[논문리뷰] Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)
DPO 논문 리뷰 (NeurIPS 2023 Oral)
Recent posts
[논문리뷰] Language Model Beats Diffusion - Tokenizer is Key to Visual Generation (MAGVIT-v2)
MAGVIT-v2 논문 리뷰 (ICLR 2024)
[논문리뷰] ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
ProlificDreamer 논문 리뷰 (NeurIPS 2023 Spotlight)
[논문리뷰] PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
PP-LiteSeg 논문 리뷰
[논문리뷰] AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
AnimateDiff 논문 리뷰 (ICLR 2024)