Embodied
-
ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints
2026-04-16 11:46:30Pei-An Chen, Yong-Ching Liang, Jia-Fong Yeh, Hung-Ting Su, Yi-Ting Chen, Min Sun, Winston HsuAbstract
Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unexpected conditions and exceptions. However, existing methods usually focus on directly executing instructions, without considering whether the target objects can actually be manipulated, meaning they fail to assess available affordances. To address this limitation, we introduce DynAfford, a benchmark that evaluates embodied agents in dynamic environments where object affordances may change over time and are not specified in the instruction. DynAfford requires agents to perceive object states, infer implicit preconditions, and adapt their actions accordingly. To enable this capability, we introduce ADAPT, a plug-and-play module that augments existing planners with explicit affordance reasoning. Experiments demonstrate that incorporating ADAPT significantly improves robustness and task success across both seen and unseen environments. We also show that a domain-adapted, LoRA-finetuned vision-language model used as the affordance inference backend outperforms a commercial LLM (GPT-4o), highlighting the importance of task-aligned affordance grounding.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14902
PDF
-
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
2026-04-15 17:59:12Dinging Li, Yingxiu Zhao, Xinrui Cheng, Kangheng Lin, Hongbo Peng, Hongxing Li, Zixuan Wang, Yuhong Dai, Haodong Li, Jia Wang, Yukang Shi, Liang Zhao, Jianjian Sun, Zheng Ge, Xiangyu Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang ShenAbstract
Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked by the cost of geometric annotation. The self-evolving paradigm offers a promising path, but its reliance on model consensus to construct pseudo-labels causes training to reinforce rather than correct the model's own geometric errors. We identify a property unique to 3D spatial reasoning that circumvents this limitation: ground truth is a deterministic consequence of the underlying geometry, computable exactly from point clouds and camera poses without any model involvement. Building on this insight, we present SpatialEvo, a self-evolving framework for 3D spatial reasoning, centered on the Deterministic Geometric Environment (DGE). The DGE formalizes 16 spatial reasoning task categories under explicit geometric validation rules and converts unannotated 3D scenes into zero-noise interactive oracles, replacing model consensus with objective physical feedback. A single shared-parameter policy co-evolves across questioner and solver roles under DGE constraints: the questioner generates physically valid spatial questions grounded in scene observations, while the solver derives precise answers against DGE-verified ground truth. A task-adaptive scheduler endogenously concentrates training on the model's weakest categories, producing a dynamic curriculum without manual design. Experiments across nine benchmarks demonstrate that SpatialEvo achieves the highest average score at both 3B and 7B scales, with consistent gains on spatial reasoning benchmarks and no degradation on general visual understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14144
PDF
-
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
2026-04-15 17:50:07Tianshuo Yang, Guanyu Chen, Yutian Chen, Zhixuan Liang, Yitian Liu, Zanxin Chen, Chunpu Xu, Haotian Liang, Jiangmiao Pang, Yao Mu, Ping LuoAbstract
While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base Vision-Language Models (VLMs). To resolve this fundamental trade-off, we propose HiVLA, a visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control. In high-level part, a VLM planner first performs task decomposition and visual grounding to generate structured plans, comprising a subtask instruction and a precise target bounding box. Then, to translate this plan into physical actions, we introduce a flow-matching Diffusion Transformer (DiT) action expert in low-level part equipped with a novel cascaded cross-attention mechanism. This design sequentially fuses global context, high-resolution object-centric crops and skill semantics, enabling the DiT to focus purely on robust execution. Our decoupled architecture preserves the VLM's zero-shot reasoning while allowing independent improvement of both components. Extensive experiments in simulation and the real world demonstrate that HiVLA significantly outperforms state-of-the-art end-to-end baselines, particularly excelling in long-horizon skill composition and the fine-grained manipulation of small objects in cluttered scenes.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14125
PDF
-
UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception
2026-04-15 17:04:34Ziming WangAbstract
We present UMI-3D, a multimodal extension of the Universal Manipulation Interface (UMI) for robust and scalable data collection in embodied manipulation. While UMI enables portable, wrist-mounted data acquisition, its reliance on monocular visual SLAM makes it vulnerable to occlusions, dynamic scenes, and tracking failures, limiting its applicability in real-world environments. UMI-3D addresses these limitations by introducing a lightweight and low-cost LiDAR sensor tightly integrated into the wrist-mounted interface, enabling LiDAR-centric SLAM with accurate metric-scale pose estimation under challenging conditions. We further develop a hardware-synchronized multimodal sensing pipeline and a unified spatiotemporal calibration framework that aligns visual observations with LiDAR point clouds, producing consistent 3D representations of demonstrations. Despite maintaining the original 2D visuomotor policy formulation, UMI-3D significantly improves the quality and reliability of collected data, which directly translates into enhanced policy performance. Extensive real-world experiments demonstrate that UMI-3D not only achieves high success rates on standard manipulation tasks, but also enables learning of tasks that are challenging or infeasible for the original vision-only UMI setup, including large deformable object manipulation and articulated object operation. The system supports an end-to-end pipeline for data acquisition, alignment, training, and deployment, while preserving the portability and accessibility of the original UMI. All hardware and software components are open-sourced to facilitate large-scale data collection and accelerate research in embodied intelligence: \href{this https URL}{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14089
PDF
-
Emerging Ideas Artificial Tripartite Intelligence: A Bio-Inspired, Sensor-First Architecture for Physical AI
2026-04-15 15:10:10You Rim Choi, Subeom Park, Hyung-Sin KimAbstract
As AI moves from data centers to robots and wearables, scaling ever-larger models becomes insufficient. Physical AI operates under tight latency, energy, privacy, and reliability constraints, and its performance depends not only on model capacity but also on how signals are acquired through controllable sensors in dynamic environments. We present Artificial Tripartite Intelligence (ATI), a bio-inspired, sensor-first architectural contract for physical AI. ATI is tripartite at the systems level: a Brainstem (L1) provides reflexive safety and signal-integrity control, a Cerebellum (L2) performs continuous sensor calibration, and a Cerebral Inference Subsystem spanning L3/L4 supports routine skill selection and execution, coordination, and deep reasoning. This modular organization allows sensor control, adaptive sensing, edge-cloud execution, and foundation model reasoning to co-evolve within one closed-loop architecture, while keeping time-critical sensing and control on device and invoking higher-level inference only when needed. We instantiate ATI in a mobile camera prototype under dynamic lighting and motion. In our routed evaluation (L3-L4 split inference), compared to the default auto-exposure setting, ATI (L1/L2 adaptive sensing) improves end-to-end accuracy from 53.8% to 88% while reducing remote L4 invocations by 43.3%. These results show the value of co-designing sensing and inference for embodied AI.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13959
PDF
-
Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
2026-04-15 14:53:09Zhen Liu, Xinyu Ning, Zhe Hu, Xinxin Xie, Weize Li, Zhipeng Tang, Chongyu Wang, Zejun Yang, Hanlin Wang, Yitong Liu, Zhongzhu PuAbstract
Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle in long-horizon, memory-dependent tasks with partial observability, occlusions, and multi-stage dependencies. Such tasks require not only precise visuomotor control, but also persistent memory, adaptive task decomposition, and explicit recovery from execution failures. To address these limitations, we propose a dual-system framework for long-horizon embodied manipulation. Our framework explicitly separates high-level semantic reasoning from low-level motor execution. A high-level planner, implemented as a VLM-based agentic module, maintains structured task memory and performs goal decomposition, outcome verification, and error-driven correction. A low-level executor, instantiated as a VLA-based visuomotor controller, carries out each sub-task through diffusion-based action generation conditioned on geometry-preserving filtered observations. Together, the two systems form a closed loop between planning and execution, enabling memory-aware reasoning, adaptive replanning, and robust online recovery. Experiments on representative RMBench tasks show that the proposed framework substantially outperforms representative baselines, achieving a 32.4% average success rate compared with 9.8% for the strongest baseline. Ablation studies further confirm the importance of structured memory and closed-loop recovery for long-horizon manipulation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13942
