论文检索

Computer Vision · Vision Models & Multimodal

Xiaojie Li, Chu Li, Shi-Zhe Chen, Xi Chen

Universal multimodal retrieval (UMR), which aims to address complex retrieval tasks where both queries and candidates span diverse modalities, has been significantly advanced by the emergence of MLLMs. While state-of-the-art MLLM-based methods in the literature predominantly adopt contrastive learning principles, they often differ in their specific training recipes. Despite their success, the mechanisms underlying their retrieval capabilities remain largely unexplored, potentially resulting in suboptimal performance and limited generalization ability. To address these issues, we present a comprehensive study aimed at uncovering the key factors that drive effective embedding learning for UMR using MLLMs. We begin by implementing a general MLLM-based embedding learning pipeline, and systematically analyze the primary contributors to high-performing universal retrieval systems. Based on this, we explore various aspects of the details in embedding generation and training strategies, including progressive transition, hard negative mining and re-ranker distillation. Notably, our findings reveal that often-overlooked factors can have a substantial impact on model performance. Building on these discoveries, we introduce a unified framework termed U-MARVEL (Universal MultimodAl RetrieVal via Embedding Learning), which outperforms state-of-the-art competitors on the M-BEIR benchmark by a large margin in supervised settings, and also exhibits strong zero-shot performance on several tasks such as composed image retrieval and text-to-video retrieval. These results underscore the generalization potential of our framework across various embedding-based retrieval tasks.

Computer Vision · Vision Models & Multimodal

Nianchen Deng, Lixin Gu, Shenglong Ye, Yinan He, Zhe Chen, Songze Li, Haomin Wang, Jinhui Yin, Qi Wei, Tianshuo Yang 等

Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain constrained by limited scale, narrow visual diversity, and restricted instruction expressiveness. To address these gaps, we present InternSpatial---the largest open-source dataset for spatial reasoning in VLMs---alongside InternSpatial-Bench, a comprehensive evaluation benchmark designed to assess spatial understanding across diverse instruction formats. InternSpatial contains 12 million question-answer(QA) pairs covering both single-view and multi-view scenarios, sourced from varied visual environments and supporting 19 distinct instruction formats that mirror real-world query patterns. InternSpatial-Bench aims to single-view assessment and also extends multi-view reasoning through a novel rotation estimation task. Experimental validation demonstrates that models trained on \trainset achieve substantial performance improvement of 12.1% on InternSpatial-Bench and 10.7% on VSI-Bench, while preserving competitive performance on general-purpose benchmarks. We expect these resources can advance the development of spatially-capable VLMs for practical applications in robotics and embodied AI systems. Our codes and datasets are publicly available at https://github.com/dengnianchen/intern-spatial.

Computer Vision · Vision Models & Multimodal

Pingyue Zhang, Zihan Huang, Yue Wang, Jieyu Zhang, Letian Xue, Zihan Wang, Qineng Wang, Keshigeyan Chandrasegaran, Ruohan Zhang, Yejin Choi 等

Spatial embodied intelligence under partial observability requires agents to actively acquire missing information rather than passively consume complete observations. While multimodal foundation models excel at passive perception and reasoning, their ability to support active, self-directed exploration to build and maintain a coherent spatial belief remains unstudied. We therefore propose Theory of Space, defined as an agent's ability to construct, revise, and exploit a spatial belief through self-directed active exploration under partial observability. We implement Theory of Space using a benchmark with textual and visual environments. Rather than solving specific tasks, the goal is curiosity-driven exploration to build a complete, accurate spatial belief. A core innovation is spatial belief probing: we prompt it to reveal its internal spatial belief as a cognitive map at each step, letting us measure the quality of its underlying spatial belief. Our evaluation of state-of-the-art models on a suite of downstream tasks reveals critical bottlenecks: (1) \textbf{The Active-Passive Gap}: Performance degrades when agents must autonomously gather information (e.g., \textsc{GPT-5.2}: $57.1{\to}46.0$); (2) \textbf{Inefficiency}: Models explore in an unsystematic way and with high redundancy, failing to match the efficiency of program-based proxies while producing no better results. Through belief probing, we diagnose that perception acts as an initial bottleneck, yet global beliefs suffer further from \textbf{instability} that causes spatial knowledge to degrade over time. Finally, a false belief paradigm reveals \textbf{Belief Inertia}: agents fail to overwrite obsolete priors, an effect especially severe in vision-based models.

Computer Vision · Vision Models & Multimodal

Shunki Uebayashi, Kento Masui, Kyohei Atarashi, Han Bao, Hisashi Kashima, Naoto Inoue, Mayu Otani, Koh Takeuchi

Multimodal Large Language Models (MLLMs) have recently emerged as general architectures capable of reasoning over diverse modalities. Benchmarks for MLLMs should measure their ability for cross‑modal integration. However, current benchmarks are filled with shortcut questions, which can be solved using only single modality, and thereby yielding unreliable rankings. For example, in vision-language cases, we can find the correct answer without either the image or the text. These low-quality questions unnecessarily increase the size and computational requirements of benchmarks. We introduce a multi-modal and multidimensional item response theory framework (M3IRT) that extends classical IRT by decomposing both model ability and item difficulty into image‑only, text‑only, and cross‑modal components. M3IRT estimates cross‑modal ability of MLLMs and each question’s cross‑modal difficulty, enabling compact, high‑quality subsets that better reflect multimodal reasoning. Across 24 VLMs on three benchmarks, M3IRT prioritizes genuinely cross‑modal questions over shortcuts and preserves ranking fidelity even when 50\% of items are artificially generated low‑quality questions, thereby reducing evaluation cost while improving reliability. M3IRT thus offers a practical tool for assessing cross‑modal reasoning and refining multimodal benchmarks.

Computer Vision · 3D Rendering & Reconstruction

Jonas Belouadi, Tamy Boubekeur, Adrien Kaiser

Material node graphs are programs that generate the 2D channels of procedural materials, including geometry such as roughness and displacement maps, and reflectance such as albedo and conductivity maps. They are essential in computer graphics for representing the appearance of virtual 3D objects parametrically and at arbitrary resolution. In particular, their directed acyclic graph structure and intermediate states enable a modular, interpretable workflow for interactive appearance modeling. However, creating such graphs remains challenging and typically requires professional training. While recent neural program synthesis approaches attempt to simplify this process, they solely represent graphs as textual programs, failing to capture the inherently visual-spatial nature of node graphs that makes them accessible to humans. To address this gap, we present MultiMat, a multimodal program synthesis framework that leverages large multimodal models to process both visual and textual graph representations for improved generation of procedural material graphs. We train our models on a new dataset of production-quality procedural materials and combine them with a constrained tree search inference algorithm that ensures static correctness while efficiently navigating the program space. Our experimental results show that our multimodal program synthesis method is more efficient in both unconditional and conditional graph synthesis with higher visual quality and fidelity than text-only baselines, establishing new state-of-the-art performance.

Computer Vision · Vision Models & Multimodal

Xintong Li, Chuhan Wang, Junda Wu, Rohan Surana, Tong Yu, Julian McAuley, Jingbo Shang

Direct Preference Optimization (DPO) has recently been extended from text-only models to vision-language models. However, existing methods rely on oversimplified pairwise comparisons, generating a single negative image via basic perturbations or similarity-based retrieval, which fail to capture the complex nature of multimodal preferences, inducing optimization bias and hallucinations. To address this issue, we propose MISP-DPO, the first framework to incorporate \emph{multiple}, semantically \emph{diverse} negative images in multimodal DPO via the Plackett-Luce model. Our method embeds prompts and candidate images in CLIP (Contrastive Language–Image Pre-training) space and applies a sparse autoencoder to uncover semantic deviations into interpretable factors. Negative samples are selected based on reconstruction difficulty, semantic deviation from the positive, and mutual diversity, yielding broader and more informative supervision. To handle multi-negative comparisons, we adopt a Plackett–Luce objective and introduce an importance sampling strategy that improves training efficiency. Experiments across five diverse benchmarks demonstrate that MISP-DPO consistently improves multimodal alignment over prior methods, validating the effectiveness of semantic-aware, multi-negative sampling in preference-based learning.

Computer Vision · Vision Models & Multimodal

Jiwan Kim, Kibum Kim, Sangwoo Seo, Chanyoung Park

Recently, efficient Multimodal Large Language Models (MLLMs) have gained significant attention as a solution to their high computational complexity, making them more practical for real-world applications. In this regard, the knowledge distillation (KD) approach has emerged as a promising alternative, which transfers the rich visual and linguistic knowledge from a larger model (teacher) to a smaller model (student). However, we observe that existing KD methods struggle to effectively distill the teacher MLLM's rich visual perception abilities to the student, a challenge that has been largely overlooked in previous studies. Through a systematic analysis, we identify visual attention misalignment between student and teacher as the main cause of this issue. Based on this insight, we propose CompoDistill, a novel KD framework that explicitly aligns the student's visual attention with that of the teacher to enhance the student's visual perception abilities. Our extensive experiments show that CompoDistill significantly improves performance on compositional reasoning tasks that require visual perception abilities while maintaining strong performance on visual question answering tasks, as done in existing studies. Furthermore, CompoDistill demonstrates effectiveness with a more advanced backbone, highlighting its generalizability.

