Daily Papers Arch&EAI

Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, especially on heterogeneous edge devices. Existing inference runtimes are designed mainly for request-response serving and therefore do not satisfy the runtime contract of embodied deployment: multi-rate execution inside closed-loop control, latency-first batch-1 inference on heterogeneous hardware, and extensible embodied interfaces beyond fixed token I/O. We present Embodied.cpp, a portable C++ inference runtime for embodied models. Based on an architectural analysis of representative VLA models and WAMs, Embodied.cpp captures a shared execution path and organizes it into five layers: input adapters, sequence builders, backbone execution, head plugins, and deployment adapters. The runtime provides modular multi-rate execution, latency-first fused inference, and extensible operator and I/O support, enabling deployment across heterogeneous devices, robots, and simulators through one backend abstraction. We evaluate Embodied.cpp on two VLA models, HY-VLA and pi0.5, and on a preliminary WAM benchmark using a LingBot-VA Transformer block. The VLA deployments achieve successful closed-loop execution with 100.0% and 91.0% task success rates, respectively. The WAM benchmark reduces block memory from 312.2 MiB to 88.1 MiB. These results show that Embodied.cpp improves deployment efficiency while preserving high accuracy across diverse embodied model architectures.

Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, especially on heterogeneous edge devices.

"Code-as-Policy" considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored. We present CaP-X, an open-access framework for systematically studying Code-as-Policy agents in robot manipulation. At its core is CaP-Gym, an interactive environment in which agents control robots by synthesizing and executing programs that compose perception and control primitives. Building on this foundation, CaP-Bench evaluates frontier language and vision-language models across varying levels of abstraction, interaction, and perceptual grounding. Across 12 models, CaP-Bench reveals a consistent trend: performance improves with human-crafted abstractions but degrades as these priors are removed, exposing a dependence on designer scaffolding. At the same time, we observe that this gap can be mitigated through scaling agentic test-time computation--through multi-turn interaction, structured execution feedback, visual differencing, automatic skill synthesis, and ensembled reasoning--substantially improves robustness even when agents operate over low-level primitives. These findings allow us to derive CaP-Agent0, a training-free framework that recovers human-level reliability on several manipulation tasks in simulation and on real embodiments. We further introduce CaP-RL, showing reinforcement learning with verifiable rewards improves success rates and transfers from sim2real with minimal gap. Together, CaP-X provides a principled, open-access platform for advancing embodied coding agents.

"Code-as-Policy" considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored.

Vision-Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations -- triplets of observations, instructions, and actions that are costly to collect at scale. We argue that this bottleneck stems from conflating two distinct learning objectives: acquiring physical competence (how to move) and acquiring semantic alignment (what to do). Crucially, only the latter requires language supervision. Building on this Decomposition Hypothesis, we propose Task-Agnostic Pretraining (TAP), a two-stage framework that first learns transferable motor priors from cheap, unlabeled interaction data -- including discarded off-task trajectories and autonomous robot play -- via a self-supervised Inverse Dynamics objective. A lightweight second stage then grounds these priors in language using minimal expert data. On the SIMPLER benchmark, TAP matches models trained on over 1M expert trajectories while using orders of magnitude less labeled data, yielding a 10% absolute gain over standard behavior cloning. On a real-world WidowX platform, TAP retains 25% success under camera perturbations where internet-scale baselines collapse to 0%, demonstrating that task-agnostic pretraining produces robust, transferable physical representations and offers a scalable path forward for Embodied AI.

Vision-Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations -- triplets of observations, instructions, and actions that are costly to collect at scale.

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, deploying these models in unstructured environments remains challenging due to the critical need for simultaneous task compliance and safety assurance, particularly in preventing potential collisions during physical interactions. In this work, we introduce a Vision-Language-Safe Action (VLSA) architecture, named AEGIS, which contains a plug-and-play safety constraint (SC) layer formulated via control barrier functions. AEGIS integrates directly with existing VLA models to improve safety with theoretical guarantees, while maintaining their original instruction-following performance. To evaluate the efficacy of our architecture, we construct a comprehensive safety-critical benchmark SafeLIBERO, spanning distinct manipulation scenarios characterized by varying degrees of spatial complexity and obstacle intervention. Extensive experiments demonstrate the superiority of our method over state-of-the-art baselines. Notably, AEGIS achieves over 50% improvement in obstacle avoidance rate while substantially increasing the task success rate by nearly 10%. All benchmark datasets, code, and supplementary materials are publicly available at https://vlsa-aegis.github.io/.

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks.

Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations. However, deploying RL on real robots remains constrained by high interaction costs, since each physical rollout is costly and reflects only one realized action-outcome path. To address this challenge, we propose WorldSample, a physically grounded data augmentation framework for real-robot RL that closes a real-synthetic loop between physical rollouts, world-model generation, and policy improvement. Grounded on real rollouts, WorldSample generates high-fidelity synthetic transitions through a post-trained world model, which greatly lowers the visual hallucination. Specifically, rather than simply using these transitions as real-world experience, WorldSample introduces Policy-Paced Learning (PPL) to regulate the training process through sample selection and scheduling, balancing useful augmentation against value overestimation and mitigating the hallucination-induced noise. Experiments on robot manipulation tasks involving contact-rich and precise tasks show that WorldSample improves policy success rate by 28% while reducing training steps by 59% compared with baselines. Furthermore, WorldSample improves world model visual fidelity by 19.4dB in PSNR and 0.47 in SSIM over demonstration-only post-training, validating the effectiveness of the real-synthetic loop for both policy and world model performance.

Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations.

We present a 65-nm risk-aware multimodal Bayesian inference engine for privacy-preserving, fully on-device skin lesion screening under uncontrolled at-home conditions. The proposed compute-in-memory architecture performs in-word Mixture-of-Gaussian sampling, improving uncertainty modeling beyond conventional unimodal Bayesian neural networks. This added probabilistic expressiveness increases equal-risk operating coverage by 1.4x, improves robustness to user-data perturbations by >1.5x, enhances process-variation resilience by 5.5x, and improves balanced accuracy by 1.8% over state-of-the-art unimodal Bayesian neural networks. Hardware robustness is further supported by calibration-free Gaussian random-number generation using complementary process variation, achieving 16.3 fJ/sample and 168.6 GSa/s/mm^2 efficiency. These results demonstrate a practical, energy-efficient, and risk-aware edge-AI solution for privacy-conscious medical screening.

We present a 65-nm risk-aware multimodal Bayesian inference engine for privacy-preserving, fully on-device skin lesion screening under uncontrolled at-home conditions.

Aerial search and rescue missions require fast and reliable victim detection under uncertain and rapidly changing environments. Deterministic deep learning models can produce overconfident false positives, forcing unmanned aircraft systems to perform costly verification maneuvers that reduce search coverage and increase rescue delay. Bayesian neural networks provide uncertainty-aware detection, but their sampling overhead is challenging for battery-constrained edge platforms. This work presents a FeFET-based Bayesian inference engine with a write-free central limit theorem Gaussian random number generator embedded in a compute-in-memory macro. By summing currents from a randomly selected subset of minimum-sized, programmed-once FeFETs, the proposed architecture eliminates energy- and endurance-intensive write operations during inference while maintaining scalable Gaussian sampling. The CLT-GRNG consumes 640 aJ per sample, providing a 560x energy-efficiency improvement over prior BNN accelerators, while the CIM tile achieves 185 TOPS/W/mm2. Evaluated on aerial search and rescue detection, the Bayesian model improves uncertainty calibration and robustness under environmental corruption, reducing risk and enabling low-confidence detections to be filtered before costly verification. These results demonstrate an energy-efficient and uncertainty-aware edge AI engine for autonomous search and rescue systems.

Aerial search and rescue missions require fast and reliable victim detection under uncertain and rapidly changing environments.

Transformer architectures have shown strong potential in time series forecasting, where multi-head self-attention is widely used to capture temporal dependencies across historical timestamps. However, standard self-attention has quadratic time and memory complexity with respect to the look-back length. This cost may limit its use in resource-constrained or high-throughput forecasting systems, where fast and memory-efficient inference is important. Through qualitative and quantitative analyses, we observe that self-attention maps in time series forecasting often contain redundant patterns across different timestamps. This phenomenon can be related to the repeated temporal patterns and relatively stable temporal correlations in many real-world time series. Motivated by this observation, we propose Self-Gating Attention (SGA), a plug-and-play attention mechanism that represents the attention score with a shared learnable matrix and an input-dependent residual component. The shared matrix captures common attention patterns, while the residual component captures input-dependent variations. In this way, SGA avoids the query and key projections used in standard attention score computation, leading to linear time and score-matrix memory complexity with respect to the look-back length. We integrate SGA into several forecasting backbones and compare it with standard self-attention and lightweight attention variants on nine publicly available real-world datasets covering electricity, finance, weather, medical monitoring, human activity, and climate records. The results show that SGA improves inference efficiency on public benchmarks while maintaining competitive forecasting performance against state-of-the-art attention mechanisms. These benchmark results provide deployment-oriented evidence.

Transformer architectures have shown strong potential in time series forecasting, where multi-head self-attention is widely used to capture temporal dependencies across historical timestamps.

