Daily Papers Arch&EAI

We present a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB images. Rather than training an end-to-end policy, our system uses a vision-language model (VLM) to produce reference-frame task grounding and primitive-level 2D keypoints, then lifts them into 3D via multi-view fusion. This lifting combines triangulation of view-wise VLM groundings with reference-view ray voting, which searches along a semantic camera ray for geometrically consistent candidates across neighboring views. The resulting 3D keypoints support both pick-and-place and tool-use: for tool-use, we retrieve an object-centric atomic action corresponding to the inferred skill category and align its stored 6D tool trajectory to the scene; for dexterous execution, we expand the lifted grasp keypoint into a task-conditioned grasp affordance region and generate feasible grasp-motion pairs with an arm-hand motion generator. Real-world experiments show improved 3D grounding accuracy and execution reliability over single-view RGB-D grounding and fine-tuned VLA baselines. We further demonstrate long-horizon manipulation through closed-loop status verification and replan, enabling zero-shot execution on unseen objects and tool-use tasks in novel scenes.

We present a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB images.

How can we scalably generate data for robotic manipulation, especially on human-like platforms such as dexterous multi-fingered hands? Learning from human videos has recently emerged as a likely answer to this question. However, difficulties in estimating hand-object interaction and crossing the human-to-robot embodiment gap have hindered the adoption of abundant monocular RGB-only human videos as the primary source of robot manipulation data. In this work, we present DO AS I DO, an algorithm to reconstruct and retarget monocular RGB human videos to multi-fingered dexterous robotic hands. DO AS I DO reconstructs hand-object interactions from various egocentric and exocentric in-the-wild video sources. The algorithm then retargets these hand-object interaction estimates into a sequence of actions executable in the real world, yielding robot-complete manipulation data from disparate human videos. Overall, DO AS I DO outperforms previous state of the art in estimating hand-object interactions and extracting dexterous manipulation trajectories from RGB videos, as we show in experiments on datasets with ground truths and on a dataset of video clips collected online. Our experiments enable us to propose an efficacy playbook for practitioners collecting human data for manipulation.

How can we scalably generate data for robotic manipulation, especially on human-like platforms such as dexterous multi-fingered hands?

Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to answer through action. Each question becomes a short tabletop episode where the agent performs a single object-placement action to select among candidate answers, yielding an action-grounded success rate with reduced control confounds. We curate a test suite of such environments across diverse commonsense and world-knowledge categories and introduce layerwise intent probing to localize answer-relevant information across the VLM backbone and action head. In a large-scale study of 7 VLA models and 9 VLM baselines, we systematically rank models across categories, finding that VLAs show solid performance on simple concepts while exhibiting larger gaps on richer semantic categories relative to their source VLMs, that VQA co-training is associated with better knowledge retention, and that answer-relevant signals peak in middle VLA layers but attenuate in upper layers. Act2Answer is available at https://tttonyalpha.github.io/act2answer/.

Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation.

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale. In this report, we investigate whether this scaling recipe can be applied to robotic manipulation to achieve genuine generalization. This is challenging because, unlike text, manipulation data is heterogeneous by nature, expensive to collect, and narrow in diversity, making alignment and scale simultaneously difficult. We present Qwen-RobotManip, a generalizable Vision-Language-Action foundation model built on Qwen-VL. Qwen-RobotManip introduces a unified alignment framework across the representation, motion, and behavioral dimensions of manipulation, making large-scale multi-source training coherent rather than conflicting. This alignment capability in turn enables Qwen-RobotManip to absorb manipulation data at a scale that prior training regimes could not sustain. A human-to-robot synthesis pipeline converts egocentric hand demonstrations into robot trajectories across 15 platforms, and a rigorous curation pipeline harmonizes heterogeneous datasets. Using only open-source datasets and human videos without proprietary data collection, Qwen-RobotManip constructs a ~38,100-hour pretraining corpus and exhibits emergent generalization capabilities, including zero-shot instruction following, robustness to perturbations, reactive error recovery, and cross-embodiment transfer. We find that standard benchmarks fail to capture pretraining quality and instead adopt OOD settings including RoboCasa365, LIBERO-Plus, EBench, RoboTwin-Clean2Rand, RoboTwin-IF, and RoboTwin-XE. Qwen-RobotManip substantially outperforms prior state-of-the-art models, including $π$0.5, across all OOD settings, ranks 1st in RoboChallenge with a 20% relative improvement, and is validated on real-robot platforms including AgileX ALOHA, Franka, UR, and ARX.

