Multimodal Grounding

Large Multimodal Models (LMMs) have achieved remarkable progress in general-purpose vision--language understanding, yet they remain limited in tasks requiring precise object-level grounding, fine-grained spatial reasoning, and controllable visual manipulation. In particular, existing systems often struggle to identify the correct instance, preserve object identity across interactions, and localize or modify designated regions with high precision. Object-centric vision provides a principled framework for addressing these challenges by promoting explicit representations and operations over visual entities, thereby extending multimodal systems from global scene understanding to object-level understanding, segmentation, editing, and generation. This paper presents a comprehensive review of recent advances at the convergence of LMMs and object-centric vision. We organize the literature into four major themes: object-centric visual understanding, object-centric referring segmentation, object-centric visual editing, and object-centric visual generation. We further summarize the key modeling paradigms, learning strategies, and evaluation protocols that support these capabilities. Finally, we discuss open challenges and future directions, including robust instance permanence, fine-grained spatial control, consistent multi-step interaction, unified cross-task modeling, and reliable benchmarking under distribution shift. We hope this paper provides a structured perspective on the development of scalable, precise, and trustworthy object-centric multimodal systems.

Recent agentic search frameworks enable deep research via iterative planning and retrieval, reducing hallucinations and enhancing factual grounding. However, they remain text-centric, overlooking the multimodal evidence that characterizes real-world expert reports. We introduce a pressing task: multimodal long-form generation. Accordingly, we propose Deep-Reporter, a unified agentic framework for grounded multimodal long-form generation. It orchestrates: (i) Agentic Multimodal Search and Filtering to retrieve and filter textual passages and information-dense visuals; (ii) Checklist-Guided Incremental Synthesis to ensure coherent image-text integration and optimal citation placement; and (iii) Recurrent Context Management to balance long-range coherence with local fluency. We develop a rigorous curation pipeline producing 8K high-quality agentic traces for model optimization. We further introduce M2LongBench, a comprehensive testbed comprising 247 research tasks across 9 domains and a stable multimodal sandbox. Extensive experiments demonstrate that long-form multimodal generation is a challenging task, especially in multimodal selection and integration, and effective post-training can bridge the gap.

Effective foundation modeling in remote sensing requires spatially aligned heterogeneous modalities coupled with semantically grounded supervision, yet such resources remain limited at scale. We present GeoMeld, a large-scale multimodal dataset with approximately 2.5 million spatially aligned samples. The dataset spans diverse modalities and resolutions and is constructed under a unified alignment protocol for modality-aware representation learning. GeoMeld provides semantically grounded language supervision through an agentic captioning framework that synthesizes and verifies annotations from spectral signals, terrain statistics, and structured geographic metadata, encoding measurable cross-modality relationships within textual descriptions. To leverage this dataset, we introduce GeoMeld-FM, a pretraining framework that combines multi-pretext masked autoencoding over aligned modalities, JEPA representation learning, and caption-vision contrastive alignment. This joint objective enables the learned representation space to capture both reliable cross-sensor physical consistency and grounded semantics. Experiments demonstrate consistent gains in downstream transfer and cross-sensor robustness. Together, GeoMeld and GeoMeld-FM establish a scalable reference framework for semantically grounded multi-modal foundation modeling in remote sensing.

Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose object grounding and tracking into separated modules and exhibit limited performance due to the scarcity of training videos, ambiguous annotations, and restricted domains. In this work, we introduce STORM, an end-to-end MLLM that jointly performs grounding and tracking within a unified framework, eliminating external detectors and enabling coherent reasoning over appearance, motion, and language. To improve data efficiency, we propose a task-composition learning (TCL) strategy that decomposes RMOT into image grounding and object tracking, allowing STORM to leverage data-rich sub-tasks and learn structured spatial--temporal reasoning. We further construct STORM-Bench, a new RMOT dataset with accurate trajectories and diverse, unambiguous referring expressions generated through a bottom-up annotation pipeline. Extensive experiments show that STORM achieves state-of-the-art performance on image grounding, single-object tracking, and RMOT benchmarks, demonstrating strong generalization and robust spatial--temporal grounding in complex real-world scenarios. STORM-Bench is released at https://github.com/amazon-science/storm-referring-multi-object-grounding.

Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchmarks. However, we observe that accuracy gains often come at the cost of reasoning quality: generated Chain-of-Thought (CoT) traces are frequently inconsistent with the final answer and poorly grounded in the visual evidence. We systematically study this phenomenon across seven challenging real-world spatial reasoning benchmarks and find that it affects contemporary MRMs such as ViGoRL-Spatial, TreeVGR as well as our own models trained with standard Group Relative Policy Optimization (GRPO). We characterize CoT reasoning quality along two complementary axes: "logical consistency" (does the CoT entail the final answer?) and "visual grounding" (does each reasoning step accurately describe objects, attributes, and spatial relationships in the image?). To address this, we propose Faithful GRPO (FGRPO), a variant of GRPO that enforces consistency and grounding as constraints via Lagrangian dual ascent. FGRPO incorporates batch-level consistency and grounding constraints into the advantage computation within a group, adaptively adjusting the relative importance of constraints during optimization. We evaluate FGRPO on Qwen2.5-VL-7B and 3B backbones across seven spatial datasets. Our results show that FGRPO substantially improves reasoning quality, reducing the inconsistency rate from 24.5% to 1.7% and improving visual grounding scores by +13%. It also improves final answer accuracy over simple GRPO, demonstrating that faithful reasoning enables better answers.

Large Multimodal Models (LMMs) achieve state-of-the-art performance in high-stakes domains like healthcare, yet their reasoning remains opaque. Current interpretability methods, such as attention mechanisms or post-hoc saliency, often fail to faithfully represent the model's decision-making process, particularly when integrating heterogeneous modalities like time-series and text. We introduce Tree-of-Evidence (ToE), an inference-time search algorithm that frames interpretability as a discrete optimization problem. Rather than relying on soft attention weights, ToE employs lightweight Evidence Bottlenecks that score coarse groups or units of data (e.g., vital-sign windows, report sentences) and performs a beam search to identify the compact evidence set required to reproduce the model's prediction. We evaluate ToE across six tasks spanning three datasets and two domains: four clinical prediction tasks on MIMIC-IV, cross-center validation on eICU, and non-clinical fault detection on LEMMA-RCA. ToE produces auditable evidence traces while maintaining predictive performance, retaining over 0.98 of full-model AUROC with as few as five evidence units across all settings. Under sparse evidence budgets, ToE achieves higher decision agreement and lower probability fidelity error than other approaches. Qualitative analyses show that ToE adapts its search strategy: it often resolves straightforward cases using only vitals, while selectively incorporating text when physiological signals are ambiguous. ToE therefore provides a practical mechanism for auditing multimodal models by revealing which discrete evidence units support each prediction.

The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to transition from simple perception to autonomous execution, yet current evaluations fail to reflect the rigorous demands of real-world manufacturing environments. Progress is hindered by data scarcity and a lack of fine-grained domain semantics in existing datasets. To bridge this gap, we introduce FORGE. Wefirst construct a high-quality multimodal dataset that combines real-world 2D images and 3D point clouds, annotated with fine-grained domain semantics (e.g., exact model numbers). We then evaluate 18 state-of-the-art MLLMs across three manufacturing tasks, namely workpiece verification, structural surface inspection, and assembly verification, revealing significant performance gaps. Counter to conventional understanding, the bottleneck analysis shows that visual grounding is not the primary limiting factor. Instead, insufficient domain-specific knowledge is the key bottleneck, setting a clear direction for future research. Beyond evaluation, we show that our structured annotations can serve as an actionable training resource: supervised fine-tuning of a compact 3B-parameter model on our data yields up to 90.8% relative improvement in accuracy on held-out manufacturing scenarios, providing preliminary evidence for a practical pathway toward domain-adapted manufacturing MLLMs. The code and datasets are available at https://ai4manufacturing.github.io/forge-web.

Understanding dynamic 4D environments through natural language queries requires not only accurate scene reconstruction but also robust semantic grounding across space, time, and viewpoints. While recent methods using neural representations have advanced 4D reconstruction, they remain limited in contextual reasoning, especially for complex semantics such as interactions, temporal actions, and spatial relations. A key challenge lies in transforming noisy, view-dependent predictions into globally consistent 4D interpretations. We introduce PanopticQuery, a framework for unified query-time reasoning in 4D scenes. Our approach builds on 4D Gaussian Splatting for high-fidelity dynamic reconstruction and introduces a multi-view semantic consensus mechanism that grounds natural language queries by aggregating 2D semantic predictions across multiple views and time frames. This process filters inconsistent outputs, enforces geometric consistency, and lifts 2D semantics into structured 4D groundings via neural field optimization. To support evaluation, we present Panoptic-L4D, a new benchmark for language-based querying in dynamic scenes. Experiments demonstrate that PanopticQuery sets a new state of the art on complex language queries, effectively handling attributes, actions, spatial relationships, and multi-object interactions. A video demonstration is available in the supplementary materials.

In science education, students frequently construct hand-drawn visual models of scientific phenomena. These drawings rely on a visual structure where information is encoded through visual objects, their attributes, and relationships. Multimodal large language models (MLLMs) are increasingly used to generate feedback on students' hand-drawn scientific models. However, the validity of such feedback depends on whether model claims are grounded in the specific visual evidence of the student drawing. This study uncovers grounding failures, consistent with modal decoupling, in off-the-shelf MLLM feedback, where outputs remain pedagogically plausible in form while contradicting the drawing or treating depicted elements as missing. Using N = 150 middle school drawings from a kinetic molecular theory unit spanning five modeling tasks and three competence levels, we generated N = 300 feedback instances with GPT-5.1. All outputs were coded for four grounding error types: object mismatch, attribute mismatch, relation mismatch, and false absence. Grounding failures were common: 41.3% of feedback instances contained at least one error. An inventory-list-first workflow reduced several error categories and lowered the overall error rate, but it did not resolve the underlying limitation: approximately one in three outputs remained flawed, with false absence as the dominant failure mode. Moreover, feedback that appears visually grounded offered little diagnostic value for identifying invalid instances. The findings indicate that modal decoupling is a substantial limitation and that valid feedback will require grounding mechanisms beyond common prompting strategies.

Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Language Models (MLLMs) can do the same, aligning distinct egocentric views through dialogue to form a coherent, allocentric mental model of a shared environment. To study this systematically, we introduce COSMIC, a benchmark for Collaborative Spatial Communication. In this setting, two static MLLM agents observe a 3D indoor environment from different viewpoints and exchange natural-language messages to solve spatial queries. COSMIC contains 899 diverse scenes and 1250 question-answer pairs spanning five tasks. We find a capability hierarchy, MLLMs are most reliable at identifying shared anchor objects across views, perform worse on relational reasoning, and largely fail at building globally consistent maps, performing near chance, even for frontier models. Moreover, we find thinking capability yields gains in anchor grounding, but is insufficient for higher-level spatial communication. To contextualize model behavior, we collect 250 human-human dialogues. Humans achieve 95% aggregate accuracy, while the best model, Gemini-3-Pro-Thinking, reaches 72%, leaving substantial room for improvement. Moreover, human conversations grow more precise as partners align on a shared spatial understanding, whereas MLLMs keep exploring without converging, suggesting limited capacity to form and sustain a robust shared mental model throughout the dialogue. Our code and data is available at https://github.com/ankursikarwar/Cosmic.

Traditional Visual Grounding (VG) predominantly relies on textual descriptions to localize objects, a paradigm that inherently struggles with linguistic ambiguity and often ignores non-verbal deictic cues prevalent in real-world interactions. In natural egocentric engagements, hand-pointing combined with speech forms the most intuitive referring mechanism. To bridge this gap, we introduce EgoPoint-Ground, the first large-scale multimodal dataset dedicated to egocentric deictic visual grounding. Comprising over 15k interactive samples in complex scenes, the dataset provides rich, multi-grained annotations including hand-target bounding box pairs and dense semantic captions. We establish a comprehensive benchmark for hand-pointing referring expression resolution, evaluating a wide spectrum of mainstream Multimodal Large Language Models (MLLMs) and state-of-the-art VG architectures. Furthermore, we propose SV-CoT, a novel baseline framework that reformulates grounding as a structured inference process, synergizing gestural and linguistic cues through a Visual Chain-of-Thought paradigm. Extensive experiments demonstrate that SV-CoT achieves an $\textbf{11.7\%}$ absolute improvement over existing methods, effectively mitigating semantic ambiguity and advancing the capability of agents to comprehend multimodal physical intents. The dataset and code will be made publicly available.

