arXiv:2610.16769v1 Announce Type: new Abstract: Geospatial reasoning links VLMs to real-world action and decision making. Reliable reasoning requires accurate spatial information and effective spatia...
arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...
The paper introduces TTL‑SR, a geometry‑aware Test‑Time Learning framework designed to improve quantitative spatial reasoning in visual‑language models. By augmenting queries with geometrically coupled auxiliary prompts, filtering unreliable predictions, and updating models with a geometry‑aware multi‑objective loss on unlabeled test data, TTL‑SR adapts models to new domains without additional 3D supervision. Experiments show substantial accuracy gains on the Q‑Spatial‑ScanNet dataset for two state‑of‑the‑art VLMs.
The paper introduces Vantage, a training‑free, model‑agnostic framework that pairs a vision‑language model with a 3D foundation model to perform Seek‑and‑View reasoning for multi‑view spatial understanding. Vantage first analyzes a question to plan a relevant viewpoint, then augments reasoning with geometry‑grounded visual evidence from that viewpoint. Experiments across six VLMs on five benchmarks show consistent improvements without fine‑tuning, demonstrating that revealing spatial evidence through view‑grounded reasoning reduces reliance on language‑based cross‑view alignment.
GeoLatent introduces a geometry‑guided latent structuring approach for 3D reasoning from 2D images, separating position, direction, and global geometry under geometric supervision. It combines Common–Residual Geometry Alignment (CR‑GEO) with routed optimization to prevent latent collapse and to direct visual answer learning through the latents while maintaining full attention. The method achieves state‑of‑the‑art performance on SPAR‑Bench and SPBench, improving geometry effective rank and overall accuracy.
DK‑VLM introduces Dual‑Kernel Attention, where a visual token’s attention is computed from both its input position and its geometric position derived from 3D points and camera poses. A semantic kernel preserves pretrained attention while a geometric kernel modulates attention via point displacements and relative view transformations, with a learned gate fusing the two. The model also employs Reference‑Frame Composition supervision to update its reference frame across successive judgments, achieving top scores on six spatial benchmarks and strong performance on VSI‑Bench and ReVSI‑32.
arXiv:2606. 26535v1 Announce Type: cross Abstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning.
Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning.
arXiv:2610.08401v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) have shown outstanding performance across diverse applications, they tend to under-use visual information...
arXiv:2610.20592v1 Announce Type: new Abstract: Existing geometry-aware Multimodal Large Language Models (MLLMs) increasingly rely on external 3D encoders to provide structural priors, but executing...
arXiv:2606. 11719v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs).
arXiv:2609.33462v2 Announce Type: replace Abstract: Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use...