Self-Rewarding Language Models
Paper
•
2401.10020
•
Published
•
145
Synthetic Data and Self-Improvement
-
-
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Paper • 2402.03620 • Published • 114 -
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Paper • 2402.07456 • Published • 41 -
Learning From Mistakes Makes LLM Better Reasoner
Paper • 2310.20689 • Published • 28 -
Best Practices and Lessons Learned on Synthetic Data for Language Models
Paper • 2404.07503 • Published • 29 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 60 -
ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
Paper • 2404.02893 • Published • 20 -
Voyager: An Open-Ended Embodied Agent with Large Language Models
Paper • 2305.16291 • Published • 9 -
Reflexion: Language Agents with Verbal Reinforcement Learning
Paper • 2303.11366 • Published • 4 -
Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
Paper • 2404.18796 • Published • 68 -
Extending Llama-3's Context Ten-Fold Overnight
Paper • 2404.19553 • Published • 33 -
Diffusion for World Modeling: Visual Details Matter in Atari
Paper • 2405.12399 • Published • 28 -
Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
Paper • 2405.20541 • Published • 21 -
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
Paper • 2406.04325 • Published • 72 -
Depth Anything V2
Paper • 2406.09414 • Published • 95 -
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Paper • 2406.08464 • Published • 65 -
Scaling Synthetic Data Creation with 1,000,000,000 Personas
Paper • 2406.20094 • Published • 96 -
Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning
Paper • 2407.20798 • Published • 23 -
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
Paper • 2408.06195 • Published • 63 -
Data curation via joint example selection further accelerates multimodal learning
Paper • 2406.17711 • Published • 3 -
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 136 -
Thinking LLMs: General Instruction Following with Thought Generation
Paper • 2410.10630 • Published • 18 -
How to Synthesize Text Data without Model Collapse?
Paper • 2412.14689 • Published • 48 -
Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
Paper • 2412.08737 • Published • 52 -
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
Paper • 2412.19723 • Published • 63 -
ProgCo: Program Helps Self-Correction of Large Language Models
Paper • 2501.01264 • Published • 19 -
Training Software Engineering Agents and Verifiers with SWE-Gym
Paper • 2412.21139 • Published • 16 -
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Paper • 2412.14922 • Published • 82 -
B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
Paper • 2412.17256 • Published • 42 -
Diving into Self-Evolving Training for Multimodal Reasoning
Paper • 2412.17451 • Published • 40 -
OpenAI o1 System Card
Paper • 2412.16720 • Published • 29 -
ResearchTown: Simulator of Human Research Community
Paper • 2412.17767 • Published • 12 -
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Paper • 2412.11605 • Published • 16 -
AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials
Paper • 2412.09605 • Published • 26