Daily Papers Arch&EAI

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.

Dexterous manipulation enables robots to purposefully alter the physical world, transforming them from passive observers into active agents in unstructured environments.

Recent advances in robot learning have accelerated progress toward generalist robots that can perform everyday tasks in human environments. Yet it remains difficult to gauge how close we are to this vision. The field lacks a reproducible, large-scale benchmark for systematic evaluation. To fill this gap, we present RoboCasa365, a comprehensive simulation benchmark for household mobile manipulation. Built on the RoboCasa platform, RoboCasa365 introduces 365 everyday tasks across 2,500 diverse kitchen environments, with over 600 hours of human demonstration data and over 1600 hours of synthetically generated demonstration data -- making it one of the most diverse and large-scale resources for studying generalist policies. RoboCasa365 is designed to support systematic evaluations for different problem settings, including multi-task learning, robot foundation model training, and lifelong learning. We conduct extensive experiments on this benchmark with state-of-the-art methods and analyze the impacts of task diversity, dataset scale, and environment variation on generalization. Our results provide new insights into what factors most strongly affect the performance of generalist robots and inform strategies for future progress in the field.

Recent advances in robot learning have accelerated progress toward generalist robots that can perform everyday tasks in human environments.

As processor designs grow more complex, verification remains bottlenecked by slow software simulation and low-quality random test stimuli. Recent research has applied software fuzzers to hardware verification, but these rely on semantically blind random mutations that may generate shallow, low-quality stimuli unable to explore complex behaviors. These limitations result in slow coverage convergence and prohibitively high verification costs. In this paper, we present Lyra, a heterogeneous RISC-V verification framework that addresses both challenges by pairing hardware-accelerated verification with an ISA-aware generative model. Lyra executes the DUT and reference model concurrently on an FPGA SoC, enabling high-throughput differential checking and hardware-level coverage collection. Instead of creating verification stimuli randomly or through simple mutations, we train a domain-specialized generative model, LyraGen, with inherent semantic awareness to generate high-quality, semantically rich instruction sequences. Empirical results show Lyra achieves up to $1.27\times$ higher coverage and accelerates end-to-end verification by up to $107\times$ to $3343\times$ compared to state-of-the-art software fuzzers, while consistently demonstrating lower convergence difficulty.

As processor designs grow more complex, verification remains bottlenecked by slow software simulation and low-quality random test stimuli.

Agile quadrotor flight pushes the limits of control, actuation, and onboard perception. While time-optimal trajectory planning has been extensively studied, existing approaches typically neglect the tight coupling between vehicle dynamics, environmental geometry, and the visual requirements of onboard state estimation. As a result, trajectories that are dynamically feasible may fail in closed-loop execution due to degraded visual quality. This paper introduces a unified time-optimal trajectory optimization framework for vision-based quadrotors that explicitly incorporates perception constraints alongside full nonlinear dynamics, rotor actuation limits, aerodynamic effects, camera field-of-view constraints, and convex geometric gate representations. The proposed formulation solves minimum-time lap trajectories for arbitrary racetracks with diverse gate shapes and orientations, while remaining numerically robust and computationally efficient. We derive an information-theoretic position uncertainty metric to quantify visual state-estimation quality and integrate it into the planner through three perception objectives: position uncertainty minimization, sequential field-of-view constraints, and look-ahead alignment. This enables systematic exploration of the trade-offs between speed and perceptual reliability. To accurately track the resulting perception-aware trajectories, we develop a model predictive contouring tracking controller that separates lateral and progress errors. Experiments demonstrate real-world flight speeds up to 9.8 m/s with 0.07 m average tracking error, and closed-loop success rates improved from 55% to 100% on a challenging Split-S course. The proposed system provides a scalable benchmark for studying the fundamental limits of perception-aware, time-optimal autonomous flight.

Agile quadrotor flight pushes the limits of control, actuation, and onboard perception.

