论文检索

Deep Learning · Large Language Models

Lukasz Borchmann, Jordy Van Landeghem, Michał Turski, Shreyansh Padarha, Ryan Kearns, Adam Mahdi, Niels Rogge, Clémentine Fourrier, Siwei Han, Huaxiu Yao 等

Multimodal agents offer a compelling path to automating complex document-intensive workflows, yet a critical question remains: do these architectures demonstrate genuine strategic reasoning, or simply conduct stochastic trial-and-error search? To address this, we introduce Agentic Document VQA, a benchmark of 2,250 human-authored questions grounded in 800 heterogeneous PDF documents. Guided by *Classical Test Theory*, we design it to maximize discriminative power and reliably differentiate between varying levels of agent capability. To rigorously assess agentic behaviour, we introduce a novel evaluation protocol for measuring the accuracy-effort trade-off. Using this framework, we find that humans show strong metacognitive calibration, adapting or abandoning failed strategies, whereas frontier agents often persist in unproductive loops with diminishing returns. We release the dataset, evaluation harness, and leaderboard to help facilitate the transition from brute-force retrieval to calibrated, efficient reasoning.

Deep Learning · Large Language Models

Minsik Choi, Geewook Kim

Instruction tuning aligns large (multimodal) language models with diverse user intents, but scaling to heterogeneous mixtures is hindered by (i) gradient interference that causes negative transfer and stiff high-curvature dynamics, and (ii) bandwidth-heavy synchronization that is often impractical on fragmented compute. We propose MERIT, a decentralized, merge-ready pipeline that splits mixtures before fine-tuning. Starting from a merge-ready initialization, MERIT estimates dataset-level gradients, builds a cosine-similarity conflict matrix, applies PCA to extract dominant conflict axes, and partitions datasets accordingly. Each partition is fine-tuned independently with no inter-partition communication, and merged once via one-shot token-weighted averaging. A local quadratic flat-basin analysis shows that merging acts as a curvature-weighted spectral filter, and that PCA-aligned splitting amplifies cancellation of high-curvature disagreement components. On Qwen2.5-VL-3B fine-tuned on 136 Vision-FLAN tasks, MERIT improves the overall benchmark average from 54.7 (centralized joint training) to 57.0 while enabling communication-free parallel fine-tuning. We further validate MERIT at 7B scale on a 1.6M-example mixture and on text-only instruction mixtures.

Tianxing Chen, Zanxin Chen, Baijun Chen, Zijian Cai, Yibin Liu, Zixuan Li, Qiwei Liang, Xianliang Lin, Yiheng Ge, Zhenyu Gu 等

Simulation-based data synthesis has emerged as a powerful paradigm for enhancing real-world robotic manipulation. However, existing synthetic datasets remain insufficient for robust bimanual manipulation due to two key challenges: (1) the lack of an autonomous self-correcting mechanism to resolve execution failures in complex coordination tasks, and (2) the scarcity of diverse visual and spatial variations required to bridge the sim-to-real gap. To this end, we present RoboTwin 2.0, a scalable simulation framework that enables closed-loop, automated, large-scale generation of diverse and realistic data, along with unified evaluation protocols for dual-arm manipulation. Built upon RoboTwin-OD, a foundational library of 731 instances across 147 categories with rich semantic annotations, our framework integrates Multimodal Large Language Models (MLLMs) with simulation-in-the-loop verification. This integration forms an automated feedback mechanism that significantly boosts the success rate of expert task program generation. To enhance robust sim-to-real transfer, RoboTwin 2.0 incorporates structured domain randomization along five axes: clutter, lighting, background, tabletop height and language instructions, thereby maximizing data diversity. We instantiate this framework across 50 dual-arm tasks spanning five robot embodiments. Empirical evaluations demonstrate that Vision-Language-Action (VLA) models pre-trained on our synthetic data achieve a 3.6x improvement in few-shot real-world transfer (over a 10-demo baseline) and a 2.2x gain in zero-shot generalization. We release the data generator, benchmark, pre-collected dataset, and code to support scalable research in robust bimanual manipulation.

