VQA
-
Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image Reasoning
2026-08-06 08:40:57Bryan Wong, Xun Xu, Huazhu Fu, Nancy F. Chen, Mun Yong YiAbstract
Whole-slide image (WSI) reasoning requires an agent to sequentially acquire visual evidence before answering a diagnostic question. Existing training-free agentic frameworks formulate this process as iterative patch retrieval based on semantic relevance to the question. However, semantic relevance does not necessarily imply diagnostic informativeness in computational pathology, where competing diagnoses often exhibit similar and overlapping morphological patterns, making many patches semantically relevant yet diagnostically non-discriminative. Consequently, relevance-based retrieval may acquire redundant observations and leave diagnostic uncertainty unresolved. We propose BEACON, a plug-and-play agentic framework that reformulates WSI reasoning as a Bayesian evidence acquisition problem. BEACON maintains a probabilistic belief over competing diagnostic hypotheses and sequentially acquires patches by maximizing expected information gain (EIG) to reduce diagnostic uncertainty. An evidence controller then determines whether to answer, acquire additional evidence, or perform higher-resolution inspection. Built entirely from off-the-shelf foundation models, BEACON requires no additional training or fine-tuning. Extensive zero-shot experiments across five WSI-VQA benchmarks demonstrate that BEACON achieves the strongest overall performance among training-free agentic frameworks while substantially improving evidence acquisition efficiency, establishing Bayesian evidence acquisition as a principled paradigm for uncertainty-aware agentic WSI reasoning. The code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.05757
PDF
-
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?
2026-08-06 08:33:13Qifeng Zhang, Kaixiang Huang, Heng Dong, Huang Fang, Junting Chen, Junjie Zhu, Yonghang Chen, Zhiyu Zhang, Wei LiAbstract
Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overlooking global spatial awareness over continuous, long-horizon visual streams. To address this limitation, we introduce the Global-Spatial-Temporal Benchmark (GST-Bench), a VQA benchmark for global spatial intelligence in video understanding, comprising human-verified questions derived from 6,790 minutes of synthetically generated video. It requires models to perform accurate spatial inference from novel viewpoints unseen in the input video and to map egocentric observations onto global top-down images. A comprehensive evaluation of 22 state-of-the-art VLMs exposes a striking gap between models and humans: the strongest zero-shot model attains only 42.68, far below the human score of 79.08. To probe the cause of this gap, we construct GST-Bench-Local and find that models, despite strong local spatial understanding under the same task formulation, still fail to consolidate long-horizon observations into a globally consistent scene representation. We further provide GST-Train, a dataset for global spatial reasoning, as a complementary resource to facilitate future research on this challenge.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05747
PDF
-
SciQNet: Two-Stage Multimodal Adaptation for Scientific Image Quality Assessment
2026-08-06 07:33:23Yin-Loon Khor, Yi-Jie Wong, Jing Jie Tan, Ming Jie LeeAbstract
Scientific images are essential for communicating experimental observations, quantitative evidence and conceptual knowledge. Unlike natural images, their quality depends on both visual clarity and scientific informativeness, making assessment challenging. In this work, we present SciQNet, a two-stage multimodal adaptation framework for scientific image quality assessment. The first stage performs domain-adaptive pretraining on scientific document images and the second stage conducts task-specific fine-tuning with joint scoring and understanding supervision. For scoring-oriented supervision, we combine instruction tuning with a Huber loss derived from rating-word logits, while understanding-oriented supervision is formulated as multiple-choice visual question answering. Experiments show that using a 40% stratified subset of the domain-adaptive data gives the best performance among the evaluated pretraining fractions, suggesting that pretraining-data relevance may be as important as pretraining-data scale. The final model achieves an SIQA-S score of 92.21, an SIQA-U score of 47.38 and a combined score of 69.80. This work presents our solution to the ICME 2026 Scientific Image Quality Assessment Challenge, which ranked 2nd in the scoring track.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05691
PDF
-
ChronoVision: Temporal Reasoning via Latent State Reconstruction
2026-08-06 05:58:22Yifan Shen, Jian Xu, Boyi Li, Yuner Zhang, Tianjiao Yu, Bingxuan Li, Houze Yang, Rushi Wang, Xu CaoAbstract
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.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05631
PDF
-
Disentangling 3D Modeling from Spatial Reasoning
2026-08-05 14:32:48Haoze Sun, Jiequan Cui, Qingshan Xu, Richang HongAbstract
