Image_Caption
-
Playing with Kruskal: algorithms for flat and hierarchical watershed cuts
2026-10-07 13:03:14Jean Cousty (LIGM), Laurent Najman (KUSTAR, LIGM), Benjamin Perret (LIGM), Deise Santana Maia (CRIStAL)Abstract
In the framework of edge-weighted graphs, watersheds have proven to be linked to well-known optimization problems, as Minimum Spanning Tree, which allowed the design of efficient algorithms for computing (hierarchical) watershed segmentations. In the present article, after reviewing the literature related to watershed segmentation, we present a detailed end-to-end pipeline of algorithms to compute (hierarchical) watershed segmentations, starting from the computation of graph-based image representations, up to the computation of connected components of the final (hierarchical) segmentation. We consider the several variations of watersheds, including their supervised and unsupervised versions, and the various ways of computing seeds, to name a few. For the first time, we bring together all these watershed notions and algorithms in a compact and understandable way. We aim at providing a reference for those interested in employing and reimplementing the watershed segmentation framework for their task at hand.
Abstract (translated)
URL
https://arxiv.org/abs/2610.10012
PDF
-
LiG-DETR: Local-in-Global Reassembly in Latent Space for Aerial Object Detection
2026-10-07 06:07:37Yupeng Zhang, Fangzhuo Gao, Juntao Cheng, Ziyi Zhao, Liang Wan, Ruize HanAbstract
Aerial object detection faces substantial scale and density variations. Small objects are easily degraded by downsampling and feature compression, while medium and large objects require sufficient global context. Existing methods mainly follow two paradigms: image slicing provides clearer local evidence but relies on independent crop-level prediction and post-processing, whereas feature- and query-level optimization preserves unified inference but operates on already compressed full-image representations, limiting recovery of fine-grained information. This raises a key question: can aerial detection directly acquire high-fidelity local evidence before feature degradation and integrate it into a unified end-to-end framework? To this end, we propose LiG-DETR, an Efficient Global-Local Reassembly framework that reformulates image slicing as high-fidelity local feature acquisition. A shared encoder extracts global and locally magnified features, which are projected into the detector feature space. The projected local features are reassembled according to their original spatial locations to form a globally aligned local feature level, and a single DETR decoder jointly decodes global and local features. To reduce redundant computation, Context-Preserved Selective Reassembly focuses high-resolution encoding on informative regions while preserving a dense feature layout, and Density-Aware Adaptive Query Allocation adapts the decoder query budget using encoder proposal scores. Experiments show substantial gains on small and medium objects while retaining strong large-object performance, with favorable accuracy--efficiency trade-offs and improved cross-domain generalization. The code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09511
PDF
-
RT-DETR-World: Transferring Rich LLM Semantics to Real-Time Open-Vocabulary Detection
2026-10-07 06:01:35Yupeng Zhang, Ziyi Zhao, Juntao Cheng, Sheng Wang, Ningnan Guo, Ruize Han, Liang WanAbstract
Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with real-time efficiency remains challenging. Beyond vocabulary scaling, zero-shot generalization may benefit from reusable visual--semantic cues learned from seen data, including attributes, actions, states, and contextual relations. Existing real-time OVD methods primarily emphasize vocabulary coverage and efficient region/query--text matching; under strict efficiency constraints, compact detectors may struggle to absorb rich instance semantics and scene context. We propose RT-DETR-World, a compact DETR-style detector that transfers the rich semantics conveyed by descriptions during training while retaining lightweight query--text matching at inference. We construct GroundingCapv2 with three levels of supervision: category names for standard OVD, object descriptions conveying instance-level semantics, and image descriptions conveying object relations and scene context. These descriptions serve only as training-time semantic supervision. To help the compact detector absorb these semantics, we propose Dual-Path Description Alignment (DDA), combining a deployment-consistent MiniLM pathway with a training-only LLM teacher. MiniLM provides query--category supervision and object-description alignment, while offline teacher features supervise matched queries and global visual representations at the object and image levels, respectively. All teacher features are precomputed, and the teacher-side modules are removed after training. We further propose Relation-Aware Negative Relaxation (RNR), which uses teacher-derived semantic similarities to relax related negatives while preserving exact positives. Experiments demonstrate competitive zero-shot accuracy and a favorable accuracy--efficiency trade-off. The code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09502
PDF
-
Multimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG Decoding
2026-10-07 03:13:03Parastoo Azizeddin, Omid Sharafi, Maryam M. ShanechiAbstract
Learning EEG representations that generalize across cognitive tasks, subjects, and recording conditions remains a key challenge in electroencephalography (EEG) decoding. Recent advances in foundation models have improved EEG decoding performance, yet a fundamental open question remains: how to effectively interface neural signals with these models to enable multi-task learning across datasets. To investigate this question, we introduce BraVista, a visual-language framework that encodes multichannel EEG signals as structured images and enables multi-task learning through instruction-conditioned vision-language models (VLMs). Our approach relies on continued post-training of a general-domain VLM, leveraging its visual and linguistic priors to adapt to neural signals without a separate large-scale EEG-specific pretraining stage. We evaluate BraVista on four datasets spanning sleep staging, emotion recognition, cognitive workload classification, and abnormal EEG detection, showing strong performance across these tasks. Further analyses show that the choice of EEG-to-image representation is critical to performance. Moreover, through controlled perturbations of the EEG signal, we observe a gradual performance degradation under increasing noise, suggesting that the model relies on EEG-relevant information rather than superficial visual patterns. Together, these findings establish structured visual representations as an effective and scalable interface between neural signals and general-domain foundation models for unified multi-task EEG decoding.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09355
PDF
-
Adaptive Visual Token Reduction for Accelerated Image Understanding
2026-10-07 00:37:50Seyoung Jeong, Jong Pil Yun, Sang Jun LeeAbstract
Large Vision-Language Models achieve strong VQA performance, but processing high-resolution, information-rich images requires substantial computation, motivating visual token reduction. However, existing methods often prune individual tokens or rely on fixed-size cropping, limiting their ability to preserve spatially structured information such as horizontally or vertically elongated text. To address this limitation, we propose ReFIT, an instruction-guided visual token reduction framework for efficient LVLM inference. ReFIT consists of Relevance-Guided Window Reshaping (RWR) and Instruction-Guided Token Refinement (ITR), where RWR captures instruction-relevant regions by adapting to their spatial characteristics, while ITR further removes unnecessary visual tokens. Experiments on four VQA benchmarks demonstrate that ReFIT improves answer accuracy while reducing computational cost, and qualitative results demonstrate its effectiveness in localizing relevant regions and removing unnecessary visual information.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09252
PDF
-
RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models
2026-10-06 15:28:36Dongchen Si, Di Wang, Mingzhen Xu, Jing Zhang, Bo Du, Liangpei ZhangAbstract
Remote sensing scene classification is a fundamental task in Earth observation and geospatial analysis. Existing approaches mainly follow three paradigms: task-specific visual classification, vision-language similarity matching, and autoregressive multimodal generation. However, visual classifiers rely on predefined label spaces, CLIP-based methods perform recognition through static image-text alignment, and multimodal large language models (MLLMs) introduce unnecessary token-level generation for classification tasks with explicit candidate categories. To address these limitations, we propose RSJEV, a one-pass multimodal decision framework for remote sensing scene classification. Unlike conventional MLLMs that formulate classification as autoregressive text generation, RSJEV reformulates scene classification as a candidate-conditioned multimodal discriminative decision process, where visual representations, task instructions, and candidate category semantics are jointly modeled. Specifically, we introduce a OnePass Decider that extracts multimodal decision states and directly estimates category probabilities within the candidate category space, eliminating autoregressive decoding while preserving vision-language interactions. Extensive experiments on three widely used remote sensing scene classification benchmarks, including UC Merced, AID, and NWPU-RESISC45, demonstrate that RSJEV achieves superior classification performance compared with representative CNN-, Transformer-, Mamba-, CLIP-, and MLLM-based methods. Moreover, RSJEV significantly reduces inference costs and achieves a better accuracy-efficiency trade-off with only a compact 0.8B-parameter model. These results demonstrate the effectiveness of state-conditioned multimodal decision making for efficient remote sensing image understanding. The code will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08539
PDF
-
RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG
2026-10-06 01:25:45Yuhui Jin, Yonghao Song, Bingchuan LiuAbstract
Most existing MEG and EEG (M/EEG) visual decoding methods align brain signals with a single global embedding extracted from a pretrained visual encoder, leaving open whether intermediate patch representations, which preserve richer and more granular rich visual information, can improve representation learning. To address this question, we introduce the Residual Patch Adapter (RPA), a lightweight, modular adapter that leverages all patch tokens from an intermediate layer of a ViT visual encoder for alignment. Through extensive ablation analyses, we first show that pooling or masking patch tokens degrades the learned representation, demonstrating that retaining the full set of patch tokens is important for EEG alignment, while the CLS token provides little unique information. We then use a series of six quantitative feature analyses to show that both higher-level semantics and lower-level visual features, including color and texture, are essential for this EEG-to-image alignment. Under current protocols, our system achieves Top-1 accuracies of 95.4\% within-subject and 35.5\% cross-subject on THINGS-EEG2, and 65.2\% and 6.7\%, respectively, on THINGS-MEG, achieving state-of-the-art (SOTA) performance across both datasets. Evaluations with alternative brain encoders, including pretrained EEG foundation models, demonstrate that the approach extends beyond the projection-based EEG encoder. Furthermore, we provide a plug-and-play interface that allows RPA to be replaced by convolution, attention, or ConvNeXt alternatives. Together, these findings provide significant insight into M/EEG-to-image representation learning by establishing design principles for leveraging the latent space of visual encoders, and open new directions for brain--image alignment and non-invasive brain--computer interface (BCI).
Abstract (translated)
URL
https://arxiv.org/abs/2609.31698
PDF
-
Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks
2026-10-04 13:23:31Boyuan Chen, Yehia Dawoud, Hailemariam Mersha, Minghao Shao, Siddharth Garg, Ramesh Karri, Muhammad ShafiqueAbstract
Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four published attack families on a 313-prompt StrongREJECT slice, using five multimodal models and an additional appendix evaluation of InternVL3.5-8B. The harmful instruction is held constant across conditions; the baseline matrix uses one draw per prompt, and paired ablations use three draws with an automated rubric judge. A bare harmful query, with or without a benign unrelated image, produces little attack success on most victims, while attack images substantially increase it. First, per-tile entropy and JPEG size do not reliably distinguish attack tiles from size-matched benign distractors, limiting density-only screening. Second, earlier tile-count ladders were confounded by payload visibility. A corrected region-count test found no detectable effect, so the role of tile-count structure remains unresolved. Third, on Qwen3-VL-8B, the E4 manipulation that removes query-specific relatedness lowers ASR by about 0.12. This supports a bounded attribution to the relatedness manipulation, although image-text congruence remains unmeasured. A within-category control reproduces the direction on overlapping stimuli. Five tests survive the global statistical correction, but only E4 supports attribution to one measured descriptor; the within-category result is a robustness check, not a separate attribution. These conclusions remain conditional on the rubric judge.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07009
PDF
-
LAS-CLIP: A Lightweight Adapter Steering Approach for CLIP's Visual Encoder
2026-10-02 14:27:35Anh-Khoa Dinh-Duc, Duc-Tai Dinh, Tam V. Nguyen, Minh-Triet TranAbstract
CLIP's visual encoder produces only global image representations, limiting its use in region-level tasks. Existing adaptations rely on visual prompting, input masking, or encoder fine-tuning, each compromising pre-trained representations. We propose LAS-CLIP, a Lightweight Adapter Steering approach that keeps every CLIP parameter frozen. A compact MaskAdapter generates per-head, per-layer attention biases from an input mask and injects them into the frozen self-attention layers, steering attention toward the target region. Crucially, because the backbone remains strictly untouched, LAS-CLIP seamlessly reverts to vanilla CLIP when no mask is provided, preserving its foundational zero-shot capabilities. With approximately 116K to 145K trainable parameters and 100K training samples on two T4 GPUs, LAS-CLIP achieves competitive or superior results compared to Alpha-CLIP on ImageNet-S zero-shot classification and RefCOCO referring expression comprehension, despite the latter fine-tuning its entire encoder on millions of samples. Qualitative analysis further confirms stronger representational fidelity under incorrect masks and in downstream generation. Our project page is link to this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.03370
PDF
-
Recursive Self-Improvement in Unified Multimodal Models
2026-10-02 08:34:21Huijuan Wang, Chufan Shi, Cheng Yang, Yaokang Wu, Taylor Berg-Kirkpatrick, Xuezhe MaAbstract
Unified multimodal models (UMMs) understand and generate both text and images, which lets a model produce its own training data. Existing self-improvement in UMMs keeps supervision on the visual side, where image understanding judges image generation. We propose recursive cross-capability self-improvement (RSI), a training loop in which the text and visual abilities of a UMM supply training data for one another. In each round, the model generates images and reads them to find where it falls short. It then writes programs aimed at these shortcomings, and execution verifies every result against its specification. Verified renders train image generation, while labeled renders and the model's own correct programs train visual understanding and program writing. Program execution thus acts as a source of truth outside the model, so errors do not accumulate across rounds. We study RSI on charts and build BasicChartBench to evaluate open models early in training. On requests worded differently from training, four rounds of RSI raise the score from 45.7% to 60.2%, while continued training stays at 46.3%. Verified construction carries most of the gain, and targeting the model's failures adds 3.5%. Along the way, the share of verified programs rises from 48.9% to 95.2%, and the reader's accuracy on edited renders rises from 55.6% to 87.4%.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03002
PDF
-
GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation
2026-10-01 23:49:56Zhenghao Zhao, Chi Zhang, Qingshuang Chen, Yelin KimAbstract
Vision foundation models such as DINOv2, SigLIP2, and MASt3R develop complementary capabilities from different pretraining objectives, yet their knowledge remains distributed across separate, specialized models. Multi-teacher knowledge distillation offers a path toward consolidating these capabilities into a single agglomerative backbone, but existing approaches assume a fixed set of teachers, and incorporating a new teacher requires repeating expensive joint distillation over the entire teacher set. We introduce GRAFT, a continual multi-teacher distillation framework that enables a unified backbone to progressively acquire capabilities from an open-ended sequence of foundation models. When a new teacher arrives, GRAFT treats the previously distilled model as a teacher for preserving learned capabilities, while the current student jointly learns from both the previous model and the incoming teacher. Furthermore, to reconcile the incompatible representation geometries of heterogeneous teachers, we introduce Teacher Specific Readout Tokens, which grant each teacher an independent read-out of the shared encoder, together with Geometry Agnostic Relational Loss that aligns a vision-language teacher by matching image-text similarity structures rather than raw feature values. We provide GRAFT model, which is a single, continually extensible backbone that unifies five domains, including image understanding, 2D dense prediction, 3D human pose estimation, 3D vision, and vision-language, delivering strong performance across all of them while acquiring each new capability at the cost of a single distillation rather than a full re-distillation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.02597
PDF
-
SALD: Self-Referenced Advantage Learning for Diffusion Models
2026-10-01 11:37:37Aryan Das, Surjo Dey, Koushik Biswas, Swalpa Kumar Roy, Moloud Abdar, Arnab Bhattacharya, Vinay Kumar VermaAbstract
Recent work on language-model adaptation has shown that single models can obtain informative training signals by evaluating their behavior in demonstrationor feedback-augmented contexts, with the help of a teacher network, which is driven by the student's learned parameters. Inspired by this internal-reference principle, we investigate how diffusion models can identify self-referenced training signals without external demonstrations or teacher networks. We introduce SALD, a self-referenced training framework that evaluates each image-caption pair at two noise levels using the same model. The easier, lower-noise path is evaluated without gradient tracking to provide a reference, while the harder, higher-noise path provides the training gradient. Rather than directly distilling the easy-path prediction, SALD uses the difference between two path errors to adapt the hardpath objective. The proposed Advantage-Guided Diffusion (AGD) converts this relative error into a differentiable sample-level weight. Temporal Advantage Memory (TAM) accumulates relative difficulty across training and adapts the future gap between the two noise levels. Spectral Advantage Decomposition (SAD) further compares the residual power spectra of the two paths and constructs a differentiable, frequency-derived latent-element weight. All components share a single set of model parameters, requiring neither an external teacher network nor additional trainable parameters during training or inference, and no modification to the inference procedure. Experiments across multiple architectures and datasets demonstrate consistent improvements in generation quality, while component-wise ablations quantify the contributions of the proposed components.
Abstract (translated)
URL
https://arxiv.org/abs/2610.01496
PDF
-
Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack
2026-10-01 03:03:08Haiming Zhao, Tai Wang, Kun Zhang, Xicheng Peng, Zhiyang LiAbstract
Science teachers frequently search for documentary excerpts not by describing what appears on screen, but by querying the abstract concepts they intend to teach. This use case exposes a limitation of existing language-based video moment retrieval methods, which typically assume that queries describe observable events, whereas instructional search requires retrieving concrete visual phenomena that instantiate an underlying scientific principle. We study this setting as concept-to-example video retrieval, an abstract-needle-in-a-haystack problem where compact curriculum concepts must be grounded in temporally sparse documentary evidence. To bridge this abstraction gap, we propose Concept-Driven Domain Adaptation (CDDA), a three-stage framework for adapting two-tower vision-language models to concept-level retrieval. CDDA treats concepts as intermediate semantic anchors: it first structures the textual embedding space with textbook and teacher-handbook example-concept pairs, then transfers this concept-aware geometry to documentary visuals under a frozen visual encoder, and finally jointly adapts both encoders with sparse visual concept supervision. From a geometric perspective, this staged alignment reduces text-concept and vision-concept angular gaps, thereby encouraging concept-level adaptation while preserving the pretrained model's concrete image description alignment. On a curated middle-school physics retrieval benchmark, CDDA achieves stronger pedagogically oriented concept retrieval than several competitive multimodal baselines, including Qwen3-VL-Embedding-2B, while maintaining concrete image-text matching after adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00973
PDF
-
ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models
2026-09-30 13:14:56Tobia Poppi, Silvia Cappelletti, Samuele Poppi, Marcella Cornia, Lorenzo Baraldi, Diego Garcia-Olano, Rita CucchiaraAbstract
Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment must suppress without unnecessarily changing benign representations. Because ethical and practical constraints prevent collecting real unsafe content at scale, existing datasets pair safe real samples with generated counterparts, but label every generated sample unsafe, even when one modality is individually safe. To address this, we introduce ShieldCLIP, the first framework to condition safety alignment on the observed safety state of each modality rather than the origin of a sample, preserving safe content while redirecting only what is unsafe. We also introduce ViSUv2, a 195k-quadruplet dataset with independent per-modality safety labels across 578 concepts and 28 categories. Using these labels, ShieldCLIP defines a four-way conditional objective beyond pair-level supervision: safe content is anchored, unsafe modalities are redirected to their safe counterparts, mixed pairs update only the unsafe branch, and coherence is enforced when both are unsafe. We evaluate ShieldCLIP on cross-modal retrieval, text-to-image generation with Stable Diffusion v1.4 and SDXL, and image-to-text generation with LLaVA. Across these settings, ShieldCLIP consistently reduces harmful outputs over prior safety-aligned encoders and strong mitigation baselines, while preserving the utility of the original embedding space. Extensive ablation studies further show that both modality-specific supervision and the selective alignment objective contribute to these gains. Source code, trained models, and ViSUv2 (under a controlled-access protocol) will be made publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39688
PDF
-
Rethinking Multi-Image Re-Representation in Multi-Image Understanding
2026-09-30 09:20:21Gengyuan Zhang, Xiao Han, Xinyu Xie, Tong Liu, Volker TrespAbstract
Multi-image understanding requires MLLMs not only to recognise the content of individual images, but also to organise visual evidence distributed across them. We study this problem through multi-image re-representation, viewing prompted Chain-of-Thought reasoning and agentic visual tool use as different ways of re-organising visual evidence during reasoning. We introduce Mosaic, a general-purpose multi-image visual harness that enables an MLLM to actively construct visual intermediates with ten composable image operations. We compare five re-representation settings on existing multi-image benchmarks and on MosaicBench, a new grounding-focused benchmark for fine-grained multi-image understanding. Our experiments show that the relative benefits of textual and visual re-representation are strongly task-dependent. Visual re-representation is particularly effective for tasks requiring precise visual evidence, including hypothesis testing, precision comparison, and orientation-sensitive reasoning, while tasks dominated by higher-level semantic content show smaller or less consistent gains. Building on this finding, we train MosaicAgent-8B to use Mosaic with reinforcement learning using only accuracy and format rewards. Without demonstration trajectories or rewards for specific tool-use, the agent learns to compose visual operations over multiple steps and exhibits diverse problem-solving patterns unpromptedly. Code and data will be released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39363
PDF
-
Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal Models
2026-09-29 20:14:33Shuyang Jiang, Fucheng Deng, Yuchuan Luo, Zhenyu WuAbstract
Unified multimodal models (UMMs) train image understanding and autoregressive image generation on shared parameters, and the two objectives are known to interfere. Existing diagnoses and remedies operate at the resolution of layers or experts, measuring conflict per layer and resolving it by separating parameters. We argue that this resolution hides an orthogonal axis. Generation in a UMM is next-token prediction over a raster sequence of visual tokens whose roles vary systematically with position, so how strongly a generation gradient interferes with understanding should depend on where in the sequence it originates. We introduce a position-resolved interference map that attributes understanding-generation gradient conflict to visual-token positions within every layer, computed from a single backward pass at $1.2\times$ the cost of a standard backward pass. On Show-o and Janus-Pro, position explains a large share of conflict variance after controlling for depth (partial $\eta^2=0.31$ vs. $0.35$ for layer on Show-o; $0.15$ vs. $0.30$ on Janus-Pro): the first quarter of the sequence has a mean gradient cosine of $-0.18$ against understanding, the last quarter $-0.02$. The dependence survives per-position gradient-norm normalization, retaining $80%$ of its effect size, and conflict strength tracks semantic content (Spearman $\rho=0.64$). Building on the map, we propose position-aware modulation (PAM), which removes the anti-aligned component of generation gradients only at high-conflict positions without changing the architecture. Under a matched trainable-parameter budget, PAM improves over layer-wise separation by $+21$ MME and $+2.4$ GenEval points on Show-o while matching it on POPE and overall FID; a random-position control recovers about $31%$ of the gain. Position-based and layer-based separation are complementary degrees of freedom and can be combined.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38485
PDF
-
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?
2026-09-29 17:36:53Jiaxin Ge, Yiming Qin, Ji Xie, Haozhe Jiang, Xiaochuang Han, Junyi Zhang, Andrew Dai, Yinfei Yang, Jitendra Malik, Ranjay Krishna, Sewon Min, Haiwen Feng, Le Xue, Baifeng Shi, Trevor Darrell, XuDong WangAbstract
Training a model to generate visual content can encourage it to learn rich perceptual capabilities related to geometry, spatial relationships, and objectness; yet, its benefits for visual understanding remain unclear. We ask: when and how does visual generation supervision improve visual understanding? We study controlled pairs of image-to-image (I2I) generation and image-to-text (I2T) understanding tasks that express the same underlying problem in different output modalities. We find that under the correct recipe, I2I training improves downstream I2T performance, with larger gains as the amount of I2I training data increases. We next ask which generation tasks benefit which understanding capabilities. To study transfer beyond paired tasks, we introduce OmniTaskonomy, a unified taxonomy spanning 19 I2I generation tasks and 25 I2T understanding capabilities. The resulting transfer map reveals selective, task-dependent benefits. Some follow intuitive correspondences, e.g., depth prediction improving metric 3D reasoning, object pointing improving counting, and jigsaw reconstruction improving 2D ordering. Interestingly, we also uncover surprising connections: 2.5D segmentation improving category recognition and Z-depth prediction improving localization. To probe these patterns, we analyze gradient alignment between generation and understanding tasks and find that stronger alignment is associated with larger downstream transfer gains. Together, our results highlight visual generation as a rich source of supervision for visual understanding and provide a roadmap for unlocking its benefits through the right training curriculum and task selection. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38079
PDF
-
PAIQ: Patch-Aligned Semantic Injection via Residual Rotation
2026-09-29 14:32:11Pinze Ren, Yuwei Zhang, Hao Chen, Linghao Meng, Chang Li, Qiankun LiAbstract
Language-aligned and self-supervised visual encoders offer complementary strengths in semantic abstraction and spatial detail. Harnessing this complementarity requires enriching local features while retaining distinctions between semantically related patches. We introduce PAIQ, a patch-aligned semantic injection framework that combines content-based cross-encoder matching with orthogonally constrained residual updates. Using DINOv3 patch features as the spatial base, PAIQ aggregates complementary SigLIP features through joint source allocation and injects the aggregate--base differences through a shared orthogonal transformation Q. This rotation adapts update directions while preserving residual norms and pairwise angles. For fixed projected features, we derive conditions for patch separability under similar semantic aggregates and show that rotation adds a nonnegative separation term over direct interpolation when the aggregate is shared. Only the projection and fusion parameters are trained; both visual encoders and the language model remain frozen, and fusion retains 196 visual tokens. Across diverse language backbones, PAIQ yields broad gains in judge-assessed correctness and reductions in hallucination severity over single-encoder interfaces on image description and visual question answering. On the 2B and 9B Qwen backbones, this compact interface outperforms the strongest evaluated fusion or token-compression baselines by about 2.9 correctness points on average.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37685
PDF
-
MG-Thinker: Bi-Axial Self-Reflection for Multi-Image Reasoning Grounding
2026-09-29 12:28:34Heyu Huang, Chi Chen, Zonghao Guo, Yuhua Li, Maosong Sun, Ruixuan LiAbstract
Reinforcement learning (RL) has recently delivered substantial gains in multimodal reasoning, opening a promising route for fine-grained visual perception. Yet for multi-image reasoning grounding (MRG), reasoning over real-world multi-image contexts toward pixel-precise localization, existing RL-based approaches overlook two characteristics intrinsic to this paradigm: a coarse-to-fine hierarchical reasoning pattern, and heterogeneously distributed task--sample difficulties. In this work, we present MG-Thinker, a post-training RL framework that advances a new MRG paradigm featuring such hierarchical reasoning, supported by a curated 25K MRG dataset with task-adaptive Chain-of-Thought (CoT) annotations that elicit multi-perspective evidence before conclusion. To remedy the heterogeneous task--sample difficulties, we further propose Bi-Axial DAPO (BiA-DAPO), which decomposes rollout advantages along an intra-group signal axis and an inter-group competence axis through two complementary mechanisms, both grounded on our defined candidate pool for stable group-level statistics. Extensive experiments show that MG-Thinker achieves state-of-the-art performance on multi-image reasoning grounding while consistently improving generalization across multi-image understanding and diverse multimodal benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37374
PDF
-
Back2Struct: Making Structured Images Editable Again
2026-09-29 08:36:32Pengyu Yan, Yixin Wu, Yunjie Tian, David DoermannAbstract
Structured images, such as diagrams, charts, and flowcharts, are inherently symbolic and can be compactly represented in an editable format, yet in practice, they are often rendered as images, and therefore not graphically editable. This mismatch presents a significant challenge for researchers, engineers, and designers who wish to incorporate modified versions of existing graphic content into new materials without manually reconstructing it. In this study, we presentBack2Struct, which "makes structured images editable again" by directly recovering vector graphics code (SVG / XML) from image representations. Given an image of a structured graphic, Back2Struct predicts semantically object-level SVG / XML code that explicitly encodes text, shapes, topology, and layout, rather than performing low-level pixel vectorization. The generated code can be seamlessly imported into tools such as PowerPoint, allowing users to edit, refine, restyle, and reuse graphic content while preserving structural fidelity. Beyond supervised fine-tuning on ground-truth SVG token sequences, we further optimize Back2Struct with reward-based learning to better match deployment-time requirements: the output should be syntactically valid, properly concise, and visually faithful to the input diagram. Specifically, we design a composite reward that jointly encourages SVG / XML compilability, length consistency with the reference code, and structural or semantic similarity between the generated and ground-truth graphics. These complementary signals guide the model to produce SVGs that are not only closer to the training distribution, but also more complete, editable, and renderable in practice. Experiments show that Back2Struct improves accuracy, editability, validity, and user alignment over baselines. Dataset and code are available at: this http URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.37016
PDF