Memory is crucial for enabling agents to tackle complex tasks with temporal and spatial dependencies. While many reinforcement learning (RL) algorithms incorporate memory, the field lacks a universal benchmark to assess an agent's memory capabilities across diverse scenarios. This gap is particularly evident in tabletop robotic manipulation, where memory is essential for solving tasks with partial observability and ensuring robust performance, yet no standardized benchmarks exist. To address this, we introduce MIKASA (Memory-Intensive Skills Assessment Suite for Agents), a comprehensive benchmark for memory RL, with three key contributions: (1) we propose a comprehensive classification framework for memory-intensive RL tasks, (2) we collect MIKASA-Base -- a unified benchmark that enables systematic evaluation of memory-enhanced agents across diverse scenarios, and (3) we develop MIKASA-Robo (pip install mikasa-robo-suite) -- a novel benchmark of 32 carefully designed memory-intensive tasks that assess memory capabilities in tabletop robotic manipulation. Our work introduces a unified framework to advance memory RL research, enabling more robust systems for real-world use. MIKASA is available at https://tinyurl.com/membenchrobots.

Memory is crucial for enabling agents to tackle complex tasks with temporal and spatial dependencies.

World models are becoming central to robotic planning and control as they enable prediction of future state transitions. Existing approaches often emphasize video generation or natural-language prediction, which are difficult to ground in robot actions and suffer from compounding errors over long horizons. Classic task and motion planning models world transitions in logical space, enabling robot-executable and robust long-horizon reasoning. However, they typically operate independently of visual perception, preventing synchronized symbolic and visual state prediction. We propose a Hierarchical World Model (H-WM) that jointly predicts logical and visual state transitions within a unified framework. H-WM combines a high-level logical world model with a low-level visual world model, integrating the long-horizon robustness of symbolic reasoning with visual grounding. The hierarchical outputs provide stable intermediate guidance for long-horizon tasks, mitigating error accumulation and enabling robust execution across extended task sequences. Experiments across multiple vision-language-action (VLA) control policies demonstrate the effectiveness and generality of H-WM's guidance.

World models are becoming central to robotic planning and control as they enable prediction of future state transitions.

In this paper, we introduce RoboLight, the first real-world robotic manipulation dataset capturing synchronized episodes under systematically varied lighting conditions. RoboLight consists of two components. (a) RoboLight-Real contains 2,800 real-world episodes collected in our custom Light Cube setup, a calibrated system equipped with eight programmable RGB LED lights. It includes structured illumination variation along three independently controlled dimensions: color, direction, and intensity. Each dimension is paired with a dedicated task featuring objects of diverse geometries and materials to induce perceptual challenges. All image data are recorded in high-dynamic-range (HDR) format to preserve radiometric accuracy. Leveraging the linearity of light transport, we introduce (b) RoboLight-Synthetic, comprising 196,000 episodes synthesized through interpolation in the HDR image space of RoboLight-Real. In principle, RoboLight-Synthetic can be arbitrarily expanded by refining the interpolation granularity. We further verify the dataset quality through qualitative analysis and real-world policy roll-outs, analyzing task difficulty, distributional diversity, and the effectiveness of synthesized data. We additionally demonstrate three representative use cases of the proposed dataset. The full dataset, along with the system software and hardware design, will be released as open-source to support continued research.

In this paper, we introduce RoboLight, the first real-world robotic manipulation dataset capturing synchronized episodes under systematically varied lighting conditions.

Diffusion policies are a powerful paradigm for robot learning, but their training is often inefficient. A key reason is that networks must relearn fundamental spatial concepts, such as translations and rotations, from scratch for every new task. To alleviate this redundancy, we propose embedding geometric inductive biases directly into the network architecture using Projective Geometric Algebra (PGA). PGA provides a unified algebraic framework for representing geometric primitives and transformations, allowing neural networks to reason about spatial structure more effectively. In this paper, we introduce hPGA-DP, a novel hybrid diffusion policy that capitalizes on these benefits. Our architecture leverages the Projective Geometric Algebra Transformer (P-GATr) as a state encoder and action decoder, while employing established U-Net or Transformer-based modules for the core denoising process. Through extensive experiments and ablation studies in both simulated and real-world environments, we demonstrate that hPGA-DP significantly improves task performance and training efficiency. Notably, our hybrid approach achieves substantially faster convergence compared to both standard diffusion policies and architectures that rely solely on P-GATr. The project website is available at: https://apollo-lab-yale.github.io/26-ICRA-hPGA-website/.

Diffusion policies are a powerful paradigm for robot learning, but their training is often inefficient.