Computer Vision · Vision Models & Multimodal

Raphaela Kang, Hongqiao Chen, Georgia Gkioxari, Pietro Perona

Spatio-temporal reasoning is a remarkable capability of Vision Language Models (VLMs), but the underlying mechanisms of such abilities remain largely opaque. We postulate that visual/geometrical and textual representations of spatial structure must be combined at some point in VLM computations. We search for such confluence, and ask whether the identified representation can causally explain aspects of input-output model behavior through a linear model. We show empirically that VLMs encode object locations by linearly binding \textit{spatial IDs to textual activations, then perform reasoning via language tokens. Through rigorous causal interventions we demonstrate that these IDs, which are ubiquitous across the model, can systematically mediate model beliefs at intermediate VLM layers. Additionally, we find that spatial IDs serve as a diagnostic tool for identifying limitations and bottlenecks in existing VLMs. We extend our analysis to video VLMs and identify an analogous linear temporal ID mechanism. By characterizing our proposed spatiotemporal ID mechanism, we elucidate a previously underexplored internal reasoning process in VLMs, toward improved interpretability and the principled design of more aligned and capable models.

Social Aspects · Everything Else

Tao GUO, Junwei Chen, Laizhong Cui

Pretrained vision-language models (VLMs), such as CLIP, have shown promise in federated learning (FL) by bringing strong multimodal representations to edge devices. However, continual adaptation remains a core challenge in practical federated settings, where task distributions evolve over time and data remain non-IID across clients. In this emerging area, recent works adopt parameter-efficient fine-tuning (PEFT) as a lightweight way to reduce communication overhead, yet they fail to preserve satisfactory performance under continual learning conditions. Meanwhile, traditional federated continual learning (FCL) methods lack the capacity to maintain cross-modal alignment crucial to VLM performance. We introduce Fed-Duet, a novel Dual Expert-orchestrated framework for efficient federated continual learning in vision-language models. Fed-Duet features a dual-expert adaptation mechanism, combining server-coordinated semantic prompts with client-personalized modular adapters. These pathways are dynamically fused via a cross-attention mechanism, enabling effective knowledge transfer while preserving multimodal alignment and mitigating forgetting. We evaluate Fed-Duet across multiple challenging continual learning tasks in federated vision-language settings and demonstrate that it achieves superior performance and stability compared to existing approaches. Our work highlights the importance of coordinated expert composition in enabling scalable and robust multimodal continual learning. The code is available at https://github.com/cocogt96/Fed-Duet.

General Machine Learning · Representation Learning

Omri Uzan, Asaf Yehudai, Roi Pony, Eyal Shnarch, Ariel Gera

Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual tokens directly to image patches and achieving state-of-the-art performance on challenging benchmarks. Recent models relying on this paradigm have massively scaled the dimensionality of their query and document representations, presenting obstacles to deployment and scalability in real-world pipelines. Furthermore, purely vision-centric approaches may be constrained by the inherent modality gap still exhibited by modern vision-language models. In this work, we connect these challenges to the paradigm of hybrid retrieval, investigating whether a lightweight dense text retriever can enhance a stronger vision-centric model. Existing hybrid methods, which rely on coarse-grained fusion of ranks or scores, fail to exploit the rich interactions within each model’s representation space. To address this, we introduce Guided Query Refinement (GQR), a novel test-time optimization method that refines a primary retriever’s query embedding using guidance from a complementary retriever’s scores. Through extensive experiments on visual document retrieval benchmarks, we demonstrate that GQR allows ColPali-based models to match the performance of models with significantly larger representations, while being up to 14x faster and requiring 54x less memory. Our findings show that GQR effectively pushes the Pareto frontier for performance and efficiency in multimodal retrieval. We release our code at https://github.com/IBM/test-time-hybrid-retrieval