General Machine Learning · Representation Learning

Pratham Yashwante, Rose Yu

The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure of the world. However, this hypothesis has largely been examined in vision and language, and it remains unclear whether time series participate in such convergence. We first examine this in a trimodal setting and find that independently pretrained time series, vision, and language encoders exhibit near-orthogonal geometry in the absence of explicit coupling. We then apply post-hoc alignment by training projection heads over frozen encoders using contrastive learning, and analyze the resulting representations with respect to geometry, scaling behavior, and dependence on information density and input modality characteristics. Our investigation reveals that overall alignment in contrastive representation spaces improves with model size, but this alignment is asymmetric: time series align more strongly with visual representations than with text, and images can act as effective intermediaries between time series and language. We further see that richer textual descriptions improve alignment only up to a threshold; training on denser captions does not lead to further improvement. Analogous effects are observed for visual representations. Our findings shed light on considerations for building multimodal systems involving non-conventional data modalities beyond vision and language.

Applications · Computer Vision

Ziwei Zhou, Zeyuan Lai, Rui Wang, Yifan Yang, Yuqing Yang, Qi Dai, Lili Qiu, Chong Luo

Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largely assess audio and video in isolation or rely on coarse embedding similarity, failing to capture fine-grained joint correctness required by realistic prompts. We introduce AVGen-Bench, a task-driven benchmark for T2AV generation, featuring high-quality prompts across 11 real-world categories. To support comprehensive assessment, we propose a multi-granular evaluation framework that combines lightweight specialist models with Multimodal Large Language Models (MLLMs), enabling evaluation from perceptual quality to fine-grained semantic controllability. Our evaluation reveals a pronounced gap between strong audio-visual aesthetics and weak semantic reliability, including persistent failures in text rendering, speech coherence, physical reasoning, and universal breakdown in musical pitch control.

Deep Learning · Large Language Models

Junming Huang, Chi Wang, Letian Li, Guangkai Xu, Donglin Huang, Hao Chen, Qiang Dai, Weiwei Xu

Large Language Models(LLMs) have revolutionized text generation and multimodal perception, but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse structural proxies, failing to capture fine-grained geometry natively. In this paper, we propose CG-MLLM, a novel Multi-modal Large Language Model (MLLM) capable of 3D captioning and high-resolution 3D generation in a single framework. Leveraging the Mixture-of-Transformer architecture, CG-MLLM decouples disparate modeling needs, where the Token-level Autoregressive (TokenAR) Transformer handles token-level content, and the Block-level Autoregressive (BlockAR) Transformer handles block-level content. By integrating a pre-trained vision-language backbone with a specialized 3D VAE latent space, CG-MLLM facilitates long-context interactions between standard tokens and spatial blocks within a single integrated architecture. Experimental results show that CG-MLLM significantly outperforms existing MLLMs in generating high-fidelity 3D objects, effectively bringing high-resolution 3D content creation into the mainstream LLM paradigm.

Social Aspects · Privacy

Xiongtao Sun, HUI LI, Jiaming Zhang, Yujie Yang, Kaili Liu, Ruxin Feng, Wen Tan, Wei Yang Bryan Lim

Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individuals through hierarchical chain-of-thought reasoning. However, existing privacy benchmarks remain structurally insufficient for this threat, as they primarily evaluate privacy perception while failing to address the more critical risk of privacy reasoning: a VLM’s ability to infer and link distributed information to construct individual profiles. To address this gap, we propose MultiPriv, the first benchmark designed to systematically evaluate individual-level privacy reasoning in VLMs. We introduce the Privacy Perception and Reasoning (PPR) framework and construct a bilingual multimodal dataset with synthetic individual profiles, where identifiers (e.g., faces, names) are linked to sensitive attributes. This design enables nine challenging tasks spanning attribute detection, cross-image re-identification, and chained inference. We conduct a large-scale evaluation of over 50 open-source and commercial VLMs. Our analysis shows that 60\% of widely used VLMs can perform individual-level privacy reasoning with up to 80\% accuracy, posing a significant threat to personal privacy. MultiPriv provides a foundation for developing and assessing privacy-preserving VLMs.

