Diagnosis by Composition: Detecting and Localizing Unseen Diseases by Composing Learned Radiological Findings
Kaihua Hou, Wei Liu, Yi Huang, Hao Zhang, Haibo Jin, Yifei Sun, Yuan gao, Zuoou Li 等 13 位作者
AI 速览：提出诊断即组合（DbC）框架，通过学习放射学征象词汇并依据指南组合征象图来诊断和定位未见疾病，在肝脏CT上优于对比方法。
Deep models for radiological diagnosis are typically trained to predict disease labels directly from images, which limits them to diseases seen during training and makes their decisions hard to interpret in radiologists' terms. Radiology, however, proceeds from visual findings to disease through published guidelines that make this decision rule explicit, interpretable, and reproducible. We introduce diagnosis by composition (DbC), a representation learning framework that encodes this findings-first logic. DbC learns a vocabulary of radiological findings by aligning image features with the text embeddings of the findings, each finding represented as a dense map over the scan. A disease is defined by a set of required findings derived from its guidelines, and its diagnosis map is a fixed, parameter-free composition of the corresponding finding maps. Because the finding-to-disease mapping is derived from guidelines rather than learned, DbC is interpretable and auditable by design, can extend to new diseases by specifying their findings without retraining, and can diagnose unseen diseases by composing their findings. On multi-phase liver CT, DbC detects and localizes unseen diseases, rare diseases from a different institution, and an external cohort significantly better than all comparators, including models that align images with disease names. DbC also improves detection and localization in the fully supervised setting and remains superior across training-set sizes. Although demonstrated on liver CT, DbC applies wherever radiological guidelines define diseases through findings.
Junfeng Wang, Jiawei Liu, Yongchao Xu, Tao Jiang, Jiangbo Ai, Jin Zhang, Chong Wang, Qixing Zhang
Complex visual question answering often requires vision-language models to think with images, i.e., actively acquire local visual evidence by zooming into informative regions of high-resolution images. Our error analysis shows that many failures in this setting originate from incorrect observation actions, where the model fails to localize key regions or obtain crops that contain sufficient evidence for answering. We further observe that bounding-box tokens exhibit substantially higher generation entropy than ordinary language tokens, indicating high uncertainty when the model decides where to look. However, existing reinforcement learning methods based on final-answer rewards provide only trajectory-level feedback, making it difficult to assign precise credit to the observation actions. We propose Observation Policy Optimization (OPO), an RL algorithm for optimizing observation actions in tool-augmented thinking with images. OPO consists of two core modules. First, Uncertainty-Guided Observation Branching (UOB) treats each image zoom-in tool call as an observation event and selectively branches at high-uncertainty, low-redundancy events during rollout, enabling efficient exploration of alternative cropping decisions and their resulting visual evidence. Second, Evidence-Localized Advantage Attribution (ELAA) compares sibling branches using local evidence-sufficiency rewards and assigns credit only to the corresponding observation-action tokens. By decoupling observation-action optimization from trajectory-level outcome supervision, OPO improves visual evidence acquisition and further enhances visual reasoning performance. Experiments show that OPO consistently improves Qwen3-VL models across scales and achieves competitive performance against larger models and tool-augmented baselines. Code is publicly available.
Yujiao Shen, Jiahe Song, Haitian Li, Jingkang Yang, Ziwei Liu
Learning from human data offers a scalable path toward embodied intelligence, yet it requires models to accurately understand fine-grained human actions from egocentric observations. However, existing benchmarks remain limited in action atomicity, temporal precision, and hand-action association. We introduce EgoActionBench, a benchmark that represents continuous human manipulation as temporally localized atomic actions associated with the left hand, right hand, or both hands. EgoActionBench contains 1,407 episodes with 41,132 human-refined action annotations. To evaluate such dense predictions, we propose an evaluation protocol that retrieves temporally eligible candidates, selects a prediction by content agreement, and scores semantic fidelity and temporal overlap alongside action precision and recall, jointly capturing what happens, when it happens, and which hand performs it. We benchmark 20 baseline models and systems on EgoActionBench and further adapt two backbones, Qwen3-VL-4B and LLaVA-OneVision-2-8B, through supervised fine-tuning followed by reinforcement learning on automatically annotated training episodes. EgoAction improves EgoActionScore by 15.9 and 23.2 points on the two backbones, and both adapted models outperform all open-source baselines. Our experiments reveal substantial limitations of current models in action atomicity, temporal precision, and hand-action association, highlighting the gap between general video understanding and the action understanding required for embodied intelligence.