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale.

Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning. Instead, OneCanvas aggregates patch features from all views onto a single equirectangular panoramic canvas. Namely, each patch is unprojected to a 3D world coordinate using its depth and camera pose, then placed on the canvas at the continuous longitude and latitude of that point as seen from the canvas origin, with no rasterization or aggregation across overlapping views. A 3D position embedding of the patch's metric coordinates is added to its feature, restoring the depth lost when collapsing the world position to an angular canvas coordinate. Patches from all frames thus share one spatial coordinate system with no fusion or major architectural modifications of the backbone. The pretrained VLM consumes this representation as if it were an ordinary image. Because the canvas can be centered on any pose of interest, the same representation directly supports situated reasoning from a specific viewpoint, a common requirement in robotics and embodied AI. Thanks to this representation, we can also introduce a spatial pretraining curriculum: by procedurally placing patch features of objects, drawn from real images, at chosen 3D world positions on an otherwise empty canvas, we generate on-the-fly supervision spanning a broad range of spatial reasoning tasks, with answer distributions controlled to reduce spatial reasoning shortcuts. OneCanvas achieves state-of-the-art accuracy on SQA3D and VSI-Bench, and generalizes to out-of-distribution data on SPBench, using an order of magnitude less training compute than the strongest competing methods.

Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning.

This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observations, including visual, linguistic, and proprioceptive inputs, through a one-step denoising process. Built upon a flow-matching formulation, the proposed adapter effectively constrains the action generation trajectory within an invertible latent space, thereby enabling efficient and high-quality dexterous action synthesis with only a single inference step. Compared with conventional iterative flow-matching policies, the proposed framework substantially reduces inference complexity while maintaining strong action prediction accuracy and stability. Extensive experiments are conducted across a diverse set of simulation benchmarks and real-world robotic platforms to evaluate the effectiveness of the proposed method. Across simulation benchmarks, the proposed adapter consistently demonstrates superior or near state-of-the-art performance on a wide range of manipulation tasks. Furthermore, real-world experiments reveal a significant improvement in inference efficiency for vision-language-action (VLA) models, reducing the average inference latency from 110 ms to 61 ms while maintaining strong task performance.

This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observations, including visual, linguistic, and proprioceptive inputs, through a one-step denoising process.

Establishing a universal benchmark for tactile representation learning in robotic manipulation remains challenging due to the diversity of tactile sensor designs, data formats, and robot embodiments. Rather than seeking to establish such, we explore a scalable and promising direction for future development: egocentric vision paired with full-hand tactile data. To this end, we introduce \textbf{HT-Bench}, a large-scale multi-task benchmark for dexterous full-hand tactile sensing, comprising 10M RGB frames and 7.8M tactile frames collected across 226 tasks. HT-Bench evaluates tactile representations from three key perspectives: whether they encode meaningful contact geometry, whether they can align tactile observations with visual information, and whether they generalize to unseen tasks. To assess these capabilities, HT-Bench includes four tasks: fine-grained tactile similarity retrieval, masked tactile inpainting, vision-to-tactile synthesis, and multimodal tactile frame prediction. We further propose \textbf{HandTouch}, a vector-quantized vision--tactile encoder that learns tactile representations through progressive spatial, cross-modal, and temporal training. Across HT-Bench, HandTouch consistently outperforms representative tactile encoder baselines, improving Recall@5 on fine-grained tactile similarity retrieval from 74.65\% to 85.23\%, reducing RMSE on masked tactile inpainting from 0.022 to 0.010, and increasing OOD cIoU on vision-to-tactile synthesis from 0.628 to 0.705. These results demonstrate the effectiveness of HandTouch and suggest that large-scale egocentric full-hand tactile data provides a scalable basis for evaluating and advancing tactile representation learning in dexterous manipulation.

Establishing a universal benchmark for tactile representation learning in robotic manipulation remains challenging due to the diversity of tactile sensor designs, data formats, and robot embodiments.