Transformers excel across domains, yet their quadratic attention complexity poses a barrier to scaling. Random-feature attention, as in Performers, can reduce this cost to linear in the sequence length by approximating the softmax kernel with positive random features drawn from an isotropic distribution. In pretrained models, however, queries and keys are typically anisotropic. This induces high Monte Carlo variance in isotropic sampling schemes unless one retrains the model or uses a large feature budget. Importance sampling can address this by adapting the sampling distribution to the input geometry, but complex data-dependent proposal distributions are often intractable. We show that by data aligning the softmax kernel, we obtain an attention mechanism which can both admit a tractable minimal-variance proposal distribution for importance sampling, and exhibits better training stability. Motivated by this finding, we introduce DARKFormer, a Data-Aware Random-feature Kernel transformer that features a data-aligned kernel geometry. DARKFormer learns the random-projection covariance, efficiently realizing an importance-sampled positive random-feature estimator for its data-aligned kernel. Empirically, DARKFormer narrows the performance gap with exact softmax attention, particularly in finetuning regimes where pretrained representations are anisotropic. By combining random-feature efficiency with data-aware kernels, DARKFormer advances kernel-based attention in resource-constrained settings.

Transformers excel across domains, yet their quadratic attention complexity poses a barrier to scaling.

Autonomous navigation under natural language instructions represents a crucial step toward embodied intelligence, enabling complex task execution in environments ranging from industrial facilities to domestic spaces. However, language-driven 3D navigation for Unmanned Aerial Vehicles (UAVs) requires precise spatial reasoning, a capability inherently lacking in current zero-shot Vision-Language Models (VLMs) which often generate ambiguous outputs and cannot guarantee geometric feasibility. Furthermore, existing Vision-Language Navigation (VLN) methods are predominantly tailored for 2.5D ground robots, rendering them unable to generalize to the unconstrained 3D spatial reasoning required for aerial tasks in small-scale, cluttered environments. In this paper, we present SoraNav, a novel framework enabling zero-shot VLM reasoning for UAV task-centric navigation. To address the spatial-semantic gap, we introduce Multi-modal Visual Annotation (MVA), which encodes 3D geometric priors directly into the VLM's 2D visual input. To mitigate hallucinated or infeasible commands, we propose an Adaptive Decision Making (ADM) strategy that validates VLM proposals against exploration history, seamlessly switching to geometry-based exploration to avoid dead-ends and redundant revisits. Deployed on a custom PX4-based micro-UAV, SoraNav demonstrates robust real-world performance. Quantitative results show our approach significantly outperforms state-of-the-art baselines, increasing Success Rate (SR) by 25.7% and navigation efficiency (SPL) by 17.3% in 2.5D scenarios, and achieving improvements of 39.3% (SR) and 24.7% (SPL) in complex 3D scenarios.

Autonomous navigation under natural language instructions represents a crucial step toward embodied intelligence, enabling complex task execution in environments ranging from industrial facilities to domestic spaces.

Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing approaches to this problem present a difficult choice: training a discrete collection of specialist models is computationally prohibitive, while dynamic methods like slimmable networks often lack the flexibility to be applied to large, pre-trained foundation models. In this work, we propose Nested Subspace Networks (NSNs), a novel architectural paradigm that enables a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets at inference time. The core of our approach is to re-parameterize linear layers to satisfy a nested subspace property, such that the function computed at a given rank is a strict subspace of the function at any higher rank. We show that this entire hierarchy of models can be optimized jointly via an uncertainty-aware objective that learns to balance the contributions of different ranks based on their intrinsic difficulty. We demonstrate empirically that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier. For example, a single NSN-adapted model can achieve a 50% reduction in inference FLOPs with only a 5 percentage point loss in accuracy. Our findings establish NSNs as a powerful framework for creating the next generation of adaptive foundation models.

Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments.

LaViRA: Zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to navigate unseen environments based on natural language instructions without any prior training. Current methods face a critical trade-off: either rely on environment-specific waypoint predictors that limit scene generalization, or underutilize the reasoning capabilities of large models during navigation. We introduce LaViRA, a simple yet effective zero-shot framework that addresses this dilemma by decomposing action into a coarse-to-fine hierarchy: Language Action for high-level planning, Vision Action for middle-level perceptual grounding, and Robot Action for low-level control. This modular decomposition allows us to leverage the distinct strengths of different scales of Multimodal Large Language Models (MLLMs) at each stage, creating a system that is powerful in its reasoning, grounding and practical control. LaViRA significantly outperforms existing state-of-the-art methods on the VLN-CE benchmark, demonstrating superior generalization capabilities in unseen environments, while maintaining transparency and efficiency for real-world deployment. Project page: https://robo-lavira.github.io/lavira-zs-vln/

LaViRA: Zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to navigate unseen environments based on natural language instructions without any prior training.

