LoRA

CARD: Personalized Text Generation via Cluster-Level Adaptation and Reward-Guided Decoding

CARD personalizes text generation via cluster-level LoRA adapters, lightweight preference vectors, and reward-…

AV-GRPO: Anchored-Modality Decoupled Diffusion Reinforcement Learning for Joint Audio-Video Generation

AV-GRPO is described as a GRPO-based reinforcement learning framework for joint audio-video models. It targets…