Zuyan Liu

6

Papers

28

Total Citations

Papers (6)

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion

PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers

Unleashing Text-to-Image Diffusion Models for Visual Perception