Advances in deep generative modelling have made it increasingly plausible to train human-level embodied agents. Yet progress has been limited by the absence of large-scale, real-time, multi-modal, and socially interactive datasets that reflect the sensory-motor complexity of natural environments. To address this, we present PLAICraft, a novel data collection platform and dataset capturing multiplayer Minecraft interactions across five time-aligned modalities: video, game output audio, microphone input audio, mouse, and keyboard actions. Each modality is logged with millisecond time precision, enabling the study of synchronous, embodied behaviour in a rich, open-ended world. The dataset comprises over 10,000 hours of gameplay from more than 10,000 global participants.\footnote{We have done a privacy review for the public release of an initial 200-hour subset of the dataset, with plans to release most of the dataset over time.} Alongside the dataset, we provide an evaluation suite for benchmarking model capabilities in object recognition, spatial awareness, language grounding, and long-term memory. PLAICraft opens a path toward training and evaluating agents that act fluently and purposefully in real time, paving the way for truly embodied artificial intelligence.
Event cameras, which capture brightness changes with high temporal resolution, inherently generate a significant amount of redundant and noisy data beyond essential object structures. The primary challenge in event-based object recognition lies in effectively removing this noise without losing critical spatial-temporal information. To address this, we propose an Adaptive Graph-based Noisy Data Removal framework for Event-based Object Recognition. Specifically, our approach integrates adaptive event segmentation based on normalized density analysis, a multifactorial edge-weighting mechanism, and adaptive graph-based denoising strategies. These innovations significantly enhance the integration of spatiotemporal information, effectively filtering noise while preserving critical structural features for robust recognition. Experimental evaluations on four challenging datasets demonstrate that our method achieves superior recognition accuracies of 83.77%, 76.79%, 99.30%, and 96.89%, surpassing existing graph-based methods by up to 8.79%, and improving noise reduction performance by up to 19.57%, with an additional accuracy gain of 6.26% compared to traditional Euclidean-based techniques.
People with blindness and low vision (pBLV) face significant challenges, struggling to navigate environments and locate objects due to limited visual cues. Spatial reasoning is crucial for these individuals, as it enables them to understand and interpret the spatial relationships in their surroundings, enhancing their ability to navigate and interact more safely and independently. Current multi-modal large language (MLLM) models for low vision people lack the spatial reasoning capabilities needed to effectively assist in these tasks. Moreover, there is a notable absence of lightweight, easy-to-use systems that allow pBLV to effectively perceive and interact with their surrounding environment. In this paper, we propose a novel spatial enhanced multi-modal large language model based approach for visually impaired individuals. By fine-tuning the MLLM to incorporate spatial reasoning capabilities, our method significantly improves the understanding of environmental context, which is critical for navigation and object recognition. The innovation extends to a hardware component, designed as an attachment for glasses, ensuring increased accessibility and ease of use. This integration leverages advanced VLMs to interpret visual data and provide real-time, spatially aware feedback to the user. Our approach aims to bridge the gap between advanced machine learning models and practical, user-friendly assistive devices, offering a robust solution for visually impaired users to navigate their surroundings more effectively and independently. The paper includes an in-depth evaluation using the VizWiz dataset, demonstrating substantial improvements in accuracy and user experience. Additionally, we design a comprehensive dataset to evaluate our method's effectiveness in realworld situations, demonstrating substantial improvements in accuracy and user experience.
Spatial perception and reasoning are core components of human cognition, encompassing object recognition, spatial relational understanding, and dynamic reasoning. Despite progress in computer vision, existing benchmarks reveal significant gaps in models' abilities to accurately recognize object attributes and reason about spatial relationships, both essential for dynamic reasoning. To address these limitations, we propose MIRAGE, a multi-modal benchmark designed to evaluate models' capabilities in Counting (object attribute recognition), Relation (spatial relational reasoning), and Counting with Relation. Through diverse and complex scenarios requiring fine-grained recognition and reasoning, MIRAGE highlights critical limitations in state-of-the-art models, underscoring the need for improved representations and reasoning frameworks. By targeting these foundational abilities, MIRAGE provides a pathway toward spatiotemporal reasoning in future research.
