Pinned Repositories
mDPO
[EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.
VADER
Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.
Contribution-statistics
Contribution statistics for paper "A method on Searching Better Activation Functions"
EAFO-code
EAFO-code for NeuIPS2024
EAFO_NIPS_Rebuttal
Sun-Haoyuan23's Repositories
Sun-Haoyuan23/Contribution-statistics
Contribution statistics for paper "A method on Searching Better Activation Functions"
Sun-Haoyuan23/EAFO-code
EAFO-code for NeuIPS2024
Sun-Haoyuan23/EAFO_NIPS_Rebuttal