We propose a new concept, Evolution 6.0, which represents the evolution of robotics driven by Generative AI. When a robot lacks the necessary tools to accomplish a task requested by a human, it autonomously designs the required instruments and learns how to use them to achieve the goal. Evolution 6.0 is an autonomous robotic system powered by Vision-Language Models (VLMs), Vision-Language Action (VLA) models, and Text-to-3D generative models for tool design and task execution. The system comprises two key modules: the Tool Generation Module, which fabricates task-specific tools from visual and textual data, and the Action Generation Module, which converts natural language instructions into robotic actions. It integrates QwenVLM for environmental understanding, OpenVLA for task execution, and Llama-Mesh for 3D tool generation. Evaluation results demonstrate a 90% success rate for tool generation with a 10-second inference time, and action generation achieving 83.5% in physical and visual generalization, 70% in motion generalization, and 37% in semantic generalization. Future improvements will focus on bimanual manipulation, expanded task capabilities, and enhanced environmental interpretation to improve real-world adaptability.

We propose a new concept, Evolution 6.0, which represents the evolution of robotics driven by Generative AI.

Locating and grasping of objects by robots is typically performed using visual sensors. Haptic feedback from contacts with the environment is only secondary if present at all. In this work, we explored an extreme case of searching for and grasping objects in complete absence of visual input, relying on haptic feedback only. The main novelty lies in the use of contacts over the complete surface of a robot manipulator covered with sensitive skin. The search is divided into two phases: (1) coarse workspace exploration with the complete robot surface, followed by (2) precise localization using the end-effector equipped with a force/torque sensor. We systematically evaluated this method in simulation and on the real robot, demonstrating that diverse objects can be located, grasped, and put in a basket. The overall success rate on the real robot for one object was 85.7% with failures mainly while grasping specific objects. The method using whole-body contacts is six times faster compared to a baseline that uses haptic feedback only on the end-effector. We also show locating and grasping multiple objects on the table. This method is not restricted to our specific setup and can be deployed on any platform with the ability of sensing contacts over the entire body surface. This work holds promise for diverse applications in areas with challenging visual perception (due to lighting, dust, smoke, occlusion) such as in agriculture when fruits or vegetables need to be located inside foliage and picked.

Locating and grasping of objects by robots is typically performed using visual sensors.

Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses and would succeed with a small corrective motion. We propose FlowCorrect, a modular interactive imitation learning approach that enables deployment-time adaptation of flow-matching manipulation policies from sparse, relative human corrections without retraining. During execution, a human provides brief corrective pose nudges via a lightweight VR interface. FlowCorrect uses these sparse corrections to locally adapt the policy, improving actions without retraining the backbone while preserving the model performance on previously learned scenarios. We evaluate on a real-world robot across four tabletop tasks: pick-and-place, pouring, cup uprighting, and insertion. With a low correction budget, FlowCorrect achieves an 80% success rate on previously failed cases while preserving performance on previously solved scenarios. The results clearly demonstrate that FlowCorrect learns from very few demonstrations and enables fast, sample-efficient, incremental, human-in-the-loop corrections of generative visuomotor policies at deployment time in real-world robotics.

Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses and would succeed with a small corrective motion.

Software-hardware co-design is essential for optimizing in-memory computing (IMC) hardware accelerators for neural networks. However, most existing optimization frameworks target a single workload, leading to highly specialized hardware designs that do not generalize well across models and applications. In contrast, practical deployment scenarios require a single IMC platform that can efficiently support multiple neural network workloads. This work presents a joint hardware-workload co-optimization framework based on an optimized evolutionary algorithm for designing generalized IMC accelerator architectures. By explicitly capturing cross-workload trade-offs rather than optimizing for a single model, the proposed approach significantly reduces the performance gap between workload-specific and generalized IMC designs. The framework is evaluated on both RRAM- and SRAM-based IMC architectures, demonstrating strong robustness and adaptability across diverse design scenarios. Compared to baseline methods, the optimized designs achieve energy-delay-area product (EDAP) reductions of up to 76.2% and 95.5% when optimizing across a small set (4 workloads) and a large set (9 workloads), respectively. The source code of the framework is available at https://github.com/OlgaKrestinskaya/JointHardwareWorkloadOptimizationIMC.