In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly acquiring implicit 3D perception and reasoning through large-scale training. Our key observation is that modern perception models excel at estimating continuous 3D geometry, whereas large language models (LLMs) are particularly effective at compositional and symbolic reasoning. Motivated by these complementary strengths, we propose the Disentangled Spatial Reasoner (DiSR), a simple yet effective framework that reconstructs the physical world into structured 3D evidence using off-the-shelf expert perception models and fine-tunes an LLM with LoRA to perform reasoning solely over this explicit geometric evidence. Without large-scale 3D VQA training or complex tool-use policies, DiSR achieves competitive performance on popular spatial reasoning benchmarks. Beyond its strong performance, DiSR offers improved interpretability, modularity, and computational efficiency, demonstrating that explicit separation of perception and reasoning is a scalable and effective alternative paradigm to end-to-end modeling for spatial intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05242
PDF
-
Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models
2026-08-05 12:32:15Houze Xu, Jizhong Li, Ziyi YeAbstract
Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control. However, existing VLA models still face major challenges in long-horizon tasks: sparse expert demonstrations constrain cross-task compositional generalization; the non-Markovian nature of long-horizon tasks makes it difficult for policies conditioned only on current observations to maintain temporal consistency; limited closed-loop error correction allows execution errors to accumulate; and end-to-end action fine-tuning may weaken the high-level semantic representations of vision-language model (VLM) backbones. To address these issues, we propose a hierarchical long-horizon VLA architecture with an explicit language-memory module. The central idea is to convert discrete temporal observations into a coherent textual memory sequence with temporal logic. The system is decoupled into a high-level VLM and a low-level VLA: the high-level VLM performs semantic reasoning through a visual question answering training paradigm, while the low-level VLA executes precise continuous control conditioned on subtask instructions and visual observations. The high-level VLM recursively updates both language memory and subtask instructions using the previous memory as a contextual anchor, enabling persistent temporal tracking and dynamic correction during long-horizon execution. We evaluate the proposed method in multiple simulation environments and conduct sim-to-real experiments on a real robotic platform. The results demonstrate that explicit language memory improves the success rate and robustness of VLA models on complex long-horizon tasks while providing an interpretable semantic account of the decision process.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04765
PDF
-
When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoning
2026-08-05 11:46:15Yongxin Wang, Ruizhe Zhou, Yueling Tang, Yingying Zhu, Xuemin Zhao, Xiaojun Chang, Xiaodan LiangAbstract
Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet benchmarks usually place questions in text, leaving it unclear whether models use the same instruction equally well across channels. We introduce Visualized Task Semantics (VTS), a controlled intervention that moves the question into the image while keeping the source problem and answer fixed. Across six MLLMs and four benchmarks, accuracy drops in all 24 model-task pairs, by 17.8 points on average. Models often transcribe the visual question correctly yet fail to use it, exposing a semantic channel gap beyond OCR. To reduce this gap, we present prompt-region grounding, whose core design aligns the question region with typed semantics and recovers its clean representation from a masked view. At matched training cost, our method raises four-benchmark VTS accuracy from 58.0 to 66.3 while preserving accuracy on the original interface, and requires no OCR or region metadata at inference. Reading task-bearing text and grounding it as an instruction for reasoning are distinct capabilities.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04726
PDF
-
CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding
2026-08-05 06:49:49Zhenyu Yi, Qiang Hu, Zhenhao Li, Jiaxuan Zhao, Yusong Sun, Lichi ZhangAbstract
Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that burden the LLM backbone, many of which capture overlapping visual evidence across adjacent slices. To understand how effectively a growing visual token budget improves performance, we perform scaling analyses on two 3D medical VQA benchmarks and find diminishing returns: cost keeps rising while accuracy saturates, and improving in-plane resolution is more effective than adding slices at comparable budgets. The budget should therefore be allocated more selectively rather than simply enlarged, yet most token compression methods are designed for 2D images or videos, where redundancy arises from spatial layout or temporal motion rather than from near-duplicate content along the depth axis. We present CARVE, a training-free framework that compresses visual tokens prior to LLM inference and casts token reduction as budget-constrained 2.5D allocation. CARVE partitions the depth axis into coherent windows and allocates tokens non-uniformly according to normalized cross-slice evidence. Under a shared budget, CARVE builds spatial anchors on representative slices and retrieves locally varying evidence from the full volume, then merges remaining eligible tokens into nearby anchors within each window. Removing roughly 80% of the visual tokens on Hulu-Med-7B, CARVE leads all compression baselines on every AMOS-MM report-generation metric, with 6.2 points higher retention of full-token quality than the strongest baseline, and preserves 98.1% of full-token performance across three VQA benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04515