Vision-Language-Action (VLA) models have shown remarkable promise in generalized robotic manipulation. However, their spatial generalization remains fragile. We argue that simply increasing the number of viewpoints is insufficient. Models often fall into the trap of Shortcut Learning, latching onto spurious correlations (e.g., fixed relative poses between objects or between the camera and robot base) rather than learning true spatial relationships. In this work, we propose a data-centric solution to enhance VLA spatial generalization. We utilize a dual-arm setup where one arm performs manipulation while the other serves as a mobile environmental camera. We systematically evaluate three data distribution patterns: Fixed, Multi-Fixed, and Moving Views. Our findings reveal that a hybrid strategy, combining continuous camera motion with diverse static viewpoints, yields the best performance by substantially reducing spurious correlations while maintaining training stability. Our experiments demonstrate that this strategy mitigates spurious correlations, enabling VLAs to generalize to unseen camera poses and object configurations where simply adding more static viewpoints fails. Crucially, we reveal that the susceptibility to shortcut learning and the struggle with spatial generalization are universal characteristics shared across diverse architectures. Consequently, all evaluated models (ACT, Diffusion, and VLA models including Pi0 and Gr00t) benefit significantly from our mixed data strategy.

Vision-Language-Action (VLA) models have shown remarkable promise in generalized robotic manipulation.

Vision-Language Navigation has increasingly emphasized high-level instruction reasoning, memory, global map construction, and instruction decomposition, while the low-level action representation remains comparatively underexplored. We propose CoFL-S, a low-level vision-language-action framework that predicts a language-conditioned flow field over the robot's local visible sector and generates continuous trajectories by rolling out the predicted field. To train this low-level representation, we convert each VLN-CE episode, originally a whole-episode instruction paired with an action sequence, into frame-level local supervision with aligned sub-instructions and matched action, trajectory, and dense flow-field targets. For evaluation, we introduce a continuous-time Habitat benchmark that isolates low-level action interfaces from instruction decomposition and executes all methods through a shared velocity-command controller, enabling decomposition-independent closed-loop comparison across different planner frequencies rather than fixed discrete forward-and-turn transitions in VLN-CE. Under matched encoders and training settings, CoFL-S consistently outperforms action-token and action-chunk baselines across planner frequencies in the continuous-time Habitat benchmark, and zero-shot real-world closed-loop deployment further shows its advantage over both baselines beyond simulation.

Vision-Language Navigation has increasingly emphasized high-level instruction reasoning, memory, global map construction, and instruction decomposition, while the low-level action representation remains comparatively underexplored.

Mutual information (MI)-inspired feature learning techniques are capable of generating low-dimensional embeddings that retain nonlinear dependence structures, but direct estimations of MI suffer from noisy probability distribution estimates in the low-data regime. The H-Score objective, computed from second-order statistics, provides a practical proxy metric for training feature extraction networks. We prove that H-Score is invariant to invertible transformations in the unrestricted functional setting, but becomes sensitive to input basis rotations under constrained approximation classes. Consequently, we study unitary preconditioning for H-Score networks and show that selecting an appropriate basis rotation reduces finite-width truncation error by concentrating predictive dependence into fewer dominant modes. We identify the fast Fourier transform (FFT) as an effective data-independent, low-cost preconditioner for approximately stationary processes, where spectral structure induces concentration of the cross-covariance singular value spectrum. We introduce training-free metrics based on spectral entropy and cumulative dependence energy to quantify basis suitability and predict downstream inference gains prior to network training. Experiments across eight multivariate datasets demonstrate that FFT preconditioning is particularly useful in resource-constrained regimes, achieving up to 50% normalized mean squared error (NMSE) reduction, while the proposed metrics correlate with observed performance gains and correctly identify cases where spectral preconditioning is detrimental.

Mutual information (MI)-inspired feature learning techniques are capable of generating low-dimensional embeddings that retain nonlinear dependence structures, but direct estimations of MI suffer from noisy probability distribution estimates in the low-data regime.

This paper presents an intelligent control framework for trajectory tracking of robotic manipulators using radial basis function (RBF) neural networks for online disturbance estimation. The proposed control structure combines model-based nonlinear control with an adaptive neural approximator that compensates for parametric uncertainties, friction, and unmodeled dynamics. A Lyapunov-based adaptation law with projection guarantees boundedness of the closed-loop signals and convergence of the tracking error to a compact region. The primary objective of this work is to investigate how the choice of activation function within the RBF network influences transient behavior, steady-state accuracy, and control smoothness. The controller is implemented on a robotic manipulator. Experimental results demonstrate that although stability is preserved for all kernels, activation function selection significantly affects adaptation dynamics and practical tracking performance. These findings demonstrate that activation function selection acts as a structural design parameter in intelligent control, directly shaping adaptation dynamics and practical closed-loop performance.

