Search Results for author: Haoyu Zhao

Found 31 papers, 12 papers with code

Combinatorial Pure Exploration for Dueling Bandit

no code implementations ICML 2020 Wei Chen, Yihan Du, Longbo Huang, Haoyu Zhao

For Borda winner, we establish a reduction of the problem to the original CPE-MAB setting and design PAC and exact algorithms that achieve both the sample complexity similar to that in the CPE-MAB setting (which is nearly optimal for a subclass of problems) and polynomial running time per round.

Position

GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs

no code implementations15 Dec 2024 Xinli Xu, Wenhang Ge, Dicong Qiu, Zhifei Chen, Dongyu Yan, Zhuoyun Liu, Haoyu Zhao, HanFeng Zhao, Shunsi Zhang, Junwei Liang, Ying-Cong Chen

We demonstrate that 3D Gaussians with physical property annotations enable applications in physics-based dynamic simulation and robotic grasping.

Material Segmentation Robotic Grasping

Automated 3D Physical Simulation of Open-world Scene with Gaussian Splatting

no code implementations19 Nov 2024 Haoyu Zhao, Hao Wang, Xingyue Zhao, Hongqiu Wang, Zhiyu Wu, Chengjiang Long, Hua Zou

Recent advancements in 3D generation models have opened new possibilities for simulating dynamic 3D object movements and customizing behaviors, yet creating this content remains challenging.

3D Generation Large Language Model +2

Can Models Learn Skill Composition from Examples?

no code implementations29 Sep 2024 Haoyu Zhao, Simran Kaur, Dingli Yu, Anirudh Goyal, Sanjeev Arora

(2) When skill categories are split into training and held-out groups, models significantly improve at composing texts with held-out skills during testing despite having only seen training skills during fine-tuning, illustrating the efficacy of the training approach even with previously unseen skills.

Common Sense Reasoning

Serp-Mamba: Advancing High-Resolution Retinal Vessel Segmentation with Selective State-Space Model

no code implementations6 Sep 2024 Hongqiu Wang, Yixian Chen, Wu Chen, Huihui Xu, Haoyu Zhao, Bin Sheng, Huazhu Fu, Guang Yang, Lei Zhu

Based on the above observations, we first devise a Serpentine Interwoven Adaptive (SIA) scan mechanism, which scans UWF-SLO images along curved vessel structures in a snake-like crawling manner.

Mamba Retinal Vessel Segmentation

EasyControl: Transfer ControlNet to Video Diffusion for Controllable Generation and Interpolation

no code implementations23 Aug 2024 Cong Wang, Jiaxi Gu, Panwen Hu, Haoyu Zhao, Yuanfan Guo, Jianhua Han, Hang Xu, Xiaodan Liang

Specifically, for the sketch-to-video generation task, EasyControl achieves an improvement of 152. 0 on FVD and 19. 9 on IS, respectively, in UCF101 compared with VideoComposer.

Image Generation Video Generation

3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning

no code implementations19 Aug 2024 Haoyu Zhao, Hao Wang, Chen Yang, Wei Shen

Existing approaches for human avatar generation--both NeRF-based and 3D Gaussian Splatting (3DGS) based--struggle with maintaining 3D consistency and exhibit degraded detail reconstruction, particularly when training with sparse inputs.

3D geometry 3DGS +2

Topology-aware Human Avatars with Semantically-guided Gaussian Splatting

no code implementations19 Aug 2024 Haoyu Zhao, Chen Yang, Hao Wang, Xingyue Zhao, Wei Shen

To capture the explicit topological structure of the human body, we employ a 3D network that integrates both topological and geometric associations for human avatar deformation.

LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding

no code implementations27 May 2024 Haoyu Zhao, Wenhang Ge, Ying-Cong Chen

LLM-Optic first employs an LLM as a Text Grounder to interpret complex text queries and accurately identify objects the user intends to locate.

Visual Grounding

MoreStyle: Relax Low-frequency Constraint of Fourier-based Image Reconstruction in Generalizable Medical Image Segmentation

1 code implementation18 Mar 2024 Haoyu Zhao, Wenhui Dong, Rui Yu, Zhou Zhao, Du Bo, Yongchao Xu

The task of single-source domain generalization (SDG) in medical image segmentation is crucial due to frequent domain shifts in clinical image datasets.

Data Augmentation Image Reconstruction +4

WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising

1 code implementation18 Mar 2024 Haoyu Zhao, Yuliang Gu, Zhou Zhao, Bo Du, Yongchao Xu, Rui Yu

Second, to better capture high-frequency components and detailed information, Frequency-Aware Multi-scale Loss (FAM) is proposed by effectively utilizing multi-scale feature space.

Image Denoising

MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing

1 code implementation29 Nov 2023 Haoyu Zhao, Tianyi Lu, Jiaxi Gu, Xing Zhang, Qingping Zheng, Zuxuan Wu, Hang Xu, Yu-Gang Jiang

The high-fidelity alignment is developed to further enhance the fidelity of both video generation and editing by taking the subject image as an additional model input.

Denoising Image to Video Generation +1

Adversarial Attacks on Combinatorial Multi-Armed Bandits

1 code implementation8 Oct 2023 Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli, Huazheng Wang, Qingyun Wu, Haoyu Zhao

Contrary to prior understanding of multi-armed bandits, our work reveals a surprising fact that the attackability of a specific CMAB instance also depends on whether the bandit instance is known or unknown to the adversary.

