论文检索

Computer Vision · Vision Models & Multimodal

Mingyang Song, Haoyu Sun, Jiawei Gu, Linjie Li, Ranjay Krishna, Yu Cheng

While augmenting Multimodal Large Language Models (MLLMs) with tools is a promising direction, current approaches face critical limitations. They often rely on single, atomic tools, failing to address the challenges of multi-turn planning, and they do not equip models with the ability to select effective tool combinations for complex tasks. To overcome these limitations, we introduce AdaReasoner, a framework that teaches models to perform dynamic tool orchestration for iterative visual reasoning. Our paradigm is designed to support a broad spectrum of tools, including computationally intensive, expert-model-based services. It features a comprehensive design that includes a new data curation methodology and a tailored Tool GRPO algorithm to optimize multi-turn tool-calling trajectories, which yields state-of-the-art models that achieve substantial gains over their baselines (+38.7\% average on 7B) and reach near-perfect accuracy on complex benchmarks like Visual Spatial Planning (97.6\%). This performance surpasses leading proprietary systems such as GPT-5 and Claude Sonnet 4, demonstrating that our approach can effectively overcome scale-based limitations by augmenting smaller models with powerful tool-use capabilities. Critically, we find that AdaReasoner develops emergent, self-adaptive behaviors: it learns to autonomously adopt beneficial tools, discard irrelevant ones, and modulate its usage frequency. This ability to curate its own optimal problem-solving strategies represents a significant step toward building more robust, scalable, and reliable reasoning agents.

Computer Vision · Vision Models & Multimodal

Sheng Cheng, Devika Subramanian

Vision-Language Models (VLMs) for radiology report generation are typically trained to mimic the narrative flow of human experts. However, we identify a potential limitation in this conventional paradigm. We hypothesize that optimizing for narrative coherence encourages models to rely on linguistic priors and inter-sentence correlations, which can weaken their grounding in direct visual evidence and lead to factual inaccuracies. To investigate this, we design a controlled experiment demonstrating that as textual context increases, a model's reliance on the input image systematically decays. We propose LLaVA-TA (Topic-guided and Anatomy-aware), a new fine-tuning framework that directly addresses this challenge by re-engineering the generation process. Instead of producing a linear narrative, LLaVA-TA decomposes the report into a set of independent, clinically-relevant topics. By training the model to generate a discrete finding for each topic conditioned on both the full image and its corresponding anatomical region, we reduce the model's reliance on narrative flow and enforce stricter visual grounding. Our experiments show that LLaVA-TA sets a new state of the art on the MIMIC-CXR dataset, significantly improving clinical accuracy on metrics like RadGraph F1 (from 29.4 to 44.0) and CheXpert F1-14 (from 39.5 to 71.5) over strong baselines. Our work demonstrates that dismantling a report's narrative structure to enforce independent, visually-grounded observations is a crucial and effective step toward building more accurate and reliable medical VLMs.

Computer Vision · Vision Models & Multimodal

Boyang Liu, Yifan Hu, Senjie Jin, Shihan Dou, Gonglei Shi, Jie Shao, Tao Gui, Xuanjing Huang

Multimodal large language models (MLLMs) are well suited to image aesthetic assessment, as they can capture high-level aesthetic features leveraging their cross-modal understanding capacity. However, the scarcity of multimodal aesthetic reasoning data and the inherently subjective nature of aesthetic judgment make it difficult for MLLMs to generate accurate aesthetic judgments with interpretable rationales. To this end, we propose Aes-R1, a comprehensive aesthetic reasoning framework with reinforcement learning (RL). Concretely, Aes-R1 integrates a pipeline, AesCoT, to construct and filter high-quality chain-of-thought aesthetic reasoning data used for cold-start. After teaching the model to generate structured explanations prior to scoring, we then employ the Relative-Absolute Policy Optimization (RAPO), a novel RL algorithm that jointly optimizes absolute score regression and relative ranking order, improving both per-image accuracy and cross-image preference judgments. Aes-R1 enables MLLMs to generate grounded explanations alongside faithful scores, thereby enhancing aesthetic scoring and reasoning in a unified framework. Extensive experiments demonstrate that Aes-R1 improves the backbone’s average PLCC/SRCC by 47.9%/34.8%, surpassing state-of-the-art baselines of similar size. More ablation studies validate Aes-R1's robust generalization under limited supervision and in out-of-distribution scenarios.

Computer Vision · Vision Models & Multimodal

Weitai Kang, Bin Lei, Gaowen Liu, Caiwen Ding, Yan Yan

Graphical user interface visual grounding (GUI-VG)—a core capability for GUI agents—has primarily relied on supervised fine-tuning (SFT) of multimodal large language models (MLLMs), demanding extensive data curation and significant training costs. However, as MLLMs continue to advance and even cover GUI domains during pretraining, the necessity of exhaustive SFT post-training becomes increasingly questionable. Meanwhile, the recent successes of rule-based reinforcement fine-tuning (RFT) suggest a more efficient alternative. However, despite its promise, the optimal manner of RFT for GUI-VG remains unexplored. To bridge this gap, we introduce GuirlVG, a reinforcement learning–based GUI-VG method built on a systematic empirical study and a novel stabilization technique. Preliminarily, we find that naive application of RFT underperforms the SFT baseline, motivating a deeper exploration of RFT. First, we decompose RFT into its core components and analyze the optimal formulation of each. Second, as part of this exploration, we propose a novel Adversarial KL Factor that dynamically stabilizes training to mitigate reward over-optimization. Third, we further explore the training configurations of RFT to enhance the effectiveness. Extensive experiments show that GuirlVG, with only 5.2K training samples, outperforms SFT methods trained on over 10M samples, achieving a +7.7% improvement on ScreenSpot, a +17.2% improvement on ScreenSpotPro and 91.9% accuracy on ScreenSpotV2.

Computer Vision · Vision Models & Multimodal

Shivank Garg, Sankalp Mittal, Manish Gupta

Communicating complex system designs or scientific processes through text alone is inefficient and prone to ambiguity. A system that automatically generates scientific architecture diagrams from text with high semantic fidelity can be useful in multiple applications like enterprise architecture visualization, AI-driven software design, and educational content creation. Hence, in this paper, we focus on leveraging language models to perform semantic understanding of the input text description to generate intermediate code that can be processed to generate high-fidelity architecture diagrams. Unfortunately, no clean large-scale open-access dataset exists, implying lack of any effective open models for this task. Hence, we contribute a comprehensive dataset, \system, comprising scientific architecture images, their corresponding textual descriptions, and associated DOT code representations. Leveraging this resource, we fine-tune a suite of small language models, and also perform in-context learning using GPT-4o. Through extensive experimentation, we show that \system{} models significantly outperform existing baseline models like DiagramAgent and perform at par with in-context learning based generations from GPT-4o. We have added code and data as Supplementary material, and will make them (and models) publicly available on acceptance.

Computer Vision · Vision Models & Multimodal

Prerit Gupta, Shourya Verma, Ananth Grama, Aniket Bera

Generating realistic, context-aware two-person motion conditioned on diverse modalities remains a fundamental challenge for graphics, animation and embodied AI systems. Real-world applications such as VR/AR companions, social robotics and game agents require models capable of producing coordinated interpersonal behavior while flexibly switching between interactive and reactive generation. We introduce DualFlow, the first unified and efficient framework for multi-modal two-person motion generation. DualFlow conditions 3D motion generation on diverse inputs, including text, music, and prior motion sequences. Leveraging rectified flow, it achieves deterministic straight-line sampling paths between noise and data, reducing inference time and mitigating error accumulation common in diffusion-based models. To enhance semantic grounding, DualFlow employs a novel Retrieval-Augmented Generation (RAG) module for two-person motion that retrieves motion exemplars using music features and LLM-based text decompositions of spatial relations, body movements, and rhythmic patterns. We use contrastive rectified flow objective to further sharpen alignment with conditioning signals and add synchronization loss to improve inter-person temporal coordination. Extensive evaluations across interactive, reactive, and multi-modal benchmarks demonstrate that DualFlow consistently improves motion quality, responsiveness, and semantic fidelity. DualFlow achieves state-of-the-art performance in two-person multi-modal motion generation, producing coherent, expressive, and rhythmically synchronized motion.

Computer Vision · Vision Models & Multimodal

Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona, Michael Oechsle, Federico Tombari, Bernt Schiele, Jan Eric Lenssen

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an *inference-time* feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiments, AnyUp sets a new state of the art for upsampled features, generalizes to different feature types, and preserves feature semantics while being efficient and easy to apply to a wide range of downstream tasks.

Computer Vision · Vision Models & Multimodal

Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona, Michael Oechsle, Federico Tombari, Bernt Schiele, Jan Eric Lenssen

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an *inference-time* feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiments, AnyUp sets a new state of the art for upsampled features, generalizes to different feature types, and preserves feature semantics while being efficient and easy to apply to a wide range of downstream tasks.

Computer Vision · Vision Models & Multimodal

Mehmet Onurcan Kaya, Desmond Elliott, Dim Papadopoulos

Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed by test-time scaling techniques, but existing methods are typically computationally demanding, contradicting the resource-efficient design goals of small models. To address these limitations, we propose two novel and efficient test-time scaling strategies that leverage the model-internal features rather than external supervision: (i) Test-Time Augmentation (TTAug), which generates multiple augmented inputs and aggregates outputs at the token level without parameter updates, and (ii) Test-Time Adaptation (TTAdapt), which adapts model parameters during inference using consensus-based pseudolabels from TTAug. Through extensive experiments across nine benchmarks, we demonstrate consistent performance improvements while maintaining computational efficiency suitable for resource-constrained environments. The generality of our approach is demonstrated both within models at different scales and across different VLMs without additional tuning.

Computer Vision · Vision Models & Multimodal

Dezhao Luo, Bohan Tang, Kang Li, Georgios Papoudakis, Jifei Song, Shaogang Gong, Jianye Hao, Jun Wang, Kun Shao

App agents, which autonomously operate mobile Apps through GUIs, have gained significant interest in real-world applications. Yet, they often struggle with long-horizon planning, failing to find the optimal actions for complex tasks with longer steps. To address this, world models are used to predict the next GUI observation based on user actions, enabling more effective agent planning. However, existing world models primarily focus on generating only textual descriptions, lacking essential visual details. To fill this gap, we propose ViMo, the first Visual world Model designed to generate future App observations as images. For the challenge of generating text in image patches, where even minor pixel errors can distort readability, we decompose GUI generation into graphic and text content generation. We propose a novel data representation, the Symbolic Text Representation (STR), to overlay text content with symbolic placeholders while preserving graphics. With this design, ViMo employs a STR Predictor to predict future GUIs’ graphics and a GUI-text Predictor for generating the corresponding text. Moreover, we deploy ViMo to enhance agent-focused tasks by predicting the outcome of actions. Experiments show that ViMo establishes visual world models as a compelling alternative to language-based approaches, producing visually plausible and functionally effective GUIs that empower App agents with more informed decisions.

Computer Vision · Vision Models & Multimodal

Xindi Wu, Hee Seung Hwang, Polina Kirichenko, Esin Tureci, Olga Russakovsky

Visual instruction tuning (VIT) datasets have grown rapidly in scale, yet the informativeness of individual training samples has largely been overlooked. Recent dataset selection methods have shown that a small fraction of such datasets enriched with informative samples can lead to efficient finetuning of Multimodal Large Language Models. In this work, we explore the impact of sample complexity on informative data curation and introduce COMPACT (COMPositional Atomic-to-complex Visual Compositional Tuning), a visual compositional tuning data recipe that scales training sample complexity by combining multiple atomic visual capabilities in a single training example. Concretely, we synthesize rich and informative text questions for each image, allowing us to significantly reduce the number of training examples required for effective visual instruction tuning. COMPACT demonstrates superior data efficiency compared to existing data reduction methods. When applied to the LLAVA-665K VIT dataset, COMPACT reduces the data budget by 90% while still achieving 100.2% of the full VIT performance (compared to only 97.5% by the state-of-the-art method) across eight multimodal benchmarks. Further, training on the COMPACT data outperforms training on the full-scale VIT data on particularly complex benchmarks such as MM-Vet (+8.6%) and MMStar (+2.9%). COMPACT offers a scalable and efficient synthetic data generation recipe to improve on vision-language tasks.

Computer Vision · Vision Models & Multimodal

Hongtao Yu, Yuxin Peng, Serge Belongie, Xiu-Shen Wei

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception capabilities, garnering significant attention. While numerous evaluation studies have emerged, assessing LVLMs both holistically and on specialized tasks, fine-grained image tasks—fundamental to computer vision—remain largely unexplored. To fill this gap, we introduce a comprehensive fine-grained evaluation benchmark, i.e., FG-BMK, comprising 1.01 million questions and 0.28 million images. Our evaluation systematically examines LVLMs from both human-oriented and machine-oriented perspectives, focusing on their semantic recognition and fine-grained feature representation capabilities. Through extensive experiments on twelve representative LVLMs/VLMs, we uncover key findings regarding the influence of training paradigms, modality alignment, perturbation susceptibility, and fine-grained category reasoning on task performance. This work provides critical insights into the limitations of current LVLMs and offers guidance for future data construction and model design in the development of more advanced LVLMs. Our code is open-source and available at https://github.com/SEU-VIPGroup/FG-BMK.

Applications · Language, Speech and Dialog

Sara Papi, Maike Züfle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues

Recent advances in large language models have laid the foundation for multimodal LLMs (MLLMs), which unify text, speech, and vision within a single framework. As these models are rapidly evolving toward general-purpose instruction following across diverse and complex tasks, a key frontier is evaluating their crosslingual and multimodal capabilities over both short- and long-form inputs. However, existing benchmarks fall short in evaluating these dimensions jointly: they are often limited to English, mostly focus on a single modality at a time, rely on short-form inputs, or lack human annotations--hindering comprehensive assessment of model performance across languages, modalities, and task complexity. To address these gaps, we introduce MCIF (Multimodal Crosslingual Instruction Following), the first crosslingual human-annotated benchmark based on scientific talks on NLP and beyond. MCIF evaluates instruction following in crosslingual, multimodal settings over different input lengths and spans four macro-tasks: recognition, translation, question answering, and summarization. It covers three core modalities (speech, vision, and text) and four diverse languages (English, German, Italian, and Chinese), fully aligned across all dimensions. This parallel design enables a systematic evaluation of MLLMs' abilities to interpret instructions across languages and effectively integrate multimodal contextual information. Our benchmarking and analysis of 23 models highlight universal challenges across modalities and tasks, indicating substantial room for improvement in future MLLMs development. MCIF is released under CC-BY 4.0 license to promote open research.

Computer Vision · Vision Models & Multimodal

Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra, Jeonghwan Kim, Madhav Kanda, Hyeonjeong Ha, Svetlana Lazebnik, Heng Ji, Unnat Jain

Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perceptual grounding. We introduce AttWarp, a lightweight method that allocates more resolution to query-relevant content while compressing less informative areas, all while pre- serving global context. At test time, AttWarp closes a simple self-correction loop: the MLLM first produces cross-modal attention on the original image, which we use to rectilinearly warp the input and re-run the same frozen model, reallocating resolution toward regions it deems important without changing weights or architecture. This attention-guided warping preserves all original image information but redistributes it non-uniformly, so small objects and subtle relationships become easier for the same model to read while the global layout remains intact. Across nine benchmarks (TextVQA, GQA, DocVQA, POPE, MMMU, MIA- Bench, MMVP, RealWorldQA, BLINK) and four MLLMs (LLaVA, Qwen-VL, InternVL, and InstructBLIP), AttWarp consistently improves accuracy, strengthens compositional reasoning, and reduces hallucinations, outperforming four competitive baselines that manipulate raw images at test time. Together, these results show that attention-guided warping prioritizes information relevant to the query while preserving context, and that the same MLLMs perform better when given such warped inputs. The code and demos are available on the project page: https://dwipddalal.github.io/Attwarp/

Computer Vision · Vision Models & Multimodal

Tianci Luo, Jinpeng Wang, Shiyu Qin, Niu Lian, Yan Feng, Bin Chen, Chun Yuan, Shu-Tao Xia

Visual In-Context Learning (VICL) aims to complete vision tasks by imitating pixel demonstrations. Recent work Condenser pioneered prompt fusion that combines the advantages of various demonstrations, which shows a promising way to extend VICL. Unfortunately, the patch-wise fusion framework and model-agnostic supervision hinder the exploitation of informative cues, thereby limiting performance gains. To overcome this deficiency, we introduce PromptHub, a framework that holistically strengthens multi-prompting through locality-aware fusion, concentration and alignment. PromptHub exploits spatial priors to capture richer contextual information, employs complementary concentration, alignment, and prediction objectives to mutually guide training, and incorporates data augmentation to further reinforce supervision. Extensive experiments on three fundamental vision tasks demonstrate the superiority of PromptHub. Moreover, we validate its universality, transferability, and robustness across out-of-distribution settings, and various retrieval scenarios. This work establishes a reliable locality-aware paradigm for prompt fusion, moving beyond prior patch-wise approaches. Code is available at https://github.com/luotc-why/ICLR26-PromptHub.

Computer Vision · Vision Models & Multimodal

Lixin Xiu, Xufang Luo, Hideki Nakayama

Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or from reliance on unimodal priors. To address this attribution gap, we introduce a novel framework using partial information decomposition (PID) to quantitatively measure the ``information spectrum'' of LVLMs---decomposing a model's decision-relevant information into redundant, unique, and synergistic components. By adapting a scalable estimator to modern LVLM outputs, our model-agnostic pipeline profiles 26 LVLMs on four datasets across three dimensions---\emph{breadth} (cross-model \& cross-task), \emph{depth} (layer-wise information dynamics), and \emph{time} (learning dynamics across training). Our analysis reveals two key results: (i) two task regimes (synergy-driven vs.\ knowledge-driven) and (ii) two stable, contrasting family-level strategies (fusion-centric vs.\ language-centric). We also uncover a consistent three-phase pattern in layer-wise processing and identify visual instruction tuning as the key stage where fusion is learned. Together, these contributions provide a quantitative lens beyond accuracy-only evaluation and offer insights for analyzing and designing the next generation of LVLMs. Code and data are available at \url{https://github.com/RiiShin/pid-lvlm-analysis}.

Computer Vision · Vision Models & Multimodal

Changwoo Baek, Jouwon Song, Sohyeon Kim, Kyeongbo Kong

Large Vision-Language Models (LVLMs) have adopted visual token pruning strategies to mitigate substantial computational overhead incurred by extensive visual token sequences. While prior works primarily focus on either attention-based or diversity-based pruning methods, in-depth analysis of these approaches' characteristics and limitations remains largely unexplored. In this work, we conduct thorough empirical analysis using effective rank (erank) as a measure of feature diversity and attention score entropy to investigate visual token processing mechanisms and analyze the strengths and weaknesses of each approach. Our analysis reveals two insights: (1) Our erank-based quantitative analysis shows that many diversity-oriented pruning methods preserve substantially less feature diversity than intended; moreover, analysis using the CHAIR dataset reveals that the diversity they do retain is closely tied to increased hallucination frequency compared to attention-based pruning. (2) We further observe that attention-based approaches are more effective on simple images where visual evidence is concentrated, while diversity-based methods better handle complex images with distributed features. Building on these empirical insights, we show that incorporating image-aware adjustments into existing hybrid pruning strategies consistently improves their performance. We also provide a minimal instantiation of our empirical findings through a simple adaptive pruning mechanism, which achieves strong and reliable performance across standard benchmarks as well as hallucination-specific evaluations. Our project page available at https://cvsp-lab.github.io/AgilePruner.

