Peng Ye

13

Papers

145

Total Citations

Papers (13)

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

All-in-One: Transferring Vision Foundation Models into Stereo Matching

DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models

Boosting Residual Networks with Group Knowledge

Scaling Physical Reasoning with the PHYSICS Dataset

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration

Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy

Consistency-aware Self-Training for Iterative-based Stereo Matching

CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling

Less is More: Efficient Model Merging with Binary Task Switch