Muzhi Zhu, Hao Zhong, Canyu Zhao, Zongze Du, Mingyu Liu, Zheng Huang, Anzhou Li, Hao Chen, Cheng Zou, Jingdong Chen 等

Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information. It is a critical component of efficient perception and decision-making in humans and advanced embodied agents. With the rise of Multimodal Large Language Models (MLLMs) as central planners in robotic systems, the lack of methods for equipping MLLMs with active perception has become a key gap. We first provide a systematic definition of MLLM-based active perception tasks and show that GPT-o3's zoom-in strategy can be viewed as a special case, though it suffers from low efficiency and inaccurate region selection. To address these issues, we propose Active-o3, a reinforcement learning framework built on GRPO that equips MLLMs with active perception capabilities. Leveraging a modular sensing-action design and a dual-form reward, Active-o3 autonomously learns efficient and stable region selection strategies without explicit supervision. We further establish a comprehensive benchmark covering both open-world tasks (small/dense-object grounding) and domain-specific scenarios (remote sensing, autonomous driving, interactive segmentation). Experimental results demonstrate that Active-o3 significantly enhances active perception capabilities compared to Qwen2.5-VL-CoT. Moreover, we show that our RL framework not only preserves the model’s general understanding ability but can also serve as a proxy task for leveraging perception data, further improving performance on benchmarks such as RealWorldQA. We hope that our work can provide a simple codebase and unified evaluation protocol to facilitate future research on active perception with MLLMs.

Deep Learning · Large Language Models

Mohamed Salim AISSI, Salim Aissi, Clément Romac, Laure Soulier, Mohamed Chetouani, Olivier Sigaud, Nicolas THOME

Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception–reasoning–decision gap in standalone Vision–Language Models (VLMs), which often overlook task-critical information. In this paper, we introduce PRISM, a framework that tightly couples perception (VLM) and decision (LLM) through a dynamic question–answer (DQA) pipeline. Instead of passively accepting the VLM’s description, the LLM critiques it, probes the VLM with goal-oriented questions, and synthesizes a compact image description. This closed-loop interaction yields a sharp, task-driven understanding of the scene. We evaluate PRISM on the ALFWorld and Room-to-Room (R2R) benchmarks. We show that: (1) PRISM significantly outperforms state-of-the-art image-based models, (2) our Interactive goal-oriented perception pipeline yields systematic and substantial gains, and (3) PRISM is fully automatic, eliminating the need for handcrafted questions or answers.

Deep Learning · Generative Models and Autoencoders

Ying Shen, Zhiyang Xu, Jiuhai Chen, Shizhe Diao, Jiaxin Zhang, Yuguang Yao, Joy Rimchala, Ismini Lourentzou, Lifu Huang

Recent advances in multimodal foundation models unifying image understanding and generation have opened exciting avenues for tackling a wide range of vision-language tasks within a single framework. Despite progress, existing unified models typically require extensive pretraining, and many of these models suffer from slow image generation speeds, limiting their practical deployment in real-time or resource-constrained settings. In this work, we propose Layerwise Timestep-Expert Flow-based Transformer (LaTtE-Flow), a novel architecture that improves the efficiency of diffusion/flow-based transformer within the unified model setting. LaTtE-Flow builds upon powerful pretrained Vision-Language Models (VLMs) to inherit strong multimodal understanding capabilities, and extends them with a novel Layerwise Timestep Experts flow-based architecture for efficient image generation. LaTtE-Flow distributes the flow-matching process across specialized groups of Transformer layers, each responsible for a distinct subset of timesteps. This design significantly improves sampling efficiency by activating only a small subset of layers at each sampling timestep. To further enhance performance, we propose a Timestep-Conditioned Residual Attention mechanism for efficient information reuse across layers. Experiments demonstrate that LaTtE-Flow achieves strong performance on multimodal understanding tasks, while achieving competitive image generation quality with around 6× faster inference speed compared to recent unified multimodal models.