This paper presents an intelligent control framework for trajectory tracking of robotic manipulators using radial basis function (RBF) neural networks for online disturbance estimation.

Flow-matching vision-language-action policies generate robot action chunks through an iterative transport process, creating an opportunity for test-time guidance without retraining the base policy. We study this opportunity in Guided Action Flow, an inference-time framework that keeps a pretrained SmolVLA policy frozen and uses a learned action-chunk critic to guide its reverse-time flow sampler. The critic is trained from real success and failure rollouts, can condition on task-description features from the frozen SmolVLA language pathway, and is used only through action gradients during sampling. We evaluate the approach on LIBERO manipulation tasks. A single-task critic improves success from 68.0% to 82.0% on one seed window and from 82.0% to 86.0% on another. A multi-family task-description critic improves validation success from 46.0% to 56.0%, while the locked held-out test gain is positive but modest, from 65.0% to 67.5%. These results support the feasibility of Q-guided inference for frozen flow-matching VLA policies, while showing that critic generalization and uncertainty-aware guidance remain the central bottlenecks.

Flow-matching vision-language-action policies generate robot action chunks through an iterative transport process, creating an opportunity for test-time guidance without retraining the base policy.

Recent advances in multimodal large models have significantly improved UAV vision-language navigation (UAV-VLN) by enhancing high-level perception and reasoning. However, existing methods mainly focus on predicting discrete actions, local targets, or sparse waypoints, while the continuous transition from navigation intent to executable UAV motion remains weakly modeled. This motion-interface gap limits the continuity, stability, and executability of generated UAV trajectories. To address this gap, we propose DynFly, a dynamic-aware continuous trajectory generation framework that bridges high-level navigation reasoning and executable UAV motion. DynFly bridges high-level navigation intent and continuous UAV motion through a lightweight trajectory generation layer. Specifically, it represents expert trajectories in B-spline control-point space and employs a Spline-DiT generator to learn conditional trajectory generation via flow matching. Furthermore, we introduce UAV-oriented dynamic-aware supervision over position, finite-difference velocity, finite-difference acceleration, heading consistency, and local target alignment, enabling the generated trajectories to better satisfy UAV motion characteristics. And our trajectory generation framework can also be integrated with an existing UAV-VLN framework while preserving its original visual-language reasoning pipeline. Extensive experiments on the OpenUAV UAV-VLN benchmark show that DynFly improves both navigation performance and trajectory quality. On the Test Unseen Full split, DynFly improves the strongest baseline by 4.69 NDTW, 2.40 SDTW, 2.14 SR points and 4.87 OSR points, while reducing NE by 4.51 m.

Recent advances in multimodal large models have significantly improved UAV vision-language navigation (UAV-VLN) by enhancing high-level perception and reasoning.

Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints. Such differences make architecture rankings difficult to interpret. This study presents a controlled benchmark of seven established CNNs across CIFAR-10, CIFAR-100, and Tiny ImageNet under a shared fine tuning protocol. The evaluation reports top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 parameter storage, and multiply accumulate operations. EfficientNetV2-S records the highest observed top-1 accuracy on all three datasets, reaching 97.57%, 86.98%, and 78.73%. EfficientNet-B0 remains within 0.85 percentage points of EfficientNetV2-S across the three datasets while requiring only about 21% of its parameters and 14% of its multiply accumulate operations on Tiny ImageNet. It therefore offers a favorable general balance between predictive performance and computational demand. MobileNetV3-Small is a strong candidate for ultra low resource settings. It uses about 40% of the parameters and 15% of the multiply accumulate operations of EfficientNet-B0 while retaining competitive accuracy. A matched comparison of ImageNet pretrained and randomly initialized EfficientNet-B0 and MobileNetV3-Small models shows that the pretrained advantage is substantially larger on CIFAR-100 and Tiny ImageNet than on CIFAR-10 under the fixed protocol. The results provide a focused reference for selecting established lightweight CNNs when predictive quality, parameter storage, and theoretical computation must be considered together.

Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.

Manipulating fast and dynamically moving targets in unstructured 3D environments remains challenging for embodied AI. Existing visual-language-action models and world models struggle with accurate 3D geometry and physically meaningful forecasting. We propose PhysMani, a framework that couples a physics-principled 3D Gaussian world model with a future-aware action policy model. The world model learns a divergence-free Gaussian velocity field via online optimization for fast and physically grounded future dynamics prediction. The policy model integrates the predicted 3D scene future dynamics through a learnable token based cross-attention module. We introduce PhysMani-Bench, a dynamic manipulation benchmark with 16 tasks, and demonstrate a superior success rate over strong baselines in both simulation and real-world robot experiments.

