Xinghao Chen

papers

2,355

total citations

papers (28)

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

ICML 2024arXiv

citations

TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba

ICCV 2025arXiv

citations

An Empirical Study of Adder Neural Networks for Object Detection

NEURIPS 2021arXiv

citations

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

CVPR 2021arXiv

citations

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state

ICML 2025arXiv

citations

BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons

NEURIPS 2022arXiv

citations

ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking

ICML 2024arXiv

citations

SlimLLM: Accurate Structured Pruning for Large Language Models

ICML 2025arXiv

citations

Single Domain Generalization for Few-Shot Counting via Universal Representation Matching

CVPR 2025arXiv

citations

Data-Free Knowledge Distillation for Image Super-Resolution

CVPR 2021

citations

Handling Long-tailed Feature Distribution in AdderNets

NEURIPS 2021

citations

Positive-Unlabeled Data Purification in the Wild for Object Detection

CVPR 2021

citations

Towards Stable and Robust AdderNets

NEURIPS 2021

citations

Random Normalization Aggregation for Adversarial Defense

NEURIPS 2022

citations

AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification

CVPR 2022

citations

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement

CVPR 2025

citations

Xinghao Chen

papers (28)

CMT: Convolutional Neural Networks Meet Vision Transformers

CARS: Continuous Evolution for Efficient Neural Architecture Search

Multimodal Token Fusion for Vision Transformers

Distilling Object Detectors via Decoupled Features

Hire-MLP: Vision MLP via Hierarchical Rearrangement

Less is More: Focus Attention for Efficient DETR

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets

Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

Kernel Based Progressive Distillation for Adder Neural Networks

TinySAM: Pushing the Envelope for Efficient Segment Anything Model

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba

An Empirical Study of Adder Neural Networks for Object Detection

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state

BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons

ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking

SlimLLM: Accurate Structured Pruning for Large Language Models

Single Domain Generalization for Few-Shot Counting via Universal Representation Matching

Data-Free Knowledge Distillation for Image Super-Resolution

Handling Long-tailed Feature Distribution in AdderNets

Positive-Unlabeled Data Purification in the Wild for Object Detection

Towards Stable and Robust AdderNets

Random Normalization Aggregation for Adversarial Defense

AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement

papers (28)

CMT: Convolutional Neural Networks Meet Vision Transformers

CARS: Continuous Evolution for Efficient Neural Architecture Search

Multimodal Token Fusion for Vision Transformers

Distilling Object Detectors via Decoupled Features

Hire-MLP: Vision MLP via Hierarchical Rearrangement

Less is More: Focus Attention for Efficient DETR

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets

Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

Kernel Based Progressive Distillation for Adder Neural Networks

TinySAM: Pushing the Envelope for Efficient Segment Anything Model

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba

An Empirical Study of Adder Neural Networks for Object Detection

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state

BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons

ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking

SlimLLM: Accurate Structured Pruning for Large Language Models

Single Domain Generalization for Few-Shot Counting via Universal Representation Matching

Data-Free Knowledge Distillation for Image Super-Resolution

Handling Long-tailed Feature Distribution in AdderNets

Positive-Unlabeled Data Purification in the Wild for Object Detection

Towards Stable and Robust AdderNets

Random Normalization Aggregation for Adversarial Defense

AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement