Image_Caption
-
LE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation
2026-10-26 06:21:21Pavodi Maniamfu, Vogel Kiketa, Zezina Kuzulu Kuetu, Jakin Mukendi Kabongo, David Mayoya Kutangila, Pescie Honore Kinkani Mampuya, L'Or Wolo SiekaAbstract
Training-free few-shot adaptation of vision-language models typically constructs a classifier from CLIP's final projected image representation, leaving intermediate representations unused. Combining them is not straightforward. Class scores from different representations differ in spread by orders of magnitude for the same query. Direct averaging allocates influence by numerical scale rather than predictive information. We propose Layer-Ensemble Gaussian Discriminant Analysis (LE-GDA), a method that fits regularized shared-covariance discriminants independently to intermediate and final representations extracted in one frozen encoder pass. LE-GDA standardizes each discriminant's class scores per query, selects a small representation multiset on labeled validation data, and combines it with the zero-shot classifier without gradient-based optimization. Across 11 datasets, four CLIP backbones, five shot counts, and three independently sampled K-shot training sets, LE-GDA achieves the highest mean accuracy of all evaluated methods on every backbone, raising the 16-shot mean from 78.01% to 79.54% over a matched GDA-CLIP (final-feature) baseline and improving that baseline for every backbone-shot combination. At one shot, LE-GDA retains a 1.20-point mean gain over the baseline even though covariance estimation is unavailable and per-query standardization is neutral. A control with richer per-class structure inside a single representation does not reproduce the gain, indicating that the benefit comes from combining representations. These results show that intermediate CLIP representations carry information beyond the final embedding and can improve training-free few-shot adaptation. Code and evaluation resources are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34901
PDF
-
Whispers from the Neighbors: Rethinking Caption Consensus as Inference-Time Evidence for Vision-Language Retrieval
2026-10-24 16:59:25Khang Nhat Hoang Vo, Belal Shoer, Abhirama Subramanyam PenamakuriAbstract
An image is rarely described only once. Retrieval benchmarks and many collections attach several captions to each picture, yet dual encoders still judge every image-caption pair in isolation. We ask what these neighboring captions contribute when a frozen encoder consults them at inference time. Fusing image similarity with similarity to an image's own captions improves text-to-image R@1 by 3.4 to 16.8 points across nine frozen encoders when the captions come from the same annotators as the queries. The gain falls to 1.9 to 7.2 points when an off-the-shelf captioner writes them, and to at most one point when they come from a different annotation source; a paraphrase-trained text encoder strengthens the text side further. A natural refinement, scoring the part of the image that the captions leave unexplained, appears to add much more under a leave-one-out evaluation. We show that this advantage arises because the correct candidate's supports are built differently from those of the negative candidates, with set size and query removal each contributing about half, and that under a fixed support index the residual reduces to a reweighting of what the captions already provide. On compositional benchmarks, the captions help by matching candidates to human descriptions of the image, without improving image-text grounding. The code is available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.33798
PDF
-
Image Clustering with Vision-Language Model Embeddings
2026-10-23 20:21:15Jo\~ao P. Matos-Carvalho, Nuno FachadaAbstract
Pretrained vision-language models provide image representations whose suitability for clustering may vary with feature extraction, image domain, and partitioning algorithm. We compare nine representation pipelines across seven image benchmarks and four clustering configurations, yielding 252 baseline combinations. Eight pipelines extract visual features, including two vision-only references; the ninth generates descriptions and embeds the resulting text. With agglomerative clustering (Ward linkage) fixed, Qwen3-VL achieves the highest adjusted Rand index (ARI) on five datasets, including 0.925 on MNIST, while BLIP-2 leads on CIFAR-10 and CIFAR-100 with ARIs of 0.925 and 0.591, respectively. A separate sensitivity analysis compares raw and L2-normalized embeddings at their original dimensionality across all 63 dataset-representation pairs. Normalization preserves the highest-ARI representation in every dataset, increases ARI in 35 pairs, decreases it in 26, and leaves two numerically unchanged. On the SVHN dataset, the highest ARI remains low, rising from 0.097 to 0.098 after normalization. The evaluated caption-mediated pipeline obtains relatively high ARI on isolated digits but does not consistently exceed direct visual features. These findings support selecting and evaluating complete representation-clustering pipelines for the intended domain, with explicit attention to extraction and normalization choices.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33265
PDF
-
MiD-VLM: Detecting and Grounding Global Semantic Misinformation in Image-Caption Pairs
2026-10-23 17:55:02Tarunya Prasad, Bharatesh ChakravarthiAbstract
Semantic misinformation can arise when an authentic image is paired with a caption that changes or distorts its narrative. Because the image itself may contain no visible signs of manipulation, methods designed to detect pixel-level artifacts can miss these misleading image-caption pairs. We study this problem using DGM4+, a dataset designed to evaluate the detection of global scene and semantic inconsistencies. We propose a multimodal model that combines image-text representations from SigLIP with visual scene features from DINOv2 through a projection MLP, and adapts Qwen2-VL-7B using LoRA. The model jointly predicts whether an image-caption pair is authentic, identifies the manipulation type, and grounds the misleading caption tokens. On the DGM4+ validation split, the model achieves an F1 score of $0.9679$ for binary authenticity classification. These results suggest that parameter-efficient adaptation of vision-language models is promising for detecting semantic inconsistencies, while also motivating further work on precise token-level grounding.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32967
PDF
-
Augmentation Strategy for DINO in Glaucoma Classification
2026-10-23 11:33:28Ashish Kumar Meena, Chandra Sekhar SeelamantulaAbstract
Self-supervised learning (SSL) offers a promising approach to medical image representation learning, yet augmentation strategies of SSL frameworks validated on natural images do not reliably transfer to specialized medical imaging domains. We analyze DINO, a knowledge-distillation based SSL framework, and empirically demonstrate that its default augmentation strategy produces unreliable representations for retinal fundus images, degrading downstream glaucoma classification performance. Guided by the principle that effective cropped views should share minimal redundant information while retaining clinically relevant signal, we redesign DINO's augmentation strategy. Our approach biases the learned representations toward diagnostically critical features rather than low-level image statistics. We evaluate our method for glaucoma classification by training a linear classifier on the frozen representations, achieving strong generalization across seven benchmark datasets. URL for code and weights: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.32511
PDF
-
Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning
2026-10-22 11:21:32Yuanze Hu, Zhichao Yang, Junwei Jing, Xin Yang, Wenxuan Liu, Tinghai Zhang, Jia Fu, Hongzhi Zhang, Xiangyu Wu, Ruiming Tang, Tingting Gao, Han LiAbstract
Detailed image captioning is usually framed as an amount problem: a model should mention more visual facts while avoiding hallucination. However, autoregressive VLMs generate captions as ordered sequences, and later generations may be produced under weaker or noisier visual grounding. We therefore argue that long-form captioning should be studied not only by what facts are mentioned, but also by where they appear. We introduce a position-aware rubric representation that decomposes dense human references into atomic visual claims, verifies generated captions against those claims, and induces a quartile-wise composition of supported, hallucinated, and generic content. This lens reveals two qualitatively different failures in long captions: models tend to produce unsupported specificity in the middle, while the final portion often escapes into vague, non-evidential language rather than simply accumulating more hallucination. A same-reference human control does not exhibit these patterns; additional human audits examine the visual validity of the induced labels. Motivated by this diagnosis, we propose PAGER (Position-Aware Grounded Evidence Reinforcement), a GRPO training objective with separate signals for supported fine-grained middle evidence, evidence-bearing tail continuation, claim coverage, and content-aware length control. The result is a closed loop: the same ordered claim representation identifies where long captions fail and supplies the position-specific reward needed to repair those failures. Experiments on detailed-caption benchmarks show that PAGER improves position-wise grounding and pairwise caption preference while preserving competitive global caption quality.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31111
PDF
-
Text-to-Image Generative Modeling Without Language Pretraining
2026-10-20 15:44:34Keshigeyan Chandrasegaran, Yue Zhao, Armin W. Thomas, Ehsan Adeli, Jiajun Wu, Juan Carlos Niebles, Li Fei-Fei, Michael PoliAbstract
Modern text-to-image (T2I) systems use internet-scale language pretraining for text-conditioned image generation. We ask whether language pretraining is necessary for strong T2I generation. We introduce Halcyon, a family of early-fusion multimodal autoregressive models pretrained entirely from scratch on GPIC, a dataset of 100M image-text pairs. Halcyon-0.52B outperforms LlamaGen-XL/8 (48.0 vs. 63.3 gFD) with 18.2$\times$ less pretraining compute. Further, Halcyon-1.6B outperforms JiT-T2I-XXL/8++ (35.3 vs. 41.0 gFD) with 275$\times$ less pretraining compute. Controlled experiments show that text-only pretraining does not improve T2I generation. Halcyon also learns image captioning by replacing caption dropout with I2T supervision, maintaining competitive T2I generation quality under the same pretraining budget. We show that strong T2I systems can be trained from scratch without internet-scale language pretraining. Code and models are available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.26863
PDF
-
HypTI: Hyperbolic Geometry-Aware Multimodal Feature Fusion Framework for Dementia Detection Based on Tabular-Image Data
2026-10-20 09:49:08Jianfei Xu, Huizhi Liang, Judith Harrison, John-Paul Taylor, Jaume Bacardit, Varun OjhaAbstract
AI-assisted dementia detection usually requires multimodal fusion of diverse data, such as clinical tabular assessments and neuroimaging data. However, most existing approaches perform feature fusion in Euclidean space. This overlooks the geometric structure of representation, including hierarchical organization in clinical assessments and multi-scale anatomical patterns in neuroimaging data. Recent studies have proved hyperbolic space provides a natural geometry for modelling hierarchical and multi-scale structures due to its exponentially expanding space. Motivated by these, we propose HypTI, a hyperbolic geometry-aware multimodal fusion framework for dementia detection based on clinical tabular assessments and MRI scans. HypTI extends hyperbolic representation learning to an underexplored tabular-MRI setting, jointly modelling clinical tabular, MRI scans, and cross-modal interactions in hyperbolic space. Specifically, clinical tabular variables are represented through learnable Lorentz prototypes to capture hierarchical relationships among assessments, while MRI scans are encoded using ROI-guided multi-scale representation learning to capture anatomical patterns across brain regions and spatial scales in Lorentz space. The multimodal representations are integrated through an adaptive fusion module generates subject-specific scale and shift coefficients to dynamically modulate and integrate the multimodal embeddings, enabling effective patient-level tabular-image representation learning for dementia detection. Experiments on OASIS-3 dataset show that the proposed framework achieves strong performance compared with representative approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27941
PDF
-
Less is More: Concise Retrieval and Critic-based Re-ranking for Composed Image Retrieval
2026-10-20 02:53:02Yuqian Zheng, Hyoju Ahn, Hyeongjin Ahn, Eunil ParkAbstract
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image based on a reference image and modification text. Recent approaches commonly rely on large vision-language models to generate target image captions for retrieval. However, these captions may include redundant semantic details, introducing noise when retrieving the target image and leading to suboptimal retrieval results. To address this issue, we propose Less-is-More CIR, a two-stage training-free framework that combines Concise Retrieval and Critic Re-ranking. In the first stage, concise target-oriented captions are generated that preserve only the most discriminative modification semantics, thereby reducing semantic noise in the retrieval. In the second stage, a critic re-rank module further evaluates the retrieved candidates from the perspectives of modification consistency and reference preservation. Extensive experiments demonstrate the effectiveness and robustness of the proposed framework for the ZS-CIR. Our code is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27538
PDF
-
Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD
2026-10-16 10:22:00Yibo Zhou, Yirong XiangAbstract
Relational out-of-distribution errors are easy to describe and hard to evaluate cleanly. An image may be natural, a caption may be fluent, and all mentioned objects may be common, yet the caption may describe the wrong relation in the image. Many evaluations intended to test this behavior can be solved without checking the pairing at all, because negatives differ in caption style, template, length, object frequency, or image statistics. We propose counterfactual pairing cycles, a blocked evaluation primitive that reuses the same two images and the same two captions on both sides of the comparison, changing only which image is paired with which caption. This makes image-only, text-only, and additive component shortcuts cancel exactly in finite samples. The same contrast also gives a training loss for relational outlier exposure and a diagnostic for bilinear vision-language scores. Across synthetic controls, GQA, and COCO, cycles separate coarse image-caption matching from directional role-binding failures, while also identifying geometric size relations that remain strongly visible in global features. In a shortcut-contaminated COCO outlier-exposure stress test, a model selected by a near-perfect shortcut validation AUROC retains substantial relational signal but remains below cycle training on exact cycles; cycle training improves CycleAcc from 0.882 to 0.927. The main lesson is simple: to test whether a model understands a pairing, the benchmark should keep the parts fixed, change the pairing, and ask only about coupling. The official implementation is available online.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23248
PDF
-
Domain-specific language alignment of multimodal embeddings towards explainable predictions
2026-10-16 08:20:18Gabriel\.e Tij\=unaityt\.e, Thijs L. van der Plas, Mohamed-Bachir Belaid, Rob Knapen, Maciej J. Soja, Ioannis N. AthanasiadisAbstract
Multimodal data are commonly fused into latent representations that improve downstream task performance but are not interpretable, limiting their application in domains that require explainable model decisions. Vision-language alignment has made image embeddings interpretable through language, but requires vast image-caption training data. However, captioned data are typically not available for multimodal embeddings, as relevant features cannot directly be observed and annotated from embeddings alone. Here, we propose a framework to language-align any embedding space that can be linked to interpretable auxiliary data. Captioning functions convert auxiliary data into partial captions; a soft contrastive loss weights pairs by the similarity of their properties that each caption describes; and a rank-based concept retrieval task evaluates alignment against the auxiliary data rather than the captions. We apply this framework to multimodal Earth embeddings to facilitate explainable predictions for two species distribution modelling tasks: S2BMS and SatBird. AlphaEarth embeddings beat previous state-of-the-art models on 6/7 metrics, while our framework language-aligns domain-specific concepts of the embedding space, outperforming previous Earth observation vision-language models on average concept retrieval for both datasets. Finally, aligned concepts recover species-habitat associations ($\rho$=0.44) and relate habitat descriptions to species predictions, showing that abstract embeddings can be interrogated in the language of domain experts.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23110
PDF
-
Beyond Sparse Captions: Aligning Slide-Level Text and Patch-Level Vision in Pathology
2026-10-15 05:24:40Daniel Shao, Dongmin Bang, Luca L. Weishaupt, Sophia J. Wagner, Nic G. Reitsam, Ming Y. Lu, Long P. Le, Richard J. Chen, Faisal MahmoodAbstract
Contrastive vision-language (VL) pretraining in computational pathology has generally relied on curated image-caption datasets sourced from social media, educational videos, and research publications. These corpora are sparse relative to the diversity of tissue morphology and difficult to scale further, as pathologists do not routinely produce descriptive captions in clinical practice. We propose to instead leverage slide-level pathology reports which can be generated during routine diagnostic workflows in a scalable manner. A key challenge in this weakly-supervised setting is that pathology reports describe macroscopic, diagnostic findings while patch-level visual features describe microscopic findings. We introduce Locked Image Multiple Instance PreTraining (LIMIT), which addresses this gap by freezing a pretrained vision encoder and fine-tuning only the text encoder: report embeddings serve as cross-attention queries over bags of patch features, producing report-conditioned slide representations optimized via InfoNCE. Using LIMIT, we establish CONCH-Z, which aligns the text encoder of CONCH v1.5 to 335k clinical reports. Evaluated across 22 tasks spanning patch-level classification, tumor detection, and slide-level subtyping, CONCH-Z establishes state-of-the-art zero-shot performance over VL encoders trained on curated caption datasets, while simultaneously closing the gap with slide-level foundation models trained with substantially more parameters and compute. The code and model is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17233
PDF
-
ReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models
2026-10-14 18:27:53Feize Wu, Zhiyuan Yan, Yuhuan Hong, Yuwei Niu, Zongjian Li, Zheyuan Liu, Bin Lin, Jinbo Yan, Jie Qin, Xudong Mao, Limeng Qiao, Guanglu Wan, Li YuanAbstract
Image-to-text (I2T) understanding and text-to-image (T2I) generation are dual tasks in unified multimodal models (UMMs). Reconstructive post-training couples these tasks, but existing reconstruction-based methods remain perception-centric and provide limited supervision for reasoning about structure, intent, and transformation. We propose ReasonUni, a reasoning-augmented reconstructive post-training framework that extends this coupling beyond perception. Given an original image and an editing instruction, the UMM first reasons about what and how to edit and describes the target state, then generates the corresponding target image conditioned on this understanding output. To jointly optimize both modules, we introduce TreeGRPO, a tree-structured reinforcement learning method that samples multiple reasoning paths and candidate images per path, then aggregates visual rewards to update both modules under a unified objective. Experiments across multiple benchmarks demonstrate consistent gains in both understanding and generation, showing that reasoning-augmented reconstruction yields genuine mutual gains for UMMs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20781
PDF
-
Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation
2026-10-14 15:17:28Yuheng Chen, Yufan Chen, Zhuojun Cai, Ruiping Liu, Junwei Zheng, Jiale Wei, Di Wen, Weijia Fan, Kunyu Peng, Jiaming Zhang, Rainer StiefelhagenAbstract
Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning. This separation leaves scientific figures, captions, and visual semantics weakly connected, and fails to measure whether a model can produce a single page-level parse that is both structurally faithful and semantically accessible. We introduce Read-Parse-Describe, a unified dataset for document parsing with visual element description generation. Given a page image, models are required to output an ordered list of layout elements containing bounding boxes, semantic labels, reading-order indices, recognized textual content, and alternative text descriptions for visual elements. The benchmark is built from 2,402 documents, comprising 18,163 continuous pages, 125,218 layout elements, and 11,338 visual instances. Besides, we further propose a plug-and-play space-awareness enhancer that reuses multi-layer visual features and injects grid-aware spatial guidance into vision-language tokens for layout-aware generation. Experiments across end-to-end VLMs and pipeline parsers show that existing systems still struggle to jointly recover reading order and visual semantics, while our enhanced model achieves strong joint performance. These results highlight the need to move beyond isolated document parsing modules toward unified models that jointly read, parse, and describe complex documents. The new dataset and code will be made publicly available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.20335
PDF
-
Rethinking Projector Training in Multimodal LLMs
2026-10-13 15:53:53Fabian Gr\"oger, Na\"el Ouerghemi, Shuo Wen, Maria Brbi\'cAbstract
Multimodal LLMs are typically trained by first aligning a vision encoder with a language model via projector training on large image-caption datasets, followed by joint training of the full multimodal model. Despite its widespread use, the role of the projector training stage remains poorly understood. We find that (i) using only $10$ to $20\%$ of the data for training the projector already recovers most downstream performance gains, and (ii) projectors trained on different datasets can be linearly interpolated while largely preserving performance. These results suggest that projector training mainly performs a coarse alignment, which many different projectors achieve equally well. Motivated by these findings, we propose PORTAL, a training-free projector initialization that requires neither paired image-caption data nor gradient-based optimization, but only per-modality summary statistics. PORTAL computes an optimal-transport-based map between Gaussian approximations of the vision and language feature distributions on a shared principal subspace, so that the projector training stage can be skipped entirely. Without any paired data, PORTAL matches the standard pipeline trained on 558k image-caption pairs across six LLM backbones, two vision encoders, and 16 benchmarks. It outperforms that pipeline in $3$ of $7$ (vision encoder, LLM) settings and reaches an average $98\%$ of its score across the other four.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18598
PDF
-
Stabilizing the Modality Gap: Null-Space Projected Continual Learning for Vision-Language Models
2026-10-13 11:41:24Tiantian Peng, Yuyang Liu, Shuo Yang, Qiuhe Hong, YongHong TianAbstract
The modality gap is intrinsic to multimodal alignment, where embeddings from different modalities remain partially separated in a shared representation space. In continual learning, CLIP-based vision-language models (VLMs) not only suffer catastrophic forgetting but also experience modality gap drift that disrupts the shared embedding geometry. Such drift degrades cross-modal alignment and generalization. We propose FPCD, an efficient framework combining Fast Null-space Projection (FNP) and Contrastive Distillation (CD). FNP accumulates compact Gram matrices of previous tasks' activations and projects gradients onto layer-adaptive approximate null spaces to reduce interference with learned representations. By replacing singular value decomposition with symmetric eigendecomposition, FNP accelerates projection-basis construction by a factor of 5-9. CD uses a small reference set to align the bidirectional image-to-text and text-to-image similarity distributions of the fine-tuned model with CLIP, thereby preserving pretrained cross-modal relations. On the 11-task MTIL benchmark, FPCD achieves 87.6% Last, 76.4% Average, and 65.2% Transfer. It also maintains more stable modality gaps and stronger zero-shot retrieval performance on COCO Captions and Flickr30k than competing methods. These results highlight the importance of controlling modality gap drift during continual adaptation of VLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2507.19839
PDF
-
MERIT: Multimodal Evidence Reasoning over Image Tables
2026-10-13 08:21:53Haoyang Jiang, Zhuotong Fan, Mingyang Yi, Ju Fan, Lanqing Hu, Xiao ZanAbstract
Table reasoning with language models typically assumes access to clean textual tables. In practice, tables are often serialized into text, which can corrupt cell contents, distort structural relationships, and discard visual cues, leaving the model to reason over incomplete evidence. In contrast, table images retain this information, but using it requires both accurate perception and reasoning grounded in the relevant cells. To address this, we propose MERIT (Multimodal Evidence Reasoning over Image Tables), a three-stage framework for learning to reason over table images, with serialized tables serving as optional auxiliary inputs (if provided). Our analysis identifies visual evidence acquisition as a bottleneck, motivating table-specific encoder adaptation through reconstruction, localization, and color-conditioned supervision. Building on the adapted representations, supervised fine-tuning teaches explicit evidence selection and reasoning using verified trajectories. Finally, reinforcement learning refines the policy with separate rewards for evidence correctness, calculation, final answers, and output format. By providing feedback on intermediate steps, the framework targets retrieval and computational errors that final-answer supervision alone does not distinguish. We evaluate the approach on table question answering and fact verification, analyze the contributions of visual inputs and training components, and assess generalization to additional datasets with different table structures and visual presentations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17937
