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

• URL: http://arxiv.org/abs/2602.18527v1
• Date: Fri, 20 Feb 2026 04:06:07 GMT
• Title: JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments
• Abstract summary: We present JAEGER, a framework that extends AV-LLMs to 3D space to enable joint spatial grounding and reasoning.<n>A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation.<n>Our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks.
• Score: 34.02990381039783
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 will be released upon acceptance.

Related papers

• SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video [88.79625979053873]
  We propose a novel framework, SpaceEra, for pre-trained vision-language models (VLMs)<n>We extend the original framework into a comprehensive system, termed SpaceEra++, which spans data construction, model design, training optimization, and prompting inference.<n>In addition, to enhance spatial reasoning, we develop SpaceAlign, which enforces pairwise object constraints by jointly exploiting absolute coordinates and relative spatial relations.
  arXiv  Detail & Related papers  (2026-07-02T06:56:29Z)
• Reinforcing Dual-Path Reasoning in Spatial Vision Language Models [113.86271063627782]
  We present a unified framework that equips a spatial VLM with two complementary reasoning paths: Language-Only Reasoning (LOR) and Detect-Then-Reason (DTR)<n>Across diverse spatial benchmarks, SR-REAL significantly outperforms spatial VLM baselines.
  arXiv  Detail & Related papers  (2026-06-16T05:32:39Z)
• VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models [55.12929235609365]
  Visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image data without explicit 3D geometric supervision.<n>Existing implicit grounding methods partially address this by aligning VLA features with those of 3D-aware foundation models.<n>We propose VEGA, a framework that directly aligns the output of the VLA's visual encoder with spatially-aware features from DINOv2-FiT3D.
  arXiv  Detail & Related papers  (2026-05-11T12:44:26Z)
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding [50.098085774845195]
  We propose a paradigm shift by leveraging the implicit spatial prior within large-scale generation models.<n>We introduce GeneEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator.
  arXiv  Detail & Related papers  (2026-03-19T17:59:58Z)
• Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models [79.18306680174011]
  DSR Suite bridges gap across aspects of dataset, benchmark and model.<n>We propose an automated pipeline that generates multiple-choice question-answer pairs from in-the-wild videos for DSR.<n>The pipeline extracts rich geometric and motion information, including camera poses, local point clouds, object masks, orientations, and 3D trajectories.
  arXiv  Detail & Related papers  (2025-12-23T17:56:36Z)
• Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation [34.44214123004662]
  We propose VLM3D, a framework for differentiable semantic and spatial critics.<n>Our core contribution is a dual-language critic signal derived from the VLM's Yes or No log-odds.<n>VLM3D establishes a principled and general path to inject the VLM's rich, language-grounded understanding of both semantics and space into diverse 3D generative pipelines.
  arXiv  Detail & Related papers  (2025-11-18T09:05:26Z)
• Video Spatial Reasoning with Object-Centric 3D Rollout [58.12446467377404]
  We propose Object-Centric 3D Rollout (OCR) to enable robust video spatial reasoning.<n>OCR introduces structured perturbations to the 3D geometry of selected objects during training.<n>OCR compels the model to reason holistically across the entire scene.
  arXiv  Detail & Related papers  (2025-11-17T09:53:41Z)
• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models [100.13033631690114]
  Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding.<n>We introduce SandboxVLM, a framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM.<n>Our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods.
  arXiv  Detail & Related papers  (2025-11-14T04:16:09Z)
• SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion [52.959716866316604]
  Camera-based 3D Semantic Scene Completion (SSC) is a critical task in autonomous driving systems.<n>We propose the Semantic-PHysical Engaged REpresentation (SPHERE) for camera-based SSC.<n>SPHERE integrates voxel and Gaussian representations for joint exploitation of semantic and physical information.
  arXiv  Detail & Related papers  (2025-09-14T09:07:41Z)
• SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing [17.185628958975528]
  3D spatial reasoning in dynamic, audio-visual environments is a cornerstone of human cognition.<n> SAVVY is the first benchmark for 3D spatial reasoning in dynamic scenes with synchronized spatial audio.
  arXiv  Detail & Related papers  (2025-06-04T19:11:20Z)
• Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding [58.38294408121273]
  We propose Cross-modal and Uncertainty-aware Agglomeration for Open-vocabulary 3D Scene Understanding dubbed CUA-O3D.<n>Our method addresses two key challenges: (1) incorporating semantic priors from VLMs alongside the geometric knowledge of spatially-aware vision foundation models, and (2) using a novel deterministic uncertainty estimation to capture model-specific uncertainties.
  arXiv  Detail & Related papers  (2025-03-20T20:58:48Z)
• 3D Audio-Visual Segmentation [52.34970001474347]
  Recognizing the sounding objects in scenes is a longstanding objective in embodied AI, with diverse applications in robotics and AR/VR/MR.<n>We propose a new approach, EchoSegnet, characterized by integrating the ready-to-use knowledge from pretrained 2D audio-visual foundation models.<n>Experiments demonstrate that EchoSegnet can effectively segment sounding objects in 3D space on our new benchmark, representing a significant advancement in the field of embodied AI.
  arXiv  Detail & Related papers  (2024-11-04T16:30:14Z)
• Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation [44.940531391847]
  We address the challenge of dense indoor prediction with sound in 2D and 3D via cross-modal knowledge distillation. We are the first to tackle dense indoor prediction of omnidirectional surroundings in both 2D and 3D with audio observations. For audio-based depth estimation, semantic segmentation, and challenging 3D scene reconstruction, the proposed distillation framework consistently achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-09-20T06:07:04Z)

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.