Kang Zhao

papers

121

total citations

papers (11)

FlatQuant: Flatness Matters for LLM Quantization

ICML 2025arXiv

citations

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

ICML 2024arXiv

citations

AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis

AAAI 2024arXiv

citations

Accelerating Transformer Pre-training with 2:4 Sparsity

ICML 2024arXiv

citations

S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis

ECCV 2024arXiv

citations

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing

AAAI 2025arXiv

citations

Task-Specific Zero-shot Quantization-Aware Training for Object Detection

ICCV 2025arXiv

citations

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

CVPR 2023

citations

Kang Zhao

papers (11)

FlatQuant: Flatness Matters for LLM Quantization

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis

Accelerating Transformer Pre-training with 2:4 Sparsity

S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing

Task-Specific Zero-shot Quantization-Aware Training for Object Detection

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

Communication Efficient SGD via Gradient Sampling With Bayes Prior

Accelerating Sparse Convolution with Column Vector-Wise Sparsity

FaceComposer: A Unified Model for Versatile Facial Content Creation

papers (11)

FlatQuant: Flatness Matters for LLM Quantization

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis

Accelerating Transformer Pre-training with 2:4 Sparsity

S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing

Task-Specific Zero-shot Quantization-Aware Training for Object Detection

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

Communication Efficient SGD via Gradient Sampling With Bayes Prior

Accelerating Sparse Convolution with Column Vector-Wise Sparsity

FaceComposer: A Unified Model for Versatile Facial Content Creation