Manipulating fast and dynamically moving targets in unstructured 3D environments remains challenging for embodied AI.

Quasi-bimodal objects, such as text, road signs, and barcodes, play a basic yet vital role in daily visual communication. By boiling these down to clear silhouettes, binarization uses a minimal language to convey essential vision cues for maximum downstream efficiency, especially for tasks that require simple geometric, topological reasoning rather than heavy appearance modeling. The catch is that frame-based imaging often struggles on mobile platforms like drones, self-driving cars, and underwater vehicles, in which rapid motion causes severe motion blur and harsh lighting washes out scene details. To overcome these physical limits, neuromorphic vision via event cameras, featuring microsecond time resolution and high dynamic range, steps in as a natural solution. Building upon this event-driven paradigm, we propose a simple yet effective dual-modal approach that harnesses the synergy between frames and events for training-free, real-time, high-frame-rate binarization on CPU-only devices. Extensive evaluations show that it earns competitive performance against leading techniques in reducing blur artifacts and delivers impressive improvements under challenging illumination at a lower computational cost. Besides, its asynchronous nature bypasses long-standing event-scarcity issues that break traditional time-binning reconstruction at fixed time slots, maintaining clear target shapes even at extreme kilohertz frame rates. Its binary results further serve as reliable representations to facilitate a range of downstream tasks. This work paves the way towards lightweight perception and interaction in embodied intelligence on resource-constrained edge platforms.

Quasi-bimodal objects, such as text, road signs, and barcodes, play a basic yet vital role in daily visual communication.

As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets. However, the end-to-end behavior of LLMs couples serving-layer policies with low-level GPU kernel execution and rapidly evolving architectures, forcing slow, deployment-specific benchmarking that is hard to generalize. We present KernelSight-LM, a fine-grained inference simulator that models token-level execution and produces kernel-level latency breakdowns. It decomposes each serving step into a roofline kernel model with a learned efficiency term, a communication model, and a host-overhead model, composed through a discrete-event scheduler that also captures mechanisms like prefix caching and continuous batching. KernelSight-LM offers two prediction tiers that trade target-GPU data for accuracy. The cross-generation tier uses no target-GPU measurements, only hardware specifications and kernel microbenchmarks from previously profiled GPUs, and predicts per-kernel latency on an unseen GPU generation to 12.1% error, a 1.8x improvement over the roofline baseline (22.0%). A second target-measured tier adds one model-agnostic kernel-microbenchmark sweep on the target GPU, sharpening per-kernel error to 3.8%, a 7.3x improvement over a comparable baseline (27.7%). Both tiers require far less target-GPU data than the prior systems they extend. In our simulator, these predictions yield end-to-end median (p50) errors across six model families of 15.4%, 12.8%, and 3.0% (TTFT, TPOT, throughput) in the cross-generation tier and 14.3%, 6.2%, and 2.7% in the target-measured tier, matching dedicated profiling tools while collecting far less on-device data. Beyond prediction, its kernel-level bottleneck breakdowns support hardware/software co-design and capacity planning.

As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets.

We address the problem of reactive motion planning for quadrotors operating in unknown environments with dynamic obstacles. Our approach leverages a 4-dimensional spatio-temporal planner, integrated with vision-based Safe Flight Corridor (SFC) generation and trajectory optimization. Unlike prior methods that rely on map fusion, our framework is mapless, enabling collision avoidance directly from perception while reducing computational overhead. Dynamic obstacles are detected and tracked using a vision-based object segmentation and tracking pipeline, allowing robust classification of static versus dynamic elements in the scene. To further enhance robustness, we introduce a backup planning module that reactively avoids dynamic obstacles when no direct path to the goal is available, mitigating the risk of collisions during deadlock situations. We validate our method extensively in both simulation and real-world hardware experiments, and benchmark it against state-of-the-art approaches, showing significant advantages for reactive UAV navigation in dynamic, unknown environments.

We address the problem of reactive motion planning for quadrotors operating in unknown environments with dynamic obstacles.