Based on the concept that ventral visual stream (VVS) mainly functions for object recognition, current unsupervised task-driven methods model VVS by contrastive learning, and have achieved good brain similarity. However, we believe functions of VVS extend beyond just object recognition. In this paper, we introduce an additional function involving VVS, named relative position (RP) prediction. We first theoretically explain contrastive learning may be unable to yield the model capability of RP prediction. Motivated by this, we subsequently integrate RP learning with contrastive learning, and propose a new unsupervised task-driven method to model VVS, which is more inline with biological reality. We conduct extensive experiments, demonstrating that: (i) our method significantly improves downstream performance of object recognition while enhancing RP predictivity; (ii) RP predictivity generally improves the model brain similarity. Our results provide strong evidence for the involvement of VVS in location perception (especially RP prediction) from a computational perspective.
Point cloud processing has gained significant attention due to its critical role in applications such as autonomous driving and 3D object recognition. However, deploying high-performance models like Point Transformer V3 in resource-constrained environments remains challenging due to their high computational and memory demands. This work introduces a novel distillation framework that leverages topology-aware representations and gradient-guided knowledge distillation to effectively transfer knowledge from a high-capacity teacher to a lightweight student model. Our approach captures the underlying geometric structures of point clouds while selectively guiding the student model's learning process through gradient-based feature alignment. Experimental results in the Nuscenes, SemanticKITTI, and Waymo datasets demonstrate that the proposed method achieves competitive performance, with an approximately 16x reduction in model size and a nearly 1.9x decrease in inference time compared to its teacher model. Notably, on NuScenes, our method achieves state-of-the-art performance among knowledge distillation techniques trained solely on LiDAR data, surpassing prior knowledge distillation baselines in segmentation performance. Our implementation is available publicly at: https://github.com/HySonLab/PointDistill
Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in multimodal large language models (MLLMs) by decomposing tasks into sub-task programs, but these methods are computationally expensive and less accurate due to poor adaptation to target data. To address this, we introduce VISTAR (Visually Interpretable Subtask-Aware Reasoning Model), a subtask-driven training framework that enhances both interpretability and reasoning by generating textual and visual explanations within MLLMs. Instead of relying on external models, VISTAR fine-tunes MLLMs to produce structured Subtask-of-Thought rationales (step-by-step reasoning sequences). Experiments on two benchmarks show that VISTAR consistently improves reasoning accuracy while maintaining interpretability. Our code and dataset will be available at https://github.com/ChengJade/VISTAR.
Understanding visual art requires reasoning across multiple perspectives -- cultural, historical, and stylistic -- beyond mere object recognition. While recent multimodal large language models (MLLMs) perform well on general image captioning, they often fail to capture the nuanced interpretations that fine art demands. We propose ArtRAG, a novel, training-free framework that combines structured knowledge with retrieval-augmented generation (RAG) for multi-perspective artwork explanation. ArtRAG automatically constructs an Art Context Knowledge Graph (ACKG) from domain-specific textual sources, organizing entities such as artists, movements, themes, and historical events into a rich, interpretable graph. At inference time, a multi-granular structured retriever selects semantically and topologically relevant subgraphs to guide generation. This enables MLLMs to produce contextually grounded, culturally informed art descriptions. Experiments on the SemArt and Artpedia datasets show that ArtRAG outperforms several heavily trained baselines. Human evaluations further confirm that ArtRAG generates coherent, insightful, and culturally enriched interpretations.
Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in viewpoint and environment remains largely underexplored. To bridge this gap, we introduce V$^2$R-Bench, a comprehensive benchmark framework for evaluating Visual Variation Robustness of LVLMs, which encompasses automated evaluation dataset generation and principled metrics for thorough robustness assessment. Through extensive evaluation on 21 LVLMs, we reveal a surprising vulnerability to visual variations, in which even advanced models that excel at complex vision-language tasks significantly underperform on simple tasks such as object recognition. Interestingly, these models exhibit a distinct visual position bias that contradicts theories of effective receptive fields, and demonstrate a human-like visual acuity threshold. To identify the source of these vulnerabilities, we present a systematic framework for component-level analysis, featuring a novel visualization approach for aligned visual features. Results show that these vulnerabilities stem from error accumulation in the pipeline architecture and inadequate multimodal alignment. Complementary experiments with synthetic data further demonstrate that these limitations are fundamentally architectural deficiencies, scoring the need for architectural innovations in future LVLM designs.
An important capacity in visual object recognition is invariance to image-altering variables which leave the identity of objects unchanged, such as lighting, rotation, and scale. How do neural networks achieve this? Prior mechanistic interpretability research has illuminated some invariance-building circuitry in InceptionV1, but the results are limited and networks with different architectures have remained largely unexplored. This work investigates ResNet18 with a particular focus on its residual stream, an architectural component which InceptionV1 lacks. We observe that many convolutional channels in intermediate blocks exhibit scale invariant properties, computed by the element-wise residual summation of scale equivariant representations: the block input's smaller-scale copy with the block pre-sum output's larger-scale copy. Through subsequent ablation experiments, we attempt to causally link these neural properties with scale-robust object recognition behavior. Our tentative findings suggest how the residual stream computes scale invariance and its possible role in behavior. Code is available at: https://github.com/cest-andre/residual-stream-interp
We investigate the ability of Vision Language Models (VLMs) to perform visual perspective taking using a novel set of visual tasks inspired by established human tests. Our approach leverages carefully controlled scenes, in which a single humanoid minifigure is paired with a single object. By systematically varying spatial configurations - such as object position relative to the humanoid minifigure and the humanoid minifigure's orientation - and using both bird's-eye and surface-level views, we created 144 unique visual tasks. Each visual task is paired with a series of 7 diagnostic questions designed to assess three levels of visual cognition: scene understanding, spatial reasoning, and visual perspective taking. Our evaluation of several state-of-the-art models, including GPT-4-Turbo, GPT-4o, Llama-3.2-11B-Vision-Instruct, and variants of Claude Sonnet, reveals that while they excel in scene understanding, the performance declines significantly on spatial reasoning and further deteriorates on perspective-taking. Our analysis suggests a gap between surface-level object recognition and the deeper spatial and perspective reasoning required for complex visual tasks, pointing to the need for integrating explicit geometric representations and tailored training protocols in future VLM development.
Recent advancements in Large Vision-Language Models (LVLMs) have significantly enhanced their ability to integrate visual and linguistic information, achieving near-human proficiency in tasks like object recognition, captioning, and visual question answering. However, current benchmarks typically focus on knowledge-centric evaluations that assess domain-specific expertise, often neglecting the core ability to reason about fundamental mathematical elements and visual concepts. We identify a gap in evaluating elementary-level math problems, which rely on explicit visual dependencies-requiring models to discern, integrate, and reason across multiple images while incorporating commonsense knowledge, all of which are crucial for advancing toward broader AGI capabilities. To address this gap, we introduce VCBENCH, a comprehensive benchmark for multimodal mathematical reasoning with explicit visual dependencies. VCBENCH includes 1,720 problems across six cognitive domains, featuring 6,697 images (averaging 3.9 per question) to ensure multi-image reasoning. We evaluate 26 state-of-the-art LVLMs on VCBENCH, revealing substantial performance disparities, with even the top models unable to exceed 50% accuracy. Our findings highlight the ongoing challenges in visual-mathematical integration and suggest avenues for future LVLM advancements. The project can be found at https://alibaba-damo-academy.github.io/VCBench/.
Recent advancements in multimodal large language models (MLLMs) have broadened the scope of vision-language tasks, excelling in applications like image captioning and interactive question-answering. However, these models struggle with accurately processing visual data, particularly in tasks requiring precise object recognition and fine visual details. Stringent token limits often result in the omission of critical information, hampering performance. To address these limitations, we introduce \SysName, a novel visual prompting mechanism designed to enhance MLLM performance while preserving essential visual details within token limits. \SysName features three key innovations: a prompt-aware strategy that dynamically highlights relevant image regions, a spatial-preserving orchestration schema that maintains object integrity, and a budget-aware prompting method that balances global context with crucial visual details. Comprehensive evaluations across multiple datasets demonstrate that \SysName consistently outperforms baseline methods, achieving up to a $26.9\%$ improvement in accuracy while significantly reducing token consumption.
In human-centered environments such as restaurants, homes, and warehouses, robots often face challenges in accurately recognizing 3D objects. These challenges stem from the complexity and variability of these environments, including diverse object shapes. In this paper, we propose a novel Lightweight Multi-modal Multi-view Convolutional-Vision Transformer network (LM-MCVT) to enhance 3D object recognition in robotic applications. Our approach leverages the Globally Entropy-based Embeddings Fusion (GEEF) method to integrate multi-views efficiently. The LM-MCVT architecture incorporates pre- and mid-level convolutional encoders and local and global transformers to enhance feature extraction and recognition accuracy. We evaluate our method on the synthetic ModelNet40 dataset and achieve a recognition accuracy of 95.6% using a four-view setup, surpassing existing state-of-the-art methods. To further validate its effectiveness, we conduct 5-fold cross-validation on the real-world OmniObject3D dataset using the same configuration. Results consistently show superior performance, demonstrating the method's robustness in 3D object recognition across synthetic and real-world 3D data.
Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary black-box models in text-only and vision-only contexts, the extent and effectiveness of such vulnerabilities remain underexplored for VLLMs. We present a comprehensive analysis demonstrating that targeted adversarial examples are highly transferable to widely-used proprietary VLLMs such as GPT-4o, Claude, and Gemini. We show that attackers can craft perturbations to induce specific attacker-chosen interpretations of visual information, such as misinterpreting hazardous content as safe, overlooking sensitive or restricted material, or generating detailed incorrect responses aligned with the attacker's intent. Furthermore, we discover that universal perturbations -- modifications applicable to a wide set of images -- can consistently induce these misinterpretations across multiple proprietary VLLMs. Our experimental results on object recognition, visual question answering, and image captioning show that this vulnerability is common across current state-of-the-art models, and underscore an urgent need for robust mitigations to ensure the safe and secure deployment of VLLMs.
Modern edge devices, such as cameras, drones, and Internet-of-Things nodes, rely on deep learning to enable a wide range of intelligent applications, including object recognition, environment perception, and autonomous navigation. However, deploying deep learning models directly on the often resource-constrained edge devices demands significant memory footprints and computational power for real-time inference using traditional digital computing architectures. In this paper, we present WISE, a novel computing architecture for wireless edge networks designed to overcome energy constraints in deep learning inference. WISE achieves this goal through two key innovations: disaggregated model access via wireless broadcasting and in-physics computation of general complex-valued matrix-vector multiplications directly at radio frequency. Using a software-defined radio platform with wirelessly broadcast model weights over the air, we demonstrate that WISE achieves 95.7% image classification accuracy with ultra-low operation power of 6.0 fJ/MAC per client, corresponding to a computation efficiency of 165.8 TOPS/W. This approach enables energy-efficient deep learning inference on wirelessly connected edge devices, achieving more than two orders of magnitude improvement in efficiency compared to traditional digital computing.
