Search Results for author: Tianhao Wu

Found 26 papers, 9 papers with code

Enhancing the Performance of DeepReach on High-Dimensional Systems through Optimizing Activation Functions

no code implementations29 Dec 2023 Qian Wang, Tianhao Wu

Hamilton-Jacobi Reachability Analysis is a formal verification method that guarantees performance and safety for dynamical systems and is widely applicable to various tasks and challenges.

Education distillation:getting student models to learn in shcools

no code implementations23 Nov 2023 Ling Feng, Danyang Li, Tianhao Wu, Xuliang Duan

Specifically, it is proposed to take fragmented student models divided from the complete student model as lower-grade models.

Incremental Learning Knowledge Distillation +1

Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment

no code implementations30 Sep 2023 Tianhao Wu, Banghua Zhu, Ruoyu Zhang, Zhaojin Wen, Kannan Ramchandran, Jiantao Jiao

In summary, this work introduces a simpler yet effective approach for aligning LLMs to human preferences through relative feedback.

reinforcement-learning World Knowledge

GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping

no code implementations12 Sep 2023 Tianhao Wu, Mingdong Wu, Jiyao Zhang, Yunchong Gan, Hao Dong

In this paper, we propose a novel task called human-assisting dexterous grasping that aims to train a policy for controlling a robotic hand's fingers to assist users in grasping objects.

ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylization

no code implementations23 Aug 2023 Wenzhao Li, Tianhao Wu, Fangcheng Zhong, Cengiz Oztireli

We highlight a research gap in radiance fields style transfer, the lack of sufficient perceptual controllability, motivated by the existing concept in the 2D image style transfer.

3D Reconstruction Style Transfer

Blockchain-empowered Federated Learning for Healthcare Metaverses: User-centric Incentive Mechanism with Optimal Data Freshness

no code implementations29 Jul 2023 Jiawen Kang, Jinbo Wen, Dongdong Ye, Bingkun Lai, Tianhao Wu, Zehui Xiong, Jiangtian Nie, Dusit Niyato, Yang Zhang, Shengli Xie

Given the revolutionary role of metaverses, healthcare metaverses are emerging as a transformative force, creating intelligent healthcare systems that offer immersive and personalized services.

Decision Making Federated Learning +1

PanoDiffusion: 360-degree Panorama Outpainting via Diffusion

no code implementations6 Jul 2023 Tianhao Wu, Chuanxia Zheng, Tat-Jen Cham

Generating complete 360-degree panoramas from narrow field of view images is ongoing research as omnidirectional RGB data is not readily available.


Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing Views

no code implementations24 Mar 2023 Hanxue Liang, Tianhao Wu, Param Hanji, Francesco Banterle, Hongyun Gao, Rafal Mantiuk, Cengiz Oztireli

We measured the quality of videos synthesized by several NVS methods in a well-controlled perceptual quality assessment experiment as well as with many existing state-of-the-art image/video quality metrics.


$α$Surf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity

no code implementations17 Mar 2023 Tianhao Wu, Hanxue Liang, Fangcheng Zhong, Gernot Riegler, Shimon Vainer, Cengiz Oztireli

While neural radiance field (NeRF) based methods can model semi-transparency and achieve photo-realistic quality in synthesized novel views, their volumetric geometry representation tightly couples geometry and opacity, and therefore cannot be easily converted into surfaces without introducing artifacts.

Surface Reconstruction

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

no code implementations NeurIPS 2023 Yunchang Yang, Han Zhong, Tianhao Wu, Bin Liu, LiWei Wang, Simon S. Du

We study stochastic delayed feedback in general multi-agent sequential decision making, which includes bandits, single-agent Markov decision processes (MDPs), and Markov games (MGs).

Decision Making

MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection

1 code implementation28 Sep 2022 Tianhao Wu, Boyang Li, Yihang Luo, Yingqian Wang, Chao Xiao, Ting Liu, Jungang Yang, Wei An, Yulan Guo

Due to the extremely large image coverage area (e. g., thousands square kilometers), candidate targets in these images are much smaller, dimer, more changeable than those targets observed by aerial-based and land-based imaging devices.

Data Augmentation

Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects

1 code implementation7 Aug 2022 Qiyu Dai, Jiyao Zhang, Qiwei Li, Tianhao Wu, Hao Dong, Ziyuan Liu, Ping Tan, He Wang

Commercial depth sensors usually generate noisy and missing depths, especially on specular and transparent objects, which poses critical issues to downstream depth or point cloud-based tasks.