PDF
-
EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development
2026-04-15 12:36:59Xueyang Zhou, Yihan Sun, Xijie Gong, Guiyao Tie, Pan Zhou, Lichao Sun, Yongchao ChenAbstract
Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantially increases the engineering overhead and development time required for stages such as evaluation environment construction, trajectory collection, model training, and evaluation. To address this challenge, we propose a new paradigm for embodied AI development in which users express goals and constraints through conversation, and the system automatically plans and executes the development workflow. We instantiate this paradigm with EmbodiedClaw, a conversational agent that turns high-frequency, high-cost embodied research activities, including environment creation and revision, benchmark transformation, trajectory synthesis, model evaluation, and asset expansion, into executable skills. Experiments on end-to-end workflow tasks, capability-specific evaluations, human researcher studies, and ablations show that EmbodiedClaw reduces manual engineering effort while improving executability, consistency, and reproducibility. These results suggest a shift from manual toolchains to conversationally executable workflows for embodied AI development.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13800
PDF
-
Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
2026-04-15 09:20:02Hanxuan Chen, Jie Zheng, Siqi Yang, Tianle Zeng, Siwei Feng, Songsheng Cheng, Ruilong Ren, Hanzhong Guo, Shuai Yuan, Xiangyue Wang, Kangli Wang, Ji PeiAbstract
Vision-and-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) represents a pivotal challenge in embodied artificial intelligence, focused on enabling UAVs to interpret high-level human commands and execute long-horizon tasks in complex 3D environments. This paper provides a comprehensive and structured survey of the field, from its formal task definition to the current state of the art. We establish a methodological taxonomy that charts the technological evolution from early modular and deep learning approaches to contemporary agentic systems driven by large foundation models, including Vision-Language Models (VLMs), Vision-Language-Action (VLA) models, and the emerging integration of generative world models with VLA architectures for physically-grounded reasoning. The survey systematically reviews the ecosystem of essential resources simulators, datasets, and evaluation metrics that facilitates standardized research. Furthermore, we conduct a critical analysis of the primary challenges impeding real-world deployment: the simulation-to-reality gap, robust perception in dynamic outdoor settings, reasoning with linguistic ambiguity, and the efficient deployment of large models on resource-constrained hardware. By synthesizing current benchmarks and limitations, this survey concludes by proposing a forward-looking research roadmap to guide future inquiry into key frontiers such as multi-agent swarm coordination and air-ground collaborative robotics.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13654
PDF
-
ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation
2026-04-15 09:01:20Jingjing Qian, Zeyuan He, Chen Shi, Lei Xiao, Li JiangAbstract
Coordinating navigation and manipulation with robust performance is essential for embodied AI in complex indoor environments. However, as tasks extend over long horizons, existing methods often struggle due to catastrophic forgetting, spatial inconsistency, and rigid execution. To address these issues, we propose ESCAPE (Episodic Spatial Memory Coupled with an Adaptive Policy for Execution), operating through a tightly coupled perception-grounding-execution workflow. For robust perception, ESCAPE features a Spatio-Temporal Fusion Mapping module to autoregressively construct a depth-free, persistent 3D spatial memory, alongside a Memory-Driven Target Grounding module for precise interaction mask generation. To achieve flexible action, our Adaptive Execution Policy dynamically orchestrates proactive global navigation and reactive local manipulation to seize opportunistic targets. ESCAPE achieves state-of-the-art performance on the ALFRED benchmark, reaching 65.09% and 60.79% success rates in test seen and unseen environments with step-by-step instructions. By reducing redundant exploration, our ESCAPE attains substantial improvements in path-length-weighted metrics and maintains robust performance (61.24% / 56.04%) even without detailed guidance for long-horizon tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13633
