Haotong Qin

Affiliations

Beihang University

papers

982

total citations

papers (18)

Towards Real-World X-Ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection

ICCV 2021arXiv

101

citations

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

ICML 2024arXiv

citations

Image Fusion via Vision-Language Model

ICML 2024arXiv

citations

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

ICML 2025arXiv

citations

Defensive Patches for Robust Recognition in the Physical World

CVPR 2022arXiv

citations

MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models

AAAI 2025arXiv

citations

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

CVPR 2025arXiv

citations

BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models

ICLR 2025arXiv

citations

ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks

AAAI 2025arXiv

citations

QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution

NEURIPS 2023

citations

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction

NEURIPS 2025arXiv

citations

BiMatting: Efficient Video Matting via Binarization

NEURIPS 2023

citations

Flexible Residual Binarization for Image Super-Resolution

ICML 2024

citations

Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization

CVPR 2025

citations

Compressing Large Language Models by Joint Sparsification and Quantization

ICML 2024

citations

Haotong Qin

Affiliations

papers (18)

Forward and Backward Information Retention for Accurate Binary Neural Networks

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Diversifying Sample Generation for Accurate Data-Free Quantization

Towards Real-World X-Ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

Image Fusion via Vision-Language Model

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

Defensive Patches for Robust Recognition in the Physical World

MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models

ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks

QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction

BiMatting: Efficient Video Matting via Binarization

Flexible Residual Binarization for Image Super-Resolution

Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization

Compressing Large Language Models by Joint Sparsification and Quantization

papers (18)

Forward and Backward Information Retention for Accurate Binary Neural Networks

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Diversifying Sample Generation for Accurate Data-Free Quantization

Towards Real-World X-Ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

Image Fusion via Vision-Language Model

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

Defensive Patches for Robust Recognition in the Physical World

MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models

ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks

QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction

BiMatting: Efficient Video Matting via Binarization

Flexible Residual Binarization for Image Super-Resolution

Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization

Compressing Large Language Models by Joint Sparsification and Quantization