Arrow Research search

Author name cluster

Ming C. Lin

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers
1 author row

Possible papers

6

NeurIPS Conference 2025 Conference Paper

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems

  • Rui Liu
  • Yu Shen
  • Peng Gao
  • Pratap Tokekar
  • Ming C. Lin

Multi-modal learning has emerged as a key technique for improving performance across domains such as autonomous driving, robotics, and reasoning. However, in certain scenarios, particularly in resource-constrained environments, some modalities available during training may be absent during inference. While existing frameworks effectively utilize multiple data sources during training and enable inference with reduced modalities, they are primarily designed for single-agent settings. This poses a critical limitation in dynamic environments such as connected autonomous vehicles (CAV), where incomplete data coverage can lead to decision-making blind spots. Conversely, some works explore multi-agent collaboration but without addressing missing modality at test time. To overcome these limitations, we propose Collaborative Auxiliary Modality Learning (CAML), a novel multi-modal multi-agent framework that enables agents to collaborate and share multi-modal data during training, while allowing inference with reduced modalities during testing. Experimental results in collaborative decision-making for CAV in accident-prone scenarios demonstrate that CAML achieves up to a 58. 1% improvement in accident detection. Additionally, we validate CAML on real-world aerial-ground robot data for collaborative semantic segmentation, achieving up to a 10. 6% improvement in mIoU.

PDF Details

NeurIPS Conference 2024 Conference Paper

Differentiable Quantum Computing for Large-scale Linear Control

  • Connor Clayton
  • Jiaqi Leng
  • Gengzhi Yang
  • Yi-Ling Qiao
  • Ming C. Lin
  • Xiaodi Wu

As industrial models and designs grow increasingly complex, the demand for optimal control of large-scale dynamical systems has significantly increased. However, traditional methods for optimal control incur significant overhead as problem dimensions grow. In this paper, we introduce an end-to-end quantum algorithm for linear-quadratic control with provable speedups. Our algorithm, based on a policy gradient method, incorporates a novel quantum subroutine for solving the matrix Lyapunov equation. Specifically, we build a quantum-assisted differentiable simulator for efficient gradient estimation that is more accurate and robust than classical methods relying on stochastic approximation. Compared to the classical approaches, our method achieves a super-quadratic speedup. To the best of our knowledge, this is the first end-to-end quantum application to linear control problems with provable quantum advantage.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

DMesh: A Differentiable Mesh Representation

  • Sanghyun Son
  • Matheus Gadelha
  • Yang Zhou
  • Zexiang Xu
  • Ming C. Lin
  • Yi Zhou

We present a differentiable representation, DMesh, for general 3D triangular meshes. DMesh considers both the geometry and connectivity information of a mesh. In our design, we first get a set of convex tetrahedra that compactly tessellates the domain based on Weighted Delaunay Triangulation (WDT), and select triangular faces on the tetrahedra to define the final mesh. We formulate probability of faces to exist on the actual surface in a differentiable manner based on the WDT. This enables DMesh to represent meshes of various topology in a differentiable way, and allows us to reconstruct the mesh under various observations, such as point clouds and multi-view images using gradient-based optimization. We publicize the source code and supplementary material at our project page (https: //sonsang. github. io/dmesh-project).

PDF Details DOI

AAAI Conference 2021 Conference Paper

Differentiable Fluids with Solid Coupling for Learning and Control

  • Tetsuya Takahashi
  • Junbang Liang
  • Yi-Ling Qiao
  • Ming C. Lin

We introduce an efficient differentiable fluid simulator that can be integrated with deep neural networks as a part of layers for learning dynamics and solving control problems. It offers the capability to handle one-way coupling of fluids with rigid objects using a variational principle that naturally enforces necessary boundary conditions at the fluid-solid interface with sub-grid details. This simulator utilizes the adjoint method to efficiently compute the gradient for multiple time steps of fluid simulation with user defined objective functions. We demonstrate the effectiveness of our method for solving inverse and control problems on fluids with one-way coupled solids. Our method outperforms the previous gradient computations, state-of-the-art derivative-free optimization, and model-free reinforcement learning techniques by at least one order of magnitude.

PDF Details

AAMAS Conference 2010 Conference Paper

Independent Navigation of Multiple Robots and Virtual Agents

  • Jamie Snape
  • Stephen J. Guy
  • Jur van den Berg
  • Sean Curtis
  • Sachin Patil
  • Ming C. Lin
  • Dinesh Manocha

We demonstrate an approach for collision- and oscillation-free navigation of multiple robots or virtual agents amongsteach other. Each entity acts independently and uses onlyboth the position and velocity of nearby entities to predicttheir future trajectories in order to avoid collisions. Entitiestake into account that the other entities are responding tothem likewise to prevent oscillations.

PDF

AAMAS Conference 2010 Conference Paper

Modeling Collision Avoidance Behavior for Virtual Humans

  • Stephen J. Guy
  • Ming C. Lin
  • Dinesh Manocha

In this paper, we present a new trajectory planning algorithm for virtual humans. Our approach focuses on implicitcooperation between multiple virtual agents in order to sharethe work of avoiding collisions with each other. Specifically, we extend recent work on multi-robot planning to bettermodel how humans avoid collisions by introducing new parameters that model human traits, such as reaction timeand biomechanical limitations. We validate this new modelbased on data of real humans walking captured by the Locanthrope project. We also show how our model extendsto complex scenarios with multiple agents interacting witheach other and avoiding nearby obstacles.

PDF