While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively understand their limits and failure modes. To address this, we introduce a comprehensive benchmark called VLA-Arena. We propose a novel structured task design framework to quantify difficulty across three orthogonal axes: (1) Task Structure, (2) Language Command, and (3) Visual Observation. This allows us to systematically design tasks with fine-grained difficulty levels, enabling a precise measurement of model capability frontiers. For Task Structure, VLA-Arena's 170 tasks are grouped into four dimensions: Safety, Distractor, Extrapolation, and Long Horizon. Each task is designed with three difficulty levels (L0-L2), with fine-tuning performed exclusively on L0 to assess general capability. Orthogonal to this, language (W0-W4) and visual (V0-V4) perturbations can be applied to any task to enable a decoupled analysis of robustness. Our extensive evaluation of state-of-the-art VLAs reveals several critical limitations, including a strong tendency toward memorization over generalization, asymmetric robustness, a lack of consideration for safety constraints, and an inability to compose learned skills for long-horizon tasks. To foster research addressing these challenges and ensure reproducibility, we provide the complete VLA-Arena framework, including an end-to-end toolchain from task definition to automated evaluation and the VLA-Arena-S/M/L datasets for fine-tuning. Our benchmark, data, models, and leaderboard are available at https://vla-arena.github.io.

While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively understand their limits and failure modes.

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal understanding, yet their enormous parameter scale and cross-modal computation incur substantial memory and latency overhead, severely limiting real-world deployment on resource-constrained devices. Binarization offers an attractive solution by drastically reducing storage and computational costs. However, existing binarization methods neglect the varying importance of weights across different layers and modalities. This causes parameters irrelevant to downstream tasks to be unnecessarily retained, whereas modality-critical weights may not be adequately optimized, resulting in significant performance degradation. To address these challenges, we develop a novel \underline{S}ignificance-\underline{A}ware \underline{B}inarization for \underline{L}arge \underline{V}ision-\underline{L}anguage \underline{M}odels (SAB-LVLM). Specifically, after constructing Hessian matrices for textual and visual inputs, we propose a spatial significance map to distinguish full-precision weights activated under a single modality from those activated across modalities. We then devise a modality-guided integration strategy to obtain the significance-aware binarization map, which measures weight significance across layers and modalities. Subsequently, this binarization map is incorporated into the binarization objective as an error reweighting term, and binarization fitting is performed through an alternating significance-weighted update scheme. Extensive experiments illustrate the superiority of our SAB-LVLM over existing binary PTQ methods under an approximately 1-bit compression constraint. Our code is accessible at https://github.com/LyuQi127/SAB_LVLM.

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal understanding, yet their enormous parameter scale and cross-modal computation incur substantial memory and latency overhead, severely limiting real-world deployment on resource-constrained devices.

Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence. To reduce policy-call frequency while preserving temporal coherence, most generative policies adopt an action chunk mechanism, executing multiple future actions in an open-loop manner under a fixed action horizon. However, this "predict-then-blindly-execute" paradigm sacrifices closed-loop reactivity: in contact-rich physical interactions, even small local perturbations can rapidly amplify within the open-loop blind spot, leading to compounding errors and ultimately task failure. To address this limitation, we propose VLA-Corrector, a lightweight corrective inference framework for action-chunked VLA policies. Without modifying the backbone policy weights, VLA-Corrector introduces a lightweight Latent-space Vision Monitor (LVM) that continuously compares predicted and actual visual feature evolution, enabling online detection of visual dynamics deviations. Once persistent deviation is detected, the system triggers a truncation event, discards the remaining stale actions, and invokes corrective replanning via Online Gradient Guidance (OGG). The detect-and-correct mechanism of VLA-Corrector naturally induces an event-triggered adaptive action horizon: it preserves long-horizon execution when the current chunk remains reliable, and invokes short-horizon corrective replanning when execution begins to drift. In doing so, VLA-Corrector mitigates the trade-off imposed by static horizons between execution robustness and policy-call frequency. It can be integrated into different VLA models without further retraining the VLA backbone, interrupting compounding errors while preserving much of the efficiency benefit of action chunking and substantially improving robustness in long-horizon, contact-rich robotic manipulation tasks.

Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence.

Vision Transformers have reshaped computer vision by using self-attention to capture global context across image regions. This makes them attractive for edge visual inspection and monitoring in applications such as renewable-energy infrastructure, industrial quality control, medical imaging, and autonomous-system sensing. However, deploying ViTs on small FPGAs remains challenging because the softmax stage in self-attention requires exponential evaluation and normalization, which are costly in hardware. Existing implementations often rely on CORDIC pipelines or BRAM-based look-up tables, increasing area and power consumption. This paper presents a BRAM-free approximate attention-weighting unit for FPGA-based ViT inference. The proposed design approximates the natural exponential in softmax using a 16-segment piecewise-linear function implemented entirely with distributed LUT fabric. Unlike base-2 approximations, the natural-exponential formulation preserves the pre-trained attention temperature and avoids model-specific recalibration. Implemented on a Xilinx Zynq-7020, the complete attention-row core uses 1444 LUTs, 77 DSPs, and no BRAM, while hardware-accurate emulation shows accuracy within a \(0.20\%\) absolute top-1 difference from the exact-softmax reference on ViT-family models. These results demonstrate the potential of the proposed core for energy-efficient ViT inference on resource-constrained edge-AI platforms.

Vision Transformers have reshaped computer vision by using self-attention to capture global context across image regions.

LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output. Dynamic 4D scenes from text alone, in which liquids flow, particles emit, rigid bodies cascade, and articulated mechanisms move, remain largely unexplored despite their value as editable content and as physics-grounded training data for video generation and embodied AI. Two challenges set the dynamic case apart from static text-to-scene work: an agent must jointly coordinate spatial layout, multiple physics solvers, temporal sequencing, camera, and lighting in a single coherent scene, and verifying motion correctness from rendered video is fundamentally harder than judging a single image. We present SimWorlds: a multi-agent framework that produces dynamic, editable 4D scenes from text, with Blender-specific procedural knowledge, a planner-coder-reviewer workflow driving a fixed ordered sequence of construction stages, a layered scene protocol enforced by a deterministic verifier, and a runtime-state inspection tool suite that catches mechanism failures the rendered image cannot reveal. We also introduce 4DBuildBench, a benchmark for assessing both visual fidelity and physical consistency of the procedural dynamic 3D scenes generated from text prompts. Experiments show that SimWorlds outperforms prior dynamic Blender generation baselines.

LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output.

On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution. However, such exploration inevitably leads to trajectories that deviate from expert demonstrations, resulting in a semantic mismatch between the executed visual stream and the original language instruction. In this work, we address this challenge by introducing Phi-Nav, a unified on-policy framework that leverages hindsight reasoning to align instructions with the agent's actual exploratory journey. Specifically, Phi-Nav operates through a three-stage dual-supervision cycle: 1) the agent performs oracle-guided on-policy exploration, sampling a trajectory while learning from expert action feedback, 2) a hindsight speaker synthesizes a path-level hindsight instruction grounded in the collected visual observations, and 3) the agent conducts a second imitation pass, treating the synthesized trajectory-instruction pair as an additional expert demonstration. Through this process, Phi-Nav bridges the critical semantic supervision gap inherent in on-policy methods, transforming semantically unlabeled movement into dense training signals. Evaluations on the R2R-CE and RxR-CE benchmarks show that Phi-Nav yields competitive performance while requiring only a fraction of the expert demonstrations used by current baselines. These results underscore the necessity of semantic exploration in VLN, positioning Phi-Nav as an effective solution for training embodied agents with limited data.

On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution.

Reward design remains a central challenge in reinforcement learning (RL). Hand-crafted rewards are often difficult to specify and may lead to suboptimal policies, while learned rewards from preferences can suffer from inefficiency and unstable training. Inspired by the dual nature of human learning explored in cognitive science, we decompose rewards into two complementary components: Formal Rewards (FR), explicitly designed based on task knowledge, and Residual Rewards (RR), learned from observations to capture implicit and nuanced preferences. Based on this decomposition, we propose CoRe, a hybrid framework that integrates FR and RR with vision-language models (VLMs) feedback to achieve preference-aligned policies without human involvement. Our contributions are twofold: (1) We propose a Formal Reward Module (FRM) that leverages VLMs to iteratively design and optimize FR based on task knowledge and preference feedback, enabling the continual improvement of policy during training; (2) We introduce a Residual Reward Module (RRM) that learns RR from video-level preference by employing VLMs to generate preference labels and capturing nuanced rewards that complement FR, ensuring alignment with human intent. Through the synergy of FRM and RRM, CoRe enables the automatic construction of reliable rewards that are efficient and preference-aligned. Extensive experiments demonstrate that CoRe outperforms existing approaches in terms of policy learning effectiveness and efficiency on ten robotic manipulation tasks in simulation and five real-worlds. Videos can be found on our project website: https://core-2026.github.io/

Reward design remains a central challenge in reinforcement learning (RL).

Scaling imitation learning to diverse multi-task robot manipulation remains challenging due to suboptimal demonstrations, behavioral multi-modality, and destructive interference across tasks. While skill-based methods offer a promising direction by decomposing behaviors into reusable abstractions, existing approaches often learn skills that are either biased toward linguistic structure or lack semantic alignment across tasks, limiting generalization. In this work, we propose AtomSkill, a novel framework that learns a semantically aligned Atomic Skill Space from demonstrations and enables robust long-horizon execution through keypose imagination. Our method introduces: (1) semantic contrastive skill alignment, which partitions demonstrations into variable-length atomic skills and employs a contrastive objective to jointly enforce semantic consistency and temporal coherence, yielding a compact and reusable skill library; and (2) action decoding with keypose imagining, where the policy predicts both a skill's terminal keypose and immediate actions, thereby supporting progress-aware skill transitions. During inference, an atomic skill diffusion sampler generates plausible skill sequences, while predicted keyposes autonomously trigger smooth skill chaining. Extensive experiments in simulation and real-world settings show that AtomSkill consistently outperforms state-of-the-art imitation learning and skill-based baselines. Project page: https://atom-skill.github.io.

Scaling imitation learning to diverse multi-task robot manipulation remains challenging due to suboptimal demonstrations, behavioral multi-modality, and destructive interference across tasks.

Tactile sensing can substantially improve contact-rich robotic manipulation, yet its practical deployment remains limited by the fragility, calibration requirements, and maintenance burden of tactile hardware. This raises a fundamental question: can robots benefit from tactile knowledge without requiring tactile sensors at deployment? We present TacImag, a tactile imagination framework that predicts tactile observations from vision and proprioception and uses the generated signals to guide manipulation policies. Trained from paired visuotactile demonstrations, TacImag enables touch-informed manipulation using only visual observations at test time. We evaluate TacImag on six simulated and four real-world manipulation tasks. Across simulation and real-world experiments, imagined tactile observations consistently improve manipulation performance without requiring tactile hardware. In real-world experiments, imagined force fields improve contact-sensitive tasks by 44.4% on average, whereas imagined tactile images improve texture-sensitive tasks by 23.3%, revealing that the effectiveness of tactile imagination depends strongly on the relationship between tactile representation and task requirements. Our results further suggest that tactile imagination does not simply recover missing tactile measurements. Instead, it acts as a form of contact-aware supervision that transforms subtle visual interaction cues into representations that are easier for manipulation policies to exploit.

Tactile sensing can substantially improve contact-rich robotic manipulation, yet its practical deployment remains limited by the fragility, calibration requirements, and maintenance burden of tactile hardware.

Training generalist Vision-Language-Action(VLA) models typically requires massive, diverse robotic datasets with high-fidelity action annotations. While egocentric human manipulation videos are abundant and capture significant environmental diversity, the absence of action labels makes them difficult to use in conventional training paradigms. To address this, we propose a latent-action-based framework designed to extract general action priors from unlabeled human videos. The architecture features a Hybrid Disentangled VQ-VAE that decouples motion dynamics from environmental backgrounds through physical masks, enabling the construction of a cross-embodiment action codebook. By pre-training on human videos with the codebook, the VLM backbone learns deep representations of action intent. For adaptation to specific embodiments, we introduce an intent-perception decoupling strategy where the VLM predicts the action intent while a separate frozen visual encoder provides state-specific features to the action expert, thereby reducing action hallucinations. Results in simulation and real-world environments show that our method, pre-trained exclusively on unlabeled human videos, performs competitively with state-of-the-art VLA models trained on massive annotated datasets, requiring only 50 trajectories for downstream adaptation.

Training generalist Vision-Language-Action(VLA) models typically requires massive, diverse robotic datasets with high-fidelity action annotations.

Video-based embodied world models provide an appealing substrate for robotic manipulation by predicting future states, yet current approaches remain limited by a fundamental entanglement: accurately modeling dynamics typically requires low-level temporal reasoning, while producing high-resolution frames demands expansive visual synthesis according to high-level semantics. This entanglement results in slow inference speed for iterative planning or too coarse predictions to retain contact-rich details. To solve this dilemma, we present Disentangled Video Generation World Model (DVG-WM), an efficient framework that explicitly decomposes world modeling into dynamics learning and visual synthesis. Conditioned on an initial observation and a language instruction, our model first generates a plausible sequence of intermediate visual states to preview the physical interaction and refines them to obtain high-fidelity videos. Furthermore, an efficient cascading mechanism is proposed, where DVG-WM uses flow matching to directly map the dynamics to video latents, and introduces a latent degradation mechanism to regenerate contact-rich details. Experiments on LIBERO and real-world platforms demonstrate improved video quality with up to 3.97 times acceleration, validating that disentangled video generation can be an efficient embodied world model for robotic manipulation.

Video-based embodied world models provide an appealing substrate for robotic manipulation by predicting future states, yet current approaches remain limited by a fundamental entanglement: accurately modeling dynamics typically requires low-level temporal reasoning, while producing high-resolution frames demands expansive visual synthesis according to high-level semantics.