paper-with-me

Papers

Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language

2025-05-28 · Guangfu Hao, Haojie Wen, Liangxuna Guo, Yang Chen, Yanchao Bi, Shan Yu

Flexible tool selection reflects a complex cognitive ability that distinguishes humans from other species, yet computational models that capture this ability remain underdeveloped. We developed a framework using low-dimensional attribute representations to bridge visual tool perception and linguistic task understanding. We constructed a comprehensive dataset (ToolNet) containing 115 common tools labeled with 13 carefully designed attributes spanning physical, functional, and psychological properties, paired with natural language scenarios describing tool usage. Visual encoders (ResNet or ViT) extract attributes from tool images while fine-tuned language models (GPT-2, LLaMA, DeepSeek) derive required attributes from task descriptions. Our approach achieves 74% accuracy in tool selection tasks-significantly outperforming direct tool matching (20%) and smaller multimodal models (21%-58%), while approaching performance of much larger models like GPT-4o (73%) with substantially fewer parameters. Ablation studies revealed that manipulation-related attributes (graspability, hand-relatedness, elongation) consistently prove most critical across modalities. This work provides a parameter-efficient, interpretable solution that mimics human-like tool cognition, advancing both cognitive science understanding and practical applications in tool selection tasks.

📄 PDF Abstract BibTeX arXiv:2505.22146

Code (0)

등록된 구현이 없습니다.

Tasks

Attribute

Methods 이 논문이 사용한 방법론

LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…

Similar Papers 제목 키워드 기반

MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs

2025-09-09 · Swati Swati, Arjun Roy, Emmanouil Panagiotou, Eirini Ntoutsi arxiv

Fairness-aware classification requires balancing performance and fairness, often intensified by intersectional biases. Conflicting fairness definitions further complicate the task, making it difficult to identify univers…

IVFS: Simple and Efficient Feature Selection for High Dimensional Topology Preservation

2020-04-02 · Xiaoyun Li, Chengxi Wu, Ping Li

Feature selection is an important tool to deal with high dimensional data. In unsupervised case, many popular algorithms aim at maintaining the structure of the original data. In this paper, we propose a simple and effec…

feature selectionVocal Bursts Intensity Prediction

A Copula Graphical Model for Multi-Attribute Data using Optimal Transport

2024-04-10 · Qi Zhang, Bing Li, Lingzhou Xue

Motivated by modern data forms such as images and multi-view data, the multi-attribute graphical model aims to explore the conditional independence structure among vectors. Under the Gaussian assumption, the conditional …

Attribute

On Irrelevance of Attributes in Flexible Prediction

2020-05-25 · Mieczyslaw A. Klopotek, Andrzej Matuszewski

This paper analyses properties of conceptual hierarchy obtained via incremental concept formation method called "flexible prediction" in order to determine what kind of "relevance" of participating attributes may be requ…

AttributeGeneral ClassificationPrediction

Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders

2020-12-01 · Zahra Atashgahi, Ghada Sokar, Tim Van der Lee, Elena Mocanu 외

Major complications arise from the recent increase in the amount of high-dimensional data, including high computational costs and memory requirements. Feature selection, which identifies the most relevant and informative…

ClusteringDenoisingDimensionality ReductionFeature Importance+1