While the field of co-speech gesture generation has seen significant advances, producing holistic, semantically grounded gestures remains a challenge. Existing approaches rely on external semantic retrieval methods, which limit their generalisation capability due to dependency on predefined linguistic rules. Flow-matching-based methods produce promising results; however, the network is optimised using only semantically congruent samples without exposure to negative examples, leading to learning rhythmic gestures rather than sparse motion, such as iconic and metaphoric gestures. Furthermore, by modelling body parts in isolation, the majority of methods fail to maintain crossmodal consistency. We introduce a Contrastive Flow Matching-based co-speech gesture generation model that uses mismatched audio-text conditions as negatives, training the velocity field to follow the correct motion trajectory while repelling semantically incongruent trajectories. Our model ensures cross-modal coherence by embedding text, audio, and holistic motion into a composite latent space via cosine and contrastive objectives. Extensive experiments and a user study demonstrate that our proposed approach outperforms state-of-the-art methods on two datasets, BEAT2 and SHOW.

Multimodal Diffusion Large Language Models (MDLLMs) achieve high-concurrency generation through parallel masked decoding, yet the architectures remain prone to multimodal hallucinations. This structural vulnerability stems from an algorithmic flaw: the decoder ranks candidate tokens based on textual likelihood without verifying localized visual support. We establish that this language-only ranking induces an objective mismatch, where language probability mass acts as a misspecified proxy for the intended multimodal task. Consequently, we reinterpret hallucination as a localized optimization error, a phenomenon where the decoder exploits language shortcuts to maximize a proxy score at the expense of visual grounding. To address this objective mismatch, we introduce VISAGE, a training-free decoding framework that calibrates the objective at inference time. VISAGE estimates the proxy discrepancy by quantifying the spatial entropy of cross-attention distributions. By enforcing a localization consensus across attention heads, the method penalizes spatially uniform distributions and re-ranks token commitments to favor visually grounded outcomes. We provide an analytical stability guarantee establishing that VISAGE maintains a bounded objective loss under estimation error. Evaluations across hallucination-sensitive and general-purpose benchmarks demonstrate the robustness of the framework, yielding relative gains of 8.59% on MMMU-val and 7.75% on HallusionBench.

Most testbeds for omni-modal models assess multimodal understanding via textual outputs, leaving it unclear whether these models can properly speak their answers. To study this, we introduce OmniACBench, a benchmark for evaluating context-grounded acoustic control in omni-modal models. Given a spoken instruction, a text script, and an image, a model must read the script aloud with an appropriate tone and manner. OmniACBench comprises 3,559 verified instances covering six acoustic features: speech rate, phonation, pronunciation, emotion, global accent, and timbre. Extensive experiments on eight models reveal their limitations in the proposed setting, despite their strong performance on prior textual-output evaluations. Our analyses show that the main bottleneck lies not in processing individual modalities, but in integrating multimodal context for faithful speech generation. Moreover, we identify three common failure modes-weak direct control, failed implicit inference, and failed multimodal grounding-providing insights for developing models that can verbalize responses effectively.

Despite the rapid progress of Multimodal Large Language Models (MLLMs), their ability to perform reliable visual grounding in high-stakes clinical software environments remains underexplored. Existing GUI benchmarks largely focus on isolated, single-step grounding queries, overlooking the sequential, workflow-driven reasoning required in real-world medical interfaces, where tasks evolve across independent steps and dynamic interface states. We introduce MedSPOT, a workflow-aware sequential grounding benchmark for clinical GUI environments. Unlike prior benchmarks that treat grounding as a standalone prediction task, MedSPOT models procedural interaction as a sequence of structured spatial decisions. The benchmark comprises 216 task-driven videos with 597 annotated keyframes, in which each task consists of 2 to 3 interdependent grounding steps within realistic medical workflows. This design captures interface hierarchies, contextual dependencies, and fine-grained spatial precision under evolving conditions. To evaluate procedural robustness, we propose a strict sequential evaluation protocol that terminates task assessment upon the first incorrect grounding prediction, explicitly measuring error propagation in multi-step workflows. We further introduce a comprehensive failure taxonomy, including edge bias, small-target errors, no prediction, near miss, far miss, and toolbar confusion, to enable systematic diagnosis of model behavior in clinical GUI settings. By shifting evaluation from isolated grounding to workflow-aware sequential reasoning, MedSPOT establishes a realistic and safety-critical benchmark for assessing multimodal models in medical software environments. Code and data are available at: https://github.com/Tajamul21/MedSPOT.

The recent advancements introduced by Large Language Models (LLMs) have transformed how Artificial Intelligence (AI) can support complex, real world tasks, pushing research outside the text boundaries towards multi modal contexts and leading to Multimodal Large Language Models (MLMs). Given the current adoption of LLM based assistants in solving technical or domain specific problems, the natural continuation of this trend is to extend the input domains of these assistants exploiting MLMs. Ideally, these MLMs should be used as real time assistants in procedural tasks, hopefully integrating a view of the environment where the user being assisted is, or even better sharing the same point of view via Virtual Reality (VR) or Augmented Reality (AR) supports, to reason over the same scenario the user is experiencing. With this work, we aim at evaluating the quality of currently openly available MLMs to provide this kind of assistance on technical tasks. To this end, we annotated a data set of furniture assembly with step by step labels and manual references: the Manual to Action Dataset (M2AD). We used this dataset to assess (1) to which extent the reasoning abilities of MLMs can be used to reduce the need for detailed labelling, allowing for more efficient, cost effective annotation practices, (2) whether MLMs are able to track the progression of assembly steps (3) and whether MLMs can refer correctly to the instruction manual pages. Our results showed that while some models understand procedural sequences, their performance is limited by architectural and hardware constraints, highlighting the need for multi image and interleaved text image reasoning.

Unified Multimodal Models (UMMs) have emerged as a promising paradigm that integrates multimodal understanding and generation within a unified modeling framework. However, current generative training paradigms suffer from inherent limitations. We present Semantically-Grounded Supervision (SeGroS), a fine-tuning framework designed to resolve the granularity mismatch and supervisory redundancy in UMMs. At its core, we propose a novel visual grounding map to construct two complementary supervision signals. First, we formulate semantic Visual Hints to compensate for the sparsity of text prompts. Second, we generate a semantically-grounded Corrupted Input to explicitly enhance the supervision of masking-based UMMs by restricting the reconstruction loss to core text-aligned regions. Extensive evaluations on GenEval, DPGBench, and CompBench demonstrate that SeGroS significantly improves generation fidelity and cross-modal alignment across various UMM architectures.

Grounded Multimodal Named Entity Recognition (GMNER) identifies named entities, including their spans and types, in natural language text and grounds them to the corresponding regions in associated images. Most existing approaches split this task into two steps: they first detect objects using a pre-trained general-purpose detector and then match named entities to the detected objects. However, these methods face a major limitation. Because pre-trained general-purpose object detectors operate independently of textual entities, they tend to detect common objects and frequently overlook specific fine-grained regions required by named entities. This misalignment between object detectors and entities introduces imprecision and can impair overall system performance. In this paper, we propose a proposal-free Query-Guided Network (QGN) that unifies multimodal reasoning and decoding through text guidance and cross- modal interaction. QGN enables accurate grounding and robust performance in open-domain scenarios. Extensive experiments demonstrate that QGN achieves top performance among compared GMNER models on widely used benchmarks.

Addressing the challenges of fragmented task definitions and the heterogeneity of unstructured data in multimodal parsing, this paper proposes the Omni Parsing framework. This framework establishes a Unified Taxonomy covering documents, images, and audio-visual streams, introducing a progressive parsing paradigm that bridges perception and cognition. Specifically, the framework integrates three hierarchical levels: 1) Holistic Detection, which achieves precise spatial-temporal grounding of objects or events to establish a geometric baseline for perception; 2) Fine-grained Recognition, which performs symbolization (e.g., OCR/ASR) and attribute extraction on localized objects to complete structured entity parsing; and 3) Multi-level Interpreting, which constructs a reasoning chain from local semantics to global logic. A pivotal advantage of this framework is its evidence anchoring mechanism, which enforces a strict alignment between high-level semantic descriptions and low-level facts. This enables ``evidence-based'' logical induction, transforming unstructured signals into standardized knowledge that is locatable, enumerable, and traceable. Building on this foundation, we constructed a standardized dataset and released the Logics-Parsing-Omni model, which successfully converts complex audio-visual signals into machine-readable structured knowledge. Experiments demonstrate that fine-grained perception and high-level cognition are synergistic, effectively enhancing model reliability. Furthermore, to quantitatively evaluate these capabilities, we introduce OmniParsingBench. Code, models and the benchmark are released at https://github.com/alibaba/Logics-Parsing/tree/master/Logics-Parsing-Omni.

Multimodal judges struggle to ground decisions in visual evidence. We present MJ1, a multimodal judge trained with reinforcement learning that enforces visual grounding through a structured grounded verification chain (observations $\rightarrow$ claims $\rightarrow$ verification $\rightarrow$ evaluation $\rightarrow$ scoring) and a counterfactual consistency reward that penalizes position bias. Even without training, our mechanism improves base-model accuracy on MMRB2 by +3.8 points on Image Editing and +1.7 on Multimodal Reasoning. After training, MJ1, with only 3B active parameters, achieves 77.0% accuracy on MMRB2 and surpasses orders-of-magnitude larger models like Gemini-3-Pro. These results show that grounded verification and consistency-based training substantially improve multimodal judgment without increasing model scale.

In situated collaboration, speakers often use intentionally underspecified deictic commands (e.g., ``pass me that''), whose referent becomes identifiable only by aligning speech with a brief co-speech pointing stroke. However, many embodied benchmarks admit language-only shortcuts, allowing MLLMs to perform well without learning the audio--visual alignment required by deictic interaction. To bridge this gap, we introduce Egocentric Co-Speech Grounding (EcoG), where grounding is executable only if an agent jointly predicts What, Where, and When. To operationalize this, we present EcoG-Bench, an evaluation-only bilingual (EN/ZH) diagnostic benchmark of 811 egocentric clips with dense spatial annotations and millisecond-level stroke supervision. It is organized under a Progressive Cognitive Evaluation protocol. Benchmarking state-of-the-art MLLMs reveals a severe executability gap: while human subjects achieve near-ceiling performance on EcoG-Bench (96.9% strict Eco-Accuracy), the best native video-audio setting remains low (Gemini-3-Pro: 17.0%). Moreover, in a diagnostic ablation, replacing the native video--audio interface with timestamped frame samples and externally verified ASR (with word-level timing) substantially improves the same model (17.0%$\to$42.9%). Overall, EcoG-Bench provides a strict, executable testbed for event-level speech--gesture binding, and suggests that multimodal interfaces may bottleneck the observability of temporal alignment cues, independently of model reasoning.

Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in long multimodal documents. We introduce BRIDGE, a benchmark for multi-hop reasoning over long scientific papers that require integrating evidence across text, tables, and figures. The dataset supports both chain-like and fan-out structures and provides explicit multi-hop reasoning annotations for step-level evaluation beyond answer accuracy. Experiments with state-of-the-art LLMs and multimodal retrieval-augmented generation (RAG) systems reveal systematic deficiencies in evidence aggregation and grounding that remain hidden under conventional answer-only evaluation. BRIDGE provides a targeted testbed for diagnosing reasoning failures in long multimodal documents.

Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of forming a complete, human-like reasoning process, because even when they improve both layout encoding and CoT-style prompting, the interaction between the two is typically learned implicitly and remains loosely coupled rather than being enforced as a systematic mechanism. So we propose DocCogito, a unified framework that integrates global layout perception with structured, region-grounded reasoning. DocCogito introduces a lightweight layout tower that distills page structure into learnable global layout prior tokens, and a deterministic Visual-Semantic Chain (VSC)-a concise structured representation less ambiguous than free-form natural-language CoT-to supervise fine-grained intermediate reasoning aligned with evidence regions. Training follows a progressive recipe, including layout perception pretraining, VSC-guided cold start, rejection sampling, and GRPO. To further strengthen the internal coupling between layout priors and VSC execution, we augment standard rewards with a fine-grained region-confidence signal that encourages reasoning traces to stay aligned with corresponding evidence regions. Extensive experiments on six benchmarks (DocVQA, WTQ, ChartQA, TextVQA, OCRBench, and InfoVQA) demonstrate strong generalization, achieving state-of-the-art results on four benchmarks.