PDF
-
VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
2026-04-15 08:05:13Yulu Gao, Bohao Zhang, Zongheng Tang, Jitong Liao, Wenjun Wu, Si LiuAbstract
Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and remote collaboration. This task is exceptionally difficult due to severe changes in scale, perspective, and occlusion, which destabilize direct pixel-level matching. While recent geometry-aware models like VGGT provide a strong foundation for feature alignment, we find they often fail at dense prediction tasks due to significant pixel-level projection drift, even when their internal object-level textntion remains consistent. To bridge this gap, we introduce VGGT-Segmentor (VGGT-S), a framework that unifies robust geometric modeling with pixel-accurate semantic segmentation. VGGT-S leverages VGGT's powerful cross-view feature representation and introduces a novel Union Segmentation Head. This head operates in three stages: mask prompt fusion, point-guided prediction, and iterative mask refinement, effectively translating high-level feature alignment into a precise segmentation mask. Furthermore, we propose a single-image self-supervised training strategy that eliminates the need for paired annotations and enables strong generalization. On the Ego-Exo4D benchmark, VGGT-S sets a new state-of-the-art, achieving 67.7% and 68.0% average IoU for Ego to Exo and Exo to Ego tasks, respectively, significantly outperforming prior methods. Notably, our correspondence-free pretrained model surpasses most fully-supervised baselines, demonstrating the effectiveness and scalability of our approach.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13596
PDF
-
Evolvable Embodied Agent for Robotic Manipulation via Long Short-Term Reflection and Optimization
2026-04-15 06:29:02Jianzong Wang, Botao Zhao, Yayun He, Junqing Peng, Xulong ZhangAbstract
Achieving general-purpose robotics requires empowering robots to adapt and evolve based on their environment and feedback. Traditional methods face limitations such as extensive training requirements, difficulties in cross-task generalization, and lack of interpretability. Prompt learning offers new opportunities for self-evolving robots without extensive training, but simply reflecting on past this http URL, extracting meaningful insights from task successes and failures remains a challenge. To this end, we propose the evolvable embodied agent (EEAgent) framework, which leverages large vision-language models (VLMs) for better environmental interpretation and policy planning. To enhance reflection on past experiences, we propose a long short-term reflective optimization (LSTRO) mechanism that dynamically refines prompts based on both past experiences and newly learned lessons, facilitating continuous self-evolution, thereby enhancing overall task success rates. Evaluations on six VIMA-Bench tasks reveal that our approach sets a new state-of-the-art, notably outperforming baselines in complex scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13533
PDF
-
RobotPan: A 360$^circ$ Surround-View Robotic Vision System for Embodied Perception
2026-04-15 04:58:23Jiahao Ma, Qiang Zhang, Peiran Liu, Zeran Su, Pihai Sun, Gang Han, Wen Zhao, Wei Cui, Zhang Zhang, Zhiyuan Xu, Renjing Xu, Jian Tang, Miaomiao Liu, Yijie GuoAbstract
Surround-view perception is increasingly important for robotic navigation and loco-manipulation, especially in human-in-the-loop settings such as teleoperation, data collection, and emergency takeover. However, current robotic visual interfaces are often limited to narrow forward-facing views, or, when multiple on-board cameras are available, require cumbersome manual switching that interrupts the operator's workflow. Both configurations suffer from motion-induced jitter that causes simulator sickness in head-mounted displays. We introduce a surround-view robotic vision system that combines six cameras with LiDAR to provide full 360$^\circ$ visual coverage, while meeting the geometric and real-time constraints of embodied deployment. We further present \textsc{RobotPan}, a feed-forward framework that predicts \emph{metric-scaled} and \emph{compact} 3D Gaussians from calibrated sparse-view inputs for real-time rendering, reconstruction, and streaming. \textsc{RobotPan} lifts multi-view features into a unified spherical coordinate representation and decodes Gaussians using hierarchical spherical voxel priors, allocating fine resolution near the robot and coarser resolution at larger radii to reduce computational redundancy without sacrificing fidelity. To support long sequences, our online fusion updates dynamic content while preventing unbounded growth in static regions by selectively updating appearance. Finally, we release a multi-sensor dataset tailored to 360$^\circ$ novel view synthesis and metric 3D reconstruction for robotics, covering navigation, manipulation, and locomotion on real platforms. Experiments show that \textsc{RobotPan} achieves competitive quality against prior feed-forward reconstruction and view-synthesis methods while producing substantially fewer Gaussians, enabling practical real-time embodied deployment. Project website: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2604.13476
