b'Siyuan Li'

research

∙ 08/17/2023

IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making

Market making (MM) has attracted significant attention in financial trad...

0 Hui Niu, et al. ∙

research

∙ 08/14/2023

IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse

Humans have the ability to reuse previously learned policies to solve ne...

0 Siyuan Li, et al. ∙

research

∙ 07/20/2023

Cascade-DETR: Delving into High-Quality Universal Object Detection

Object localization in general environments is a fundamental part of vis...

0 Mingqiao Ye, et al. ∙

research

∙ 07/06/2023

Learning to Solve Tasks with Exploring Prior Behaviours

Demonstrations are widely used in Deep Reinforcement Learning (DRL) for ...

0 Ruiqi Zhu, et al. ∙

research

∙ 05/08/2023

Behavior Contrastive Learning for Unsupervised Skill Discovery

In reinforcement learning, unsupervised skill discovery aims to learn di...

4 Rushuai Yang, et al. ∙

research

∙ 05/06/2023

LibAM: An Area Matching Framework for Detecting Third-party Libraries in Binaries

Third-party libraries (TPLs) are extensively utilized by developers to e...

0 Siyuan Li, et al. ∙

research

∙ 04/17/2023

InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction

Large language models have unlocked strong multi-task capabilities from ...

0 Xiao Wang, et al. ∙

research

∙ 12/09/2022

Non-equispaced Fourier Neural Solvers for PDEs

Solving partial differential equations is difficult. Recently proposed n...

0 Haitao Lin, et al. ∙

research

∙ 11/25/2022

CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels

Pre-trained vision-language models like CLIP have recently shown superio...

1 Siyuan Li, et al. ∙

research

∙ 11/12/2022

Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

We investigate a practical domain adaptation task, called source-free do...

0 Ziyi Zhang, et al. ∙

research

∙ 10/24/2022

IDRL: Identifying Identities in Multi-Agent Reinforcement Learning with Ambiguous Identities

Multi-agent reinforcement learning(MARL) is a prevalent learning paradig...

3 Shijie Han, et al. ∙

research

∙ 10/15/2022

CUP: Critic-Guided Policy Reuse

The ability to reuse previous policies is an important aspect of human i...

0 Jin Zhang, et al. ∙

research

∙ 07/26/2022

Tracking Every Thing in the Wild

Current multi-category Multiple Object Tracking (MOT) metrics use class ...

3 Siyuan Li, et al. ∙

research

∙ 05/27/2022

Architecture-Agnostic Masked Image Modeling – From ViT back to CNN

Masked image modeling (MIM), an emerging self-supervised pre-training me...

6 Siyuan Li, et al. ∙

research

∙ 03/23/2022

UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection

Finding relevant moments and highlights in videos according to natural l...

0 Ye Liu, et al. ∙

research

∙ 03/15/2022

Style Transformer for Image Inversion and Editing

Existing GAN inversion methods fail to provide latent codes for reliable...

0 Xueqi Hu, et al. ∙

research

∙ 12/09/2021

A Shared Representation for Photorealistic Driving Simulators

A powerful simulator highly decreases the need for real-world tests when...

10 Saeed Saadatnejad, et al. ∙

research

∙ 10/01/2021

Offline Reinforcement Learning with Reverse Model-based Imagination

In offline reinforcement learning (offline RL), one of the main challeng...

0 Jianhao Wang, et al. ∙

research

∙ 05/31/2021

Efficient Hierarchical Exploration with Stable Subgoal Representation Learning

Goal-conditioned hierarchical reinforcement learning (HRL) serves as a s...

0 Siyuan Li, et al. ∙

research

∙ 09/21/2020

Deep Clustering and Representation Learning that Preserves Geometric Structures

In this paper, we propose a novel framework for Deep Clustering and Repr...

0 Lirong Wu, et al. ∙

research

∙ 01/23/2020

Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals

Our goal is to capture the pose of neuroscience model organisms, without...

4 Siyuan Li, et al. ∙

research

∙ 10/10/2019

Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards

Hierarchical Reinforcement Learning (HRL) is a promising approach to sol...

37 Siyuan Li, et al. ∙

research

∙ 03/20/2019

Single Image Deraining: A Comprehensive Benchmark Analysis

We present a comprehensive study and evaluation of existing single image...

0 Siyuan Li, et al. ∙

research

∙ 02/28/2019

PFLD: A Practical Facial Landmark Detector

Being accurate, efficient, and compact is essential to a facial landmark...

8 Xiaojie Guo, et al. ∙

research

∙ 06/11/2018

Context-Aware Policy Reuse

Transfer learning can greatly speed up reinforcement learning for a new ...

2 Siyuan Li, et al. ∙

research

∙ 04/08/2018

Fast Single Image Rain Removal via a Deep Decomposition-Composition Network

Rain effect in images typically is annoying for many multimedia and comp...

0 Siyuan Li, et al. ∙

research

∙ 11/29/2017

Deep Eyes: Binocular Depth-from-Focus on Focal Stack Pairs

Human visual system relies on both binocular stereo cues and monocular f...

0 Xinqing Guo, et al. ∙

research

∙ 10/17/2017

Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

We introduce a large-scale 3D shape understanding benchmark using data a...

0 Li Yi, et al. ∙

research

∙ 09/24/2017

An Optimal Online Method of Selecting Source Policies for Reinforcement Learning

Transfer learning significantly accelerates the reinforcement learning p...

0 Siyuan Li, et al. ∙

research

∙ 08/02/2017

A Learning-based Framework for Hybrid Depth-from-Defocus and Stereo Matching

Depth from defocus (DfD) and stereo matching are two most studied passiv...

0 Zhang Chen, et al. ∙

Siyuan Li

Featured Co-authors