Computer Vision · Vision Models & Multimodal

Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin

Human perception for effective object tracking in 2D video streams arises from the implicit use of prior 3D knowledge and semantic reasoning. In contrast, most generic object tracking (GOT) methods primarily rely on 2D features of the target and its surroundings, while neglecting 3D geometric cues, making them susceptible to partial occlusion, distractors, and variations in geometry and appearance. To address this limitation, we introduce GOT-Edit, an online cross-modality model editing approach that integrates geometry-aware cues into a generic object tracker from a 2D video stream. Our approach leverages features from a pre-trained Visual Geometry Grounded Transformer to infer geometric cues from only a few 2D images. To address the challenge of seamlessly combining geometry and semantics, GOT-Edit performs online model editing. By leveraging null-space constraints during model updates, it incorporates geometric information while preserving semantic discrimination, yielding consistently better performance across diverse scenarios. Extensive experiments on multiple GOT benchmarks demonstrate that GOT-Edit achieves superior robustness and accuracy, particularly under occlusion and clutter, establishing a new paradigm for combining 2D semantics with 3D geometric reasoning for generic object tracking. The project page is available at https://chenshihfang.github.io/GOT-EDIT.

Computer Vision · Everything Else

Jing Lin, Ruisi Wang, Junzhe Lu, Ziqi Huang, Guorui Song, AILING ZENG, Xian Liu, Chen Wei, Wanqi Yin, Qingping SUN 等

Despite recent advances in 3D human motion generation (MoGen) on standard benchmarks, existing models still face a fundamental bottleneck in their generalization capability. In contrast, adjacent generative fields, most notably video generation (ViGen), have demonstrated remarkable generalization in modeling human behaviors, highlighting transferable insights that MoGen can leverage. Motivated by this observation, we present a comprehensive framework that systematically transfers knowledge from ViGen to MoGen across three key pillars: data, modeling, and evaluation. First, we introduce ViMoGen-228k, a large-scale dataset comprising 228,000 high-quality motion samples that integrates high-fidelity optical MoCap data with semantically annotated motions from web videos and synthesized samples generated by state-of-the-art ViGen models. The dataset includes both text–motion pairs and text–video–motion triplets, substantially expanding semantic diversity. Second, we propose ViMoGen, a flow-matching-based diffusion transformer that unifies priors from MoCap data and ViGen models through gated multimodal conditioning. To enhance efficiency, we further develop ViMoGen-light, a distilled variant that eliminates video generation dependencies while preserving strong generalization. Finally, we present MBench, a hierarchical benchmark designed for fine-grained evaluation across motion quality, prompt fidelity, and generalization ability. Extensive experiments show that our framework significantly outperforms existing approaches in both automatic and human evaluations. The code, data, and benchmark will be made publicly available.

Deep Learning · Robustness

Hefei Mei, Zirui Wang, Shen You, Minjing Dong, Chang Xu

Large Vision-Language Models (LVLMs) have demonstrated capabilities in multimodal understanding, yet their vulnerability to adversarial attacks raises significant concerns. To achieve practical attacking, this paper aims at efficient and transferable untargeted attacks under limited perturbation sizes. Considering this objective, white‑box attacks require full‑model gradients and task‑specific labels, making costs scale with tasks, while black‑box attacks rely on proxy models, typically requiring large perturbation sizes and elaborate transfer strategies. Given the centrality and widespread reuse of the vision encoder in LVLMs, we adopt a gray‑box setting that targets the vision encoder alone for efficient but effective attacking. We theoretically establish the feasibility of vision‑encoder‑only attacks, laying the foundation for our gray‑box setting. Based on this analysis, we propose perturbing patch tokens rather than the class token, informed by both theoretical and empirical insights. We generate adversarial examples by minimizing the cosine similarity between clean and perturbed visual features, without accessing the subsequent models, tasks, or labels. This significantly reduces computational overhead while eliminating the task and label dependence. VEAttack has achieved a performance degradation of 94.5% on image caption task and 75.7% on visual question answering task. We also reveal some key observations to provide insights into LVLM attack/defense: 1) hidden layer variations of LLM, 2) token attention differential, 3) Möbius band in transfer attack, 4) low sensitivity to attack steps.

