paper-with-me

Papers

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback

2023-11-21 · Minghe Gao, Juncheng Li, Hao Fei, Liang Pang, Wei Ji, Guoming Wang, Zheqi Lv, Wenqiao Zhang, Siliang Tang, Yueting Zhuang

Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks. Unlike end-to-end models that need task-specific data, it advances in performing visual processing and reasoning in an unsupervised manner. Current visual programming methods generate programs in a single pass for each task where the ability to evaluate and optimize based on feedback, unfortunately, is lacking, which consequentially limits their effectiveness for complex, multi-step problems. Drawing inspiration from benders decomposition, we introduce De-fine, a training-free framework that automatically decomposes complex tasks into simpler subtasks and refines programs through auto-feedback. This model-agnostic approach can improve logical reasoning performance by integrating the strengths of multiple models. Our experiments across various visual tasks show that De-fine creates more robust programs. Moreover, viewing each feedback module as an independent agent will yield fresh prospects for the field of agent research.

📄 PDF Abstract BibTeX arXiv:2311.12890

Code (0)

등록된 구현이 없습니다.

Tasks

Logical Reasoning

Similar Papers 제목 키워드 기반

Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes

2023-01-04 · Justin Reppert, Ben Rachbach, Charlie George, Luke Stebbing 외

Language models (LMs) can perform complex reasoning either end-to-end, with hidden latent state, or compositionally, with transparent intermediate state. Composition offers benefits for interpretability and safety, but m…

BOOST: Bootstrapping Strategy-Driven Reasoning Programs for Program-Guided Fact-Checking

2025-04-03 · Qisheng Hu, Quanyu Long, Wenya Wang

Program-guided reasoning has shown promise in complex claim fact-checking by decomposing claims into function calls and executing reasoning programs. However, prior work primarily relies on few-shot in-context learning (…

Claim VerificationDiversityFact CheckingIn-Context Learning

Code Repair with LLMs gives an Exploration-Exploitation Tradeoff

2024-05-26 · Hao Tang, Keya Hu, Jin Peng Zhou, Sicheng Zhong 외

Iteratively improving and repairing source code with large language models (LLMs), known as refinement, has emerged as a popular way of generating programs that would be too complex to construct in one shot. Given a bank…

Code RepairLanguage ModelingLanguage ModellingProgram Synthesis+2

Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing

2025-04-04 · Mayank Kothyari, Sunita Sarawagi, Soumen Chakrabarti, Gaurav Arora 외

LLMs are increasingly used as seq2seq translators from natural language utterances to structured programs, a process called semantic interpretation. Unlike atomic labels or token sequences, programs are naturally represe…

Semantic Parsing

Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos

2025-08-10 · Tuyen Tran, Thao Minh Le, Quang-Hung Le, Truyen Tran arxiv

Vision-language alignment in video must address the complexity of language, evolving interacting entities, their action chains, and semantic gaps between language and vision. This work introduces Planner-Refiner, a frame…

Referring Video Object Segmentation