The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments. While structured pruning offers a pathway to compression, existing state-of-the-art methods often rely on gradient-based importance ranking or stochastic gating, which suffer from instability, structural degeneration, and the need for extensive manual hyperparameter tuning. In this paper, we introduce CAHP (Complementary Attention Head Pruning), a novel post-hoc framework that redefines head selection as a global graph-theoretical problem. Rather than evaluating heads in isolation, CAHP utilizes graph-based clustering combined with information-theoretic distance measures to identify and preserve a topologically diverse subset of complementary attention heads. Without requiring a predefined sparsity level or pruning ratio, the framework automatically determines the number of selected attention heads across layers by identifying a diminishing marginal performance curve, where pruning additional heads leads to a sharp degradation in performance, as determined by the chosen polynomial degree. Extensive evaluations on the SST-5 and MNLI benchmarks, across different Transformer model scales, demonstrate that CAHP consistently outperforms competitive baselines, particularly in high-compression regimes. Furthermore, our structural analysis shows that CAHP avoids the "proximity bias" of gradient-based pruning methods, which tend to preserve heads mainly in layers close to the output, and instead retains a functionally critical set of attention heads in the model's intermediate layers.

The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments.

Pre-training Large Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators. While increasing model and dataset scale remains the dominant driver of performance, Mixture-of-Experts (MoEs) architectures have recently achieved state-of-the-art results by decoupling parameter count from computational cost. This efficiency enables training massive models on constrained compute budgets, yet it typically requires the high-speed interconnects of a single datacenter. To overcome these physical limits, recent approaches such as DiLoCo and Photon use low-communication data-parallel methods to enable scaling across geographically distributed, weakly connected data centers. However, these methods suffer from a fundamental inefficiency: they require full model replicas at every site, which imposes prohibitive memory constraints and communication overheads. In this work, we introduce FoMoE, a system that breaks the full-replica paradigm by partitioning expert layers across workers. We demonstrate that FoMoE: (I) reduces communication costs by up to 1.42x over efficient baselines and 45.44x over DDP via partial expert replication in the studied regimes; (II) achieves empirical throughput speedups of up to 1.4x through a novel skip-token mechanism; and (III) shows stable routing in the trained proxy regimes and projects the communication/memory benefits to 100B-scale configurations through system modelling.

Pre-training Large Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators.

Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experimentation by generating action-consistent video rollouts. However, persistent world modeling remains challenging in manipulation: frequent end-effector occlusions and rapid wrist-camera motion make the current observation insufficient for predicting future views, causing models to forget or hallucinate scene details seen in earlier frames. Existing memory retrieval strategies often fail to identify informative history in dynamic manipulation scenarios. To address this limitation, we propose Mem-World, a memory-augmented multi-view action-conditioned world model. At its core, we present W-VMem, a 4D wrist-view-centered surfel-indexed memory that anchors historical observations to temporally evolving surface elements. By explicitly modeling when and where scene elements are observed, W-VMem enables geometry-aware retrieval of relevant history frames conditioned on future actions. During generation, relevant history frames are selected via surfel-based rendering and scoring, providing informative and non-redundant context for prediction. Extensive experiments show that Mem-World generates persistent rollouts in complex manipulation scenarios, enables more reliable policy evaluation than Ctrl-World, improving the Pearson correlation with real-world performance by 14.5\%, and supports effective policy improvement through synthetic data generation, increasing success rates from 58\% to 72\% on long-horizon tasks.

Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experimentation by generating action-consistent video rollouts.

Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation. However, current simulators lack the fidelity to faithfully model the complex deformation and transduction mechanics of tactile sensors, severely hindering sim-to-real transfer in robot learning pipelines. To address this challenge, we propose a multi-modal representation learning framework that aligns heterogeneous tactile modalities within a shared latent space, eliminating the need for accurate raw-signal simulation while preserving relevant contact information. Our approach employs modality-specific encoders to project diverse tactile observations, such as simulated penetration depth and real-world capacitance, into a common embedding space. The model is trained using self- and cross-reconstruction objectives alongside contrastive alignment, encouraging modality-invariant yet information-rich representations. We evaluate the learned embeddings on indenter shape identification, force prediction, and geometric reconstruction tasks, training exclusively in simulation and testing directly on real sensor measurements. Our results demonstrate zero-shot sim-to-real transfer across physically dissimilar representations. Furthermore, incorporating multi-physics simulation modalities yields more informative embeddings that transfer across diverse downstream tasks, demonstrating a 16.7% reduction in force prediction error and a 45.8% reduction in shape reconstruction error. Finally, we release an efficient Warp-based implementation of a penalty-based tactile simulation model for Isaac Lab, enabling scalable tactile data generation.

Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation.

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.

Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions due to compounding execution errors; Can a reinforcement learning policy trained purely in simulation improve the robustness of real-world VLAs zero-shot? Residual RL, which learns a corrective policy on top of a frozen VLA, offers a natural framework, but existing approaches face a fundamental sim-to-real dilemma: privileged-state methods require lossy distillation for deployment; image-based methods suffer from the visual domain gap; and real-world RL is costly and unsafe. We propose an object-centric residual RL framework that refines VLA actions using object poses, enabling a compact observation space that transfers consistently between simulation and reality. To align the two domains, we additionally replay the same teleoperation demonstrations in simulation to train a sim counterpart of the real-world VLA. The residual RL policy is trained only in simulation with pose noise injection and dropout, and transfers zero-shot to the real robot. Across five manipulation tasks on a real Franka Research 3 (FR3) robot, our method improves the success rate from 42% to 76% zero-shot, and the improved rollouts can be further reused to retrain the base VLA for self-improvement without additional teleoperation. Project page: https://www.microsoft.com/en-us/research/articles/object-centric-residual-rl/

Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions due to compounding execution errors; Can a reinforcement learning policy trained purely in simulation improve the robustness of real-world VLAs zero-shot?

Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limiting robustness and contractility in manipulation tasks. We propose STORM (Slot-based Task-aware Object-centric Representation for robotic Manipulation), a lightweight object-centric adaptation module that augments frozen visual foundation models with a small set of semantic-aware slots for robotic manipulation. Rather than retraining large backbones, STORM employs a multi-phase training strategy: object-centric slots are first stabilized through visual--semantic pretraining using language embeddings, then jointly adapted with a downstream manipulation policy. This staged learning prevents degenerate slot formation and preserves semantic consistency while aligning perception with task objectives. Experiments on object discovery benchmarks and simulated manipulation tasks show that STORM improves generalization to visual distractors, and control performance compared to directly using frozen foundation model features or training object-centric representations end-to-end. Our results highlight multi-phase adaptation as an efficient mechanism for transforming generic foundation model features into task-aware object-centric representations for robotic control.

Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limiting robustness and contractility in manipulation tasks.

Generalist embodied agents require more than object recognition: they must reason about spatial relations, actions, procedures, human intentions, environmental constraints, and commonsense consequences from situated visual observations. Yet existing visual and embodied question answering benchmarks often provide limited control over the reasoning dependencies being tested, making it difficult to distinguish grounded embodied reasoning from shortcut-driven visual or linguistic pattern matching. We present ERQA-Plus, a diagnostic benchmark for reasoning in embodied AI. ERQA-Plus contains 1,766 question-answer instances grounded in 711 robot-centric images and organized according to a structured taxonomy spanning perceptual, action-centric, social-interaction, navigation-environmental, and contextual commonsense reasoning. The dataset is constructed using a multi-stage generation and validation pipeline that combines taxonomy-guided question generation, automatic quality judging, iterative revision, and human assessment to improve visual grounding, answer validity, and reasoning quality. We benchmark representative general-purpose vision-language models and embodied models, including LLaVA-NeXT-8B, Prismatic-7B, MiniCPM-V-4.5-8B, Qwen3-VL, RoboRefer-8B, and RoboBrain2.5-8B. Although the strongest model, Qwen3-VL-32B, achieves 83.4% overall accuracy and 61.4 SBERT score, category-level results reveal persistent weaknesses in spatial reasoning, procedural reasoning, event prediction, and intention inference. ERQA-Plus therefore provides a fine-grained evaluation framework for measuring not only whether embodied agents answer correctly, but also which forms of embodied reasoning they can and cannot perform reliably. The dataset is available https://huggingface.co/datasets/huggingdas/erqa-plus and the project page at https://github.com/LUNAProject22/erqa-plus.

Generalist embodied agents require more than object recognition: they must reason about spatial relations, actions, procedures, human intentions, environmental constraints, and commonsense consequences from situated visual observations.

Photonic quantum machine learning offers a route to trainable physical representations built from phase, interference and measurement. However, its role in scientific machine learning remains largely unexplored. Physics-informed neural fields provide a natural setting, because differential equations require trial spaces that preserve phase, frequency and derivative structure. Here we introduce a photonic quantum neural field in which coordinates become trainable optical phases, are mixed by multi-photon Fock-space interference and are decoded from photon-number measurements. The photonic circuit is optimized as the neural-field representation itself, not as a fixed feature map or hardware accelerator. Photonic measurement is therefore a trainable representation on which the physics-informed residual is minimized. Across seven elliptic, wave, nonlinear dispersive and inverse PDE benchmarks, we observe a phase-complexity transition: classical coordinate and Fourier-feature networks suffice in smooth regimes, whereas the photonic field is most accurate when residual derivatives amplify phase mismatch. In the hardest regimes it gives the lowest errors, with margins reaching an order of magnitude and about one quarter of the trainable parameters of classical baselines. Frozen and shuffled controls, together with noise stress tests, attribute this gain to learned interference and stable Fock-probability readout under compound perturbations. These results identify photonic quantum measurement as a representation-learning principle for scientific machine learning.

Photonic quantum machine learning offers a route to trainable physical representations built from phase, interference and measurement.

Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting the drift a forward-only model cannot penalize. Second, cross-view consistency trains the model to inpaint each camera view from the other, keeping the multi-camera observation coherent over long rollouts without any explicit memory mechanism. Third, test-time consistency reuses the inverse dynamics mode at inference as a per-action-chunk uncertainty signal that terminates rollouts whose generated frames drift away from the requested actions. We also demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison rather than aggregate ranking alone. Across seven real-world vision-language-action policies, SC3-Eval attains a closed-loop Pearson correlation of $0.929$ and MMRV of $0.119$, outperforming three strong prior video-model-based baselines, and generalizes to new tasks.

Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale.

In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance. In this study, we evaluate pose increment, pose velocity, joint position increment, and joint velocity across two vision-based manipulation tasks: object picking and pushing. We train policies in simulation and deploy them to the real world using sim-to-real transfer. We find that action-space representation indeed significantly affects sim-to-real performance. In particular, we find that the joint velocity action space is best for the vision-based picking and pushing tasks in terms of smoothness and final task performance. We also provide practical guidance for RL practitioners in choosing action spaces for both simulation and real-world experiments.

In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance.

Action chunking has become a common interface for vision-language-action (VLA) models, enabling low-frequency policy inference to drive high-frequency robot execution. However, once an action chunk is committed, its open-loop execution can be brittle under stochastic dynamics, hardware execution errors, and partial observability. We propose DREAM-Chunk, a test-time scaling method that augments chunking-based policies with a lightweight latent world model, without requiring additional policy fine-tuning. At test time, DREAM-Chunk samples multiple candidate action chunks, rolls out their predicted latent futures, and selects actions from the chunk whose predicted state best matches the observed rollout. In this way, DREAM-Chunk uses additional test-time computation to cover multiple plausible stochastic futures and improve reactivity during long-horizon chunk execution. On the Kinetix benchmark, DREAM-Chunk improves robustness under increasing action noise and benefits from larger candidate sample sizes, especially when demonstrations contain corrective behaviors. We further validate DREAM-Chunk on four manipulation tasks across two robot platforms and two VLA policies under various sources of stochasticity. Across simulation and hardware experiments, DREAM-Chunk improves the robustness of action-chunking policies in stochastic dynamics.

Action chunking has become a common interface for vision-language-action (VLA) models, enabling low-frequency policy inference to drive high-frequency robot execution.

Federated Learning (FL) is a promising paradigm for finetuning Large Language Models (LLMs) across distributed data sources while preserving data privacy. However, finetuning such large models is challenging on edge devices due to its high resource demand. Zeroth-order Optimization (ZO) estimates gradients through finite-difference approximations, which rely on function evaluations under random perturbations of the model parameters. Consequently, ZO with task alignment provides a potential solution, allowing finetuning using only forward passes with inference-level memory requirements and low communication overhead, but it suffers from slow convergence and higher computational demand. In this paper, we propose a new ZO-based method that applies a more efficient technique to reduce the computational demand associated with using a large number of perturbations while preserving their convergence benefits. This is achieved by splitting the model into consecutive blocks and allocating a higher number of perturbations to the second block, enabling efficient reuse of intermediate activations to update the full network with fewer forward evaluations. Our evaluation on RoBERTa-large, OPT1.3B, LLaMa-3-3.2B models shows up to $3\times$ reduction in computation compared to the other ZO-based techniques, while retaining the memory and communication benefits over first-order federated learning techniques.

Federated Learning (FL) is a promising paradigm for finetuning Large Language Models (LLMs) across distributed data sources while preserving data privacy.

The potential impacts of world models (WMs, i.e., learned simulators) on robotics are far-reaching -- policy evaluation, policy improvement, and test-time planning -- all with limited real-world interaction. To unlock these downstream capabilities, a WM needs to jointly satisfy three desiderata: $\textit{(i)}$ fidelity (i.e., producing simulated trajectories that correlate with reality), $\textit{(ii)}$ consistency (i.e., producing simulated trajectories that are coherent over long horizons), and $\textit{(iii)}$ efficiency (i.e., producing simulated trajectories quickly). We propose WEAVER (World Estimation Across Views for Embodied Reasoning): a WM architecture that simultaneously achieves all three desiderata, providing state-of-the-art results on robotic manipulation tasks. WEAVER is a multi-view WM trained to predict future latents and reward values via a flow-matching loss. We distill the key design decisions across model architecture, memory, and prediction objectives required to unlock the kinds of long-horizon dynamic manipulation tasks that have confounded prior world modeling approaches. We apply WEAVER in robotic hardware, demonstrating its effectiveness at policy evaluation ($ρ$=0.870 correlation with real-world success rate), policy improvement (real-world success rate improvement of $38\%$ on top of the $π_{0.5}$ robot foundation model), and test-time planning (real-world success rate improvement of $14\%$ with a $5-10\times$ speedup over prior WMs). WEAVER also demonstrates better performance than prior WMs when evaluated on out-of-distribution scenarios. Code, models, and videos at: https://arnavkj1995.github.io/WEAVER/ .

The potential impacts of world models (WMs, i.e., learned simulators) on robotics are far-reaching -- policy evaluation, policy improvement, and test-time planning -- all with limited real-world interaction.

Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation must occur on sub-microsecond timescales. Meeting these requirements demands low-latency, fixed-precision computation under strict memory constraints, a regime in which conventional Multi-Layer Perceptrons (MLPs) are both inefficient and numerically unstable. We identify key properties of Kolmogorov-Arnold Networks (KANs) that align with these constraints. Specifically, we show that: (i) KAN updates exploiting B-spline locality are sparse, enabling superior on-chip resource scaling, and (ii) KANs are inherently robust to fixed-point quantization. By implementing fixed-point online training on Field-Programmable Gate Arrays (FPGAs), a representative platform for on-chip computation, we demonstrate that KAN-based online learners are significantly more efficient and expressive than MLPs across a range of low-latency and resource-constrained tasks. To our knowledge, this work is the first to demonstrate model-free online learning at sub-microsecond latencies.

Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation must occur on sub-microsecond timescales.

We introduce VEGA, an approach for training navigation VisionLanguage-Action (VLA) models from unlabeled egocentric navigation videos. Internet-scale egocentric videos provide a scalable source of navigation-relevant visual observations, capturing cluttered scenes, close-range obstacles, and natural human motion through real-world spaces. However, these videos are not directly usable for policy learning because they do not provide obstacle-aware trajectories conditioned on explicit navigation goals in the robot's coordinate frame. VEGA addresses this gap by reconstructing local scene geometry from monocular video, sampling navigation goals (represented as text, image, or spatial waypoints) and generating obstacle-aware trajectories using the constructed geometry. The resulting trajectory distribution is then used to train a flow-matching VLA navigation policy. By using geometry exclusively during training, VEGA distills obstacle-aware planning directly into a vision-based policy. Furthermore, we introduce VEGA-Bench, a benchmark containing 250k scenes and approximately 5 million navigation goals paired with scene geometry, designed to evaluate goal progress, collision avoidance, and obstacle clearance of VLAs. Our evaluation shows that VEGA achieves competitive goal progress while reducing collisions by 33.0% and improving obstacle clearance by 17.9% over the strongest baseline on VEGABench, while improving success by at least 150.0%, reducing collisions by at least 66.7%, and improving obstacle clearance by at least 60.0% in real-world trials. Ultimately, we demonstrate that video-derived geometric supervision provides a scalable and effective signal for training obstacle-aware navigation VLAs. The code and benchmark will be released at the time of publication.

We introduce VEGA, an approach for training navigation VisionLanguage-Action (VLA) models from unlabeled egocentric navigation videos.

Edge-AI systems increasingly require real-time CNN inference under strict energy, performance, security, and privacy constraints. Approximate computing improves hardware efficiency by exploiting the error resilience of neural network workloads; however, most approximate CNN accelerators do not jointly consider secure, privacy-aware edge deployment. This paper presents SPARX, a Secure and Privacy-Aware Approximate CNN Acceleration framework integrated within a heterogeneous RV32IMC RISC-V System-on-Chip (SoC). SPARX combines a custom RISC-V instruction extension, an approximate logarithmic CNN acceleration unit, a lightweight differential-noise-based privacy engine, and a challenge-response authentication mechanism. To guide arithmetic selection, an approximation-aware decision framework is introduced that uses the Approximation Severity Index (ASI), Approximation Efficiency (AE), Quality of Approximation (QoA), Approximation Figure-of-Merit (AFOM), and Hardware Acceleration Efficiency (HAE). Evaluation across 11 state-of-the-art approximate MAC architectures identifies the Iterative Logarithmic Multiplier (ILM) as the most suitable design, achieving 51.7% area reduction, 81.5% power reduction, and 2.13x throughput improvement compared with an accurate radix-4 Booth MAC, while only reducing ResNet-20/CIFAR-10 accuracy by 2.82 percentage points. FPGA implementation on a Xilinx VC707 platform achieves 58.4 GOPS/W energy efficiency at 250 MHz, while 28-nm CMOS physical implementation validates ASIC feasibility

Edge-AI systems increasingly require real-time CNN inference under strict energy, performance, security, and privacy constraints.

World foundation models (WFMs) are powerful simulators, yet they predominantly operate in a single-view setting and lack the multi-view 3D consistency required for robotic manipulation. While robotic systems rely on multiple cameras (egocentric, eye-to-hand, and wrist-mounted) for policy learning, current multi-view world models simply concatenate view tokens without explicit geometric reasoning. This causes cross-view object drift, depth inconsistency, and texture misalignment. We trace these failures to two deficiencies: the absence of an explicit inter-view communication mechanism and the lack of a 3D geometric prior. We argue that resolving both simultaneously is necessary and sufficient. To address this, we present PAIWorld, a framework that augments diffusion-transformer world models via three core components: (1) Geometry-Aware Cross-View Attention blocks that establish an explicit pathway across views, (2) Geometric Rotary Position Embedding that encodes camera ray directions and extrinsic poses into the attention mechanism, and (3) Latent 3D-REPA, which distills 3D-aware features from frozen 3D foundation models to ensure 3D consistency. Built upon a DiT-based world foundation model, PAIWorld achieves state-of-the-art multi-view 3D consistency on robotic manipulation benchmarks, ranking 1st on the WorldArena leaderboard and 2nd on the AgiBot-Challenge2026 leaderboard, while enabling downstream applications such as model-based planning, world action models, and multi-view policy post-training.

World foundation models (WFMs) are powerful simulators, yet they predominantly operate in a single-view setting and lack the multi-view 3D consistency required for robotic manipulation.

Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps. Large language models (LLMs) now approach this through two routes: internalized reasoning and externalized agent scaffolding (frameworks that decompose problems collaboratively amongst multiple LLMs). To determine whether these routes are exclusive or complementary, we introduce MedicalAgentsBench, a filtered benchmark of 862 complex clinical questions drawn from the union of eight medical datasets via difficulty-aware curation and contamination screening. Evaluating three internalized reasoning models (DeepSeek-R1, o1-mini, and o3-mini), seven base models, and nine externalized agent-based methods, we find that internalized and externalized approaches each independently improve performance, and that their benefits compound: the highest accuracy is achieved by layering agent workflows onto an internalized reasoning model (i.e., o3-mini + MDAgents with 35.1%). Pareto analysis shows this combination dominates the cost-performance frontier; moreover, lightweight optimization on inexpensive models offers an entry point for resource-constrained settings. Our benchmark is at https://github.com/gersteinlab/MedicalAgentsBench.

Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps.

Embodied agents that navigate cities rely on world models that predict how their surroundings will change as they move. But for navigation, what matters is not what the buildings look like; it is where the agent can go. Most world models nonetheless predict appearance, learning how a scene looks rather than the space an agent can move through. Those that do target geometry, such as bird's-eye-view occupancy grids, flatten the three-dimensional environment onto a ground plane, discarding the above-ground and multi-level structure that shapes real navigation. What is missing is a predictive target that captures the navigable geometry an agent actually traverses, without photometric entanglement and without collapsing the third dimension. Our key idea is to model the open volume between buildings, the negative space, encoded as a 3D isovist: a spherical visibility-depth map recording the distance to the nearest surface in every direction. We introduce an embodied world model that predicts the next isovist from a short history of past isovists and a movement action. The prediction is formulated as a depth residual so the decoder inherits sharp building edges, trained with self-rollout scheduled sampling to keep corrupted context on the geometry manifold, and equipped with a persistent latent bird's-eye-view spatial map for cross-path consistency. Our central finding is emergent and unexpected: a single city-blind model trained on Manhattan and Paris develops a cross-city spatial signature, with city identity linearly decodable from its temporal latents far above single-frame baselines, so the signature lives in the learned dynamics rather than in appearance. The representation is lightweight, interpretable, and reproducible, offering a geometric substrate for spatial reasoning in embodied AI, robotics, and urban analysis, released with an open dataset and pipeline.

