Sucheng Ren

17

Papers

49

Total Citations

Papers (17)

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

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

Rejuvenating image-GPT as Strong Visual Representation Learners

Reciprocal Transformations for Unsupervised Video Object Segmentation

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

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

Co-Advise: Cross Inductive Bias Distillation

A Simple Data Mixing Prior for Improving Self-Supervised Learning

Shunted Self-Attention via Multi-Scale Token Aggregation

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

On Feature Decorrelation in Self-Supervised Learning

Multimodal Knowledge Expansion

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

TENet: Triple Excitation Network for Video Salient Object Detection

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

Mamba-Reg: Vision Mamba Also Needs Registers

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