PDF
-
Understanding Unified VLMs: From Attention Probing to Guidance Tuning for Multimodal Generation
2026-10-10 23:40:27Zhengyang Luo, Xiaoyu Qiu, Zhiheng Tan, Yuchen Liang, Yingbin Liang, Liyue ShenAbstract
Unified vision-language models (VLMs) perform both text-to-image (T2I) and image-to-text (I2T) generation with one shared Transformer backbone, yet how the backbone processes the condition in either direction remains poorly understood. We study this question from the perspective of conditional guidance: we probe every attention head to show the activation difference between two branches of classifier-free guidance (CFG) with different conditional guidance. On two unified VLMs of autoregressive and masked-diffusion paradigms, the probing reveals a subset of heads that are more sensitive to the change of condition while others are agnostic to it. This characteristic pattern holds in both T2I and I2T generation and is largely stable across data samples, demonstrating the internal mechanism of unified VLMs. Motivated by this, we propose a new inference-time intervention approach for unified multimodal generation, named \textit{HeadTuned-CFG}, which uses the probed condition-change awareness to select and tune the conditional guidance at the attention-head level. Experiments show consistent benefits in both multimodal generation directions of unified VLMs without additional training, and in particular substantial improvements over strong baselines in T2I generation. These results further support the key finding of our probing analysis: the observed pattern of functional specialization is an intrinsic property of unified VLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15227
PDF
-
Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback
2026-10-09 17:58:15Yucheng Yang, Xiaoxiao Sun, Shusheng Yang, Jiakang Chen, Serena Yeung-LevyAbstract
Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text representations through joint attention. These representations then guide subsequent image updates, raising a question: does this feedback help correct deviations from the prompt, or preserve them? We find that image-to-text (I2T) feedback can preserve the objects and attributes already represented in the evolving image, including errors. Transplanting I2T messages can rescue failures or disrupt successes. At matched intervention strengths, suppressing the influence of I2T feedback improves generation, whereas opposite controls degrade it. These findings motivate Semantic Feedback Guidance (SFG), which suppresses the influence of I2T feedback by guiding away from an auxiliary branch that strengthens this feedback and weakens text-to-image conditioning. The in-place variant, iSFG, directly suppresses I2T feedback and strengthens text-to-image conditioning, requiring no extra model evaluations. Temporal interventions motivate running the SFG branch during the first 20% of image sampling steps, requiring about $1.2\times$ the base NFE without classifier-free guidance (CFG). Experiments across three image-generation backbones show gains in alignment and preference-model scores. On FLUX, adding SFG to CFG raises GenEval from $0.6661$ to $0.7479$; on SD3.5M, iSFG adds $+1.33$ HPSv2.1 over CFG at zero extra NFE. The control also transfers to text-to-video and image-to-video generation, improving VBench scores. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13941
PDF
-
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
2026-10-09 17:56:59Bhanu Tokas, Rahul Nair, Rockwell Jackson, Hannah KernerAbstract
Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpret classification and regression models. They require access to model weights or large concept-annotated datasets, and most methods cannot provide image-level attribution. We propose Hide and Seek (HnS), a new method for concept-level attribution that does not require access to model weights or labeled concept datasets. HnS can interpret a wide range of vision models. Given a concept and image set, HnS retrieves concept-aligned images using a vision-language model, localizes the concept within each image, masks the localized region, and measures attribution from the change in the black-box model's output between the original and masked images. This enables faithful attribution by directly measuring the model's behavior and supporting local attributions. We validated HnS on CelebA and COCO-Stuff. Compared to existing methods, HnS showed better agreement with ground-truth attributions. We demonstrated the applicability of HnS on diverse tasks, including image captioning and satellite image segmentation, where no existing concept attribution method can be used. We provided our anonymous code in the supplementary material.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13935
PDF