Audio-visual speech recognition (AVSR) is an extension of ASR that incorporates visual signals. Current AVSR approaches primarily focus on lip motion, largely overlooking rich context present in the video such as speaking scene and on-screen text. To tackle such CAVSR (AVSR including rich visual Context), we propose VASR designed to "see" and reason the visual context to improve speech recognition. Specifically, we construct an Audio-Visual Chain-of-Thought (AV-CoT) that explicitly enforces intermediate cross-modal grounding between acoustic signals and visual evidence. This evidence-driven reasoning mitigates the "single-modality dominance" problem, where models either over-rely on visual context or fail to utilize it. Besides, to address the data scarcity, we construct and release a corresponding data pipeline and test set. Experiments show that AV-CoT effectively mitigates the single-modality dominance, achieving state-of-the-art performance in CAVSR. The project is open-sourced.

Dexterous manipulation enables robots to purposefully alter the physical world, transforming them from passive observers into active agents in unstructured environments. This capability is the cornerstone of physical artificial intelligence. Despite decades of advances in hardware, perception, control, and learning, progress toward general manipulation systems remains fragmented due to the absence of widely adopted standard benchmarks. The central challenge lies in reconciling the variability of the real world with the reproducibility and authenticity required for rigorous scientific evaluation. To address this, we introduce ManipulationNet, a global infrastructure that hosts real-world benchmark tasks for robotic manipulation. ManipulationNet delivers reproducible task setups through standardized hardware kits, and enables distributed performance evaluation via a unified software client that delivers real-time task instructions and collects benchmarking results. As a persistent and scalable infrastructure, ManipulationNet organizes benchmark tasks into two complementary tracks: 1) the Physical Skills Track, which evaluates low-level physical interaction skills, and 2) the Embodied Reasoning Track, which tests high-level reasoning and multimodal grounding abilities. This design fosters the systematic growth of an interconnected network of real-world abilities and skills, paving the path toward general robotic manipulation. By enabling comparable manipulation research in the real world at scale, this infrastructure establishes a sustainable foundation for measuring long-term scientific progress and identifying capabilities ready for real-world deployment.

Multimedia event extraction (M2E2) aims to predict triggers, ground arguments across text and images, and then assemble them into schema-consistent event records. Recent LLM-based approaches have shown strong potential for M2E2, but their intermediate event hypotheses often remain implicit, and event-argument linking is still tightly coupled with role binding. This leaves little opportunity to inspect or revise intermediate event hypotheses and makes predictions brittle to early errors. To bridge this gap, we present ECHO, a multi-agent framework that reframes M2E2 as iterative refinement over an explicit Multimedia Event Hypergraph (MEHG). Instead of relying on implicit linear generation, ECHO performs auditable atomic updates over a shared hypergraph, making intermediate event structures explicit and revisable. Furthermore, we introduce a Link-then-Bind strategy that decouples event-argument linking from role binding, reducing premature semantic commitment during structured prediction. Extensive experiments on the M2E2 benchmark show that ECHO consistently outperforms prior state-of-the-art approaches, achieving gains of 7.3 and 15.5 F1 points on event mention and argument role, respectively.

Recent advances in training-free visual prompting, such as Set-of-Mark, have emerged as a promising direction for enhancing the grounding capabilities of multimodal language models (MLMs). These techniques operate by partitioning the input image into object regions and annotating them with marks, predominantly boxes with numeric identifiers, before feeding the augmented image to the MLM. However, these approaches treat marked objects as isolated entities, failing to capture the relationships between them. On these premises, we propose Graph-of-Mark (GoM), the first pixel-level visual prompting technique that overlays scene graphs onto the input image for spatial reasoning tasks. We evaluate GoM across 3 open-source MLMs and 4 different datasets, conducting extensive ablations on drawn components and investigating the impact of auxiliary graph descriptions in the text prompt. Our results demonstrate that GoM consistently improves the zero-shot capability of MLMs in interpreting object positions and relative directions, improving base accuracy in visual question answering and localization up to 11 percentage points.