PDF
-
Exploration and Exploitation Errors Are Measurable for Language Model Agents
2026-04-14 17:59:57Jaden Park, Jungtaek Kim, Jongwon Jeong, Robert D. Nowak, Kangwook Lee, Yong Jae LeeAbstract
Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these settings is the ability to both explore the problem space and exploit acquired knowledge effectively. However, systematically distinguishing and quantifying exploration and exploitation from observed actions without access to the agent's internal policy remains challenging. To address this, we design controllable environments inspired by practical embodied AI scenarios. Each environment consists of a partially observable 2D grid map and an unknown task Directed Acyclic Graph (DAG). The map generation can be programmatically adjusted to emphasize exploration or exploitation difficulty. To enable policy-agnostic evaluation, we design a metric to quantify exploration and exploitation errors from agent's actions. We evaluate a variety of frontier LM agents and find that even state-of-the-art models struggle on our task, with different models exhibiting distinct failure modes. We further observe that reasoning models solve the task more effectively and show both exploration and exploitation can be significantly improved through minimal harness engineering. We release our code \href{this https URL}{here}.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13151
PDF
-
XRZero-G0: Pushing the Frontier of Dexterous Robotic Manipulation with Interfaces, Quality and Ratios
2026-04-14 17:34:21Junming Wang, Teng Pu, Wingmun Fung, Jindong Wang, Shanchang Wang, Yuan Deng, Shuyuan Wang, Ziwei Liu, Kunhao Pan, Ping Yang, Peng Zhai, Yuxin Liang, Xiaofan Li, Jiabi Sun, Renchao Xu, Xiaotian Tian, Pengfei Yan, Guoqiang Ye, Liang Li, Qian Wang, Ruyi Gan, Hao WangAbstract
The acquisition of high-quality, action-aligned demonstration data remains a fundamental bottleneck in scaling foundation models for dexterous robot manipulation. Although robot-free human demonstrations (e.g., the UMI paradigm) offer a scalable alternative to traditional teleoperation, current systems are constrained by sub-optimal hardware ergonomics, open-loop workflows, and a lack of systematic data-mixing strategies. To address these limitations, we present XRZero-G0, a hardware-software co-designed system for embodied data collection and policy learning. The system features an ergonomic, virtual reality interface equipped with a top-view camera and dual specialized grippers to directly improve collection efficiency. To ensure dataset reliability, we propose a closed-loop collection, inspection, training, and evaluation pipeline for non-proprioceptive data. This workflow achieves an 85% data validity rate and establishes a transparent mechanism for quality control. Furthermore, we investigate the empirical scaling behaviors and optimal mixing ratios of robot-free data. Extensive experiments indicate that combining a minimal volume of real-robot data with large-scale robot-free data (e.g., a 10:1 ratio) achieves performance comparable to exclusively real-robot datasets, while reducing acquisition costs by a factor of twenty. Utilizing XRZero-G0, we construct a 2,000-hour robot-free dataset that enables zero-shot cross-embodiment transfer to a target physical robot, demonstrating a highly scalable methodology for generalized real-world this http URL project repository: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2604.13001
PDF
-
Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots
2026-04-14 15:57:27Yifei Yan, Linqi YeAbstract