Software-hardware co-design is essential for optimizing in-memory computing (IMC) hardware accelerators for neural networks.

Recent progress in vision-language-action (VLA) models has demonstrated strong potential for dual-arm manipulation, enabling complex behaviors and generalization to unseen environments. However, mainstream bimanual VLA formulations largely overlook the critical challenge of combinatorial diversity. Different pairings of single-arm behaviors can induce qualitatively distinct task behaviors, yet existing models do not explicitly account for this structure. We argue that effective bimanual VLAs should support skill reuse - the ability to recombine previously learned single-arm skills across novel left-right pairings - thereby avoiding the need to separately learn every possible combination. Current VLA designs entangle skills across arms, preventing such recomposition and limiting scalability. To address this limitation, we propose SkillVLA, a framework explicitly designed to enable skill reuse in dual-arm manipulation. Extensive experiments demonstrate that SkillVLA substantially improves skill composition, increasing overall success rate from 0% to 51%, and achieves strong performance on cooperative and long-horizon tasks.

Recent progress in vision-language-action (VLA) models has demonstrated strong potential for dual-arm manipulation, enabling complex behaviors and generalization to unseen environments.

Overparameterized machine learning (ML) methods such as neural networks may be prohibitively resource intensive for devices with limited computational capabilities. Hyperdimensional computing (HDC) is an emerging resource efficient and low-complexity ML method that allows hardware efficient implementations of (re-)training and inference procedures. In this paper, we propose a maximum-margin HDC classifier, which significantly outperforms baseline HDC methods on several benchmark datasets. Our method leverages a formal relation between HDC and support vector machines (SVMs) that we established for the first time. Our findings may inspire novel HDC methods with potentially more hardware-oriented implementations compared to SVMs, thus enabling more efficient learning solutions for various intelligent resource-constrained applications.

Overparameterized machine learning (ML) methods such as neural networks may be prohibitively resource intensive for devices with limited computational capabilities.

Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual learning in relatively small behavior cloning (BC) policy models trained from scratch, its behavior in modern large-scale pretrained Vision-Language-Action (VLA) models remains underexplored. In this work, we found that pretrained VLAs are remarkably resistant to forgetting compared with smaller policy models trained from scratch. Simple Experience Replay (ER) works surprisingly well on VLAs, sometimes achieving zero forgetting even with a small replay data size. Our analysis reveals that pretraining plays a critical role in downstream continual learning performance: large pretrained models mitigate forgetting with a small replay buffer size while maintaining strong forward learning capabilities. Furthermore, we found that VLAs can retain relevant knowledge from prior tasks despite performance degradation during learning new tasks. This knowledge retention enables rapid recovery of seemingly forgotten skills through finetuning. Together, these insights imply that large-scale pretraining fundamentally changes the dynamics of continual learning, enabling models to continually acquire new skills over time with simple replay. Code and more information can be found at https://ut-austin-rpl.github.io/continual-vla

Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones.

Central Bank Digital Currency (CBDCs) are becoming a new digital financial tool aimed at financial inclusion, increased monetary stability, and improved efficiency of payment systems, as they are issued by central banks. One of the most important aspects is that the CBDC must offer secure offline payment methods to users, allowing them to retain cash-like access without violating Anti-Money Laundering and Counter-terrorism Financing (AML/CFT) rules. The offline CBDC ecosystems will provide financial inclusion, empower underserved communities, and ensure equitable access to digital payments, even in connectivity-poor remote locations. With the rapid growth of Internet of Things (IoT) devices in our everyday lives, they are capable of performing secure digital transactions. Integrating offline CBDC payment with IoT devices enables seamless, automated payment without internet connectivity. However, IoT devices face special challenges due to their resource-constrained nature. This makes it difficult to include features such as double-spending prevention, privacy preservation, low-computation operation, and digital identity management. The work proposes a privacy-preserving offline CBDC model with integrated secure elements (SEs), zero-knowledge proofs (ZKPs), and intermittent synchronisation to conduct offline payments on IoT hardware. The proposed model is based on recent improvements in offline CBDC prototypes, regulations and cryptographic design choices such as hybrid architecture that involves using combination of online and offline payment in IoT devices using secure hardware with lightweight zero-knowledge proof cryptographic algorithm.