PDF
-
Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning
2026-08-05 05:03:35Pengcheng Pan, Xinfang ZhangAbstract
High-resolution pixels and crop or zoom tools give multimodal large language models the ability to inspect an image, but they do not provide a reliable task-conditioned policy for deciding where to inspect. Q-CueGraph makes this decision explicit. It maps a question and an image representation to budgeted, coordinate-level observations for a frozen reader. Text-rich images use a reusable OCR/layout graph; natural-image search instantiates query-conditioned visual nodes behind the same selection, composition, and budgeting interface. Optional utility refinement learns which candidate crops the frozen reader can use from training-answer correctness, without region-box supervision. With a frozen Qwen2.5-VL-7B reader, Q-CueGraph reaches 0.833 accuracy on V*Bench versus 0.696 for full-image inference from a 19% image-area budget, and reaches 92% of full-image ANLS on InfographicVQA from about half the image area. Across six benchmarks, explicit observation is most valuable when evidence is localizable, the question discriminates its location, and resolution limits full-image reading.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04452
PDF
-
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
2026-08-04 17:45:16Zhen Fang, Yu Zeng, Wenxuan Huang, Yiming Zhao, Shiting Huang, Tianfei Ren, Qi Lu, Qingnan Ren, Qisheng Su, Lionel Z. Wang, Qingyu Yin, Shuang Chen, Zehui Chen, Lin Chen, Zhenfei Yin, Yao Hu, Shaohui Lin, Wanli Ouyang, Shaosheng Cao, Feng ZhaoAbstract
We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration. Preliminary evaluations reveal two critical bottlenecks in current models: (1) modality bias, where agents bypass visual tools in favor of textual search, and (2) parametric knowledge leakage, where models rely on internal memory rather than genuine tool-augmented execution. To address these challenges, we propose Video-DR, featuring a decoupled perception-exploration pipeline with stage-wise tool unlocking that compels exhaustive cross-frame visual grounding prior to web retrieval. Our framework adopts a two-stage training recipe: supervised fine-tuning followed by Group Relative Policy Optimization (GRPO), enabling autonomous exploration that breaks the imitation-learning ceiling. Furthermore, we curate Video-DR-Bench, a human-AI collaborative benchmark comprising 200 complex, multi-hop VQA instances. Empirical results demonstrate that our Video-DeepResearch-35B-A3B establishes a new state-of-the-art of 64.0% average accuracy, surpassing proprietary Claude-4.5-Sonnet (59.0%) by 5.0 points and significantly outperforming GPT-5 (52.5%) and Gemini 2.5 Pro (57.5%). The 30B-A3B variant achieves 59.3%, competitive with Claude-4.5-Sonnet and demonstrating the effectiveness of our training paradigm even at compact scale. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03979
PDF
-
CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
2026-08-04 16:23:39Mercy Prasanna Ranjit, Anirban Porya, Sathvik Joel, Niharika Vadlamudi, Nikhilesh Chowdary Eathamukkala, Prasanth V V, Abhyuday Kumara Swamy, Pranay Narhari Umredkar, Pradeep Narayan, Vivek Rajagopal, Tanuja GanuAbstract
A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend. Today's Vision-Language Models (VLMs) treat these as separate problems, if they address them at all, leaving a gap between what radiologists need and what generative models provide. We introduce CARE-X, a chest X-ray VLM that narrows this gap by unifying auxiliary discriminative supervision with reward-aligned generation. CARE-X augments its generative backbone with focal-loss classification and composite-loss grounding heads, co-trained alongside the language-modeling objective. This auxiliary supervision produces discriminative diagnostic predictions with tunable decision thresholds and precise spatial localization while also improving report quality, providing evidence that structured prediction and generation reinforce one another. Building on this foundation, Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) leverages task-specific reward signals for report generation, visual question answering (VQA), and spatial grounding, directly optimizing the clinical quality metrics that matter in practice. The result is state-of-the-art performance on the majority of metrics across four report-generation benchmarks, 94.0% VQA accuracy on ReXVQA (+6.0 pp over the next-best baseline), and generative spatial decoding that reaches near parity with dedicated detection heads. Separately, to address measurement-dependent diagnoses, we couple Qwen3-VL-4B-Instruct with native tool-calling capabilities for invoking deterministic measurement tools, while retaining full visual access to the image. This hybrid inference yields +43.6 pp average F1 over perception-only baselines across five measurement-dependent conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03890
