Xin Dong

19

Papers

761

Total Citations

Papers (19)

Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon

NeurIPS 2017arXiv

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Hymba: A Hybrid-head Architecture for Small Language Models

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks

A Simple Background Augmentation Method for Object Detection with Diffusion Model

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling

Dressing in the Wild by Watching Dance Videos

SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning

MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing

SphereFed: Hyperspherical Federated Learning

Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?

DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder

DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval

Segment Every Out-of-Distribution Object

Pose2Seg: Detection Free Human Instance Segmentation

A Main/Subsidiary Network Framework for Simplifying Binary Neural Networks

Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning