-
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 140 -
Orion-14B: Open-source Multilingual Large Language Models
Paper • 2401.12246 • Published • 10 -
MambaByte: Token-free Selective State Space Model
Paper • 2401.13660 • Published • 48 -
MM-LLMs: Recent Advances in MultiModal Large Language Models
Paper • 2401.13601 • Published • 44
Collections
Discover the best community collections!
Collections including paper arxiv:2405.19107
-
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 65 -
Understanding and Diagnosing Deep Reinforcement Learning
Paper • 2406.16979 • Published • 8 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 59 -
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Paper • 2407.00617 • Published • 7
-
mDPO: Conditional Preference Optimization for Multimodal Large Language Models
Paper • 2406.11839 • Published • 36 -
Pandora: Towards General World Model with Natural Language Actions and Video States
Paper • 2406.09455 • Published • 14 -
WPO: Enhancing RLHF with Weighted Preference Optimization
Paper • 2406.11827 • Published • 14 -
In-Context Editing: Learning Knowledge from Self-Induced Distributions
Paper • 2406.11194 • Published • 15
-
Understanding the performance gap between online and offline alignment algorithms
Paper • 2405.08448 • Published • 14 -
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
Paper • 2405.19332 • Published • 15 -
Offline Regularised Reinforcement Learning for Large Language Models Alignment
Paper • 2405.19107 • Published • 12 -
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
Paper • 2406.00888 • Published • 30
-
Diffusion World Model
Paper • 2402.03570 • Published • 7 -
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
Paper • 2401.16335 • Published • 1 -
Towards Efficient and Exact Optimization of Language Model Alignment
Paper • 2402.00856 • Published -
ODIN: Disentangled Reward Mitigates Hacking in RLHF
Paper • 2402.07319 • Published • 13