PDF
-
Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding
2026-08-04 15:36:17Jiapeng Li, Yong Li, Junjie Zhou, Fan Zhang, Yu LiuAbstract
Geospatial and urban applications increasingly require models to compare heterogeneous evidence across street-view imagery, remote-sensing observations, text descriptions, region proposals, and temporal change cues. However, existing multimodal embedding models and benchmarks are still largely designed and evaluated around general-purpose image-text matching, leaving unclear whether unified embedding space can support heterogeneous geospatial tasks involving spatial relationships, fine-grained semantics, and temporal changes. To address this gap, we make three key contributions. First, we introduce GeoMEB, a large-scale multimodal embedding benchmark that standardizes 45 urban evaluation tasks across retrieval, visual question answering, change detection, classification, and visual grounding, together with training collections comprising 1.32M examples and 286K evaluation queries. Second, we present Geo-Embed, a unified embedding model that adapts a shared vision-language backbone to instruction-conditioned query-target matching over heterogeneous geospatial inputs, including single images, multiple images, text, regions, and masks. On GeoMEB, Geo-Embed achieves the strongest overall performance among representative multimodal embedders, with a 15.3% relative improvement over the strongest baseline. These results motivate future geospatial embedders that organize training and evaluation around explicit query-target relations, including semantic, cross-view, region-level, and temporal correspondence.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03826
PDF
-
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
2026-08-04 14:28:42Chunyang Jiang, Pingping Zhang, Yuzhi Zhao, Wenao Ma, Zhijian Hou, Mengyang Wu, Yiyang Cai, Senkang Hu, Sitong Cheng, Chi-Min Chan, Wei Xue, Yike GuoAbstract
Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate. Self-augmentation offers a promising alternative by enabling models to expand their own training data without external supervision. However, existing MLLM self-augmentation methods are largely text-centric, while image augmentation remains underexplored and typically relies on generic or handcrafted transformations that are weakly aligned with the model's actual incapability. We propose Failure-informed Image Self-Augmentation (\textbf{FISA}), a framework for MLLM self-improvement that constructs augmented images from the model's own failure cases. Our method generates visually challenging yet answer-preserving image complications, verifies their utility through self-examination, and applies dual fidelity filtering to avoid semantic distortion. Experiments on visual question answering benchmarks show that the proposed method consistently improves performance across both in-distribution and out-of-distribution settings. Further experiments validate the compatibility of FISA with existing textual self-augmentation approaches, the superior data efficiency of the synthesized samples over generic image augmentation baselines, and the practical effectiveness of the proposed filtering strategy.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03733
PDF
-
From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology
2026-08-04 11:51:16Basit Alawode, Moshira Ali Abdalla, Dwarikanath Mahapatra, Muhammad Muzammal Naseer, Sajid JavedAbstract
Vision Transformers (ViTs) and their hierarchical variants have achieved strong performance in Computational Pathology (CPath). However, most are pre-trained on single-resolution Whole Slide Images (WSIs), limiting their generalization across arbitrary resolutions. Gigapixel WSIs inherently contain diagnostic patterns at multiple scales, including cellular morphologies, tissue architectures, and global context, mirroring how expert pathologists examine WSIs. We introduce Multi-Resolution Pyramid Transformer (MRPT), a model that hierarchically aggregates multi-resolution information from cellular to tissue and WSI levels. MRPT employs a biologically meaningful Consecutive Cross-Resolution Attention (CCRA) mechanism to capture scale-independent interactions and enforces multi-resolution semantic consistency by aligning embeddings across resolutions, yielding robust and generalizable WSI representations. Pre-trained in a multi-resolution self-supervised manner on 624M patches, 2.4M regions, and 36K WSIs, MRPT learns rich coarse-to-fine histopathology features. Extensive experiments on 34 diverse datasets show that MRPT surpasses recent foundation models and Multimodal Large Language Models (MLLMs) in cancer subtype classification, tissue phenotyping, and Visual Question Answering (VQA) for WSI understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03508
PDF
-
DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning
2026-08-04 08:04:59Le Xiang, Zhicheng Guan, Hong Chen, Xiaocong Lin, Zhenghua Lei, Teng Hu, Bolei He, Long ZengAbstract