Central Bank Digital Currency (CBDCs) are becoming a new digital financial tool aimed at financial inclusion, increased monetary stability, and improved efficiency of payment systems, as they are issued by central banks.

Achieving 3D spatial awareness is crucial for surgical robotic manipulation, where precise and delicate operations are required. Existing methods either explicitly reconstruct the surgical scene prior to manipulation, or enhance multi-view features by adding wrist-mounted cameras to supplement the default stereo endoscopes. However, both paradigms suffer from notable limitations: the former easily leads to error accumulation and prevents end-to-end optimization due to its multi-stage nature, while the latter is rarely adopted in clinical practice since wrist-mounted cameras can interfere with the motion of surgical robot arms. In this work, we introduce the Spatial Surgical Transformer (SST), an end-to-end visuomotor policy that empowers surgical robots with 3D spatial awareness by directly exploring 3D spatial cues embedded in endoscopic images. First, we build Surgical3D, a large-scale photorealistic dataset containing 30K stereo endoscopic image pairs with accurate 3D geometry, addressing the scarcity of 3D data in surgical scenes. Based on Surgical3D, we finetune a powerful geometric transformer to extract robust 3D latent representations from stereo endoscopes images. These representations are then seamlessly aligned with the robot's action space via a lightweight multi-level spatial feature connector (MSFC), all within an endoscope-centric coordinate frame. Extensive real-robot experiments demonstrate that SST achieves state-of-the-art performance and strong spatial generalization on complex surgical tasks such as knot tying and ex-vivo organ dissection, representing a significant step toward practical clinical deployment. The dataset and code will be released.

Achieving 3D spatial awareness is crucial for surgical robotic manipulation, where precise and delicate operations are required.

Vision-Language Models (VLMs) have shown remarkable capabilities in spatial reasoning, yet they remain fundamentally limited to qualitative precision and lack the computational precision required for real-world robotics. Current approaches fail to leverage metric cues from depth sensors and camera calibration, instead reducing geometric problems to pattern recognition tasks that cannot deliver the centimeter-level accuracy essential for robotic manipulation. We present TIGeR (Tool-Integrated Geometric Reasoning), a novel framework that transforms VLMs from perceptual estimators to geometric computers by enabling them to generate and execute precise geometric computations through external tools. Rather than attempting to internalize complex geometric operations within neural networks, TIGeR empowers models to recognize geometric reasoning requirements, synthesize appropriate computational code, and invoke specialized libraries for exact calculations. To support this paradigm, we introduce TIGeR-300K, a comprehensive tool-invocation-oriented dataset covering point transformations, pose estimation, and spatial compatibility verification, complete with tool invocation sequences and intermediate computations. Through a two-stage training pipeline combining supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT) with our proposed hierarchical reward design, TIGeR achieves SOTA performance on geometric reasoning benchmarks while demonstrating centimeter-level precision in real-world robotic manipulation tasks.

Vision-Language Models (VLMs) have shown remarkable capabilities in spatial reasoning, yet they remain fundamentally limited to qualitative precision and lack the computational precision required for real-world robotics.

Effective human-robot collaboration (HRC) requires translating high-level intent into contact-stable whole-body motion while continuously adapting to a human partner. Many vision-language-action (VLA) systems learn end-to-end mappings from observations and instructions to actions, but they often emphasize reactive (System 1-like) behavior and leave under-specified how sustained System 2-style deliberation can be integrated with reliable, low-latency continuous control. This gap is acute in multi-agent HRC, where long-horizon coordination decisions and physical execution must co-evolve under contact, feasibility, and safety constraints. We address this limitation with cognition-to-control (C2C), a three-layer hierarchy that makes the deliberation-to-control pathway explicit: (i) a VLM-based grounding layer that maintains persistent scene referents and infers embodiment-aware affordances/constraints; (ii) a deliberative skill/coordination layer-the System 2 core-that optimizes long-horizon skill choices and sequences under human-robot coupling via decentralized MARL cast as a Markov potential game with a shared potential encoding task progress; and (iii) a whole-body control layer that executes the selected skills at high frequency while enforcing kinematic/dynamic feasibility and contact stability. The deliberative layer is realized as a residual policy relative to a nominal controller, internalizing partner dynamics without explicit role assignment. Experiments on collaborative manipulation tasks show higher success and robustness than single-agent and end-to-end baselines, with stable coordination and emergent leader-follower behaviors.

