# JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments

arXiv: https://arxiv.org/abs/2602.18527 · HTML: https://mlsanity.com/paper/2602.18527/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 10 of 10)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [Grounded 3D-LLM with Referent Tokens](https://mlsanity.com/paper/2405.10370/) (2024)
- [Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation](https://mlsanity.com/paper/2411.02293/) (2024)
- [video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models](https://mlsanity.com/paper/2506.15220/) (2025)
- [N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2512.16561/) (2025)

## Built on by (most cited first, 4 of 4)

- [Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding](https://mlsanity.com/paper/2606.10738/) (2026)
- [OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents](https://mlsanity.com/paper/2609.23407/) (2026)
- [FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs](https://mlsanity.com/paper/2610.11310/) (2026)
- [SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning](https://mlsanity.com/paper/2610.17131/) (2026)

## Abstract (arXiv)

Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints, and datasets are available at https://github.com/liuzhan22/JAEGER.