Imagen de Portada

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Xiyao, Yang, Zhengyuan, Feng, Chao, Lu, Hongjin, Li, Linjie, Lin, Chung-Ching, Lin, Kevin, Huang, Furong, Wang, Lijuan
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension
por: Wang, Xiyao, et al.
Publicado: (2024)

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
por: Ni, Minheng, et al.
Publicado: (2025)

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
por: Wang, Xiyao, et al.
Publicado: (2025)

Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation
por: Yang, Zhengyuan, et al.
Publicado: (2023)

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
por: Li, Ming, et al.
Publicado: (2025)

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
por: Wang, Xiyao, et al.
Publicado: (2024)

Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising
por: Lin, Yan-Bo, et al.
Publicado: (2025)

STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models
por: Chiang, Cheng-Han, et al.
Publicado: (2025)

Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
por: Zhai, Yuanhao, et al.
Publicado: (2024)

DisCo: Disentangled Control for Realistic Human Dance Generation
por: Wang, Tan, et al.
Publicado: (2023)

Comprehensive Analysis of Transparency and Accessibility of ChatGPT, DeepSeek, And other SoTA Large Language Models
por: Sapkota, Ranjan, et al.
Publicado: (2025)

ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning
por: Liao, Jiaqi, et al.
Publicado: (2025)

Measurement of LLM's Philosophies of Human Nature
por: Ni, Minheng, et al.
Publicado: (2025)

GenXD: Generating Any 3D and 4D Scenes
por: Zhao, Yuyang, et al.
Publicado: (2024)

MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities
por: Yu, Weihao, et al.
Publicado: (2024)

IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation
por: Zhai, Yuanhao, et al.
Publicado: (2024)

SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models
por: Chiang, Cheng-Han, et al.
Publicado: (2025)

LiVOS: Light Video Object Segmentation with Gated Linear Matching
por: Liu, Qin, et al.
Publicado: (2024)

Audio-Aware Large Language Models as Judges for Speaking Styles
por: Chiang, Cheng-Han, et al.
Publicado: (2025)

TechImage-Bench: Rubric-Based Evaluation for Technical Image Generation
por: Ni, Minheng, et al.
Publicado: (2025)

Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation
por: Cho, Jaemin, et al.
Publicado: (2023)

COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training
por: Wang, Alex Jinpeng, et al.
Publicado: (2024)

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
por: Yu, Weihao, et al.
Publicado: (2023)

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
por: Wang, Xiyao, et al.
Publicado: (2024)

Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance
por: Aiyappa, Rachith, et al.
Publicado: (2024)

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
por: Miao, Zichen, et al.
Publicado: (2024)

SCULPT: Constraint-Guided Pruned MCTS that Carves Efficient Paths for Mathematical Reasoning
por: Fang, Qitong, et al.
Publicado: (2026)

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
por: Hong, Yining, et al.
Publicado: (2024)

ShowUI: One Vision-Language-Action Model for GUI Visual Agent
por: Lin, Kevin Qinghong, et al.
Publicado: (2024)

Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
por: Hao, Yunzhuo, et al.
Publicado: (2025)

Computer-Use Agents as Judges for Generative User Interface
por: Lin, Kevin Qinghong, et al.
Publicado: (2025)

Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models
por: Wang, Alex Jinpeng, et al.
Publicado: (2025)

Glance: Accelerating Diffusion Models with 1 Sample
por: Dong, Zhuobai, et al.
Publicado: (2025)

DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS
por: Wang, Yingxu, et al.
Publicado: (2025)

Beyond the Node: Clade-level Selection for Efficient MCTS in Automatic Heuristic Design
por: Lai, Kezhao, et al.
Publicado: (2026)

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
por: Xu, Shijia, et al.
Publicado: (2026)

VideoGUI: A Benchmark for GUI Automation from Instructional Videos
por: Lin, Kevin Qinghong, et al.
Publicado: (2024)

Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
por: Liu, Fuxiao, et al.
Publicado: (2023)

SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation
por: Xu, Bin, et al.
Publicado: (2024)

Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
por: Wu, Tao, et al.
Publicado: (2025)