As reinforcement learning for humanoid robots evolves from single-task to multi-skill paradigms, efficiently expanding new skills while avoiding catastrophic forgetting has become a key challenge in embodied intelligence. Existing approaches either rely on complex topology adjustments in Mixture-of-Experts (MoE) models or require training extremely large-scale models, making lightweight deployment difficult. To address this, we propose Tree Learning, a multi-skill continual learning framework for humanoid robots. The framework adopts a root-branch hierarchical parameter inheritance mechanism, providing motion priors for branch skills through parameter reuse to fundamentally prevent catastrophic forgetting. A multi-modal feedforward adaptation mechanism combining phase modulation and interpolation is designed to support both periodic and aperiodic motions. A task-level reward shaping strategy is also proposed to accelerate skill convergence. Unity-based simulation experiments show that, in contrast to simultaneous multi-task training, Tree Learning achieves higher rewards across various representative locomotion skills while maintaining a 100% skill retention rate, enabling seamless multi-skill switching and real-time interactive control. We further validate the performance and generalization capability of Tree Learning on two distinct Unity-simulated tasks: a Super Mario-inspired interactive scenario and autonomous navigation in a classical Chinese garden environment.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12909
PDF
-
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
2026-04-14 11:52:59Ziyuan Xia, Jingyi Xu, Chong Cui, Yuanhong Yu, Jiazhao Zhang, Qingsong Yan, Tao Ni, Junbo Chen, Xiaowei Zhou, Hujun Bao, Ruizhen Hu, Sida PengAbstract
Training embodied AI agents depends critically on the visual fidelity of simulation environments and the ability to model dynamic humans. Current simulators rely on mesh-based rasterization with limited visual realism, and their support for dynamic human avatars, where available, is constrained to mesh representations, hindering agent generalization to human-populated real-world scenarios. We present Habitat-GS, a navigation-centric embodied AI simulator extended from Habitat-Sim that integrates 3D Gaussian Splatting scene rendering and drivable gaussian avatars while maintaining full compatibility with the Habitat ecosystem. Our system implements a 3DGS renderer for real-time photorealistic rendering and supports scalable 3DGS asset import from diverse sources. For dynamic human modeling, we introduce a gaussian avatar module that enables each avatar to simultaneously serve as a photorealistic visual entity and an effective navigation obstacle, allowing agents to learn human-aware behaviors in realistic settings. Experiments on point-goal navigation demonstrate that agents trained on 3DGS scenes achieve stronger cross-domain generalization, with mixed-domain training being the most effective strategy. Evaluations on avatar-aware navigation further confirm that gaussian avatars enable effective human-aware navigation. Finally, performance benchmarks validate the system's scalability across varying scene complexity and avatar counts.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12626
PDF
-
Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models
2026-04-14 06:59:27Ravikumar Balakrishnan, Sanket Mendapara, Ankit GargAbstract
We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents, from browser automation and computer-use systems to camera-equipped embodied agents. In practice, the attack surface is heterogeneous: adversarial text appears at varying font sizes and under diverse visual conditions, while the growing ecosystem of VLMs exhibits substantial variation in vulnerability, complicating defensive approaches. Evaluating 1,000 prompts from SALAD-Bench across four VLMs, namely, GPT-4o, Claude Sonnet 4.5, Mistral-Large-3, and Qwen3-VL-4B-Instruct under varying font sizes (6--28px) and visual transformations (rotation, blur, noise, contrast changes), we find: (1) font size significantly affects attack success rate (ASR), with very small fonts (6px) yielding near-zero ASR while mid-range fonts achieve peak effectiveness; (2) text attacks are more effective than image attacks for GPT-4o (36% vs 8%) and Claude (47% vs 22%), while Qwen3-VL and Mistral show comparable ASR across modalities; (3) text-image embedding distance from two multimodal embedding models (JinaCLIP and Qwen3-VL-Embedding) shows strong negative correlation with ASR across all four models (r = -0.71 to -0.93, p < 0.01); (4) heavy degradations increase embedding distance by 10--12% and reduce ASR by 34--96%, while rotation asymmetrically affects models (Mistral drops 50%, GPT-4o unchanged). These findings highlight that model-specific robustness patterns preclude one-size-fits-all defenses and offer empirical guidance for practitioners selecting VLM backbones for agentic systems operating in adversarial environments.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12371
PDF
-
Human-Inspired Context-Selective Multimodal Memory for Social Robots
2026-04-13 21:42:40Hangyeol Kang, Slava Voloshynovskiy, Nadia Magnenat ThalmannAbstract