Applications · Computer Vision

Jiapeng Shi, junke Wang, Zuyao You, Bo He, Zuxuan Wu

Recent advancements in Video Large Language Models (Video LLMs) have demonstrated impressive results, yet existing approaches handle either temporal or spatial dimension in isolation, struggling in the analysis of complex events that require spatial-temporal integration. To bridge this gap, we propose VideoLoom, a unified Video LLM for joint spatial-temporal understanding. To facilitate the development of fine-grained spatial and temporal localization capabilities, we curate LoomData-8.7k, a character-centric video dataset with temporally grounded and spatially localized captions. With this, VideoLoom achieves the state-of-the-art performance across a variety of spatial and temporal benchmarks. In addition, we introduce LoomBench, a benchmark consisting of temporal, spatial, and compositional video–question pairs, with a novel metric $J$&$F_{bi-fore}$, enabling a comprehensive evaluation of Video LLMs from diverse aspects. Collectively, these contributions offer a universal and effective suite for joint spatial-temporal video understanding, setting a new standard in multimodal intelligence.

Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, Huaxiu Yao

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to overcome this constraint by allowing models to act as their own critics or reward providers. Yet, purely text-based self-evaluation struggles to verify complex visual reasoning steps and often suffers from evaluation hallucinations. To address these challenges, inspired by recent advances in tool-integrated reasoning, we propose Agent0-VL, a self-evolving vision-language agent that achieves continual improvement with tool-integrated reasoning. Agent0-VL incorporates tool usage not only into reasoning but also into self-evaluation and self-repair, enabling the model to introspect, verify, and refine its reasoning through evidence-grounded analysis. It unifies two synergistic roles within a single LVLM: a Solver that performs multi-turn tool-integrated reasoning, and a Verifier that generates structured feedback and fine-grained self-rewards through tool-grounded critique. These roles interact through a Self-Evolving Reasoning Cycle, where tool-based verification and reinforcement learning jointly align the reasoning and evaluation distributions for stable self-improvement. Through this zero-external-reward evolution, Agent0-VL aligns its reasoning and verification behaviors without any human annotation or external reward models, achieving continual self-improvement. Experiments on chart reasoning, geometric problem solving, and visual scientific analysis show that Agent0-VL achieves an 12.5% improvement over the Qwen-VL base model.

Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, Huaxiu Yao

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to overcome this constraint by allowing models to act as their own critics or reward providers. Yet, purely text-based self-evaluation struggles to verify complex visual reasoning steps and often suffers from evaluation hallucinations. To address these challenges, inspired by recent advances in tool-integrated reasoning, we propose Agent0-VL, a self-evolving vision-language agent that achieves continual improvement with tool-integrated reasoning. Agent0-VL incorporates tool usage not only into reasoning but also into self-evaluation and self-repair, enabling the model to introspect, verify, and refine its reasoning through evidence-grounded analysis. It unifies two synergistic roles within a single LVLM: a Solver that performs multi-turn tool-integrated reasoning, and a Verifier that generates structured feedback and fine-grained self-rewards through tool-grounded critique. These roles interact through a Self-Evolving Reasoning Cycle, where tool-based verification and reinforcement learning jointly align the reasoning and evaluation distributions for stable self-improvement. Through this zero-external-reward evolution, Agent0-VL aligns its reasoning and verification behaviors without any human annotation or external reward models, achieving continual self-improvement. Experiments on chart reasoning, geometric problem solving, and visual scientific analysis show that Agent0-VL achieves an 12.5% improvement over the Qwen-VL base model.

Applications · Computer Vision

Hongrui Jia, Chaoya Jiang, Yongrui Heng, Shikun Zhang, Wei Ye

As Large Multimodal Models (LMMs) scale up and reinforcement learning (RL) methods mature, LMMs have made notable progress in complex reasoning and decision making. Yet training still relies on static data and fixed recipes, making it difficult to diagnose capability blind spots or provide dynamic, targeted reinforcement. Motivated by findings that test driven error exposure and feedback based correction outperform repetitive practice, we propose Diagnostic-driven Progressive Evolution (DPE), a spiral loop where diagnosis steers data generation and reinforcement, and each iteration re-diagnoses the updated model to drive the next round of targeted improvement. DPE has two key components. First, multiple agents annotate and quality control massive unlabeled multimodal data, using tools such as web search and image editing to produce diverse, realistic samples. Second, DPE attributes failures to specific weaknesses, dynamically adjusts the data mixture, and guides agents to generate weakness focused data for targeted reinforcement. Experiments on Qwen3-VL-8B-Instruct and Qwen2.5-VL-7B-Instruct show stable, continual gains across eleven benchmarks, indicating DPE as a scalable paradigm for continual LMM training under open task distributions.

