01

Active Prompt Learning with Vision-Language Model Priors

02

Retrieval-Augmented Generation with Estimation of Source Reliability

03

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training

04

K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean

05

Iterative Prompt Refinement for Safer Text-to-Image Generation

06

Rethinking DPO: The Role of Rejected Responses in Preference Misalignment

07

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations

08

Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss Landscapes

9

GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs

10

Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition