Yukang Chen

11

Papers

781

Total Citations

Papers (11)

LISA: Reasoning Segmentation via Large Language Model

WorldModelBench: Judging Video Generation Models As World Models

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

NeurIPS 2025arXiv

SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Mixture-of-Scores: Robust Image-Text Data Valuation via Three Lines of Code

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

NVILA: Efficient Frontier Visual Language Models

Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs

VisionZip: Longer is Better but Not Necessary in Vision Language Models