Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Xiyao, Yang, Zhengyuan, Li, Linjie, Lu, Hongjin, Xu, Yuancheng, Lin, Chung-Ching, Lin, Kevin, Huang, Furong, Wang, Lijuan
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
by: Wang, Xiyao, et al.
Published: (2025)

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

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

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

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

Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
by: Wang, Xiyao, et al.
Published: (2024)

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

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

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

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

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

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

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

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

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

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

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

Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
by: Xu, Yuancheng, et al.
Published: (2023)

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

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

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

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

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

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

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

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

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

Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents
by: Lin, Yiqi, et al.
Published: (2025)

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

EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing
by: Zheng, Kaizhi, et al.
Published: (2024)

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models
by: Zheng, Xiangxi, et al.
Published: (2025)

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

Bring Metric Functions into Diffusion Models
by: An, Jie, et al.
Published: (2024)

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

List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs
by: Yan, An, et al.
Published: (2024)

Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning
by: Wang, Alex Jinpeng, et al.
Published: (2024)

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

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

Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding
by: Liang, Yongyuan, et al.
Published: (2025)

EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing
by: Chen, Tianyu, et al.
Published: (2025)