Lin Li

13

Papers

55

Total Citations

Papers (13)

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation

Dynamic Uncertainty Estimation for Offline Reinforcement Learning

MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis

OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift

Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting

The Devil Is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

Compositional Feature Augmentation for Unbiased Scene Graph Generation

Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge

Zero-Shot Learning for Materials Science Texts: Leveraging Duck Typing Principles

Improving Generalization in Offline Reinforcement Learning via Latent Distribution Representation Learning

Adder Attention for Vision Transformer

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models