Zihao Xin, Wentong Li, Yixuan Jiang, Bin Wang, Piji Li, Jianke Zhu, Jie Qin, Sheng-Jun Huang

Vision-and-Language Navigation (VLN) empowered by Multimodal Large Language Models (MLLMs) is promise, yet remains challenged by long-horizon tasks with complex user instructions. Existing approaches that continuously condition on full instructions incur high latency due to abundant visual tokens and exacerbates instruction interference, where irrelevant text noise induces hallucinations. To address these limitations, we propose IDEAL-VLN ( \textbf{I}nstruction \textbf{DE}composition and \textbf{A}ction a\textbf{L}ignment ), a novel paradigm that reformulates navigation as a causal inference chain. We decompose the task into two sequential steps: Semantic Anchoring and Action Alignment. We adopt a \textit{Think-Before-Act} mechanism that first infers the immediate semantic anchor from the global context and then generates actions conditioned solely on this anchor. This design constructs an explicit information bottleneck, suppressing spurious correlations from irrelevant instruction. Moreover, to alleviate cognitive collapse and limited exploration during training, we introduce a hierarchical correction framework that combines semantic-level thought correction with a spatially-aware adaptive intervention strategy. This strategy adjusts expert intervention probability based on geodesic distance, effectively defining a semantic safety boundary. To support this paradigm, we contribute the Instruction-Aligned Navigation Dataset containing 160K image-text pairs. Extensive experiments demonstrate that IDEAL-VLN achieves state-of-the-art performance and robustness across major benchmarks while significantly reducing inference costs.

Applications · Computer Vision

Wenbin Wang, Yuge Huang, Jianqing Xu, Yue Yu, Jiangtao Yan, Shouhong Ding, Pan Zhou, Yong Luo

Rapid advances in AI-generated image (AIGI) technology enable highly realistic synthesis, threatening public information integrity and security. Recent studies have demonstrated that incorporating texture-level artifact features alongside semantic features into multimodal large language models (MLLMs) can enhance their AIGI detection capability. However, our preliminary analyses reveal that artifact features exhibit high intra-feature similarity, leading to an almost uniform attention map after the softmax operation. This phenomenon causes attention dilution, thereby hindering effective fusion between semantic and artifact features. To overcome this limitation, we propose a lightweight fusion adapter, TranX-Adapter, which integrates a Task-aware Optimal-Transport Fusion that leverages the Jensen-Shannon divergence between artifact and semantic prediction probabilities as a cost matrix to transfer artifact information into semantic features, and an X-Fusion that employs cross-attention to transfer semantic information into artifact features. Experiments on standard AIGI detection benchmarks upon several advanced MLLMs, show that our TranX-Adapter brings consistent and significant improvements (up to +6% accuracy). Code can be found in supplementary material.

Applications · Computer Vision

Tingran Wang, Changshuo Wang, Pinjie Xu, ZhangHuang, Yuan Shi, Linjun Sun, Weijun Li

Three-dimensional (3D) reasoning segmentation aims to segment target objects based on text instructions and 3D spatial cues. Recent efforts in 3D reasoning leverage Multimodal Large Language Models (MLLMs) to bridge the gap between text and 3D data. However, since MLLMs are primarily trained on text-image pairs, directly adapting them to unstructured 3D point clouds often fails to capture implicit semantic intent and reliably localize objects. This paper introduces TVDRNet to address these challenges. Inspired by Active Vision theory, where humans selectively choose optimal viewpoints to better observe targets, TVDRNet employs a differentiable renderer to simulate this active process in 3D perception. By using text instructions as supervision to optimize intrinsic and extrinsic rendering parameters, the TVDRNet identifies the optimal viewpoints for observing the 3D scene, and therefore learning 'where to look' based on what the text instruction 'asked to find'. This process generates informative, task-relevant 2D images that are compatible with MLLMs. TVDRNet comprises: (1) the AVPL module, establishing a learnable mapping from semantics to optimal rendering parameters; and (2) the MGL module, fusing multi-modalities via semantic grouping to guide mask generation. Experiments show TVDRNet achieves SOTA performance in 3D reasoning segmentation (Reason3D, Instruct3D) and 3D visual grounding (ScanRefer).

