Guangnan Ye

large language model (4) sample-based explanation (2) model faithfulness (2) semantic evaluation (2) influence function (2) hessian-free method (2) classifier combination (1) responsible ai (1) adversarial robustness (1) entropy reduction (1) knowledge graph (1) adversarial attack (1) diffusion model (1) reward hacking (1) alternating direction method (1) structure learning (1) cross-domain benchmark (1) dynamic time warping (1) 3d generation (1) foundation model (1)