GroundSight at GroundLM 2026 Shared Tasks: GoldenViewVQA introduces a new VQA benchmark that requires models to answer driving‑scene questions while also identifying the camera view that supports the answer. The authors present CoVeR‑VQA, a training‑free, multi‑stage verification and correction framework that starts with GPT‑5.6 zero‑shot predictions and applies successive view‑specific, prior‑guided, and cross‑split group‑level verifications using Gemini‑3.6‑Flash, Claude‑Opus‑5, and semantic question grouping. On the official test set, CoVeR‑VQA achieves 84.75 % joint accuracy, surpassing the zero‑shot baseline by 13.56 percentage points, and the final run reaches 88.14 % joint accuracy after evaluator‑informed post‑hoc corrections.
arXiv:2607. 00491v1 Announce Type: cross Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input.
arXiv:2608. 08021v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context.
arXiv:2609.32352v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have shown increasing potential for medical image understanding, yet their capabilities in ophthalmic imaging r...
The paper introduces Rendering-Free Lookahead (RFL), a method for active robot vision that selects camera motions to reveal information needed for viewpoint-dependent question answering. RFL predicts future answerability—how well a view can answer a question—using a student model trained via distillation from a privileged teacher that renders future views with 3D Gaussian Splatting. In deployment, RFL chooses camera motions without rendering, achieving a 43% improvement in mean judge score over a baseline on 377 unseen test episodes.
arXiv:2609.35823v1 Announce Type: new Abstract: Vision-language models (VLMs) have made substantial progress in autonomous driving, but their success has primarily been studied in ego-centric scenes....
arXiv:2601. 19099v2 Announce Type: replace-cross Abstract: Vision--language models (VLMs) achieve strong performance on many multimodal benchmarks but remain brittle on spatial reasoning tasks that require aligning abstract overhead representations with egocentric views.
The paper introduces TerraAgent, a training‑free framework that enhances remote sensing visual question answering by integrating three modules: GDR for demonstration retrieval, MACE for evidence‑typed sub‑question decomposition, and CVA for counterfactual evidence auditing. It demonstrates significant improvements on multiple benchmarks, raising accuracy, visual‑dependency scores, and reducing prior‑only answers and hallucinations without fine‑tuning.
arXiv:2610.19564v1 Announce Type: new Abstract: A spatial answer depends on the reference frame specified in language and its supporting visual evidence. Item accuracy alone obscures whether correctn...
StateSight is a new benchmark designed to isolate and evaluate the ability of vision‑language models to reconstruct latent spatial structure from a single image. It consists of three procedurally generated task families—cube‑net opposite‑face reasoning, occluded cube‑tower counting, and 4‑neighbor connected‑component counting—each with 300 deterministic prompts and exact‑match scoring. The benchmark also includes a companion dataset, StateSight‑Steps, with 900 image‑text examples and 3,600 intermediate visual states to aid analysis of reconstruction errors.
arXiv:2606. 00616v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos.
arXiv:2608. 16480v1 Announce Type: cross Abstract: We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-language reasoning in roadside sequences.
The paper introduces PanoVideoBench, a manually annotated benchmark with 1,000 questions covering five categories and 15 question types for panoramic video understanding, and identifies cross‑view tracking and sphere‑time evidence integration as weak points in existing models. To address these gaps, the authors create PanoVideoCoT, a dataset of 13,465 QA‑CoT pairs generated via sphere‑time‑grounded synthesis, and train PanoVideoReasoner using panoramic CoT fine‑tuning and evidence‑privileged on‑policy self‑distillation. The resulting model achieves 55.7% accuracy on PanoVideoBench, improving the baseline by 12.5 points and surpassing the previous state‑of‑the‑art by 2.6 points, particularly in spatial, cross‑view, and temporal reasoning.