Li, Yixuan
109 publications
TMLR
2025
Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
NeurIPS
2025
Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs
ICCV
2025
ObjectGS: Object-Aware Scene Reconstruction and Scene Understanding via Gaussian Splatting
ICML
2025
Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
ICLRW
2025
Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
NeurIPS
2024
BackdoorAlign: Mitigating Fine-Tuning Based Jailbreak Attack with Backdoor Enhanced Safety Alignment
NeurIPS
2024
Is a Picture Worth a Thousand Words? Delving into Spatial Reasoning for Vision Language Models