Yanye Lu

5

Papers

22

Total Citations

Papers (5)

Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation

V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer

Auto-Regressively Generating Multi-View Consistent Images

Enhancing Image Restoration Transformer via Adaptive Translation Equivariance

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension