Daily Papers Arch&EAI

Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action (VLA) models offer a promising framework, but they assume temporally aligned reasoning and control, despite semantic inference being inherently delayed relative to real-time action. We introduce Think-in-Control (TIC)-VLA, a latency-aware framework that explicitly models delayed semantic reasoning during action generation. TIC-VLA defines a delayed semantic-control interface that conditions action generation on delayed vision-language semantic states and explicit latency metadata, in addition to current observations, enabling policies to compensate for asynchronous reasoning. We further propose a latency-consistent training pipeline that injects reasoning inference delays during imitation learning and online reinforcement learning, aligning training with asynchronous deployment. To support realistic evaluation, we present DynaNav, a physics-accurate, photo-realistic simulation suite for language-guided navigation in dynamic environments. Extensive experiments in simulation and on a real robot show that TIC-VLA consistently outperforms prior VLA models while maintaining robust real-time control under multi-second reasoning latency. Project website: https://ucla-mobility.github.io/TIC-VLA/

Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control.

Many dexterous manipulation tasks are non-markovian in nature, yet little attention has been paid to this fact in the recent upsurge of the vision-language-action (VLA) paradigm. Although they are successful in bringing internet-scale semantic understanding to robotics, existing VLAs are primarily "stateless" and struggle with memory-dependent long horizon tasks. In this work, we explore a way to impart both spatial and temporal memory to a VLA by incorporating a language scratchpad. The scratchpad makes it possible to memorize task-specific information, such as object positions, and it allows the model to keep track of a plan and progress towards subgoals within that plan. We evaluate this approach on a split of memory-dependent tasks from the ClevrSkills environment, on MemoryBench, as well as on a challenging real-world pick-and-place task. We show that incorporating a language scratchpad significantly improves generalization on these tasks for both non-recurrent and recurrent models.

Many dexterous manipulation tasks are non-markovian in nature, yet little attention has been paid to this fact in the recent upsurge of the vision-language-action (VLA) paradigm.

Vision-language-action (VLA) models have shown remarkable capabilities in robotic manipulation, but their performance is sensitive to the $\textbf{action chunk length}$ used during training, termed $\textbf{horizon}$. Our empirical study reveals an inherent trade-off: longer horizons provide stronger global foresight but degrade fine-grained accuracy, while shorter ones sharpen local control yet struggle on long-term tasks, implying fixed choice of single horizons being suboptimal. To mitigate the trade-off, we propose a $\textbf{mixture of horizons (MoH)}$ strategy. MoH rearranges the action chunk into several segments with different horizons, processes them in parallel with a shared action transformer, and fuses outputs with a light linear gate. It has three appealing benefits. 1) MoH exploits long-term foresight and short-term precision jointly within a single model, improving both performance and generalizability to complex tasks. 2) MoH is plug-and-play for full-attention action modules with minimal training or inference overhead. 3) MoH enables dynamic inference with adaptive horizons, which selects stable actions through cross-horizon consensus, achieving 2.5$\times$ higher throughput than baselines while preserving superior performance. Extensive experiments over flow-based policies $π_0$, $π_{0.5}$, and one-step regression policy $π_{\text{reg}}$ demonstrate that MoH yields consistent and significant gains on both simulations and real-world tasks. Notably, under mixed-task setting, $π_{0.5}$ with MoH reaches a new state-of-the-art with 99$\%$ average success rate on LIBERO after only $30k$ training iterations. Project page: https://timsty1.github.io/moh/

Vision-language-action (VLA) models have shown remarkable capabilities in robotic manipulation, but their performance is sensitive to the $\textbf{action chunk length}$ used during training, termed $\textbf{horizon}$.

Dense Video Object Captioning (DVOC) is the task of jointly detecting, tracking, and captioning object trajectories in a video, requiring the ability to understand spatio-temporal details and describe them in natural language. Due to the complexity of the task and the high cost associated with manual annotation, previous approaches resort to training strategies with limited data, potentially leading to suboptimal performance. To circumvent this issue, we propose to generate captions about spatio-temporally localized entities leveraging a state-of-the-art VLM, and extend the LVIS and LV-VIS datasets with our synthetic captions (LVISCap and LV-VISCap). Moreover, we introduce an end-to-end model, CaptionFormer, capable of jointly detecting, segmenting, tracking and captioning object trajectories. CaptionFormer achieves state-of-the-art DVOC results on three existing benchmarks, VidSTG, VLN and BenSMOT. The datasets and code are available at https://www.gabriel.fiastre.fr/captionformer/.

Dense Video Object Captioning (DVOC) is the task of jointly detecting, tracking, and captioning object trajectories in a video, requiring the ability to understand spatio-temporal details and describe them in natural language.

Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static datasets, but accurate value estimation remains challenging under limited state-action coverage. Existing physics-informed approaches address this by imposing pointwise distance-like geometric constraints derived from Hamilton--Jacobi--Bellman (HJB) optimality principles, often through first-order partial differential equations such as the Eikonal equation. However, enforcing local consistency through explicit differential structure can become unstable in complex, high-dimensional environments. Our key insight is to instead reinterpret distance-like constraints as an expectation over a local spatial measure. By aggregating constraints over this measure rather than evaluating them pointwise, the objective acts as a spatial mollifier, inducing distance-like value geometry without requiring expensive differential operators. We refer to this as Mollified Value Learning (MVL). Experiments across navigation and high-dimensional robotic manipulation tasks show that MVL learns structured, value representations, improving goal-reaching performance, when used with implicit value representation learning methods. Open-source codes are available at https://github.com/HrishikeshVish/MVL.

Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static datasets, but accurate value estimation remains challenging under limited state-action coverage.

This paper addresses the challenge of simultaneously compensating for state-dependent uncertainties and enforcing time-varying state constraints in Euler-Lagrange systems, a common requirement in robotics that remains underserved by existing control designs. A novel adaptive control framework is developed that combines an artificial time-delay-based uncertainty estimation strategy, also known as time-delay estimation, with a barrier Lyapunov function to enforce constraint-aware control design. Specifically, a state-dependent upper bound on the time-delay estimation approximation error is analytically formulated, and an adaptive law is constructed to estimate its parameters online, enabling real-time state-dependent uncertainty compensation without relying on prior model knowledge. To ensure constraint compliance, the barrier Lyapunov function-based controller enforces time-varying bounds on both position and velocity. The resulting architecture is provably stable via Lyapunov analysis. Experimental results on a five-degree-of-freedom robotic manipulator validate the framework's capability, compared with the state of the art, in maintaining strict adherence to safety-critical constraints under dynamic uncertainties.

This paper addresses the challenge of simultaneously compensating for state-dependent uncertainties and enforcing time-varying state constraints in Euler-Lagrange systems, a common requirement in robotics that remains underserved by existing control designs.

Modular visual reasoning systems increasingly rely on shared working memory for multi-step collaboration, yet the failure dynamics of intermediate state evolution in low-capacity regimes remain underexplored. We study failure modes of collaborative reasoning with weak learners (4B--8B models) through the lens of noise accumulation. We introduce CoSee, an auditing framework that formalizes the read-write-verify loop to trace information flow in document visual question answering. Across multi-page, chart, and web-based benchmarks, we find a counter-intuitive degradation: naive shared workspaces often amplify hallucinations rather than resolve them. We identify two dominant failure modes: Noise Reinforcement, where ungrounded notes are reused as evidence, and Policy Collapse, where added context shifts the model toward under-specified, short-form answers. Using cost-accuracy Pareto frontiers, we show that increased compute can correlate negatively with performance without explicit verification. Our findings suggest that for resource-constrained agents, the bottleneck lies not in reasoning depth but in communication fidelity, providing trace-level diagnostics and a mechanistic baseline for reliable modular design.

Modular visual reasoning systems increasingly rely on shared working memory for multi-step collaboration, yet the failure dynamics of intermediate state evolution in low-capacity regimes remain underexplored.

Robotics manipulation usually assumes that the shape and pose of the object are known to the robot prior to motion planning. However, precise geometric information is not always available in practice, and pose inference suffers from sensor uncertainties and view occlusion. In this work, we propose a unified model-based geometric framework integrating robotic haptic perception, modeling, and manipulation planning. Our novelties involve: \textit{i)} Introducing Bayesian Optimization (BO) to guide the haptic exploration for object shape inference, where superellipses are used to approximate geometric boundary; \textit{ii)} Adaptive formulation of manipulation potential encoding object geometry for quasi-static robot-object interaction; \textit{iii)} Proposing an online Ordinary Differential Equation (ODE) for real-time pose inference based on model prediction and tactile feedback. We deploy our system on a 2D robotic sorting task, and vary object geometries to validate the robustness and generalizability of our framework in both simulation and a real-world multi-arm setup.

Robotics manipulation usually assumes that the shape and pose of the object are known to the robot prior to motion planning.

Road segmentation is a fundamental perception task for autonomous driving and intelligent robotic systems, requiring both high accuracy and real-time inference, especially for deployment on resource-constrained edge devices. Existing multi-modal road segmentation methods often rely on heavy transformer-based encoders to achieve state-of-the-art performance, but their enormous computational cost prohibits real-time deployment on embedded platforms. To address this dilemma, we propose LiteViLNet, a lightweight multi-modal network that fuses RGB texture information and LiDAR geometric information for efficient road segmentation. Specifically, we design a dual-stream lightweight encoder and depth-wise separable convolutions to extract hierarchical features from both modalities with minimal parameters. We further propose a Multi-Scale Feature Fusion Module (MSFM) to facilitate cross-modal interaction at different levels, and a large-kernel-bridge module to capture long-range dependencies with linear complexity. Extensive experiments on the KITTI Road dataset and real-world applications demonstrate that LiteViLNet achieves a promising balance between accuracy and efficiency. Notably, with only 14.04M parameters, our model attains a 96.36% MaxF score, ranking the best among all CNN-based methods and being comparable to larger transformer-based models, and runs at 163.79 FPS in model-only inference on RTX 4060 Ti (22.18 FPS on Jetson Orin NX). It outperforms numerous heavy-weight methods in inference speed while maintaining highly competitive accuracy, fully validating the potential of LiteViLNet for real-time embedded deployment in autonomous driving and intelligent robotics.

Road segmentation is a fundamental perception task for autonomous driving and intelligent robotic systems, requiring both high accuracy and real-time inference, especially for deployment on resource-constrained edge devices.

Real-world household robots require Vision-Language-Action (VLA) foundation models that can acquire reusable manipulation skills across diverse objects, task conditions, and household environments. Deformable-object folding is a representative challenge, requiring robots to handle clothing items from random initial states across varying categories, geometries, materials, and scenes. However, existing VLA systems commonly train separate policies for different object categories, while naively mixed multi-task training often suffers from task interference and degraded performance. To move beyond category-specific folding policies, we introduce DeMaVLA, a VLA foundation model for generalizable Deformable Manipulation. DeMaVLA adopts a VLM backbone with an action expert and formulates continuous action generation using flow matching. To improve efficiency, the action expert is constructed by pruning every other transformer layer while preserving layer-wise alignment with the VLM backbone, reducing training and inference cost. DeMaVLA is first pre-trained on approximately 5,000 hours of selected real-world dual-arm demonstrations to acquire general manipulation priors. It is then post-trained on mixed folding data that aggregates self-collected demonstrations and corrective trajectories from real-robot failures across multiple folding tasks through a human-in-the-loop Data Aggregation~(DAgger) pipeline. Experiments show that DeMaVLA achieves competitive performance on RoboTwin and strong real-world results on our household folding benchmark. These results highlight the value of scalable real-world data, efficient action generation, and corrective learning for general-purpose VLA policies in deformable-object manipulation.

Real-world household robots require Vision-Language-Action (VLA) foundation models that can acquire reusable manipulation skills across diverse objects, task conditions, and household environments.

Learning generalizable vision-language-action (VLA) models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies in both visual observations and executable actions. While latent action models reduce the action execution gap by learning action abstractions, they still rely on visual features. Thus, misaligned human and robot visual representations can lead to inconsistencies in policy inputs and induce domain-dependent latent actions, hindering effective co-training with human videos. To address this, we propose HARP, a human-robot aligned representation learning framework for more effective VLA pretraining from human videos. Specifically, HARP uses limited paired human-robot demonstrations as cross-embodiment bridges and abundant unpaired human and robot videos as a scalable dynamics supervision data source. It trains a robot-adapted visual encoder and a latent action model with manipulation-centric auxiliary cues and a source-relative pair-discriminative alignment loss, which adapts robot representations toward human semantics while preserving pair-level discrimination. The learned aligned vision encoder and latent action model provide a unified vision and action representation for VLA-style policy learning, where human and robot videos provide vision-language-to-latent-action supervision and a lightweight robot action head grounds latent actions into executable commands. Experiments on feature visualization, simulation, and realworld manipulation show improved human-robot alignment and downstream policy performance, achieving 4.481 average length on CALVIN ABC$\rightarrow$D and a 7.1\% realworld success rate gain over the strongest baseline.

Learning generalizable vision-language-action (VLA) models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies in both visual observations and executable actions.

Interactive video world models generate video chunk by chunk in response to user-controlled camera movements, enabling applications such as real-time game simulation, virtual scene navigation, and embodied AI training. However, scaling to long interactive trajectories is prohibitively expensive due to growing context memory, quadratic attention complexity, and repeated denoising steps. We present Light Interaction, a training-free inference acceleration framework for interactive video world models. Our key insight is that interaction naturally enables trajectory-dependent adaptive computation: retrieved spatial memory can be discarded during novel exploration, temporal context can be adjusted according to local latent dynamics, and early-step model outputs can be reused when the camera revisits familiar regions. Based on this insight, Light Interaction combines adaptive context management, denoising cache acceleration, and hardware-software co-designed 3D block sparse attention with fused Triton kernels. Evaluated on HY-WorldPlay and Matrix-Game-3.0, Light Interaction achieves up to 2.59x speedup without model retraining while maintaining competitive visual quality.

Interactive video world models generate video chunk by chunk in response to user-controlled camera movements, enabling applications such as real-time game simulation, virtual scene navigation, and embodied AI training.

Foundation models have become a dominant paradigm in machine learning, achieving remarkable performance across diverse tasks through large-scale pretraining. However, they often yield overconfident, uncalibrated predictions. The standard approach to quantifying epistemic uncertainty are ensembles of multiple independently trained models. But their computational cost scales linearly with ensemble size, making them impractical for large foundation models. We propose Singular Value Ensemble (SVE), a parameter-efficient implicit ensembling method. SVE builds on a simple, but powerful core assumption: namely, that the singular vectors of the weight matrices correspond to meaningful directions in the representation space. If the singular vectors are indeed meaningful (orthogonal) "knowledge directions", then a model ensemble can be obtained by modulating only how strongly each direction contributes to the output. Rather than learning new parameters for each ensemble member, we freeze the singular vectors and only train per-member singular values that rescale the contribution of each direction in that shared knowledge basis. Ensemble diversity emerges naturally during joint training as stochastic initialization and random batch sampling cause different members to converge to different combinations of the same underlying knowledge. SVE performs comparable to an explicit ensemble, while increasing the parameter count of the base model by <1%, making principled uncertainty estimation accessible in resource-constrained settings. We validate SVE on NLP and vision tasks with various different backbones and show that it improves calibration while maintaining predictive accuracy.

Foundation models have become a dominant paradigm in machine learning, achieving remarkable performance across diverse tasks through large-scale pretraining.

Outdoor vision-language navigation (VLN) in long-range, open-world environments is frequently disrupted by semantic-cue interruptions, where informative goal cues become sparse, occluded, or leave the field of view. Once such cues disappear, agents enter a cue-free phase and often degrade into backtracking, oscillatory headings, or aimless exploration. While memory-based methods attempt to bridge these gaps, they often fail under traversability-driven detours: the remembered cue direction may be infeasible, forcing detours that prolong cue-free phases and gradually render robot-centric cues stale and implicit histories blurred. This makes traversability a stability condition for maintaining goal-directed guidance, rather than merely a local safety concern. We propose a unified outdoor VLN framework that survives semantic-cue interruptions by maintaining traversability-consistent executable guidance throughout prolonged cue-free phases. Specifically, our method extracts semantic bearings from visibility-gated goal or exploration cues and grounds them into executable headings using a real-time near-field traversability profile, providing goal-consistent feasible guidance beyond reject-only safety filtering. To prevent guidance degradation during detours, we lift intermittent 2D evidence into a world-aligned 3D cue memory with an uncertainty-aware readout mechanism, ensuring guidance remains continuously reachable and stable as the robot moves. We evaluate the framework on quadrupedal and wheeled platforms over 600--1000 m routes. Our method improves simulation success rate by over 10 percentage points over the strongest baseline and achieves a real-world success rate of 40%, compared to 17.5% for the strongest baseline, with substantially higher robustness during prolonged cue-free intervals.

Outdoor vision-language navigation (VLN) in long-range, open-world environments is frequently disrupted by semantic-cue interruptions, where informative goal cues become sparse, occluded, or leave the field of view.

Safe physical interaction is critical for deploying robotic manipulators in human-robot interaction and contact-rich tasks, where uncertainty, external forces, and actuator limitations can compromise both performance and safety. We propose an online adaptive impedance control framework that enforces joint-state safety while achieving compliant interaction under uncertain dynamics. The approach combines a quadratic-program-based safety filter with a novel composed position-velocity non-smooth control barrier function (NCBF), enabling joint position and velocity constraints to be enforced through a unified relative-degree-one barrier. Unknown dynamics are compensated online using an interval type-2 fuzzy logic system, while actuator torque limits are handled through soft constraints with exact penalty recovery of feasible solutions. A disturbance-observer-enhanced safety mechanism improves robustness against modelling errors and external interaction forces. Using composite Lyapunov analysis, we prove forward invariance of the safe set and the uniform ultimately boundedness of the impedance-tracking error. Simulations on a 7-DOF manipulator with severe parametric uncertainty and external interaction wrenches demonstrate safe constraint satisfaction and robust impedance tracking.

Safe physical interaction is critical for deploying robotic manipulators in human-robot interaction and contact-rich tasks, where uncertainty, external forces, and actuator limitations can compromise both performance and safety.

Recent aerial vision-language-action (VLA) models show promising single-UAV capabilities, such as tracking moving objects and navigating to language-specified landmarks. However, it remains unclear whether these capabilities can transfer to air-ground cooperation, where a UAV and a UGV must act jointly in a shared, closed-loop physical world. We study this question with CARLA-Air, a single-process air-ground evaluation environment that unifies CARLA and AirSim inside one Unreal Engine runtime. By sharing the same world state, physics tick, and sensing pipeline, CARLA-Air enables physically consistent UAV--UGV interaction and precise measurement of simulation-timestamp alignment and effective coordination latency. Using CARLA-Air, we evaluate representative aerial VLA and planning baselines on two complementary diagnostic tasks: moving-platform landing and occlusion-recovery escort. The results show that current aerial VLA models can often track or follow a ground partner, but struggle to convert this single-agent competence into stable cooperative behavior. State prompting provides limited benefit, and naive bidirectional interaction fails to consistently improve performance and can amplify errors for most baselines. These findings suggest that, under the tested text-based cue interfaces, zero-shot cooperative air-ground VLA requires three components beyond the current paradigm: explicit partner-state grounding, low-latency action coordination, and team-level objective alignment. Our code is available at https://github.com/louiszengCN/CarlaAir.

Recent aerial vision-language-action (VLA) models show promising single-UAV capabilities, such as tracking moving objects and navigating to language-specified landmarks.

Vision-Language-Action (VLA) models have demonstrated promising capability in autonomous driving, highlighting the potential of unified multimodal architectures for jointly modeling perception and planning. However, how current VLA-based driving behavior is grounded in visual information remains poorly understood. Existing evaluation protocols mainly focus on aggregate performance metrics, lacking structured and practical diagnostics to quantify visual-behavior dependency. In this work, we introduce a structured multi-level visual perturbation framework to analyze visual-behavior dependency in VLA-based driving models systematically. The framework organizes controlled visual perturbations along three complementary dimensions: channellevel degradation, information-level disruption, and structurelevel modification. We apply it to VLA-based driving systems and evaluate behavioral responses under both open-loop trajectory prediction and interactive closed-loop safety evaluation. Experimental results reveal evaluation-dependent dependency patterns and uneven visual grounding across abstraction levels. These findings call for more structured analyses and principled design of VLA driving models to better understand how visual information shapes behavior and develop safer, more robust systems.

Vision-Language-Action (VLA) models have demonstrated promising capability in autonomous driving, highlighting the potential of unified multimodal architectures for jointly modeling perception and planning.

Graph condensation (GC) is pivotal for enabling Graph Neural Networks (GNNs) deployment in resource-constrained scenarios by compressing large-scale graphs into compact synthetic counterparts. Existing GC methods commonly suffer from computational inefficiency due to coupled optimization as well as encountering poor generalization across GNN architectures. To address these challenges, this study proposes an Efficient and Scalable Graph Condensation with Structure-Preserving (SP-ESGC), which possesses a decoupled design that separates node condensation from graph structure generation. Specifically, it first employs heat kernel feature propagation to generate node representation via spectral graph theory-inspired diffusion. Further, a novel hybrid clustering strategy is designed to extracts discriminative intra-class centroids from the node representation. Finally, a pre-trained edge predictor infers transferable structural patterns from the original graph, ensuring accurate synthetic graph generation. Extensive experiments on real-world graph datasets demonstrate that the proposed SP-ESGC implementes a precise GC with significantly high computational efficiency. Moreover, SP-ESGC also generalizes well across diverse GNN architectures.

Graph condensation (GC) is pivotal for enabling Graph Neural Networks (GNNs) deployment in resource-constrained scenarios by compressing large-scale graphs into compact synthetic counterparts.

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robot control. However, their performance remains fundamentally constrained by the availability of high-quality robot trajectory data. In current robot learning practice, such data are primarily collected through human teleoperation, which is labor-intensive, costly, and difficult to scale. In this paper, we propose RDGen, a sim-to-real reinforcement learning framework for generating high-quality robot demonstrations. Rather than employing reinforcement learning solely as the final control policy, RDGen leverages trained RL policies as a structured trajectory generator. The system consists of a VLM-based task parser that identifies task-relevant objects, a Grounding DINO-based object localizer, and an RL policy transferred from simulation to the real robot. Successful rollouts are then harvested as clean, high-quality demonstrations for downstream VLA training, while the simulation stage further provides a scalable source of additional trajectories at little marginal cost. Experiments on a pick-and-place task demonstrate that the transferred RL policy achieves a high task success rate. Compared with human teleoperation, RDGen produces significantly smoother trajectories and yields superior downstream VLA performance. These results indicate that RL-generated demonstrations can serve as more reliable and consistent supervisory signals for robot policy learning.

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robot control.

Vision-Language-Action (VLA) policies have emerged as a versatile paradigm for generalist robotic manipulation. However, precise object placement under compositional language remains challenging for end-to-end VLA policies. Slot-level placement requires reliable slot grounding and centimeter-level geometric precision. To this end, we propose AnySlot, a framework that reduces compositional complexity by introducing an explicit spatial visual goal between language grounding and control. AnySlot converts language into a visual goal by rendering a spatial marker at the intended slot, then executes this goal with a goal-conditioned VLA policy. This hierarchical design decouples high-level slot selection from low-level execution, improving semantic accuracy and spatial robustness. Furthermore, recognizing the lack of benchmarks for such precision-demanding tasks, we introduce SlotBench, a structured simulation benchmark with nine task categories for evaluating spatial reasoning in slot-level placement. Extensive experiments show that AnySlot significantly outperforms flat VLA baselines and modular grounding methods in zero-shot slot-level placement.

Vision-Language-Action (VLA) policies have emerged as a versatile paradigm for generalist robotic manipulation.

We present a novel hierarchical spatiotemporal action tokenizer for in-context imitation learning. We first propose a hierarchical approach, which consists of two successive levels of vector quantization. In particular, the lower level assigns input actions to fine-grained subclusters, while the higher level further maps fine-grained subclusters to clusters. Our hierarchical approach outperforms the non-hierarchical counterpart, while mainly exploiting spatial information by reconstructing input actions. Furthermore, we extend our approach by utilizing both spatial and temporal cues, forming a hierarchical spatiotemporal action tokenizer, namely HiST-AT. Specifically, our hierarchical spatiotemporal approach conducts multi-level clustering, while simultaneously recovering input actions and their associated timestamps. Finally, extensive evaluations on multiple simulation and real robotic manipulation benchmarks show that our approach establishes a new state-of-the-art performance in in-context imitation learning.

We present a novel hierarchical spatiotemporal action tokenizer for in-context imitation learning.

Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where goal-driven data collection creates a dataset bias. In such datasets, language instructions are highly predictable from visual observations alone, causing the conditional mutual information between instructions and actions to vanish, a phenomenon we term Information Collapse. Consequently, models degenerate into vision-only policies that ignore language constraints and fail in out-of-distribution (OOD) settings. To address this, we propose LangForce, a novel framework that enforces instruction following via Bayesian decomposition. By introducing learnable Latent Action Queries, we construct a dual-branch architecture to estimate both a vision-only prior $p(a \mid v)$ and a language-conditioned posterior $π(a \mid v, \ell)$. We then optimize the policy to maximize the conditional Pointwise Mutual Information (PMI) between actions and instructions. This objective effectively penalizes the vision shortcut and rewards actions that explicitly explain the language command. Without requiring new data, LangForce significantly improves generalization. Extensive experiments across on SimplerEnv and RoboCasa demonstrate substantial gains, including an 11.3% improvement on the challenging OOD SimplerEnv benchmark, validating the ability of our approach to robustly ground language in action.

Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios.

To enable an efficient interaction of non-communicating mobile robots in collision avoidance scenarios, we present a novel combined trajectory planning and prediction algorithm. Inverse optimal control is used to estimate unknown goal states of all robots based on observed past trajectories. Each robot also takes the perspective of other robots in considering self-prediction and solves a joint prediction problem using the estimated goal states. The resulting predictions are then considered for planning. Simulation results of scenarios with 2-8 robots show that the median of the durations until all vehicles reach their goals is 9.8 % faster compared to planning with constant acceleration based estimated goal states. Moreover, the proposed approach never leads to the solver being unable to find a solution to the planning or prediction problem.

To enable an efficient interaction of non-communicating mobile robots in collision avoidance scenarios, we present a novel combined trajectory planning and prediction algorithm.

Diffusion-based visuomotor policies perform well in robotic manipulation, yet current methods still inherit image-generation-style decoders and multi-step sampling. We revisit this design from a frequency-domain perspective. Robot action trajectories are highly smooth, with most energy concentrated in a few low-frequency discrete cosine transform modes. Under this structure, we show that the error of the optimal denoiser is bounded by the low-frequency subspace dimension and residual high-frequency energy, implying that denoising error saturates after very few reverse steps. This also suggests that action denoising requires a much simpler denoising model than image generation. Motivated by this insight, we propose Hyper-DP3 (HDP3), a pocket-scale 3D diffusion policy with a lightweight Diffusion Mixer decoder that supports two-step DDIM inference. Our synthetic experiments validate the theory and support the sufficiency of two-step denoising. Futhermore, across RoboTwin2.0, Adroit, MetaWorld, and real-world tasks, HDP3 achieves state-of-the-art performance with fewer than 1% of the parameters of prior 3D diffusion-based policies and substantially lower inference latency.

Diffusion-based visuomotor policies perform well in robotic manipulation, yet current methods still inherit image-generation-style decoders and multi-step sampling.

Large-scale Vision-Language-Action (VLA) pretraining is increasingly adopted as the foundation for robot policies, yet the evidence for pretrained VLAs is almost invariably reported after task-specific fine-tuning.This leaves a foundational question unanswered: does VLA pretraining itself yield executable robot behavior, or does it merely furnish a better initialization for downstream policy learning? We present Wall-OSS-0.5, an open-source 4B VLA built upon a 3B VLM backbone augmented with action-generation components, designed so that pretrained robotic capability is directly measurable on physical hardware.The model is pretrained across more than 20 embodiments, processing over one million robot trajectories per epoch alongside a grounded multimodal corpus. We adopt a gradient-bridged co-training recipe in which three objectives play distinct and complementary roles: discrete action prediction routes strong VLM-native gradients into the backbone, multimodal prediction preserves grounded vision-language understanding, and continuous flow matching serves as the deployment-time action interface. Before task-specific fine-tuning, the pretrained checkpoint achieves non-trivial zero-shot real-robot behavior, completing several tasks, including a held-out deformable manipulation task, at high task progress on a 17-task suite. After fine-tuning, the same checkpoint serves as a stronger adaptation prior, reaching 60.5% average task progress on 15 real-robot tasks and outperforming π_0.5 by 17.5%. Multimodal evaluations further confirm that action training does not erode grounded vision-language competence: the model preserves broad vision-language ability while strengthening embodied grounding. Together, these results reposition VLA pretraining from an initialization strategy to a directly testable, already useful source of robot capability.

Large-scale Vision-Language-Action (VLA) pretraining is increasingly adopted as the foundation for robot policies, yet the evidence for pretrained VLAs is almost invariably reported after task-specific fine-tuning.This leaves a foundational question unanswered: does VLA pretraining itself yield executable robot behavior, or does it merely furnish a better initialization for downstream policy learning?

1D-CNNs play a crucial role for time-series analysis on tiny smart sensor systems, e.g. for biosignal analysis, predictive maintenance, or structural health monitoring. LUTbased precomputation has emerged as an interesting optimization technique to implement such neural networks on FPGAs. The core idea is to precompute all possible outputs of a neural network layer and store them directly in the lookup tables of the FPGAs. This enables highly resource-efficient networks with ultra-low latency but suffers from poor scalability. Previous work has explored using depthwise-separable convolutions to improve scalability. In this paper, we generalize this approach to consider additional forms of grouped convolutions. Based on this, we propose a novel type of convolutional block and an algorithm to guide the choice of hyper parameters for this block. We evaluate our approach on a medical time-series dataset for predicting atrial fibrillation using the MIT-BIH database (ECG recordings). The resulting hardware accelerators are small enough to be deployed on an AMD Spartan 7 S15. They achieve a F1-Score of up to 95% while only requiring 2,844 LUTs and no DSPs or BRAM.

1D-CNNs play a crucial role for time-series analysis on tiny smart sensor systems, e.g.

Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that compromise reliability in real-world deployment. Detecting such failures during execution is therefore critical for the robust deployment of embodied systems. Existing failure detection methods either rely on expensive action resampling or external models, while alternatives propagate trajectory-level labels uniformly across every timestep, obscuring localized failure signals. In this paper, we propose \textbf{Hide-and-Seek}, a framework that formulates VLA failure detection as a coarsely supervised learning problem. By combining inter-trajectory and intra-trajectory contrastive objectives, Hide-and-Seek localizes failure-indicative actions and induces temporally structured failure signals from trajectory-level supervision alone, without any step-level annotation. We evaluate Hide-and-Seek on LIBERO, VLABench, and a real-world robotic platform across three representative VLA policies: OpenVLA, $π_0$, and $π_{0.5}$.Our method achieves state-of-the-art multi-task failure detection performance with a practical accuracy--timeliness trade-off under conformal prediction, and generalizes well to both seen and unseen tasks.

Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that compromise reliability in real-world deployment.

Reinforcement learning is a promising approach for improving the capabilities of vision-language-action (VLA) models while avoiding the heavy data requirements of imitation learning. However, its effectiveness for VLA models is often constrained by sparse supervision and the difficulty of designing informative reward signals for long-horizon manipulation. In this work, we present Feat2Go, a fine-grained value estimation framework for embodied reinforcement learning. Specifically, Feat2Go first derives a continuous progress target from a pretrained visual world model by measuring patch-level similarity to subgoal states and partitioning episodes into semantic stages with trend-based clustering. We then train an embodied value model to predict this structural progress from the current observation and task instruction, and use the predicted value to reshape terminal rewards during policy optimization. The proposed framework is compatible with existing VLA policy reinforcement learning pipelines, including PPO and GRPO, and does not rely on manual reward engineering. Extensive experiments on ManiSkill3 and RoboTwin 2.0 demonstrate that Feat2Go consistently improves the performance of existing VLA models under both single-arm and bimanual manipulation settings. More specifically, on ManiSkill3, Feat2Go improves OpenVLAOFT from 17.5% to 82.9% average out-of-distribution success while retaining 96.9% in-distribution performance. On RoboTwin 2.0, Feat2Go achieves an average success rate of 88.8% in domain-randomized task settings, outperforming prior reinforcement learning methods.

Reinforcement learning is a promising approach for improving the capabilities of vision-language-action (VLA) models while avoiding the heavy data requirements of imitation learning.

Long-horizon planning for non-prehensile robot manipulation is challenging due to underactuated and discontinuous interactions. We propose a hierarchical formulation of model predictive path integral (MPPI) control that guides robot-level planning with a separately computed object-level plan to achieve efficient long-horizon prediction. We first solve a simplified object-only problem, assuming the object can be actuated directly, and use the planned object trajectory as a reference in solving the joint robot-object planning problem. We evaluate our method in both simulation and hardware using a 6-DoF xArm6 manipulator to perform object pushing tasks in which the target object must reach a goal while avoiding static obstacles, necessitating non-myopic reasoning. Our object-informed MPPI increases task success by 40\% with a 26\% faster control frequency in simulation, and by 20\% in real experiments with similar computation as regular MPPI.

Long-horizon planning for non-prehensile robot manipulation is challenging due to underactuated and discontinuous interactions.

Malaria remains a leading cause of mortality in sub-Saharan Africa, where scarce diagnostic infrastructure makes timely, accurate diagnosis particularly challenging. While deep learning offers a compelling path toward automated malaria screening, clinical adoption is hindered by computational cost and opacity in decision-making. This work benchmarks four deep learning models spanning a wide range of designed design architectures and model capacities on the NLM-Malaria dataset, jointly evaluating predictive performance, robustness, and post-hoc explainability. We find that lightweight, efficient-by-design models match their heavier counterparts in predictive performance, and the Friedman test confirms no statistically significant performance differences. CAM-based XAI methods consistently localize diagnostically relevant regions, while fine-grained attribution methods produce less targeted explanations, particularly with heavier backbones. Robustness evaluation under three types of image corruption further reveals that model confidence degrades faster than accuracy, providing a practical signal for human review. However, no XAI method is robust to corruption, with explanation reliability degrading at noise levels plausible in clinical practice, even when predictions remain accurate. These findings support the deployment of lightweight architectures for malaria diagnosis in resource-constrained settings, while highlighting the vulnerability of post-hoc explanations as an important consideration for responsible clinical deployment.

Malaria remains a leading cause of mortality in sub-Saharan Africa, where scarce diagnostic infrastructure makes timely, accurate diagnosis particularly challenging.