Embodied agents that navigate cities rely on world models that predict how their surroundings will change as they move.

Embedded machine learning moves inference from cloud services to resource-constrained devices that must acquire data, preprocess signals, run a model, and act within tight limits on memory, energy, and latency. This paper presents a systems-oriented synthesis of an embedded machine-learning workflow for microcontroller-class platforms. The emphasis is placed on engineering decisions that are often hidden in generic machine-learning introductions: sampling and buffering, feature extraction as dimensionality reduction, validation under class imbalance, model/runtime co-design, and streaming deployment. Two representative signal families are used throughout the paper. The first is inertial motion recognition, where a two-second, three-axis accelerometer window is transformed from raw samples into root-mean-square and spectral features before classification. The second is keyword spotting, where audio is sampled, anti-aliased, transformed into mel-frequency cepstral coefficients, and processed by a compact one-dimensional convolutional network. The paper concludes with practical design rules for robust on-device inference, including data curation, quantization, thresholding, scheduling, and field monitoring.

Embedded machine learning moves inference from cloud services to resource-constrained devices that must acquire data, preprocess signals, run a model, and act within tight limits on memory, energy, and latency.

Deformable Linear Objects (DLOs), such as wires and cables, are central to industrial assembly. Unlike rigid objects, whose state is captured by a 6-DoF pose, DLOs have an infinite-dimensional configuration space and deform continuously under contact with grippers, fixtures, and the workspace, making them a demanding benchmark for general dexterous manipulation. Despite their importance, policy development and comparison remain difficult: existing benchmarks are often tied to specific hardware setups, lack modular and customizable task assets, or study generic deformable-object tasks without the fixtures relevant to real-world industrial wire manipulation. Few benchmarks align simulation, real-world data, and shared evaluation protocols. To bridge this gap, we introduce WireCraft, a simulation benchmark for industrial DLO manipulation with configurable difficulty and assets, spanning three task families: connector insertion, clip routing, and channel seating. It supports two complementary DLO physics models, articulated and deformable, and the trajectories come from both simulation and a physical UR5. We benchmark reinforcement learning (RL), imitation learning (IL), and vision-language-action (VLA) policies under shared metrics. Privileged state-based RL solves a representative setting in each task family with over 82\% success, confirming the tasks are well-posed. For connector insertion, however, the transition from reaching the socket to contact-rich alignment remains a key bottleneck for vision RL, IL, and VLA policies. These results indicate that industrial DLO manipulation, though tractable under privileged state, remains an open challenge for current vision-based learning. The benchmark, data, and tools will be open-sourced upon acceptance.

Deformable Linear Objects (DLOs), such as wires and cables, are central to industrial assembly.

Structured State Space Models (SSMs), including the S4 and S4D architectures, have recently emerged as powerful alternatives to attention-based models for capturing long-range dependencies in sequential data. Despite their strong empirical performance, deploying these models in time- and resource-constrained settings remains challenging due to their computational and memory demands. In this paper, we propose a novel incremental, operator-level pruning approach for S4- and S4D-based models that significantly reduces inference cost while preserving predictive performance. To the best of our knowledge, this is the first work to systematically investigate structured operator pruning for SSMs. Our method progressively prunes model operators by interleaving structured masking with fine-tuning, while jointly monitoring accuracy and inference latency. We implement this approach within a unified training and evaluation framework that enables systematic exploration of efficiency-accuracy trade-offs. Experiments across multiple benchmark datasets show that pruning up to 70% of the model operators preserves the performance of the original models in most cases, while substantially reducing inference latency. These results demonstrate that structured operator pruning is an effective and previously unexplored strategy for improving the efficiency of SSMs and facilitate their deployment in practical, resource-constrained scenarios.

Structured State Space Models (SSMs), including the S4 and S4D architectures, have recently emerged as powerful alternatives to attention-based models for capturing long-range dependencies in sequential data.