Daquan Zhou

papers

6,389

total citations

papers (16)

DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-efficient Fine-Tuning

ICCV 2023arXiv

citations

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

ICLR 2024arXiv

citations

Expanding Small-Scale Datasets with Guided Imagination

NEURIPS 2023arXiv

citations

Dataset Quantization

ICCV 2023arXiv

citations

AutoSpace: Neural Architecture Search With Less Human Interference

ICCV 2021arXiv

citations

AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction

ICCV 2025

citations

PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought

CVPR 2024

citations

Daquan Zhou

papers (16)

Coordinate Attention for Efficient Mobile Network Design

Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning

Shunted Self-Attention via Multi-Scale Token Aggregation

Rethinking Bottleneck Structure for Efficient Mobile Network Design

All Tokens Matter: Token Labeling for Training Better Vision Transformers

ConvBERT: Improving BERT with Span-based Dynamic Convolution

Deep Model Reassembly

Diffusion Probabilistic Model Made Slim

Sharpness-Aware Training for Free

DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-efficient Fine-Tuning

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Expanding Small-Scale Datasets with Guided Imagination

Dataset Quantization

AutoSpace: Neural Architecture Search With Less Human Interference

AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction

PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought

papers (16)

Coordinate Attention for Efficient Mobile Network Design

Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning

Shunted Self-Attention via Multi-Scale Token Aggregation

Rethinking Bottleneck Structure for Efficient Mobile Network Design

All Tokens Matter: Token Labeling for Training Better Vision Transformers

ConvBERT: Improving BERT with Span-based Dynamic Convolution

Deep Model Reassembly

Diffusion Probabilistic Model Made Slim

Sharpness-Aware Training for Free

DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-efficient Fine-Tuning

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Expanding Small-Scale Datasets with Guided Imagination

Dataset Quantization

AutoSpace: Neural Architecture Search With Less Human Interference

AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction

PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought