Ruihao Gong

papers

1,037

total citations

papers (17)

Once Quantization-Aware Training: High Performance Extremely Low-Bit Architecture Search

ICCV 2021arXiv

citations

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes

AAAI 2024arXiv

citations

Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

AAAI 2024arXiv

citations

Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM

NEURIPS 2025

citations

OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance

ICML 2025arXiv

citations

AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints

AAAI 2025

citations

Compressing Large Language Models by Joint Sparsification and Quantization

ICML 2024

citations

Annealing-Based Label-Transfer Learning for Open World Object Detection

CVPR 2023

citations

Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition

CVPR 2020

citations

Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization

CVPR 2023

citations

Lossy and Lossless (L2) Post-training Model Size Compression

ICCV 2023

citations

Ruihao Gong

papers (17)

Forward and Backward Information Retention for Accurate Binary Neural Networks

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models

Towards Unified INT8 Training for Convolutional Neural Network

Diversifying Sample Generation for Accurate Data-Free Quantization

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

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

Once Quantization-Aware Training: High Performance Extremely Low-Bit Architecture Search

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes

Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM

OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance

AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints

Compressing Large Language Models by Joint Sparsification and Quantization

Annealing-Based Label-Transfer Learning for Open World Object Detection

Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition

Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization

Lossy and Lossless (L2) Post-training Model Size Compression

papers (17)

Forward and Backward Information Retention for Accurate Binary Neural Networks

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models

Towards Unified INT8 Training for Convolutional Neural Network

Diversifying Sample Generation for Accurate Data-Free Quantization

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

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

Once Quantization-Aware Training: High Performance Extremely Low-Bit Architecture Search

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes

Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM

OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance

AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints

Compressing Large Language Models by Joint Sparsification and Quantization

Annealing-Based Label-Transfer Learning for Open World Object Detection

Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition

Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization

Lossy and Lossless (L2) Post-training Model Size Compression