Xin Dong

papers

635

total citations

papers (18)

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

CVPR 2023arXiv

153

citations

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

NEURIPS 2025arXiv

104

citations

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

CVPR 2022arXiv

citations

Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

NEURIPS 2025arXiv

citations

Segment Every Out-of-Distribution Object

CVPR 2024arXiv

citations

A Simple Background Augmentation Method for Object Detection with Diffusion Model

ECCV 2024arXiv

citations

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

AAAI 2025arXiv

citations

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

ICML 2025arXiv

citations

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

ICCV 2025arXiv

citations

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

NEURIPS 2025arXiv

citations

DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval

AAAI 2025arXiv

citations

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

NEURIPS 2023

citations

Xin Dong

papers (18)

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

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

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Hymba: A Hybrid-head Architecture for Small Language Models

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

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks

Dressing in the Wild by Watching Dance Videos

SphereFed: Hyperspherical Federated Learning

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

Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

Segment Every Out-of-Distribution Object

A Simple Background Augmentation Method for Object Detection with Diffusion Model

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

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

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

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval

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

papers (18)

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

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

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Hymba: A Hybrid-head Architecture for Small Language Models

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

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks

Dressing in the Wild by Watching Dance Videos

SphereFed: Hyperspherical Federated Learning

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

Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

Segment Every Out-of-Distribution Object

A Simple Background Augmentation Method for Object Detection with Diffusion Model

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

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

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

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval

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