World models (WMs) have demonstrated strong potential for end-to-end autonomous driving by learning predictive representations of future scene dynamics. However, generating future videos during inference introduces substantial computational overhead, leading many recent driving WMs to adopt a single front camera as input for efficient deployment. This design restricts spatial coverage in safety-critical maneuvers such as lane changes, merges, and turns. To address this limitation, we propose SV-WAM, a surround-view world-action model (WAM) that preserves full six-camera observations while maintaining efficient inference. SV-WAM leverages future-video prediction as dense training supervision for action learning within a shared generative model, rather than as an inference-time output. At the core of this design is an action-centered causal mask that prevents action tokens from attending to future-video tokens during joint action-video denoising. Consequently, the video branch can be discarded at deployment, enabling efficient action-only planning. Furthermore, we introduce a differentiable drivable-area compliance regularizer that penalizes vehicle-footprint corners approaching or crossing drivable boundaries, improving planning safety and boundary awareness. Extensive experiments on the closed-loop NAVSIMv2 benchmark and the open-loop nuScenes benchmark demonstrate that SV-WAM achieves state-of-the-art planning performance with low inference latency and competitive zero-shot transfer capability.
Bo Gou, Jicheng Zhang, Jianlong Xiong, Tao He, Hai Wu, Bentian Liu, Yijiao Wang, Yu Zhang 等 13 位作者
Automated classification of standard echocardiographic views is crucial for efficient clinical workflow but faces three main challenges. First, publicly available datasets are scarce and limited in scale and view coverage. Second, the performance of some modern video-level architectures for echocardiographic view classification remains underexplored. Third, some view categories exhibit highly similar spatial appearances, making single-frame features insufficient for discrimination, while heterogeneous frame quality complicates robust temporal information fusion. To address these challenges, we release the Echocardiographic Videos of Nine Views (EV9V) dataset, comprising 5,138 videos, 910,579 frames, and 9 standard views, which is, to the best of our knowledge, the largest openly released echocardiography video dataset. Furthermore, we propose a Spatio-Temporal Fusion Model (STFM), an efficient dual-stream framework that jointly captures spatial anatomical structures and temporal cardiac dynamics. The STFM leverages uncertainty-aware learning to preferentially sample representative video segments during training and evidence-based fusion during inference, improving robustness to variations in frame quality across echocardiographic videos. Extensive experiments demonstrate that STFM achieves competitive performance and effectiveness compared with diverse video classification architectures, including two-dimensional and three-dimensional convolutional neural networks, recurrent neural networks, and Transformers. The code is released at https://huggingface.co/datasets/bgx666/EV9V and the EV9V dataset is available at https://github.com/bgx666/stfm.
Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers
Jiongfan Yang, Weichen Fan, Haiwen Diao, Zhongang Cai, Ziwei Liu
AI 速览：SpecSlot通过将每个空间锚点拆成多个按DCT频带分工的slot，让全局注意力只处理低频slot、高频细节在局部交互，从而在不加长全局序列的前提下提升像素空间生成式Transformer的细节建模能力。
Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expensive. We observe that finer detail does not necessarily require more global communication: low-frequency structure benefits from global exchange, while high-frequency detail can be modeled locally. Based on this insight, we introduce SpecSlot, a pixel-space rectified-flow Transformer that decouples output detail from the length of the global attention sequence. SpecSlot expands each spatial anchor into multiple slots, each assigned a disjoint band of DCT coefficients; this separates anchor density from spectral subdivision. Only the lowest-frequency slot from each anchor participates in global attention, while all slots interact locally. This allows the model to increase spectral detail without enlarging the global sequence. A spatial head further adds a local correction to the spectral prediction, while the generative state, target, and loss remain in pixel space. On ImageNet-256, SpecSlot achieves a comparable final FID to a FLOPs-matched JiT control while converging faster. On ImageNet-512, it improves FID by 2.84 over the control with 3.9% fewer FLOPs, and comes within only 0.69 FID of JiT-B/16 at 38.2% lower cost. On text-to-image generation, SpecSlot surpasses JiT-B/8 on DPG-Bench by 1.06 at 40.6% lower forward cost.
Probing Spatial State Representations in Visual Foundation Models
Baiqiao Yin, Zhongang Cai, Ruisi Wang, Qiwei Liang, Lei Yang, Ziwei Liu
AI 速览：该研究通过四个层级的冻结特征探针，检验视觉基础模型在流式自我中心观测下是否具备可维持、可预测更新并可用于目标导向动作的空间状态表征。
An observer sees only part of the surrounding world, yet must keep track of what lies beyond the current view. Spatial perception therefore involves more than recognizing individual images: it calls for a persistent spatial state that is updated under self-motion and used to guide action. Do visual foundation models provide representations that support such a state? We study this question through four levels of spatial capability---spatial structure, object persistence, predictive spatial update, and actionability---using frozen-feature probes on ten representations under streaming egocentric observations of static indoor environments. The resulting capability profiles vary across tasks, network layers, and prefix lengths: strong readout of the visible scene does not ensure accurate object persistence or future-feature retrieval. Matched controls separate readout accuracy from reliance on visual history and motion. Native future prediction retains recoverable spatial structure, but a spatial reader trained on real features does not transfer to predicted features unchanged. Finally, goal-dependent candidate selection does not establish reliable continuous action utility: predicted actions respond to goal changes, yet supplying the correct goal does not reliably improve progress. Across the four levels, object persistence and actionability build on camera-pose readout, whereas feature prediction builds on visible-scene readout. Together, these findings motivate evaluating spatial representations not only by what can be decoded from them, but by whether that information is maintained beyond observation, updated predictively, and used for goal-directed action.
Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback enable coherent, controllable multi-shot videos. In parallel, video world models provide action-conditioned observations and predicted futures, serving as interactive environments for agents. We study their intersection through the agent harness: an executable runtime that constructs context, exposes tools, maintains state, routes feedback, and manages budgets around video models. This report examines three directions. First, agentic video generation, where harnesses coordinate scripting, shot planning, asset management, production, and editing, alongside the evaluation challenges of these systems. Second, agentic world modeling, where harnesses mediate observation, control, execution, and state. We discuss hybrid designs in which game engines or agent-written programs maintain world state while video models render observations, and how agents and world models can mutually evaluate and improve one another. Third, recursive self-improvement (RSI) in video model development, distinguishing output revisions, updates to harness state, generator parameters, and evaluators, and changes to the improvement procedure itself. We identify how these improvements feed back into subsequent development. Across these directions, we analyze essential agent capabilities, including audiovisual perception, long-horizon planning, memory, code-based interaction, feedback-guided control, skill reuse, and multi-agent coordination. We conclude with challenges in autonomous video production, lifelong memory, programmable hybrid control, autonomous model development, provenance, cost accounting, and evaluation linking video quality and task performance to sustained improvements in models and harnesses.
