The results show that format-valid responses can mask failures to recover the spatial structure required for verifiable visual inference, and that format-valid responses can mask failures to recover the spatial structure required for verifiable visual inference.
Abstract
Vision-language models are increasingly used for multimodal question answering, yet their ability to reconstruct latent spatial structure from a single image remains difficult to isolate. Broad benchmarks often combine perception, optical character recognition, domain knowledge, linguistic priors, and reasoning in the same evaluation. We introduce StateSight, a procedurally generated benchmark for cube-net opposite-face reasoning, occluded cube-tower counting, and 4-neighbor connected-component counting. Each task family contains 300 single-image prompts with deterministic oracle labels and exact-match scoring. OpenAI GPT-5.5, using the API model identifier gpt-5.5, achieved 59.3%, 33.3%, and 28.3% accuracy across the three tasks, while Claude Sonnet 5 achieved 53.3%, 18.7%, and 7.3%. All final direct runs had zero format errors. A 30-participant human baseline on 60 items exceeded both models on every task, with mean accuracies of 80.8%, 68.8%, and 64.3%. Visible-derivation analysis identified recurring errors in image-state reconstruction and reasoning procedure. We also introduce StateSight-Steps, a companion dataset of 900 interleaved image-text examples and 3,600 deterministic intermediate visual states. The results show that format-valid responses can mask failures to recover the spatial structure required for verifiable visual inference.
For the coarse attributes the authors study, MLLMs encode the visual evidence but cannot reliably control their reliance on it, indicating that for the coarse attributes they study, MLLMs cannot reliably control their reliance on it.
Jiaang Li, Chengzu Li, Zhaochong An et al.· arXiv.org· 0 citations
Recent vision-language-action (VLA) methods improve manipulation performance by aligning their representations with 3D scene geometry. However, these methods often struggle with long-horizon manipulation and observation aliasing between visually similar states due to a lack of temporal information: the 3D scene geometry captures only the current state, rather than how it has evolved over time. To resolve this, we present Temporal Forcing, a 4D representation alignment method for VLA models. Specifically, we first introduce a history pathway that enables a vanilla VLA model to summarize observation history into temporally aware latent representations. Then, the latent representations are aligned with the geometric features extracted by a pretrained 4D foundation model, which captures the evolving 3D world through temporally consistent geometric representations, enabling a deeper understanding of dynamic environments. Temporal Forcing reaches 98.8% on LIBERO, outperforming its base model by 2.2 points. On a physical hidden-placement task, it raises full-task success from 20.0% to 43.3%. Code will be publicly available.
Xing-Yu Ding, Yuzhong Zhao, Chunming Zhao et al.· 0 citations
This work proposes MCR-GRPO, a marginal contribution assignment framework that derives box-level credit directly from each sampled response, preserving GRPO's response-level comparison while enabling box-aware optimization of structured multi-object grounding.
Xinheng Han, Jianfeng Wang, Yu Chen et al.· 0 citations
Vision-language models (VLMs) have shown strong performance on multimodal reasoning tasks, yet their ability to perform quantitative analysis of technical drawings remains largely unexplored. This study evaluates the instruction-guided zero-shot performance of three open-source VLMs, on the task of estimating room areas from color-coded residential floor plan images. Of the three models tested, two produced quantitatively evaluable structure outputs. A dataset of 100 floor plans, comprising 472 plan-level room-type evaluation comparisons derived from 894 ground-truth room instances, was used to compare predicted and ground truth areas. Results show moderate predictive correlation (R2 ≈ 0.71), but substantial estimation errors (MAPE ≈ 43%), with noticeably larger errors for smaller rooms. A classical pixel counting baseline, using color segmentation, achieved MAPE = 5.68% at the room-instance level, and MAPE = 1.58% when evaluated at the floor plan level, highlighting the limitations of the tested VLMs for precise geometric estimation under this controlled setup. These findings suggest that while the evaluated open-source VLMs can approximate spatial proportions in simplified color-coded layouts, their quantitative accuracy remains significantly below that of deterministic image analysis methods.
N. Aliyev, Á. Barsi· Periodica polytechnica. Civi...· 0 citations
Multimodal large language models excel at passive perception but struggle with complex visual cognitive tasks requiring multi-step temporal reasoning. This degradation largely stems from the inherent ambiguity of language-based reasoning, which often fails to accurately articulate continuous visual transformations. To address this, we propose ChronoVision, a multimodal framework designed to align visual logic with latent imagery. During supervised fine-tuning, a Reconstructive Visual Head predicts the latent representation of the final transformed state, while an ROI Attention Locating module focuses the model on key visual evidence via semantic span queries. In post-training, we apply reinforcement learning with an implicit process grounding mechanism, guided by a composite reward function that evaluates outcome correctness, latent process alignment, and unsupervised visual focus. Furthermore, we introduce Vbvr-VQA, a novel dataset that evaluates temporal tracking by reformulating video reasoning into a strict image-ordering task. Experiments demonstrate that ChronoVision achieves state-of-the-art performance on Vbvr-VQA with 74.8% in-domain and 71.6% out-of-domain accuracy, alongside a strong 55.0% accuracy on IntPhys2, a highly challenging cross-domain benchmark.
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with questions requiring precise spatial reasoning and fine-grained visual understanding. These limitations often manifest as object, attribute, and spatial hallucinations, where models generate confident but visually unsupported responses due to insufficient region-level and fine-grained visual grounding. To address this challenge, we propose ReVA, a region-aware VQA model that employs a frozen CLIP ViT-L/14 Vision Transformer (ViT) and a Qwen2.5-7B-Instruct large language model (LLM) connected through a dual bridge that aligns both whole-image and region-level representations with the LLM's embedding space. The image bridge maps final transformer block features into image tokens. The region bridge maps cropped features from enriched intermediate features across ViT blocks so early texture and later object cues are more evident, into K region tokens for every bounding box. ReVA uses a detector stack that supplies automatic zero-shot bounding boxes that are both question-agnostic and question-dependent, using RAM++ (Recognize Anything Model), spaCy, and Grounding DINO. The image tokens and region tokens are concatenated as an LLM prompt prefix to jointly encode scene-level context and fine-grained regional evidence when answering questions. Evaluated on VQAv2, MMBench, POPE, and SEED-Bench, ReVA achieves 82.85% mean F1 on POPE, compared with 81.14% for an image-token baseline without region tokens. These results demonstrate that explicit region-aware visual representations reduce object hallucination and improve the factual grounding of MLLMs.
A. Senthil· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
