploiting the quantum interference induced by the s…
PRIMAL3: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Leveraging LaCAM3
Chengyang He, Tanishq Duhan, Gadiel Sznaier Camps +6
We present PRIMAL3, an ultra-large-scale learning-based framework for multi-agent pathfinding (MAPF) that integrates reinforcement learning, topology-aware communication, LaCAM3-gu…
IEC-Independent Coupling Between Water Uptake and Ionic Conductivity in Anion-Conducting Polymer Films
Joan Montes de Oca, Ruilin Dong, Gervasio Zaldivar +5
Anion exchange membranes (AEMs) are promising candidates for replacing proton exchange membranes (PEMs) in electrochemical devices such as fuel cells, electrolyzers, batteries, and…
Controlling radiative dynamics of a giant -type atom via interference induced by the vacuum of a waveguide
Ci-Ming Deng, Ge Sun, Jing Lu +1
We investigate the dynamics of a -type giant atom (GA) whose both transition coupled to the guided modes of a one-dimensional (1D) waveguide at two spatially separated points w…
Tunable single-photon frequency converter in a waveguide with a giant V-type atom
Hongzheng Wu, Ge Sun, Jing Lu +1
We study the single-photon scattering in a one-dimensional (1D) waveguide coupled to one transition of a -type giant atom (GA), whose other transition is coherently driven by an…
Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition
Kehua Feng, Keyan Ding, Hongzhi Tan +8
Reliable evaluation of large language models (LLMs) is impeded by two key challenges: objective metrics often fail to reflect human perception of natural language, and exhaustive h…