Large visual language models (VLMs) have shown strong multi-modal medical reasoning ability, but most operate as end-to-end black boxes, diverging from clinicians' evidence-based, staged workflows and hindering clinical accountability. Complementarily, expert visual grounding models can accurately localize regions of interest (ROIs), providing explicit, reliable evidence that improves both reasoning accuracy and trust. In this paper, we introduce CARE, advancing Clinical Accountability in multi-modal medical Reasoning with an Evidence-grounded agentic framework. Unlike existing approaches that couple grounding and reasoning within a single generalist model, CARE decomposes the task into coordinated sub-modules to reduce shortcut learning and hallucination: a compact VLM proposes relevant medical entities; an expert entity-referring segmentation model produces pixel-level ROI evidence; and a grounded VLM reasons over the full image augmented by ROI hints. The VLMs are optimized with reinforcement learning with verifiable rewards to align answers with supporting evidence. Furthermore, a VLM coordinator plans tool invocation and reviews evidence-answer consistency, providing agentic control and final verification. Evaluated on standard medical VQA benchmarks, our CARE-Flow (coordinator-free) improves average accuracy by 10.9% over the same size (10B) state-of-the-art (SOTA). With dynamic planning and answer review, our CARE-Coord yields a further gain, outperforming the heavily pre-trained SOTA by 5.2%. Our experiments demonstrate that an agentic framework that emulates clinical workflows, incorporating decoupled specialized models and explicit evidence, yields more accurate and accountable medical AI. Project page: https://xypb.github.io/CARE-Project-Page/

Emerging unified editing models have demonstrated strong capabilities in general object editing tasks. However, it remains a significant challenge to perform fine-grained editing in complex multi-entity scenes, particularly those where targets are not visually salient and require spatial reasoning. To this end, we propose InterCoG, a novel text-vision Interleaved Chain-of-Grounding reasoning framework for fine-grained image editing in complex real-world scenes. The key insight of InterCoG is to first perform object position reasoning solely within text that includes spatial relation details to explicitly deduce the location and identity of the edited target. It then conducts visual grounding via highlighting the editing targets with generated bounding boxes and masks in pixel space, and finally rewrites the editing description to specify the intended outcomes. To further facilitate this paradigm, we propose two auxiliary training modules: multimodal grounding reconstruction supervision and multimodal grounding reasoning alignment to enforce spatial localization accuracy and reasoning interpretability, respectively. We also construct GroundEdit-45K, a dataset comprising 45K grounding-oriented editing samples with detailed reasoning annotations, and GroundEdit-Bench for grounding-aware editing evaluation. Extensive experiments substantiate the superiority of our approach in highly precise edits under spatially intricate and multi-entity scenes.

Establishing stable mappings between natural language expressions and visual percepts is a foundational problem for both cognitive science and artificial intelligence. Humans routinely ground linguistic reference in noisy, ambiguous perceptual contexts, yet the mechanisms supporting such cross-modal alignment remain poorly understood. In this work, we introduce a computational framework designed to model core aspects of human referential interpretation by integrating linguistic utterances with perceptual representations derived from large-scale, crowd-sourced imagery. The system approximates human perceptual categorization by combining scale-invariant feature transform (SIFT) alignment with the Universal Quality Index (UQI) to quantify similarity in a cognitively plausible feature space, while a set of linguistic preprocessing and query-transformation operations captures pragmatic variability in referring expressions. We evaluate the model on the Stanford Repeated Reference Game corpus (15,000 utterances paired with tangram stimuli), a paradigm explicitly developed to probe human-level perceptual ambiguity and coordination. Our framework achieves robust referential grounding. It requires 65% fewer utterances than human interlocutors to reach stable mappings and can correctly identify target objects from single referring expressions 41.66% of the time (versus 20% for humans).These results suggest that relatively simple perceptual-linguistic alignment mechanisms can yield human-competitive behavior on a classic cognitive benchmark, and offers insights into models of grounded communication, perceptual inference, and cross-modal concept formation. Code is available at https://anonymous.4open.science/r/metasequoia-9D13/README.md .