Sihang Li

sparse autoencoder (2) chain of thought (2) molecule captioning (2) language model (2) large language model (2) object detection (1) feature extraction (1) domain generalization (1) multimodal learning (1) chain-of-thought reasoning (1) 3d vision (1) visual localization (1) multi-modal learning (1) adversarial training (1) pose estimation (1) scene representation (1) flow matching (1) data augmentation (1) scene graph (1) feature attribution (1)