Computer Vision · Image and Video Generation

Junhao Chen, Yulia Tsvetkov, Xiaochuang Han

Recent progress in multimodal generation has increasingly combined autoregressive (AR) and diffusion-based approaches, leveraging their complementary strengths: AR models capture long-range dependencies and produce fluent, context-aware outputs, while diffusion models operate in continuous latent spaces to refine high-fidelity visual details. However, existing hybrids often lack systematic guidance on how and why to allocate model capacity between these paradigms. In this work, we introduce $\textit{MADFormer}$, a Mixed Autoregressive and Diffusion Transformer that serves as a testbed for analyzing AR-diffusion trade-offs. $\textit{MADFormer}$ partitions image generation into spatial blocks, using AR layers for one-pass global conditioning across blocks and diffusion layers for iterative local refinement within each block. Through controlled experiments on FFHQ-1024 and ImageNet, we identify two key insights: (1) block-wise partitioning significantly improves performance on high-resolution images, and (2) vertically mixing AR and diffusion layers yields better quality-efficiency balances---improving FID by up to 75\% under constrained inference compute. Our findings offer practical design principles for future hybrid generative models. Code and models will be released upon publication.

Computer Vision · Vision Models & Multimodal

Qiangya Guo, Gang Dai, Zhuoman Liu, Shuangping Huang, Yunqing Hu, Huiyuan Zhang, Tianshui Chen

Computer-Aided Design (CAD), renowned for its flexibility and precision, serves as the foundation of digital design. Recently, some efforts adopt Large Language Models (LLMs) for generating parametric CAD command sequences from text instructions. However, our study reveals that LLMs pre-trained on large-scale general data are not proficient at directly outputting task-specific CAD sequences. Instead of relying on direct generation, we introduce a Plan then Act process where user instructions are first parsed into a chain-like operational plan via an LLM, which is then used to generate accurate command sequences. Specifically, we propose PTA, a new bi-level CAD command sequence generation method. The PTA consists of two critical stages: high-level plan generation and low-level command generation. During the high-level stage, an LLM-based Planner completes the planning process, parsing user instructions into a high-level operation plan. Following this, at the low-level generation stage, we introduce an Actioner equipped with a requirement-aware mechanism to extract design requirements (e.g., dimensions, geometric relationships) from user instructions. This extracted information is used to guide the low-level command sequence generation, improving the alignment of the generated sequences with user requirements. Experimental results demonstrate that our PTA outperforms existing methods in both quantitative and qualitative evaluations. Code is available at https://github.com/QiferG/Plan-then-Act.

Computer Vision · Image and Video Generation

Wanhee Lee, Klemen Kotar, Rahul Venkatesh, Jared Watrous, Honglin Chen, Khai Loong Aw, Daniel Yamins

Understanding 3D scenes requires flexible combinations of visual reasoning tasks, including depth estimation, novel view synthesis, and object manipulation, all of which are essential for perception and interaction. Existing approaches have typically addressed these tasks in isolation, preventing them from sharing a common representation or transferring knowledge across tasks. A conceptually simpler but practically non-trivial alternative is to unify these diverse tasks into a single model, reducing different tasks from separate training objectives to merely different prompts and allowing for joint training across all datasets. In this work, we present a physical world model for unified 3D understanding and interaction 3WM, formulated as a probabilistic graphical model in which nodes represent multimodal scene elements such as RGB, optical flow, and camera pose. Diverse tasks emerge from different inference pathways through the graph: novel view synthesis from RGB and dense flow prompts, object manipulation from RGB and sparse flow prompts, and depth estimation from RGB and camera conditioning, all zero-shot without task-specific training. 3WM outperforms specialized baselines without the need for finetuning by offering precise controllability, strong geometric consistency, and robustness in real-world scenarios, achieving state-of-the-art performance on NVS and 3D object manipulation. Beyond predefined tasks, the model supports composable inference pathways, such as moving objects aside while navigating a 3D environment, enabling complex geometric reasoning. This demonstrates that a unified model can serve as a practical alternative to fragmented task-specific systems, taking a step towards a general-purpose visual world model.