Memory is fundamental to social interaction, enabling humans to recall meaningful past experiences and adapt their behavior accordingly based on the context. However, most current social robots and embodied agents rely on non-selective, text-based memory, limiting their ability to support personalized, context-aware interactions. Drawing inspiration from cognitive neuroscience, we propose a context-selective, multimodal memory architecture for social robots that captures and retrieves both textual and visual episodic traces, prioritizing moments characterized by high emotional salience or scene novelty. By associating these memories with individual users, our system enables socially personalized recall and more natural, grounded dialogue. We evaluate the selective storage mechanism using a curated dataset of social scenarios, achieving a Spearman correlation of 0.506, surpassing human consistency ($\rho=0.415$) and outperforming existing image memorability models. In multimodal retrieval experiments, our fusion approach improves Recall@1 by up to 13\% over unimodal text or image retrieval. Runtime evaluations confirm that the system maintains real-time performance. Qualitative analyses further demonstrate that the proposed framework produces richer and more socially relevant responses than baseline models. This work advances memory design for social robots by bridging human-inspired selectivity and multimodal retrieval to enhance long-term, personalized human-robot interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12081
PDF
-
LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
2026-04-13 16:30:35Dujun Nie, Fengjiao Chen, Qi Lv, Jun Kuang, Xiaoyu Li, Xuezhi Cao, Xunliang CaiAbstract
While the shortage of explicit action data limits Vision-Language-Action (VLA) models, human action videos offer a scalable yet unlabeled data source. A critical challenge in utilizing large-scale human video datasets lies in transforming visual signals into ontology-independent representations, known as latent actions. However, the capacity of latent action representation to derive robust control from visual observations has yet to be rigorously evaluated. We introduce the Latent Action Representation Yielding (LARY) Benchmark, a unified framework for evaluating latent action representations on both high-level semantic actions (what to do) and low-level robotic control (how to do). The comprehensively curated dataset encompasses over one million videos (1,000 hours) spanning 151 action categories, alongside 620K image pairs and 595K motion trajectories across diverse embodiments and environments. Our experiments reveal two crucial insights: (i) General visual foundation models, trained without any action supervision, consistently outperform specialized embodied latent action models. (ii) Latent-based visual space is fundamentally better aligned to physical action space than pixel-based space. These results suggest that general visual representations inherently encode action-relevant knowledge for physical control, and that semantic-level abstraction serves as a fundamentally more effective pathway from vision to action than pixel-level reconstruction.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11689
PDF
-
Micro-Dexterity in Biological Micromanipulation: Embodiment, Perception, and Control
2026-04-13 15:50:20Kangyi Lu, Lan Wei, Zongcai Tan, Dandan ZhangAbstract
Microscale manipulation has advanced substantially in controlled locomotion and targeted transport, yet many biomedical applications require precise and adaptive interaction with biological micro-objects. At these scales, manipulation is realized through three main classes of platforms: embodied microrobots that physically interact as mobile agents, field-mediated systems that generate contactless trapping or manipulation forces, and externally actuated end-effectors that interact through remotely driven physical tools. Unlike macroscale manipulators, these systems function in fluidic, confined, and surface-dominated environments characterized by negligible inertia, dominant interfacial forces, and soft, heterogeneous, and fragile targets. Consequently, classical assumptions of dexterous manipulation, including rigid-body contact, stable grasping, and rich proprioceptive feedback, become difficult to maintain. This review introduces micro-dexterity as a framework for analyzing biological micromanipulation through the coupled roles of embodiment, perception, and control. We examine how classical manipulation primitives, including pushing, reorientation, grasping, and cooperative manipulation, are reformulated at the microscale; compare the architectures that enable them, from contact-based micromanipulators to contactless field-mediated systems and cooperative multi-agent platforms; and review the perception and control strategies required for task execution. We identify the current dexterity gap between laboratory demonstrations and clinically relevant biological manipulation, and outline key challenges for future translation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11640
PDF
