paper-with-me

홈 › Papers

Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study

2025-02-17 · Yujie Lin, Ante Wang, Moye Chen, Jingyao Liu, Hao liu, Jinsong Su, Xinyan Xiao

Recently, inference-time scaling of chain-of-thought (CoT) has been demonstrated as a promising approach for addressing multi-modal reasoning tasks. While existing studies have predominantly centered on text-based thinking, the integration of both visual and textual modalities within the reasoning process remains unexplored. In this study, we pioneer the exploration of inference-time scaling with multi-modal thought, aiming to bridge this gap. To provide a comprehensive analysis, we systematically investigate popular sampling-based and tree search-based inference-time scaling methods on 10 challenging tasks spanning various domains. Besides, we uniformly adopt a consistency-enhanced verifier to ensure effective guidance for both methods across different thought paradigms. Results show that multi-modal thought promotes better performance against conventional text-only thought, and blending the two types of thought fosters more diverse thinking. Despite these advantages, multi-modal thoughts necessitate higher token consumption for processing richer visual inputs, which raises concerns in practical applications. We hope that our findings on the merits and drawbacks of this research line will inspire future works in the field.

📄 PDF Abstract BibTeX arXiv:2502.11514

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones

2025-05-27 · Parsa Mirtaheri, Ezra Edelman, Samy Jelassi, Eran Malach 외

Inference-time computation has emerged as a promising scaling axis for improving large language model reasoning. However, despite yielding impressive performance, the optimal allocation of inference-time computation rema…

Language ModelingLanguage ModellingLarge Language Model

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

2026-02-12 · Leon Liangyu Chen, Haoyu Ma, Zhipeng Fan, Ziqi Huang 외 arxiv

Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especial…

Visual Reasoning

MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains

2025-08-25 · Kaiwen Wei, Rui Shan, Dongsheng Zou, Jianzhong Yang 외 arxiv

Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augmented generation (RAG) into multi-step reas…

Knowledge Graphs

When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs

2025-10-25 · Keyu Wang, Tian Lyu, Guinan Su, Jonas Geiping 외 arxiv

Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs). Although existing methods demonstrate strong performance retention on general knowledge tasks, their e…

General Knowledge

Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods

2025-04-18 · Junlin Wang, Shang Zhu, Jon Saad-Falcon, Ben Athiwaratkun 외

There is intense interest in investigating how inference time compute (ITC) (e.g. repeated sampling, refinements, etc) can improve large language model (LLM) capabilities. At the same time, recent breakthroughs in reason…

Large Language Model