Long Document Visual Question Answering (LongDocVQA) requires Multimodal Large Language Models (MLLMs) to locate, integrate, and reason over heterogeneous document elements distributed across multiple pages. Existing approaches, including end-to-end MLLMs, retrieval-augmented generation (RAG) pipelines, and document agents, often lack explicit mechanisms to represent and verify how grounded evidence is progressively composed during reasoning, limiting both answer accuracy and traceability. In this paper, we cast LongDocVQA as an explicit evidence graph reasoning problem rather than implicit answer prediction. To this end, we propose DocTrace, a hierarchical framework that progressively performs evidence localization, structured document parsing, and evidence graph reasoning to enable explicit evidence provenance. To effectively learn these capabilities, we develop a two-stage training framework: joint Supervised Fine-Tuning (SFT) first initializes evidence localization and graph reasoning abilities, followed by task-specific Group Relative Policy Optimization (GRPO) with dedicated rewards to further optimize these capabilities. Extensive experiments on MMLongBench-Doc, LongDocURL, and SlideVQA demonstrate that DocTrace consistently outperforms both existing open-source baselines and proprietary MLLMs. Compared with the Qwen3-VL-8B-Instruct backbone, DocTrace achieves absolute improvements of 14.4, 11.3, and 11.7 points on the three benchmarks, respectively. Beyond competitive performance, DocTrace constructs traceable evidence graphs with explicit node-level provenance, enabling transparent and verifiable reasoning for long document understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03292
PDF
-
Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds
2026-08-04 05:03:17Ning Zhu, An Chen, Mengfei Zhao, Juntao Xu, Jingze Liang, Boyuan Gu, Liang-Jian DengAbstract
Text-to-image diffusion models can generate individual concepts well, but they often omit or merge concepts incorrectly with multiple concepts. We trace these failures to an early coordination bottleneck: before denoising begins, prompt-conditioned attention may allocate different concepts to strongly overlapping spatial support, which can keep their attention coupled as denoising proceeds. This observation motivates treating compositional generation as a boundary-condition problem rather than repeatedly controlling the evolving trajectory. To this end, we propose Rectify-then-Diffuse (RTD), a training-free framework that rectifies the initial allocation once before standard denoising. Firstly, we propose Soft-Overlap Disentanglement (SOD), which converts normalized overlap between pilot concept maps into a differentiable and layout-agnostic separation objective. Secondly, we introduce Isotropic Gradient Rectification (IGR), which normalizes the SOD gradient and applies a bounded latent displacement with a consistent scale across prompts and initializations. Extensive experiments show that RTD achieves state-of-the-art compositional fidelity and robust gains. On the AE-Bench object pair subset, RTD improves BLIP-VQA by 45.8% and ImageReward by 19.6% over CO3 while running 2.3$\times$ faster. Code will be released at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.03135
PDF
-
Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding
2026-08-04 00:32:09Lucy Lin, Ayush Jain, Yifan Liu, Katerina FragkiadakiAbstract
Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to frame-centric tokenization and limited context windows. 3D geometry provides a natural compression mechanism for visual streams: depth and camera pose enable observations from multiple views and time steps to be fused into a persistent, world-aligned representation. While recent 3D LMMs leverage geometry-aware representations to improve spatial reasoning, they continue to lag behind specialist 3D perception systems on grounding and segmentation tasks. We argue that a key limitation is geometry-aware decoding: existing methods communicate 3D predictions through language tokens, proposal selection, or lightweight grounding queries, creating a bottleneck between language reasoning and dense geometric prediction. Building on these insights, we introduce Qwen-3D, a geometry-aware LMM that compresses visual information within the Qwen backbone using multi-view geometric cues, enabling efficient long-horizon visual reasoning over static scenes. Qwen-3D augments visual tokens with 3D Rotary Positional Embeddings, allowing attention to operate directly in 3D scene space rather than across independent image frames and thereby facilitating scalable cross-view and temporal reasoning. To bridge language and geometry, Qwen-3D incorporates a query-based segmentation decoder that grounds language directly in the underlying 3D scene representation, unifying referential grounding, instance segmentation, and visual question answering across both images and videos. Across a diverse set of benchmarks, Qwen-3D surpasses existing 3D LMMs and outperforms several large proprietary 2D models. Notably, Qwen-3D achieves these improvements while maintaining strong performance on standard 2D vision-language benchmarks by jointly training on 2D and 3D data.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02980
PDF
-
In-Context Collapse in Vision-Language Models and How to Mitigate it?
