Sucheng Ren

papers

1,110

total citations

papers (19)

Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip Reading

CVPR 2021

citations

Delving Deep Into Many-to-Many Attention for Few-Shot Video Object Segmentation

CVPR 2021

citations

Sucheng Ren

papers (19)

Shunted Self-Attention via Multi-Scale Token Aggregation

On Feature Decorrelation in Self-Supervised Learning

TENet: Triple Excitation Network for Video Salient Object Detection

What If We Recaption Billions of Web Images with LLaMA-3?

Co-Advise: Cross Inductive Bias Distillation

SG-Former: Self-guided Transformer with Evolving Token Reallocation

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

A Simple Data Mixing Prior for Improving Self-Supervised Learning

Multimodal Knowledge Expansion

Learning from Multiple Annotator Noisy Labels via Sample-Wise Label Fusion

Rejuvenating image-GPT as Strong Visual Representation Learners

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

Mamba-Reg: Vision Mamba Also Needs Registers

Reciprocal Transformations for Unsupervised Video Object Segmentation

Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip Reading

Delving Deep Into Many-to-Many Attention for Few-Shot Video Object Segmentation

papers (19)

Shunted Self-Attention via Multi-Scale Token Aggregation

On Feature Decorrelation in Self-Supervised Learning

TENet: Triple Excitation Network for Video Salient Object Detection

What If We Recaption Billions of Web Images with LLaMA-3?

Co-Advise: Cross Inductive Bias Distillation

SG-Former: Self-guided Transformer with Evolving Token Reallocation

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

A Simple Data Mixing Prior for Improving Self-Supervised Learning

Multimodal Knowledge Expansion

Learning from Multiple Annotator Noisy Labels via Sample-Wise Label Fusion

Rejuvenating image-GPT as Strong Visual Representation Learners

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

Mamba-Reg: Vision Mamba Also Needs Registers

Reciprocal Transformations for Unsupervised Video Object Segmentation

Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip Reading

Delving Deep Into Many-to-Many Attention for Few-Shot Video Object Segmentation