From Modalities to Propositions: A Language-Centric Framework for Multimodal Intelligence

• URL: http://arxiv.org/abs/2607.16560v1
• Date: Sat, 18 Jul 2026 00:08:47 GMT
• Title: From Modalities to Propositions: A Language-Centric Framework for Multimodal Intelligence
• Abstract summary: We propose a language representation for multimodal data in which any observation, whether image, video, or text, is expressed as a bag of atomic propositions.<n>A global semantic codebook unifies these into a shared vocabulary of canonical atomic propositions.<n>We demonstrate the framework on autonomous driving and open-world data.
• Score: 32.47084374717649
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a language representation for multimodal data in which any observation, whether image, video, or text, is expressed as a bag of atomic propositions, simple statements about the entities, actions, and relations in a scene. A global semantic codebook unifies these into a shared vocabulary of canonical atomic propositions, placing every modality and observation into one interpretable space that spans fine grained facts to high level concepts and composes into richer ones. This brings interpretability with reasoning, cross-modal understanding and retrieval, and compositionality that enables complex multimodal understanding, rich data curation and complex structured retrieval. We demonstrate the framework on autonomous driving and open-world data.

Related papers

• Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms [70.51538670020267]
  We propose a hierarchical taxonomy that organizes the field into two primary dimensions: multimodal datasets and multimodal methods.<n>On the data side, we categorize resources ranging from Tactile-Vision datasets, Tactile-Language datasets, Tactile-Vision-Language datasets, and Tactile-Vision-Other datasets.<n>On the method side, we structure prior work into three core pillars: (1) Multimodal Perception and Recognition, (2) Cross-Modal Generation, focusing on bidirectional translation between tactile, vision, and text, and (3) Multimodal Interaction, emphasizing feedback control and language-guided manipulation.
  arXiv  Detail & Related papers  (2026-05-17T09:09:30Z)
• Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision [13.21187394955871]
  EgoPoint-Thought is the first large-scale multimodal dataset dedicated to egocentric deictic visual grounding.<n>It provides rich, multi-grained annotations including hand-target bounding box pairs and dense semantic captions.<n>We propose SV-CoT, a novel baseline framework that reformulates grounding as a structured inference process.
  arXiv  Detail & Related papers  (2026-03-27T17:49:56Z)
• A Parallel Cross-Lingual Benchmark for Multimodal Idiomaticity Understanding [15.171586338601522]
  Potentially idiomatic expressions (PIEs) construe meanings inherently tied to the everyday experience of a language community.<n>We present XMPIE, a parallel multilingual and multimodal dataset of potentially idiomatic expressions.
  arXiv  Detail & Related papers  (2026-01-13T15:20:28Z)
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
  Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
  arXiv  Detail & Related papers  (2025-10-17T02:33:16Z)
• GridMind: A Multi-Agent NLP Framework for Unified, Cross-Modal NFL Data Insights [0.0]
  This paper introduces GridMind, a framework that unifies structured, semi-structured, and unstructured data through Retrieval-Augmented Generation (RAG) and large language models (LLMs)<n>This approach aligns with the evolving field of multimodal representation learning, where unified models are increasingly essential for real-time, cross-modal interactions.
  arXiv  Detail & Related papers  (2025-03-24T18:33:36Z)
• Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment [0.0]
  We propose UMaT, a framework that unifies visual and auditory inputs as structured text for large language models.<n>It significantly improves state-of-the-art Long Video Question Answering accuracy.
  arXiv  Detail & Related papers  (2025-03-12T05:28:24Z)
• Hierarchical Banzhaf Interaction for General Video-Language Representation Learning [60.44337740854767]
  Multimodal representation learning plays an important role in the artificial intelligence domain.<n>We introduce a new approach that models video-text as game players using multivariate cooperative game theory.<n>We extend our original structure into a flexible encoder-decoder framework, enabling the model to adapt to various downstream tasks.
  arXiv  Detail & Related papers  (2024-12-30T14:09:15Z)
• ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension [71.03445074045092]
  We propose ClawMachine, offering a new methodology that explicitly notates each entity using token collectives groups of visual tokens.<n>Our method unifies the prompt and answer of visual referential tasks without using additional syntax.<n>ClawMachine achieves superior performance on scene-level and referential understanding tasks with higher efficiency.
  arXiv  Detail & Related papers  (2024-06-17T08:39:16Z)
• Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining? [34.609984453754656]
  We aim to elucidate the impact of comprehensive linguistic knowledge, including semantic expression and syntactic structure, on multimodal alignment. Specifically, we design and release the SNARE, the first large-scale multimodal alignment probing benchmark.
  arXiv  Detail & Related papers  (2023-08-24T16:17:40Z)
• Kosmos-2: Grounding Multimodal Large Language Models to the World [107.27280175398089]
  We introduce Kosmos-2, a Multimodal Large Language Model (MLLM) It enables new capabilities of perceiving object descriptions (e.g., bounding boxes) and grounding text to the visual world. Code and pretrained models are available at https://aka.ms/kosmos-2.
  arXiv  Detail & Related papers  (2023-06-26T16:32:47Z)
• High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning [112.51498431119616]
  This paper studies efficient representation learning for high-modality scenarios involving a large set of diverse modalities. A single model, HighMMT, scales up to 10 modalities (text, image, audio, video, sensors, proprioception, speech, time-series, sets, and tables) and 15 tasks from 5 research areas.
  arXiv  Detail & Related papers  (2022-03-02T18:56:20Z)
• Cross-Modal Discrete Representation Learning [73.68393416984618]
  We present a self-supervised learning framework that learns a representation that captures finer levels of granularity across different modalities. Our framework relies on a discretized embedding space created via vector quantization that is shared across different modalities.
  arXiv  Detail & Related papers  (2021-06-10T00:23:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.