Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge
with Curriculum Preference Learning

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

9 October 2024

Xiyao Wang

Furong Huang

Papers citing "Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning"

6 / 6 papers shown

Title
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement X. Wang Z. Yang Chao Feng Hongjin Lu Linjie Li Chung-Ching Lin Kevin Qinghong Lin Furong Huang Lijuan Wang OODD ReLM VLM LRM 57 1 0 10 Apr 2025
ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos Haolin Yang Feilong Tang Ming Hu Yulong Li Junjie Guo Yexin Liu Zelin Peng Junjun He Zongyuan Ge VGen DiffM 92 0 0 20 Mar 2025
VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning Y. Liu Kevin Qinghong Lin C. Chen Mike Zheng Shou LM&Ro LRM 57 0 0 17 Mar 2025
Data-Efficient Multi-Agent Spatial Planning with LLMs Huangyuan Su Aaron Walsman Daniel Garces Sham Kakade Stephanie Gil LLMAG Presented at ResearchTrend Connect \| LLMAG on 28 Mar 2025 126 0 0 26 Feb 2025
Streaming Looking Ahead with Token-level Self-reward H. Zhang Ruixin Hong Dong Yu 34 1 0 24 Feb 2025
Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement Xiyao Wang Jiuhai Chen Zhaoyang Wang Yuhang Zhou Yiyang Zhou ... Tianyi Zhou Tom Goldstein Parminder Bhatia Furong Huang Cao Xiao 53 33 0 24 May 2024