35 citations · 116 across the 24 of their papers we have counts for
25 papers
ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration
Shaobin Ling, Yun Wang, Chenyou Fan +2
Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: open-loop methods that compile tasks into formal representations for exte…
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts
Yun Wang, Longguang Wang, Chenghao Zhang +6
Recently, learning-based stereo matching networks have advanced significantly. However, they often lack robustness and struggle to achieve impressive cross-domain performance due t…
Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA
Yuhan Ma, Haiqi Jiang, Chenyou Fan
Large Language Models (LLMs) have shown outstanding performance across wide range of downstream tasks. This competency is attributed to their substantial parameter size and pre-tra…
Low-Parameter Federated Learning with Large Language Models
Jingang Jiang, Xiangyang Liu, Chenyou Fan
We study few-shot Natural Language Understanding (NLU) tasks with Large Language Models (LLMs) in federated learning (FL) scenarios. It is a challenging task due to limited labeled…
Towards Applying Powerful Large AI Models in Classroom Teaching: Opportunities, Challenges and Prospects
Kehui Tan, Tianqi Pang, Chenyou Fan +1
This perspective paper proposes a series of interactive scenarios that utilize Artificial Intelligence (AI) to enhance classroom teaching, such as dialogue auto-completion, knowled…
Carbon Price Forecasting with Quantile Regression and Feature Selection
Tianqi Pang, Kehui Tan, Chenyou Fan
Carbon futures has recently emerged as a novel financial asset in the trading markets such as the European Union and China. Monitoring the trend of the carbon price has become crit…
Federated Prompting and Chain-of-Thought Reasoning for Improving LLMs Answering
Xiangyang Liu, Tianqi Pang, Chenyou Fan
We investigate how to enhance answer precision in frequently asked questions posed by distributed users using cloud-based Large Language Models (LLMs). Our study focuses on a typic…
Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation
Junjie Hu, Chenyou Fan, Liguang Zhou +3
With the rapid advancements in autonomous driving and robot navigation, there is a growing demand for lifelong learning models capable of estimating metric (absolute) depth. Lifelo…
Progressive Self-Distillation for Ground-to-Aerial Perception Knowledge Transfer
Junjie Hu, Chenyou Fan, Mete Ozay +3
We study a practical yet hasn't been explored problem: how a drone can perceive in an environment from different flight heights. Unlike autonomous driving, where the perception is…
Dense Depth Distillation with Out-of-Distribution Simulated Images
Junjie Hu, Chenyou Fan, Mete Ozay +2
We study data-free knowledge distillation (KD) for monocular depth estimation (MDE), which learns a lightweight model for real-world depth perception tasks by compressing it from a…
Deep Depth Completion from Extremely Sparse Data: A Survey
Junjie Hu, Chenyu Bao, Mete Ozay +4
Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e.g., LiDARs. It plays an essential role in various applicatio…
Learn2Agree: Fitting with Multiple Annotators without Objective Ground Truth
Chongyang Wang, Yuan Gao, Chenyou Fan +4
The annotation of domain experts is important for some medical applications where the objective ground truth is ambiguous to define, e.g., the rehabilitation for some chronic disea…
Boosting Light-Weight Depth Estimation Via Knowledge Distillation
Junjie Hu, Chenyou Fan, Hualie Jiang +4
Monocular depth estimation (MDE) methods are often either too computationally expensive or not accurate enough due to the trade-off between model complexity and inference performan…
Federated Few-Shot Learning with Adversarial Learning
Chenyou Fan, Jianwei Huang
We are interested in developing a unified machine learning model over many mobile devices for practical learning tasks, where each device only has very few training data. This is a…
Projection Robust Wasserstein Distance and Riemannian Optimization
Tianyi Lin, Chenyou Fan, Nhat Ho +2
Projection robust Wasserstein (PRW) distance, or Wasserstein projection pursuit (WPP), is a robust variant of the Wasserstein distance. Recent work suggests that this quantity is m…
Federated Generative Adversarial Learning
Chenyou Fan, Ping Liu
This work studies training generative adversarial networks under the federated learning setting. Generative adversarial networks (GANs) have achieved advancement in various real-wo…
Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
Chenyou Fan, Xiaofan Zhang, Shu Zhang +3
In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively…
Improved Sample Complexity for Stochastic Compositional Variance Reduced Gradient
Tianyi Lin, Chenyou Fan, Mengdi Wang +1
Convex composition optimization is an emerging topic that covers a wide range of applications arising from stochastic optimal control, reinforcement learning and multi-stage stocha…
Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos
Mingze Xu, Chenyou Fan, Yuchen Wang +2
In a world of pervasive cameras, public spaces are often captured from multiple perspectives by cameras of different types, both fixed and mobile. An important problem is to organi…
Improved Oracle Complexity of Variance Reduced Methods for Nonsmooth Convex Stochastic Composition Optimization
Tianyi Lin, Chenyou Fan, Mengdi Wang
We consider the nonsmooth convex composition optimization problem where the objective is a composition of two finite-sum functions and analyze stochastic compositional variance red…
Multi-Task Spatiotemporal Neural Networks for Structured Surface Reconstruction
Mingze Xu, Chenyou Fan, John D Paden +2
Deep learning methods have surpassed the performance of traditional techniques on a wide range of problems in computer vision, but nearly all of this work has studied consumer phot…
Forecasting Hands and Objects in Future Frames
Chenyou Fan, Jangwon Lee, Michael S. Ryoo
This paper presents an approach to forecast future presence and location of human hands and objects. Given an image frame, the goal is to predict what objects will appear in the fu…
Identifying First-person Camera Wearers in Third-person Videos
Chenyou Fan, Jangwon Lee, Mingze Xu +4
We consider scenarios in which we wish to perform joint scene understanding, object tracking, activity recognition, and other tasks in environments in which multiple people are wea…
DeepDiary: Automatic Caption Generation for Lifelogging Image Streams
Chenyou Fan, David J. Crandall
Lifelogging cameras capture everyday life from a first-person perspective, but generate so much data that it is hard for users to browse and organize their image collections effect…