Multi-Armed Bandits

Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation

1 code implementation7 Sep 2023 Jiaxi Gu, Shicong Wang, Haoyu Zhao, Tianyi Lu, Xing Zhang, Zuxuan Wu, Songcen Xu, Wei zhang, Yu-Gang Jiang, Hang Xu

Conditioned on an initial video clip with a small number of frames, additional frames are iteratively generated by reusing the original latent features and following the previous diffusion process.

Action Recognition Decoder +4

Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection

1 code implementation ICCV 2023 Wenhang Ge, Tao Hu, Haoyu Zhao, Shu Liu, Ying-Cong Chen

We show that together with a reflection direction-dependent radiance, our model achieves high-quality surface reconstruction on reflective surfaces and outperforms the state-of-the-arts by a large margin.

3D Reconstruction Multi-View 3D Reconstruction +1

Do Transformers Parse while Predicting the Masked Word?

no code implementations14 Mar 2023 Haoyu Zhao, Abhishek Panigrahi, Rong Ge, Sanjeev Arora

We also show that the Inside-Outside algorithm is optimal for masked language modeling loss on the PCFG-generated data.

Constituency Parsing Language Modeling +2

Task-Specific Skill Localization in Fine-tuned Language Models

1 code implementation13 Feb 2023 Abhishek Panigrahi, Nikunj Saunshi, Haoyu Zhao, Sanjeev Arora

Given the downstream task and a model fine-tuned on that task, a simple optimization is used to identify a very small subset of parameters ($\sim0. 01$% of model parameters) responsible for ($>95$%) of the model's performance, in the sense that grafting the fine-tuned values for just this tiny subset onto the pre-trained model gives performance almost as well as the fine-tuned model.

Continual Learning parameter-efficient fine-tuning

Coresets for Vertical Federated Learning: Regularized Linear Regression and $K$-Means Clustering

1 code implementation26 Oct 2022 Lingxiao Huang, Zhize Li, Jialin Sun, Haoyu Zhao

Vertical federated learning (VFL), where data features are stored in multiple parties distributively, is an important area in machine learning.

Clustering regression +1

SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression

1 code implementation20 Jun 2022 Zhize Li, Haoyu Zhao, Boyue Li, Yuejie Chi

We then propose a unified framework SoteriaFL for private federated learning, which accommodates a general family of local gradient estimators including popular stochastic variance-reduced gradient methods and the state-of-the-art shifted compression scheme.

Federated Learning Privacy Preserving

BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression

1 code implementation31 Jan 2022 Haoyu Zhao, Boyue Li, Zhize Li, Peter Richtárik, Yuejie Chi

Communication efficiency has been widely recognized as the bottleneck for large-scale decentralized machine learning applications in multi-agent or federated environments.

Faster Rates for Compressed Federated Learning with Client-Variance Reduction

no code implementations24 Dec 2021 Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtárik

In the convex setting, COFIG converges within $O(\frac{(1+\omega)\sqrt{N}}{S\epsilon})$ communication rounds, which, to the best of our knowledge, is also the first convergence result for compression schemes that do not communicate with all the clients in each round.

Federated Learning

FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning

no code implementations10 Aug 2021 Haoyu Zhao, Zhize Li, Peter Richtárik

We propose a new federated learning algorithm, FedPAGE, able to further reduce the communication complexity by utilizing the recent optimal PAGE method (Li et al., 2021) instead of plain SGD in FedAvg.

Federated Learning

Combinatorial Pure Exploration of Dueling Bandit

no code implementations23 Jun 2020 Wei Chen, Yihan Du, Longbo Huang, Haoyu Zhao

For Borda winner, we establish a reduction of the problem to the original CPE-MAB setting and design PAC and exact algorithms that achieve both the sample complexity similar to that in the CPE-MAB setting (which is nearly optimal for a subclass of problems) and polynomial running time per round.

Position

Combinatorial Semi-Bandit in the Non-Stationary Environment

no code implementations10 Feb 2020 Wei Chen, Li-Wei Wang, Haoyu Zhao, Kai Zheng

In a special case where the reward function is linear and we have an exact oracle, we design a parameter-free algorithm that achieves nearly optimal regret both in the switching case and in the dynamic case without knowing the parameters in advance.

Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Setting

no code implementations14 Nov 2019 Haoyu Zhao, Wei Chen

The problem is more challenging than the standard online learning scenario since the private value distribution is non-stationary, meaning that the distribution of bidders' private values may change over time, and we need to use the \emph{non-stationary regret} to measure the performance of our algorithm.

Mildly Overparametrized Neural Nets can Memorize Training Data Efficiently

no code implementations26 Sep 2019 Rong Ge, Runzhe Wang, Haoyu Zhao

It has been observed \citep{zhang2016understanding} that deep neural networks can memorize: they achieve 100\% accuracy on training data.

Stochastic One-Sided Full-Information Bandit

no code implementations20 Jun 2019 Haoyu Zhao, Wei Chen

In this paper, we study the stochastic version of the one-sided full information bandit problem, where we have $K$ arms $[K] = \{1, 2, \ldots, K\}$, and playing arm $i$ would gain reward from an unknown distribution for arm $i$ while obtaining reward feedback for all arms $j \ge i$.

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