Social Aspects · Trustworthy Machine Learning

Tavish McDonald, Bo Lei, Stanislav Fort, Bhavya Kailkhura, Brian Bartoldson

Models are susceptible to adversarially out-of-distribution (OOD) data despite large training-compute investments into their robustification. Zaremba et al. (2025) make progress on this problem at test time, showing LLM reasoning improves satisfaction of model specifications designed to thwart attacks, resulting in a correlation between reasoning effort and robustness to jailbreaks. However, this benefit of test compute fades when attackers are given access to gradients or multimodal inputs. We address this gap, clarifying that inference-compute offers benefits even in such cases. Our approach argues that compositional generalization, through which OOD data is understandable via its in-distribution (ID) components, enables adherence to defensive specifications on adversarially OOD inputs. Namely, we posit the Robustness from Inference Compute Hypothesis (RICH): inference-compute defenses profit as the model's training data better reflects the attacked data’s components. We empirically support this hypothesis across vision language model and attack types, finding robustness gains from test-time compute if specification following on OOD data is unlocked by compositional generalization. For example, InternVL 3.5 gpt-oss 20B gains little robustness when its test compute is scaled, but such scaling adds significant robustness if we first robustify its vision encoder. This correlation of inference-compute's robustness benefit with base model robustness is the rich-get-richer dynamic of the RICH: attacked data components are more ID for robustified models, aiding compositional generalization to OOD data. Thus, we advise layering train-time and test-time defenses to obtain their synergistic benefit.

Computer Vision · Vision Models & Multimodal

Ashutosh Chaubey, Jiacheng Pang, Maksim Siniukov, Mohammad Soleymani

Emotion understanding is essential for building socially intelligent agents. Although recent multimodal large language models (MLLMs) have shown strong performance on this task, two key challenges remain: (i) spurious associations between emotions and irrelevant audiovisual cues and (ii) hallucination of audiovisual cues driven by text priors in the language model backbone. To quantify and understand these issues, we introduce **EmoReAlM**, a benchmark designed to evaluate MLLMs for cue–emotion associations, hallucinations and modality agreement. We then propose **AVEm-DPO**, a preference optimization technique that aligns model responses with both audiovisual inputs and emotion-centric queries. Specifically, we construct preferences over (i) responses exhibiting spurious associations or hallucinations and (ii) audiovisual input pairs guided by textual prompts. We also include a regularization term that penalizes reliance on text priors, thereby mitigating modality-specific cue hallucinations. Experimental results on DFEW, RAVDESS and EMER demonstrate that our method significantly improves the performance of the reference baseline models (6-19\% of relative performance) in zero-shot settings. By providing both a rigorous benchmark and a robust optimization framework, this work enables principled evaluation and improvement of MLLMs for emotion understanding and social AI.

Computer Vision · Vision Models & Multimodal

Minji Kim, Taekyung Kim, Bohyung Han

Video Large Language Models (VideoLLMs) extend the capabilities of vision-language models to spatiotemporal inputs, enabling tasks such as video question answering (VideoQA). Despite recent advances in VideoLLMs, their internal mechanisms on where and how they extract and propagate video and textual information remain less explored. In this study, we investigate the internal information flow of VideoLLMs using mechanistic interpretability techniques. Our analysis reveals consistent patterns across diverse VideoQA tasks: (1) temporal reasoning in VideoLLMs initiates with active cross-frame interactions in early-to-middle layers, (2) followed by progressive video-language integration in middle layers. This is facilitated by alignment between video representations and linguistic embeddings containing temporal concepts. (3) Upon completion of this integration, the model is ready to generate correct answers in middle-to-late layers. (4) Based on our analysis, we show that VideoLLMs retain their VideoQA performance by selecting these effective information pathways while suppressing a substantial amount of attention edges, e.g., 58% in LLaVA-NeXT-7B-Video-FT. These findings provide a blueprint for how VideoLLMs perform temporal reasoning and offer practical insights for improving model interpretability and downstream generalization.

Computer Vision · Vision Models & Multimodal

Qi Zhang, Suvam Bag, Rupanjali Kukal, Mikael Figueroa, Rishi Madhok, Nikolaos Karianakis, Fuxun Yu

Map generation tasks feature extensive non-structural *vectorized data* (e.g., points, polylines, and polygons) and thus pose significant challenges to common pixel-wise generative models. Conventional approaches use multiple stages, first segmenting these features at the pixel level and then performing vectorized post-processing, with errors and complexity compounding at each stage. Motivated by the recent success of auto-regressive language modeling, we propose the first map foundation model, named Map Auto-Regressor (MARS), that is capable of generating both multi-polyline road networks and polygon buildings in a unified manner. For training MARS, we collected to our knowledge the largest multi-class map extraction dataset totaling 3.4M examples, which we call MAP-3M. Across four road and building datasets, MARS outperforms or matches the performance of multistage baselines. Additionally, we develop a ``Chat with MARS'' capability that enables interactive human-in-the-loop map generation and correction, supported by the auto-regressive nature of our end-to-end approach. We release our MAP-3M dataset and project demo page at (1) https://huggingface.co/datasets/bag-lab/MAP-3M and (2) https://huggingface.co/spaces/bag-lab/MARS, respectively.