Guanglu Song

papers

1,646

total citations

papers (22)

Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction

ICCV 2023arXiv

citations

FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis

ECCV 2024arXiv

citations

Self-Slimmed Vision Transformer

ECCV 2022arXiv

citations

Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance

CVPR 2024arXiv

citations

Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection

ICCV 2023arXiv

citations

EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

ICML 2025arXiv

citations

Discriminability Distillation in Group Representation Learning

ECCV 2020arXiv

citations

ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model

ECCV 2024

citations

MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines

ICLR 2025

citations

Towards Robust Face Recognition with Comprehensive Search

ECCV 2022arXiv

citations

Unifying Visual Perception by Dispersible Points Learning

ECCV 2022arXiv

citations

See Further When Clear: Curriculum Consistency Model

CVPR 2025arXiv

citations

Switchable K-Class Hyperplanes for Noise-Robust Representation Learning

ICCV 2021

citations

Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes

NEURIPS 2022

citations

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

ECCV 2022

citations

Rethinking Robust Representation Learning under Fine-Grained Noisy Faces

ECCV 2022arXiv

citations

UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors

ICCV 2023

citations

Masked Autoencoders Are Stronger Knowledge Distillers

ICCV 2023

citations

Guanglu Song

papers (22)

DETRs with Collaborative Hybrid Assignments Training

Revisiting the Sibling Head in Object Detector

LMDrive: Closed-Loop End-to-End Driving with Large Language Models

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths

Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction

FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis

Self-Slimmed Vision Transformer

Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance

Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection

EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

Discriminability Distillation in Group Representation Learning

ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model

MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines

Towards Robust Face Recognition with Comprehensive Search

Unifying Visual Perception by Dispersible Points Learning

See Further When Clear: Curriculum Consistency Model

Switchable K-Class Hyperplanes for Noise-Robust Representation Learning

Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

Rethinking Robust Representation Learning under Fine-Grained Noisy Faces

UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors

Masked Autoencoders Are Stronger Knowledge Distillers

papers (22)

DETRs with Collaborative Hybrid Assignments Training

Revisiting the Sibling Head in Object Detector

LMDrive: Closed-Loop End-to-End Driving with Large Language Models

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths

Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction

FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis

Self-Slimmed Vision Transformer

Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance

Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection

EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

Discriminability Distillation in Group Representation Learning

ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model

MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines

Towards Robust Face Recognition with Comprehensive Search

Unifying Visual Perception by Dispersible Points Learning

See Further When Clear: Curriculum Consistency Model

Switchable K-Class Hyperplanes for Noise-Robust Representation Learning

Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

Rethinking Robust Representation Learning under Fine-Grained Noisy Faces

UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors

Masked Autoencoders Are Stronger Knowledge Distillers