Deep Learning · Robustness

You Yiwei, Jiaan Wei, Zan Chen, Bo Wang

Vision-Language Models (VLMs) achieve remarkable performance on multimodal tasks but remain highly vulnerable to adversarial examples, making transferable attacks essential for realistic robustness evaluation. Recent Adversarial Evolution Triangle (AET) methods improve transferability by interpolating over a simplex formed by clean and historical adversarial samples, yet rely on finite random sampling to approximate effective perturbation distributions, which is unstable under limited budgets. In this paper, we propose Dirichlet Distributional Gradient Aggregation (DDGA), a distribution-aware adversarial attack framework that explicitly models and optimizes perturbations over the AET simplex. DDGA parameterizes simplex mixing weights with a learnable Dirichlet policy and optimizes the expected adversarial objective via policy gradient, replacing heuristic sampling with principled distributional optimization. Moreover, we exploit the closed-form covariance of the learned distribution to construct orthogonal perturbations that enhance gradient diversity. Extensive experiments on image-text retrieval and image captioning demonstrate that DDGA consistently outperforms state-of-the-art transfer-based attacks across multiple VLM architectures.

Deep Learning · Large Language Models

Lin Chen, zhaoxiaoke, Kun Ding, Weiwei Feng, Changtao Miao, Zili Wang, Guo Wenxuan, Ying Wang, Kaiyuan Zheng, Bo Zhang 等

Multimodal Large Language Models (MLLMs) demonstrate impressive cross-modal capabilities, yet their substantial size poses significant deployment challenges. Knowledge distillation (KD) is a promising solution for compressing these models, but existing methods primarily rely on static next-token alignment, neglecting the dynamic token interactions, which embed essential capabilities for multimodal understanding and generation. To this end, we introduce **Align-TI**, a novel KD framework designed from the perspective of **T**oken **I**nteractions. Our approach is motivated by the insight that MLLMs rely on two primary interactions: vision-instruction token interactions to extract relevant visual information, and intra-response token interactions for coherent generation. Accordingly, Align-TI introduces two components: IVA enables the student model to imitate the teacher's instruction-relevant visual information extract capability by aligning on salient visual regions. TPA captures the teacher's dynamic generative logic by aligning the sequential token-to-token transition probabilities. Extensive experiments demonstrate Align-TI's superiority. Notably, our approach achieves 2.6% relative improvement over Vanilla KD, and our distilled Align-TI-2B even outperforms LLaVA-1.5-7B (a much larger MLLM) by 7.0%, establishing a new state-of-the-art distillation framework for training parameter-efficient MLLMs.

General Machine Learning · Everything Else

Shuyu Wu, Ziqiao Ma, Xiaoxi Luo, Yidong Huang, Josue Torres-Fonseca, Freda Shi, Joyce Chai

Symbol grounding (Harnad, 1990) describes how symbols such as words acquire their meanings by connecting to real-world sensorimotor experiences. Recent work has shown preliminary evidence that grounding may emerge in (vision-)language models trained at scale without using explicit grounding objectives. Yet, the specific loci of this emergence and the mechanisms that drive it remain largely unexplored. To address this problem, we introduce a controlled evaluation framework that systematically traces how symbol grounding arises within the internal computations through mechanistic and causal analysis. Our findings show that grounding concentrates in middle-layer computations and is implemented through the aggregate mechanism, where attention heads aggregate the environmental ground to support the prediction of linguistic forms. This phenomenon replicates in multimodal dialogue and across architectures (Transformers and state-space models), but not in unidirectional LSTMs. Our results provide behavioral and mechanistic evidence that symbol grounding can emerge in language models, with practical implications for predicting and potentially controlling the reliability of generation.