Pose Estimation Transparent objects

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

1 code implementation17 Jun 2022 Yuanpei Chen, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Yiran Geng, Hao Dong, Zongqing Lu, Song-Chun Zhu, Yaodong Yang

In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects.

Few-Shot Learning Offline RL +2

D$^2$NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video

no code implementations31 May 2022 Tianhao Wu, Fangcheng Zhong, Andrea Tagliasacchi, Forrester Cole, Cengiz Oztireli

We introduce Decoupled Dynamic Neural Radiance Field (D$^2$NeRF), a self-supervised approach that takes a monocular video and learns a 3D scene representation which decouples moving objects, including their shadows, from the static background.

Image Segmentation Semantic Segmentation +1

GraspARL: Dynamic Grasping via Adversarial Reinforcement Learning

no code implementations4 Mar 2022 Tianhao Wu, Fangwei Zhong, Yiran Geng, Hongchen Wang, Yongjian Zhu, Yizhou Wang, Hao Dong

we formulate the dynamic grasping problem as a 'move-and-grasp' game, where the robot is to pick up the object on the mover and the adversarial mover is to find a path to escape it.

Object reinforcement-learning +1

$ \text{T}^3 $OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area

1 code implementation1 Mar 2022 Zheng Yuan, Tianhao Wu, Qinwen Wang, Yiying Yang, Lei LI, Lin Zhang

Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games.

Decision Making

Nearly Optimal Policy Optimization with Stable at Any Time Guarantee

no code implementations21 Dec 2021 Tianhao Wu, Yunchang Yang, Han Zhong, LiWei Wang, Simon S. Du, Jiantao Jiao

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms.

Reinforcement Learning (RL)

A Credibility-aware Swarm-Federated Deep Learning Framework in Internet of Vehicles

1 code implementation9 Aug 2021 Zhe Wang, Xinhang Li, Tianhao Wu, Chen Xu, Lin Zhang

This paper proposes a Swarm-Federated Deep Learning framework in the IoV system (IoV-SFDL) that integrates SL into the FDL framework.

BIG-bench Machine Learning Edge-computing

VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects

no code implementations ICLR 2022 Ruihai Wu, Yan Zhao, Kaichun Mo, Zizheng Guo, Yian Wang, Tianhao Wu, Qingnan Fan, Xuelin Chen, Leonidas Guibas, Hao Dong

In this paper, we propose object-centric actionable visual priors as a novel perception-interaction handshaking point that the perception system outputs more actionable guidance than kinematic structure estimation, by predicting dense geometry-aware, interaction-aware, and task-aware visual action affordance and trajectory proposals.

A Multi-intersection Vehicular Cooperative Control based on End-Edge-Cloud Computing

no code implementations1 Dec 2020 Mingzhi Jiang, Tianhao Wu, Zhe Wang, Yi Gong, Lin Zhang, Ren Ping Liu

In particular, we propose a Multi-intersection Vehicular Cooperative Control (MiVeCC) to enable cooperation among vehicles in a large area with multiple unsignalized intersections.

Cloud Computing Management

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot

1 code implementation NeurIPS 2020 Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Li-Wei Wang, Jason D. Lee

In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods and surprisingly find that: (1) A set of methods which aims to find good subnetworks of the randomly-initialized network (which we call "initial tickets"), hardly exploits any information from the training data; (2) For the pruned networks obtained by these methods, randomly changing the preserved weights in each layer, while keeping the total number of preserved weights unchanged per layer, does not affect the final performance.

Network Pruning

Light Field Image Super-Resolution Using Deformable Convolution

1 code implementation7 Jul 2020 Yingqian Wang, Jungang Yang, Longguang Wang, Xinyi Ying, Tianhao Wu, Wei An, Yulan Guo

In this paper, we propose a deformable convolution network (i. e., LF-DFnet) to handle the disparity problem for LF image SR.

Image Super-Resolution

DeOccNet: Learning to See Through Foreground Occlusions in Light Fields

1 code implementation10 Dec 2019 Yingqian Wang, Tianhao Wu, Jungang Yang, Longguang Wang, Wei An, Yulan Guo

In this paper, we handle the LF de-occlusion (LF-DeOcc) problem using a deep encoder-decoder network (namely, DeOccNet).

Cannot find the paper you are looking for? You can Submit a new open access paper.