At the core of the Transformer, the Softmax normalizes the attention matrix to be right stochastic. Previous research has shown that this often destabilizes training and that enforcing the attention matrix to be doubly stochastic (through Sinkhorn's algorithm) consistently improves performance across different tasks, domains and Transformer flavors. However, Sinkhorn's algorithm is iterative, approximative, non-parametric and thus inflexible w.r.t. the obtained doubly stochastic matrix (DSM). Recently, it has been proven that DSMs can be obtained with a parametric quantum circuit, yielding a novel quantum inductive bias for DSMs with no known classical analogue. Motivated by this, we demonstrate the feasibility of a hybrid classical-quantum doubly stochastic Transformer (QDSFormer) that replaces the Softmax in the self-attention layer with a variational quantum circuit. We study the expressive power of the circuit and find that it yields more diverse DSMs that better preserve information than classical operators. Across multiple small-scale object recognition tasks, we find that our QDSFormer consistently surpasses both a standard Vision Transformer and other doubly stochastic Transformers. Beyond the established Sinkformer, this comparison includes a novel quantum-inspired doubly stochastic Transformer (based on QR decomposition) that can be of independent interest. The QDSFormer also shows improved training stability and lower performance variation suggesting that it may mitigate the notoriously unstable training of ViTs on small-scale data.
Inspired by the dual-stream theory of the human visual system (HVS) - where the ventral stream is responsible for object recognition and detail analysis, while the dorsal stream focuses on spatial relationships and motion perception - an increasing number of video quality assessment (VQA) works built upon this framework are proposed. Recent advancements in large multi-modal models, notably Contrastive Language-Image Pretraining (CLIP), have motivated researchers to incorporate CLIP into dual-stream-based VQA methods. This integration aims to harness the model's superior semantic understanding capabilities to replicate the object recognition and detail analysis in ventral stream, as well as spatial relationship analysis in dorsal stream. However, CLIP is originally designed for images and lacks the ability to capture temporal and motion information inherent in videos. To address the limitation, this paper propose a Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment (DVLTA-VQA), which decouples CLIP's visual and textual components, and integrates them into different stages of the NR-VQA pipeline. Specifically, a Video-Based Temporal CLIP module is proposed to explicitly model temporal dynamics and enhance motion perception, aligning with the dorsal stream. Additionally, a Temporal Context Module is developed to refine inter-frame dependencies, further improving motion modeling. On the ventral stream side, a Basic Visual Feature Extraction Module is employed to strengthen detail analysis. Finally, a text-guided adaptive fusion strategy is proposed to enable dynamic weighting of features, facilitating more effective integration of spatial and temporal information.
Tactile sensing is crucial for achieving human-level robotic capabilities in manipulation tasks. VBTSs have emerged as a promising solution, offering high spatial resolution and cost-effectiveness by sensing contact through camera-captured deformation patterns of elastic gel pads. However, these sensors' complex physical characteristics and visual signal processing requirements present unique challenges for robotic applications. The lack of efficient and accurate simulation tools for VBTS has significantly limited the scale and scope of tactile robotics research. Here we present Taccel, a high-performance simulation platform that integrates IPC and ABD to model robots, tactile sensors, and objects with both accuracy and unprecedented speed, achieving an 18-fold acceleration over real-time across thousands of parallel environments. Unlike previous simulators that operate at sub-real-time speeds with limited parallelization, Taccel provides precise physics simulation and realistic tactile signals while supporting flexible robot-sensor configurations through user-friendly APIs. Through extensive validation in object recognition, robotic grasping, and articulated object manipulation, we demonstrate precise simulation and successful sim-to-real transfer. These capabilities position Taccel as a powerful tool for scaling up tactile robotics research and development. By enabling large-scale simulation and experimentation with tactile sensing, Taccel accelerates the development of more capable robotic systems, potentially transforming how robots interact with and understand their physical environment.
Complex video object segmentation continues to face significant challenges in small object recognition, occlusion handling, and dynamic scene modeling. This report presents our solution, which ranked second in the MOSE track of CVPR 2025 PVUW Challenge. Based on an existing segmentation framework, we propose an improved model named MASSeg for complex video object segmentation, and construct an enhanced dataset, MOSE+, which includes typical scenarios with occlusions, cluttered backgrounds, and small target instances. During training, we incorporate a combination of inter-frame consistent and inconsistent data augmentation strategies to improve robustness and generalization. During inference, we design a mask output scaling strategy to better adapt to varying object sizes and occlusion levels. As a result, MASSeg achieves a J score of 0.8250, F score of 0.9007, and a J&F score of 0.8628 on the MOSE test set.