An Lanji, Dawei Liu, Jin Li, Haoran Xu, Mei Chen, Yu Tian
Diffusion transformers (DiTs) have become the dominant architecture for high-fidelity image synthesis, yet they suffer from slow training convergence and high computational cost. Two recent lines of work address this from complementary angles: Representation Alignment (REPA) accelerates DiT training by aligning intermediate features with a pretrained external representation model (e.g., DINOv2), while Representation Auto-Encoders (RAE) replace the pixel-space VAE with a compact representation-space tokenizer learned from self-supervised features. However, these approaches are developed and applied in isolation: REPA still relies on a pixel-space VAE for latent diffusion, and RAE does not exploit the alignment signal that accelerates the diffusion backbone. We present \textbf{UniRA}, a unified framework that couples representation alignment and representation auto-encoding into a single objective. UniRA learns a representation-space tokenizer whose output serves simultaneously as the diffusion target and the alignment anchor, so the tokenizer, the diffusion backbone, and the external representation model are co-optimized. We give a theoretical result showing that this joint optimization preserves the representation quality of the external model while accelerating diffusion convergence, and we derive a principled weighting that balances the reconstruction, alignment, and generation objectives. On ImageNet class-conditional generation at 256*256 and 512*512, UniRA matches or surpasses state-of-the-art DiTs (SD3, REPA, RAE) in FID while reducing training steps by up to 5*. We further show that the unified representation space supports improved zero-shot classification and linear probing, confirming that generation and understanding benefit from a shared, aligned latent space.
Xuanang Gao, Zhiwei Ning, Gengming Zhang, Jiaxi Cao, Runze Yang, Zhonglong Zheng, Jie Yang, Rong Xiao 等 9 位作者
Robust depth estimation aims to maintain high-quality depths across diverse conditions. However, most existing methods estimate depth without taking into account the object-level information. As a result, the predicted depth may easily deviate within objects and become blurred under adverse conditions. To overcome this weakness, we propose RoSAMDepth, a novel framework that can assist robust self-supervised depth estimation in leveraging rich and diverse object-level priors from the Segment Anything Model (SAM). We focus on incorporating object-level information across three key aspects: a segment-guided representation contrasting method that injects object-level awareness into the feature representation space; an adaptive regional outlier masking strategy combined with a regional Gaussian likelihood loss that enforces regional depth smoothness; and an object-level reliability estimation strategy that mitigates the influence of unreliable supervision. Extensive experiments across multiple datasets and diverse weather conditions demonstrate that our method produces sharper, more accurate depth predictions, consistently outperforming state-of-the-art methods. Our code is available at https://github.com/xagao/RoSAMDepth.
Bingchao Wang, Yongcheng Jing, Shunyu Liu, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng Tao
Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each action as text. However, these VLMs decode every action token by token, and even agents that score candidate actions keep a large language model or VLM in the loop, making them slow and memory-hungry. To address these issues, we propose GUI-JEPA, to our knowledge the first decoder-free GUI agent policy built on a Joint-Embedding Predictive Architecture (JEPA), which selects actions in the latent space of a JEPA encoder pretrained on unlabelled GUI screenshots. Its action- and region-conditioned latent predictor turns the screen latent into one latent per candidate action, letting lightweight heads score all candidates against the instruction in a single batched pass, without decoding a token. We further show that the scorer relies on this latent pathway and that the predictor is trained for the decision itself: a randomly initialised predictor does just as well as one pretrained on screen dynamics. On AndroidControl, GUI-JEPA is 2.8-4.0x faster on the same GPU than a Qwen2.5-VL-7B agent we fine-tune with the same inputs, while reaching 86-92% of its in-distribution accuracy with 6% of its parameters. Code is available at https://github.com/bcwang-sjtu/GUI-JEPA
Bingchao Wang, Yongcheng Jing, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng Tao
