The paper evaluates the performance of Vision-Language Models (VLMs) in a collaborative dialogue task requiring spatial reconstruction, finding that while detailed text representations improve results…

The paper introduces PAR3D, a unified part-aware 3D-MLLM framework, to enhance 3D scene understanding by enabling models to reason about and ground both whole objects and their fine-grained parts.

The paper proposes GASP, a framework that injects fundamental geometric priors directly into Vision-Language Models (VLMs) using ground-truth video geometry, significantly enhancing 3D spatial reasoni…

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…

Reasmory introduces a structured programming framework that uses explicit 3D memory and a Domain-Specific Language (DSL) to reliably enhance Vision-Language Models' spatial reasoning capabilities, ach…

ROVER is a lightweight, learnable plugin that efficiently routes and integrates object-centric visual evidence across multiple images and objects, significantly improving performance on grounded multi…

The paper introduces MOV-Bench, a challenging benchmark for multi-hop audio-visual reasoning, and proposes AOP-Agent, an agentic framework that significantly improves open-source Omni-LLMs' ability to…

The paper proposes AsyMoE, a novel Mixture of Experts architecture for Large Vision-Language Models that explicitly models the inherent asymmetry between visual and linguistic modalities, achieving si…

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…

SSR3D-LLM introduces a structured spatial reasoning interface for unified 3D-LLMs, allowing fine-grained object grounding by generating and processing sequential latent spatial steps.

The paper proposes BRACS, a training-free steering framework that adaptively corrects visual grounding failures in large vision-language models, significantly reducing object hallucination without sac…

The paper introduces Partial Information Decomposition (PID) to quantitatively separate unique, redundant, and synergistic contributions of different modalities (e.g., vision, language) in multimodal…

This paper introduces a new evaluation framework, SpatialUncertain, demonstrating that current Vision-Language Models (VLMs) are prone to overconfident and incorrect answers to spatial questions when…

The paper introduces ERGeoBench, a comprehensive diagnostic benchmark designed to evaluate the fine-grained capabilities of multimodal large language models (MLLMs) for embodied geo-localization acros…

LayerRoute introduces a lightweight, input-conditioned adapter that selectively skips transformer blocks in agentic language models, achieving significant FLOPs reduction while improving performance.

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…

The paper proposes Dynamic Adapter Routing (DAR), a novel method that significantly improves continual multimodal retrieval by adaptively selecting and merging specialized adapters.

The paper proposes xModel-KD, a cross-modal knowledge distillation framework, to improve 3D point cloud segmentation by effectively transferring rich appearance cues from 2D images to sparse 3D geomet…

This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.

The paper proposes Astra, an agentic framework that equips Vision-Language Models (VLMs) with the ability to perform spatial reasoning by actively generating and utilizing imagined visual evidence fro…