Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies Paper • 2404.08197 • Published Apr 12 • 27
LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing Paper • 2402.10294 • Published Feb 15 • 22
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models Paper • 2402.19427 • Published Feb 29 • 52
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation Paper • 2401.08417 • Published Jan 16 • 32
InstructVideo: Instructing Video Diffusion Models with Human Feedback Paper • 2312.12490 • Published Dec 19, 2023 • 17
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback Paper • 2312.00849 • Published Dec 1, 2023 • 8
Diffusion Model Alignment Using Direct Preference Optimization Paper • 2311.12908 • Published Nov 21, 2023 • 47
Reward models on the hub Collection UNMAINTAINED: See RewardBench... A place to collect reward models, an often not released artifact of RLHF. • 18 items • Updated Apr 13 • 25
Woodpecker: Hallucination Correction for Multimodal Large Language Models Paper • 2310.16045 • Published Oct 24, 2023 • 14
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback Paper • 2309.00267 • Published Sep 1, 2023 • 47
Contrastive Prefence Learning: Learning from Human Feedback without RL Paper • 2310.13639 • Published Oct 20, 2023 • 24
Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection Paper • 2307.07205 • Published Jul 14, 2023 • 2