Effective human-robot collaboration (HRC) requires translating high-level intent into contact-stable whole-body motion while continuously adapting to a human partner.

Vision-Language Navigation (VLN) is evolving from single-point pathfinding toward the more challenging Multi-Goal VLN. This task requires agents to accurately identify multiple entities while collaboratively reasoning over their spatial-physical constraints and sequential execution order. However, generic Retrieval-Augmented Generation (RAG) paradigms often suffer from spatial hallucinations and planning drift when handling multi-object associations due to the lack of explicit spatial modeling.To address these challenges, we propose RAGNav, a framework that bridges the gap between semantic reasoning and physical structure. The core of RAGNav is a Dual-Basis Memory system, which integrates a low-level topological map for maintaining physical connectivity with a high-level semantic forest for hierarchical environment abstraction. Building on this representation, the framework introduces an anchor-guided conditional retrieval and a topological neighbor score propagation mechanism. This approach facilitates the rapid screening of candidate targets and the elimination of semantic noise, while performing semantic calibration by leveraging the physical associations inherent in the topological neighborhood.This mechanism significantly enhances the capability of inter-target reachability reasoning and the efficiency of sequential planning. Experimental results demonstrate that RAGNav achieves state-of-the-art (SOTA) performance in complex multi-goal navigation tasks.

Vision-Language Navigation (VLN) is evolving from single-point pathfinding toward the more challenging Multi-Goal VLN.

Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial structure. We propose PROSPECT, a unified streaming navigation agent that couples a streaming Vision-Language-Action (VLA) policy with latent predictive representation learning. PROSPECT uses CUT3R as a streaming 3D foundation spatial encoder to produce long-context, absolute-scale spatial features, and fuses them with SigLIP semantic features via cross-attention. During training, we introduce learnable stream query tokens that query the streaming context and predict next-step 2D and 3D latent features (rather than pixels or explicit modalities), supervised in the latent spaces of frozen SigLIP and CUT3R teachers. The predictive branch shapes internal representations without inference overhead. Experiments on VLN-CE benchmarks and real-robot deployment demonstrate state-of-the-art performance and improved long-horizon robustness under diverse lighting. We will release code for the community soon.

Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial structure.

Motivation: Sparse autoencoders (SAEs) decompose foundation model activations into interpretable features, but causal feature-to-feature interactions across network depth remain unknown for biological foundation models. Results: We introduce causal circuit tracing by ablating SAE features and measuring downstream responses, and apply it to Geneformer V2-316M and scGPT whole-human across four conditions (96,892 edges, 80,191 forward passes). Both models show approximately 53 percent biological coherence and 65 to 89 percent inhibitory dominance, invariant to architecture and cell type. scGPT produces stronger effects (mean absolute d = 1.40 vs. 1.05) with more balanced dynamics. Cross-model consensus yields 1,142 conserved domain pairs (10.6x enrichment, p < 0.001). Disease-associated domains are 3.59x more likely to be consensus. Gene-level CRISPRi validation shows 56.4 percent directional accuracy, confirming co-expression rather than causal encoding.

Motivation: Sparse autoencoders (SAEs) decompose foundation model activations into interpretable features, but causal feature-to-feature interactions across network depth remain unknown for biological foundation models.

Convolutional Neural Networks (CNNs) have achieved state-of-the-art accuracy in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). However, their high computational cost, latency, and memory footprint make its deployment challenging on resource-constrained platforms such as small satellites. While adversarial robustness is critical for real-world SAR ATR, it is often overlooked in system-level optimizations. Achieving both robustness and inference efficiency requires a unified framework that considers adversarially trained models together with hardware constraints. We present a model-hardware co-design framework for CNN-based SAR ATR that integrates robustness-preserving model compression with FPGA accelerator design. The compression stage includes hardware-guided structured pruning, where a hardware performance model derived from the FPGA design predicts the pruning impact on latency and resource usage. This enables the generation of Pareto-optimal models that improve hardware efficiency under user-defined objectives, while maintaining adversarial robustness within a predefined tolerance. We design an FPGA accelerator with channel-aware Processing Element (PE) allocation that supports both fully pipelined streaming and temporal resource-reuse architectures. An automated design generation flow efficiently maps the compressed models to optimized FPGA implementations. Experiments on the widely used MSTAR and FUSAR-Ship datasets across three CNN architectures show that our framework produces models up to 18.3x smaller with 3.1x fewer MACs while preserving robustness. Our FPGA implementation achieves up to 68.1x (6.4x) lower inference latency and up to 169.7x (33.2x) better energy efficiency compared to CPU (GPU) baselines, demonstrating the effectiveness of the proposed co-design framework for robust and efficient SAR ATR on FPGA platforms.

