# SceneBind: Binding What and Where Across Vision, Audio and Language

arXiv: https://arxiv.org/abs/2607.15265 · HTML: https://mlsanity.com/paper/2607.15265/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 47 of its 55 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [Audio-Visual Scene Analysis with Self-Supervised Multisensory Features](https://mlsanity.com/paper/1804.03641/) (2018)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding](https://mlsanity.com/paper/2311.18482/) (2023)
- [Learning to Localize Sound Source in Visual Scenes](https://mlsanity.com/paper/1803.03849/) (2018)
- [OneLLM: One Framework to Align All Modalities with Language](https://mlsanity.com/paper/2312.03700/) (2023)
- [Localizing Visual Sounds the Hard Way](https://mlsanity.com/paper/2104.02691/) (2021)
- [GridMM: Grid Memory Map for Vision-and-Language Navigation](https://mlsanity.com/paper/2307.12907/) (2023)
- [Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection](https://mlsanity.com/paper/2405.10300/) (2024)
- [Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching](https://mlsanity.com/paper/2010.05466/) (2020)
- [SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning](https://mlsanity.com/paper/2206.08312/) (2022)
- [Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1807.00129/) (2018)
- [X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning](https://mlsanity.com/paper/2311.18799/) (2023)
- [Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation](https://mlsanity.com/paper/2104.02026/) (2021)
- [Mix and Localize: Localizing Sound Sources in Mixtures](https://mlsanity.com/paper/2211.15058/) (2022)

## Abstract (arXiv)

We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it is). SceneBind addresses this gap by representing each scene as a semantic-spatial entity, combining a global semantic embedding with object-centric semantic-spatial slots. This representation explicitly captures object-level semantics, spatial attributes, and uncertainty. We further propose SceneBind Matching, a semantic-spatial matching scheme that integrates global scene similarity with object alignment, supporting cross-modal scene retrieval and object grounding. To train and evaluate SceneBind, we curate a novel real-world binaural audio-visual dataset with structured semantic and spatial annotations, and propose a training protocol for aligning semantic and spatial signals across modalities. SceneBind is compatible with large-scale pretrained semantic encoders, adds lightweight spatial modeling with only a few additional tokens. It achieves state-of-the-art scene and spatial retrieval while enabling strong zero-shot transfer to downstream tasks such as audio-visual localization.