GUI grounding on high-resolution screens fails mostly on small targets, and zooming in is a common training-free remedy. However, most existing zooming pipelines do not match the zoom to the target's size, accept the zoomed answer unconditionally and never revisit a wrong answer. To address these issues, we propose AdaGround, a training-free framework with three components: (1) Token-Normalized Adaptive Zooming, which sets the magnification, field of view and zoom depth of each sample from the model's own estimate of the target size; (2) Verifier-in-the-Loop Refinement, which uses one marked-click Yes/No verifier to keep or reject each zoom, choose between zoom chains, trigger re-grounding and, with an existence query, decide when to abstain; and (3) Compositional Structure Grounding, which composes spreadsheet cells from their headers. On Qwen3-VL models, AdaGround surpasses state-of-the-art training-free zooming methods and many trained GUI models, improving accuracy over the backbone by 7.4 to 20.6 points on OSWorld-G and ScreenSpot-Pro, and its gains carry over to held-out UI-Vision. Code is available at https://github.com/bcwang-sjtu/AdaGround
The space of possible visual content is enormous, and arguably unbounded. Any training set, however large, therefore covers only a tiny fraction of it. Yet generative models are typically trained to fit only the images they are given. In visual autoregressive (AR) generation, for example, each token is predicted from the preceding ground-truth (GT) tokens and supervised solely by the GT next token. Confining learning to observed data in this way limits how much of the visual distribution a model can capture. In this work, we hypothesize that letting a model imagine beyond its training data, by exploring plausible visual realizations it has never observed, can ease this limitation. We use visual AR generation as a proof of concept, since its fixed, discrete token space makes imagination easier to steer and constrain. We propose Next Token Imagination (NTI), a method that allows the model to explore beyond the GT next token, subject to a carefully designed criterion that keeps this imagination bounded by the underlying visual distribution. Extensive experiments on ImageNet show that NTI substantially and consistently improves the fidelity of generated images, approaching state-of-the-art diffusion and AR models while using a smaller model and lower training cost.
Xing Liu, Yifan Guo, Hongtai Lv, Lei Lou, Yuyi Tan, Jiang Du, Xijia Zhang, Ming Zhang 等 21 位作者
Intraoperative frozen-section diagnosis of central nervous system (CNS) lesions guides surgical decisions but is challenged by artefacts, diagnostic complexity and time constraints. Most pathology foundation models have limited exposure to CNS frozen tissue. Here we present FOCUS, a subspecialty foundation model pretrained on 27,930 frozen-section whole-slide images enriched for CNS tissue. FOCUS ranked first across all 11 diagnostic and 12 biomarker-prediction tasks in the internal test cohort, achieving mean AUCs of 0.969 and 0.877, respectively. This advantage was retained in the temporal and external test cohorts. We further organized a WHO-aligned diagnostic hierarchy, where FOCUS also outperformed comparator models. In a reader study, FOCUS assistance enabled junior readers to approach or exceed unassisted senior readers in hierarchical diagnostic accuracy and granularity. More importantly, FOCUS assistance enabled readers to correctly identify a mean of 63.0% of initially missed lymphoma cases (73.2% among junior readers), potentially avoiding unnecessary extensive resection. These findings highlight the potential of FOCUS to provide clinically actionable support for intraoperative CNS pathology and inform surgical decisions.
Physical understanding and reasoning depend on forming compact and generalizable representations of the world. While modern vision-language models can recognize and explain diverse physical events, they often lack explicit representations of the underlying mechanisms-such as object states, physical parameters, and governing dynamics-needed for reliably reasoning how the world evolves and responds to interventions. In this work, we introduce Code-as-World, a paradigm that represents physical worlds through executable world representations. By expressing physical composition, dynamic evolution, and visual appearance as executable code, Code-as-World provides a compact, quantitatively grounded, and controllable abstraction of the physical world. To construct such representations from multimodal observations, such as natural-language descriptions or real-world videos, we develop an agentic discovery loop inspired by abductive reasoning, where an agent proposes, executes, renders, verifies, and iteratively refines executable world hypotheses. As a concrete application, we use verified executable worlds to provide scalable physical supervision for training vision-language models on quantitative physical reasoning. Experiments show that Code-as-World-VL achieves state-of-the-art performance on QuantiPhy and surpasses leading proprietary models, highlighting the potential of executable world representations as a scalable foundation for physical intelligence.