Computer Vision · Vision Models & Multimodal

Mitchell Keren Taraday, Shahaf Wagner, Chaim Baskin

Multimodal retrieval still leans on embedding-based models like CLIP for fast vector search over pre-computed image embeddings. Yet, unlike text retrieval where joint-encoder rerankers are standard, comparable vision–language rerankers are largely absent. We find that seminal joint encoders such as BLIP are severely bottlenecked by an expensive visual feature-extraction stage, preventing practical deployment at scale. Motivated by this bottleneck, we introduce EDJE , an Efficient Discriminative Joint Encoder that precomputes vision tokens offline and compresses them via a lightweight attention-based adapter, so online inference runs only a compact joint encoder over a small set of visual tokens plus the text. EDJE preserves strong retrieval performance while drastically reducing storage and online compute, enabling high-throughput inference. Specifically, EDJE processes 50k image–text pairs/second while requiring 49kB of disk storage per image, matching prior art on Flickr (zero-shot) and COCO (fine-tuned) retrieval.

Computer Vision · Vision Models & Multimodal

Wenfang Sun, Hao Chen, Yingjun Du, Yefeng Zheng, Cees G Snoek

Large vision-language models have achieved remarkable progress in visual reasoning, yet most existing systems rely on single-step or text-only reasoning, limiting their ability to iteratively refine understanding across multiple visual contexts. To address this limitation, we introduce a new multi-round visual reasoning benchmark with training and test sets spanning both detection and segmentation tasks, enabling systematic evaluation under iterative reasoning scenarios. We further propose RegionReasoner, a reinforcement learning framework that enforces grounded reasoning by requiring each reasoning trace to explicitly cite the corresponding reference bounding boxes, while maintaining semantic coherence via a global–local consistency reward. This reward extracts key objects and nouns from both global scene captions and region-level captions, aligning them with the reasoning trace to ensure consistency across reasoning steps. RegionReasoner is optimized with structured rewards combining grounding fidelity and global–local semantic alignment. Experiments on detection and segmentation tasks show that RegionReasoner-7B, together with our newly introduced benchmark RegionDial-Bench, considerably improves multi-round reasoning accuracy, spatial grounding precision, and global–local consistency, establishing a strong baseline for this emerging research direction.

Computer Vision · Vision Models & Multimodal

Jingqi Tong, Jixin Tang, Hangcheng Li, Yurong Mou, Ming Zhang, Jun Zhao, Yanbo Wen, Fan Song, Jiahao Zhan, Yuyang Lu 等

Vision-language reinforcement learning (RL) has primarily focused on narrow domains (e.g. geometry or chart reasoning). This leaves broader training scenarios and resources underexplored, limiting the exploration and learning of Vision Language Models (VLMs) through RL. We find video games inherently provide rich visual elements and mechanics that are easy to verify. To fully leverage the multimodal and verifiable rewards in video games, we propose Game-RL, constructing diverse game tasks for RL training to boost VLMs’ general reasoning ability. To obtain training data, we propose Code2Logic, a novel approach that adapts game code to synthesize reasoning data with unlimited examples and controllable difficulty gradation, thus obtaining the GameQA dataset of 30 games and 158 verifiable tasks. Remarkably, RL training solely on GameQA enables multiple VLMs to generalize across 7 diverse out-of-domain vision-language benchmarks, demonstrating the value of Game-RL for enhancing VLMs’ general reasoning. Furthermore, game data provides improvements comparable to general multimodal reasoning datasets (e.g. geometry/chart). More importantly, scaling up game diversity or game data volume consistently improves VLMs' generalizable reasoning capabilities. Our findings highlight scaling reinforcement learning in game environments as a promising direction for enhancing generalizable multimodal reasoning in foundation models. All code, dataset and model weights are released at \url{https://github.com/tongjingqi/Game-RL}.