# FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs

arXiv: https://arxiv.org/abs/2610.11310 · HTML: https://mlsanity.com/paper/2610.11310/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 66 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 20 of 20)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM](https://mlsanity.com/paper/2510.15870/) (2025)
- [Aria Everyday Activities Dataset](https://mlsanity.com/paper/2402.13349/) (2024)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2512.16561/) (2025)
- [EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models](https://mlsanity.com/paper/2406.10224/) (2024)
- [EgoSound: Benchmarking Sound Understanding in Egocentric Videos](https://mlsanity.com/paper/2602.14122/) (2026)
- [OWL: Geometry-Aware Spatial Reasoning for Audio Large Language Models](https://mlsanity.com/paper/2509.26140/) (2025)
- [The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models](https://mlsanity.com/paper/2601.02954/) (2026)
- [PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs](https://mlsanity.com/paper/2601.21124/) (2026)
- [JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments](https://mlsanity.com/paper/2602.18527/) (2026)
- [EgoAVU: Egocentric Audio-Visual Understanding](https://mlsanity.com/paper/2602.06139/) (2026)
- [Spatial Audio Motion Understanding and Reasoning](https://mlsanity.com/paper/2509.14666/) (2025)
- [FloorPlan-VLN: A New Paradigm for Floor Plan Guided Vision-Language Navigation](https://mlsanity.com/paper/2603.17437/) (2026)

## Abstract (arXiv)

While 3D spatial reasoning in dynamic egocentric environments is crucial for embodied intelligence, audio-visual large language models (AV-LLMs) lack explicit mechanisms to process and internalize global geometry directly from raw sensory streams. Existing approaches either require costly fine-tuning or underutilize the model's cross-modal reasoning capacities. In this paper, we propose FloorSAV, a novel framework that explicitly grounds spatial audio-visual context by rendering a dynamic 2D floormap. By integrating 3D point clouds, camera trajectories, spatial audio cues, and semantically grounded object landmarks, we inject this floormap into the AV-LLM as a synchronized stream with an egocentric video. AV-LLMs utilize their multi-modal capabilities to jointly reason over visual, auditory, and geometric cues in a single inference with floormap interpretation guidance. We further introduce SAVED-Bench (Spatial Audio-Visual Egocentric Benchmark with Dynamic Agents), constructing essential tasks of spatial capability in real-world scenarios: dynamic relativity, regional, and path reasoning QAs. FloorSAV improves AV-LLMs' spatial reasoning on various tasks from both SAVED-Bench and SAVVY-Bench. Studies with ground-truth floormaps demonstrate the substantial potential of FloorSAV with accurate spatial information.