Peng Ye

17

Papers

145

Total Citations

Papers (17)

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

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

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

Boosting Residual Networks with Group Knowledge

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

Scaling Physical Reasoning with the PHYSICS Dataset

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

Less is More: Efficient Model Merging with Binary Task Switch

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

CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling

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

b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search

RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionary

Neural-Symbolic Entangled Framework for Complex Query Answering

Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing