Junyi Wu

8

Papers

26

Total Citations

Papers (8)

Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer

CaO2: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation

Enhanced Visual-Semantic Interaction with Tailored Prompts for Pedestrian Attribute Recognition

Efficient Multimodal Dataset Distillation via Generative Models

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition

On the Faithfulness of Vision Transformer Explanations

QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation