paper-with-me

Papers

Compositional Structures in Neural Embedding and Interaction Decompositions

2024-07-12 · Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto

We describe a basic correspondence between linear algebraic structures within vector embeddings in artificial neural networks and conditional independence constraints on the probability distributions modeled by these networks. Our framework aims to shed light on the emergence of structural patterns in data representations, a phenomenon widely acknowledged but arguably still lacking a solid formal grounding. Specifically, we introduce a characterization of compositional structures in terms of "interaction decompositions," and we establish necessary and sufficient conditions for the presence of such structures within the representations of a model.

📄 PDF Abstract BibTeX arXiv:2407.08934

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Linear Spaces of Meanings: Compositional Structures in Vision-Language Models

2023-02-28 · ICCV 2023 1 · Matthew Trager, Pramuditha Perera, Luca Zancato, Alessandro Achille 외

We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-e…

DisentanglementRetrieval

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

2025-03-21 · CVPR 2025 1 · Davide Berasi, Matteo Farina, Massimiliano Mancini, Elisa Ricci 외

Vision-Language Models (VLMs) learn a shared feature space for text and images, enabling the comparison of inputs of different modalities. While prior works demonstrated that VLMs organize natural language representation…

Sampling Bag of Views for Open-Vocabulary Object Detection

2024-12-24 · Hojun Choi, Junsuk Choe, Hyunjung Shim

Existing open-vocabulary object detection (OVD) develops methods for testing unseen categories by aligning object region embeddings with corresponding VLM features. A recent study leverages the idea that VLMs implicitly …

object-detectionObject DetectionOpen-vocabulary object detectionOpen Vocabulary Object Detection

Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering

2024-04-05 · Lili Liang, Guanglu Sun, Jin Qiu, Lizhong Zhang

Compositional spatio-temporal reasoning poses a significant challenge in the field of video question answering (VideoQA). Existing approaches struggle to establish effective symbolic reasoning structures, which are cruci…

Question AnsweringVideo Question Answering

TenExp: Mixture-of-Experts-Based Tensor Decomposition Structure Search Framework

2026-03-03 · Ting-Wei Zhou, Xi-Le Zhao, Sheng Liu, Wei-Hao Wu 외 arxiv

Recently, tensor decompositions continue to emerge and receive increasing attention. Selecting a suitable tensor decomposition to exactly capture the low-rank structures behind the data is at the heart of the tensor deco…