Convolutional Neural Networks (CNNs) have achieved state-of-the-art accuracy in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR).

Model Predictive Control (MPC) enables reliable trajectory optimization under dynamics constraints, but often depends on accurate dynamics models and carefully hand-designed cost functions. Recent learning-based MPC methods aim to reduce these modeling and cost-design burdens by learning dynamics, priors, or value-related guidance signals. Yet many existing approaches still rely on deterministic gradient-based solvers (e.g., differentiable MPC) or parametric sampling-based updates (e.g., CEM/MPPI), which can lead to mode collapse and convergence to a single dominant solution. We propose Q-SVMPC, a Q-guided Stein variational MPC method with an RL-informed policy prior, which casts learning-based MPC as trajectory-level posterior inference and refines trajectory particles via SVGD under learned soft Q-value guidance to explicitly preserve diverse solutions. Experiments on navigation, robotic manipulation, and a real-world fruit-picking task show improved sample efficiency, stability, and robustness over MPC, model-free RL, and learning-based MPC baselines.

Model Predictive Control (MPC) enables reliable trajectory optimization under dynamics constraints, but often depends on accurate dynamics models and carefully hand-designed cost functions.

While Unmanned Aerial Vehicles (UAVs) have gained significant traction across various fields, path planning in 3D environments remains a critical challenge, particularly under size, weight, and power (SWAP) constraints. Traditional modular planning systems often introduce latency and suboptimal performance due to limited information sharing and local minima issues. End-to-end learning approaches streamline the pipeline by mapping sensory observations directly to actions but require large-scale datasets, face significant sim-to-real gaps, or lack dynamical feasibility. In this paper, we propose a self-supervised UAV trajectory planning pipeline that integrates a learning-based depth perception with differentiable trajectory optimization. A 3D cost map guides UAV behavior without expert demonstrations or human labels. Additionally, we incorporate a neural network-based time allocation strategy to improve the efficiency and optimality. The system thus combines robust learning-based perception with reliable physics-based optimization for improved generalizability and interpretability. Both simulation and real-world experiments validate our approach across various environments, demonstrating its effectiveness and robustness. Our method achieves a 31.33% improvement in position tracking error and 49.37% reduction in control effort compared to the state-of-the-art.

While Unmanned Aerial Vehicles (UAVs) have gained significant traction across various fields, path planning in 3D environments remains a critical challenge, particularly under size, weight, and power (SWAP) constraints.

Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale demonstration datasets. Although reinforcement learning (RL)-based post-training has proven effective in addressing data scarcity, its application to VLA models is hindered by the non-resettable nature of real-world environments. This limitation is particularly critical in high-risk domains such as industrial automation, where interactions often induce state changes that are costly or infeasible to revert. Furthermore, existing VLA approaches lack a reliable mechanism for detecting task completion, leading to redundant actions that reduce overall task success rates. To address these challenges, we propose RehearseVLA:, an RL-based post-training framework that replaces physical interaction with a low-cost world model-based virtual simulator. RehearseVLA: consists of two key components: (1) a physically-consistent world simulator that generates temporally consistent future visual observations, and (2) a vision-language model (VLM)-guided instant reflector that provides continuous reward signals and predicts action termination. This simulated environment enables VLA models to safely explore and generalize beyond their initial imitation learning distribution. Our method achieves notable performance gains with as few as five expert demonstrations per task. Experiments on complex robotic manipulation tasks demonstrate that RehearseVLA: effectively overcomes the data inefficiency, safety constraints, and inefficient execution of conventional VLA models that rely on real-world interaction, offering a practical and scalable solution for post-training in resource-constrained settings. Our code is available at https://github.com/amap-cvlab/world-env.

Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale demonstration datasets.