Jinming Wu ByteDance Inc., Zihao Deng, Wei Li Bytedance, Yiding Liu Tiktok, Bo You ByteDance Inc., Bo Li, Zejun MA TikTok, Ziwei Liu Nanyang Technological University
Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information. Existing approaches such as retrieval-augmented generation (RAG) and prompt engineered search agents rely on rigid pipelines, often leading to inefficient or excessive search behaviors. We present MMSearch-R1, the first end-to-end reinforcement learning framework that enables LMMs to perform on-demand, multi-turn search in real-world Internet environments. Our framework integrates both image and text search tools, allowing the model to reason about when and how to invoke them guided by an outcome-based reward with a search penalty. To support training, We collect a multimodal search VQA dataset through a semi-automated pipeline that covers diverse visual and textual knowledge needs and curate a search-balanced subset with both search-required and search-free samples, which proves essential for shaping efficient and on-demand search behavior. Extensive experiments on knowledge-intensive and info-seeking VQA tasks show that our model not only outperforms traditional RAG-based baselines of the same model size, but also matches the performance of a larger RAG-based model while reducing search calls by over 30%. We further analyze key empirical findings to offer actionable insights for advancing research in multimodal search.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Kairui Hu Nanyang Technological University, Penghao Wu Nanyang Technological University, Fanyi Pu, Wang Xiao, Xiang Yue Carnegie Mellon University, Bo Li, Yuanhan Zhang, Ziwei Liu Nanyang Technological University
Humans acquire knowledge through three cognitive stages: perceiving information, comprehending knowledge, and adapting knowledge to solve novel problems. Videos serve as an effective medium for knowledge acquisition, facilitating a natural progression through these learning stages. However, existing video benchmarks fail to evaluate the knowledge acquisition capabilities of Large Multimodal Models (LMMs). To address this gap, we introduce Video-MMMU, a multi-modal, multi-discipline, multi-track benchmark that evaluates LMMs’ ability to acquire knowledge from college-level, educational videos. Video-MMMU features a collection of 300 videos and 900 human-annotated questions across six disciplines, evaluating knowledge acquisition through stage-aligned question-answer pairs: Perception, Comprehension, and Adaptation. Beyond measuring final accuracy, Video-MMMU proposes the performance gain metric that quantifies an LMM’s learning gain from video, shifting the focus of evaluation from absolute performance to learning efficiency. Our evaluation reveals a substantial gap between human learners and current LMMs, highlighting the need to improve models’ ability to learn and adapt knowledge from video content.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Shuang Cheng, Yuhua Jiang, Zineng Zhou, Dawei Liu Shanghai Jiao Tong University and Shanghai Artificial Intelligence Laboratory, Tao Wang Bytedance group, Linfeng Zhang Shanghai Jiaotong University, Biqing Qi University of Hong Kong and Shanghai Artificial Intelligence Laboratory, Bowen Zhou Tsinghua University
Block-wise discrete diffusion offers an attractive balance between parallel generation and causal dependency modeling, making it a promising backbone for vision-language modeling. However, its practical adoption has been limited by high training cost, slow convergence, and instability, which have so far kept it behind strong autoregressive (AR) baselines. We present SDAR-VL, the first systematic application of block-wise discrete diffusion to large-scale vision-language understanding (VLU), together with an integrated framework for efficient and stable training. This framework unifies three components: 1) Asynchronous Block-wise Noise Scheduling to diversify supervision within each batch; 2) Effective Mask Ratio Scaling for unbiased loss normalization under stochastic masking; and 3) a Progressive Beta Noise Curriculum that increases effective mask coverage while preserving corruption diversity. Experiments on 21 single-image, multi-image, and video benchmarks show that SDAR-VL consistently improves training efficiency, convergence stability, and task performance over conventional block diffusion. On this evaluation suite, SDAR-VL sets a new state of the art among diffusion-based vision-language models and, under matched settings, matches or surpasses strong AR baselines such as LLaVA-OneVision as well as the global diffusion baseline LLaDA-V, establishing block-wise diffusion as a practical backbone for VLU.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Kai Zou, Ziqi Huang, Yuhao Dong, Shulin Tian Nanyang Technological University, Dian Zheng The Chinese University of Hong Kong, Hongbo Liu, Jingwen He, Bin Liu University of Science and Technology of China 等 10 位作者
Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that inherently couple them. To address this gap, we present Uni-MMMU, a comprehensive and discipline-aware benchmark that systematically unfolds the bidirectional synergy between generation and understanding across eight reasoning-centric domains, including science, coding, mathematics, and puzzles. Each task is bidirectionally coupled, demanding models to (i) leverage conceptual understanding to guide precise visual synthesis, or (ii) utilize generation as a cognitive scaffold for analytical reasoning. Uni-MMMU incorporates verifiable intermediate reasoning steps, unique ground truths, and a reproducible scoring protocol for both textual and visual outputs. Through extensive evaluation of state-of-the-art unified, generation-only, and understanding-only models, we reveal substantial performance disparities and cross-modal dependencies, offering new insights into when and how these abilities reinforce one another, and establishing a reliable foundation for advancing unified models.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Shuhang Chen, Hangjie Yuan DAMO Academy, Alibaba Group, Yunqiu Xu National University of Singapore, Pengwei Liu, Tao Feng Tsinghua University, Tsinghua University, Jun Cen Alibaba Group, Zeying Huang Intelligent Learning Tech(Zhejiang), Yi Yang Zhejiang University
Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially in reliably perceiving and interpreting diagrams. Inspired by human problem-solving, we hypothesize that the ability to extract meaningful information from diagrams is pivotal, as it directly conditions subsequent inference.Hence, we introduce FlowVerse, a comprehensive benchmark that provides a fine-grained evaluation of MLLMs’ perception and reasoning capabilities. Our preliminary results on FlowVerse reveal that existing MLLMs exhibit substantial limitations when extracting essential information and reasoned properties from diagrams and performing complex reasoning based on these visual inputs. In response, we introduce MathFlow, a modular problem-solving pipeline that decouples perception and inference into distinct stages, thereby optimizing each independently. Given the perceptual limitations observed in current MLLMs, we trained MathFlow-P-7B as a dedicated perception model.Experimental results indicate that MathFlow-P-7B yields substantial performance gains when integrated with various closed-source and open-source inference models. This demonstrates the effectiveness of the MathFlow pipeline and its compatibility with diverse inference frameworks. Project page: https://github.com/MathFlow-zju/MathFlow.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Xueqing Peng Yale University, Lingfei Qian Yale University, Yan Wang Yale University, Ruoyu Xiang, Yueru He Columbia University, Yang Ren Yale University, Mingyang Jiang, Vincent Jim Zhang 等 47 位作者
Real-world financial analysis involves information across multiple languages and modalities, from reports and news to scanned filings and meeting recordings. Yet most existing evaluations of LLMs in finance remain text-only, monolingual, and largely saturated by current models. To bridge these gaps, we present MultiFinBen, the first expert-annotated multilingual (five languages) and multimodal (text, vision, audio) benchmark for evaluating LLMs in realistic financial contexts. MultiFinBen introduces two new task families: multilingual financial reasoning, which tests cross-lingual evidence integration from filings and news, and financial OCR, which extracts structured text from scanned documents containing tables and charts. Rather than aggregating all available datasets, we apply a structured, difficulty-aware selection based on advanced model performance, ensuring balanced challenge and removing redundant tasks. Evaluating 21 leading LLMs shows that even frontier multimodal models like GPT-4o achieve only 46.01% overall, stronger on vision and audio but dropping sharply in multilingual settings. These findings expose persistent limitations in multilingual, multimodal, and expert-level financial reasoning. All datasets, evaluation scripts, and leaderboards are publicly released.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表