2026-08-03 19:44:45Mohammad RostamiAbstract
Many-shot in-context learning (ICL) lets vision-language models (VLMs) adapt from image--label demonstrations without weight updates, and is widely assumed to improve as more demonstrations are supplied. We show the opposite: as demonstrations accumulate, a subset of VLMs undergo an \emph{in-context collapse}, a sharp, sometimes catastrophic accuracy drop spanning synthetic classification, natural-image classification, and VQA benchmarks, in some models falling below chance while outputs remain well-formed. Across an open VLM panel ($0.5$B--$11$B) and a frontier model (Claude Sonnet 4.5), the collapse is graded. Two capabilities turn out to be dissociable: robustness to accumulating demonstrations and the ability to learn a novel rule in context, their combinations yield three reproducible regimes. A parameter-matched lesion-and-rescue causally localizes the collapse to the vision-language integration pathway: an adapter on the connector and early/mid layers restores genuine learning (remap accuracy $0.39!\rightarrow!0.91$ at 16 shots), while an equal-capacity adapter on the late readout does not. We propose \textsc{CircA}, whose core is a one-time integration vaccine: trained once on one synthetic task, it transfers collapse-resistance to unseen task families (chance$\rightarrow$$0.71$/$0.60$ on CIFAR/Fashion). The layers best for in-context integration are not the layers best for weight-based consolidation, the late readout achieves higher accuracy and less forgetting at fewer parameters. The collapse is an integration failure at the vision--language interface, correctable by a lightweight, transferable intervention.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02830
PDF
-
A General-Purpose VLM Can Teach an Astronomy Foundation Model to Better Recognize Galaxy Morphology
2026-08-03 14:26:25Dichang Zhang, Jiaqi Deng, Yixuan Shao, Yuanpeng Liu, Jiali Cui, Zhiqiang Lao, Heather Yu, Liang Peng, Simon Birrer, Dimitris SamarasAbstract
Existing astronomy foundation models provide strong galaxy representations, but adapting them to new survey conditions and survey-specific morphology recognition tasks still requires substantial human supervision. We show that VLM-based VQA systems contain meaningful visual-semantic priors that can serve as weak supervision for downstream morphology classifiers and improve morphology classification under limited human-label budgets. We first introduce a survey-oriented VQA benchmark spanning two representative imaging regimes and evaluate state-of-the-art VLMs on galaxy morphology questions. The results show that these models capture useful morphology signals and informative uncertainty, but are not sufficiently reliable to replace human annotators. Motivated by this finding, we use a general-purpose VLM as a morphology teacher for Zoobot, an astronomy foundation model pretrained on large-scale Galaxy Zoo annotations. Across two survey domains and multiple annotation budgets, the VLM teacher consistently improves Zoobot's downstream morphology classification. These results demonstrate that a general-purpose VLM provides knowledge complementary to an astronomy foundation model and can teach it to better recognize galaxy morphology under limited human supervision. The resulting pipeline is designed for label-efficient adaptation to forthcoming large-scale surveys, including the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) and the Nancy Grace Roman Space Telescope. The benchmark and code are publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02300
PDF
-
HAFI-VLM: A Frequency Perspective for Diagnosing and Enhancing Visual Perception in Vision-Language Models
2026-08-03 12:15:33Jin Cui, Chuanchang Su, Jiayi Lu, Xinyue Long, Boran Zhao, Pengju RenAbstract
Vision-language models (VLMs) remain unreliable when predictions require fine-grained visual evidence. We identify a previously overlooked cause: spectral response rigidity. Despite substantial frequency variation across images and tasks, pretrained vision encoders exhibit persistent, encoder-specific layerwise spectral profiles that change only marginally under downstream fine-tuning. Since pretrained vision encoders only receive images, they cannot adapt spectral extraction to the evidence required by the current query. We therefore propose HAFI-VLM, which introduces a task-conditioned frequency pathway while preserving the pretrained semantic representation. Hierarchical Adaptive Frequency Injection (HAFI) retrieves complementary low-, mid-, and high-frequency evidence at multiple encoder depths using text-modulated, spatially aligned cross-attention. A Visual Enrichment Layer Adapter further recalibrates shallow LLM attention to effectively utilize the enriched visual tokens. Experiments on LLaVA-1.5 and Qwen2.5-VL demonstrate consistent improvements in general VQA, text-rich understanding, and hallucination robustness, outperforming representation-level enhancement methods and most resolution- or cropping-based approaches without additional high-resolution encoding. Mechanistic analyses show that HAFI restores task-dependent spectral allocation while retaining semantic attention, establishing frequency enrichment as a distinct and effective route for improving VLM perception.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02124
PDF
