arXiv:2607.17056v1 Announce Type: new
Abstract: Most existing watermarking techniques are primarily designed for low-resolution images, with few methods tailored for high-resolution images. Moreover, the embedding capacity is often limited to fixed lengths (e.g., 30, 100, 256 bits, etc.), which struggles to meet practical demands. To address these issues, this paper proposes a high-capacity robust watermarking method for high-resolution images, capable of embedding a watermark of 4 KB (32,768 bits) into images with a resolution of 1024*1024, achieving an embedding rate of 0.0313 bpp. Specifically, this paper adopts a block-wise strategy to effectively embed the watermark into local regions, enabling the network to train and learn normally even under low-resource conditions. The encoder and decoder structures respectively employ a reversible symmetric architecture with three convolutional and three deconvolutional layers, ensuring consistency in the coupling and decoupling of the watermark and image features. Additionally, the loss function combines global and local losses with weighted contributions. By incorporating constraints on the visual quality and robustness of local block regions, the overall imperceptibility and robustness of the image are further enhanced. Extensive experimental results verify that the proposed method is effective and feasible in high-resolution image scenarios with high-capacity watermarking, while demonstrating strong robustness against various noise attacks.
Science Journals
arXiv:2607.17069v1 Announce Type: new
Abstract: AI-based visual perception systems are increasingly deployed in infrastructure surveillance, including roadside monitoring units, highway cameras, and smart-city pedestrian management systems. The security vulnerability of these systems to physical adversarial attacks poses a direct threat to the reliable operation of transportation infrastructure. We propose AdvSerial, a dynamic 2D--3D joint optimization framework for generating continuous high-angle physical adversarial patches against pedestrian detectors in infrastructure-based scenarios. We UV-map a boundary-aware quilted texture onto 3D garments, combine 2D digital attacks with 3D sparse- and continuous-frame rendering, and explicitly suppress person-specific semantic features while enforcing temporal continuity. A Feature Smooth Quilting strategy reduces visible patch boundaries and bounds cross-seam feature discontinuities. A serial-frame loss encourages long uninterrupted sequences of detection failures. In physical world experiments, AdvSerial achieves a 74.8% attack success rate on YOLO-v5 and degrades mean detection confidence from 84.30% to 39.38%. Experiments spanning eight detectors with different architectures demonstrate strong transferability. Notably, it achieves an $89.71%$ attack success rate on YOLO-v2 and resists both patch-detection defenses (NapGuard) and 3D-temporal perception (Sparse4D-v3). The results reveal persistent, temporally consistent failure modes under high-angle surveillance, and motivate the design of motion-aware and 3D-aware defenses for security-critical infrastructure deployments.
arXiv:2607.17074v1 Announce Type: new
Abstract: Mixture of Experts (MoE) architectures have emerged as a dominant paradigm for scaling Large Language Models (LLMs). However, MoE inference on conventional hardware is constrained by three fundamental bottlenecks. These encompass the massive memory bandwidth required to fetch non-contiguous expert weights, the non-deterministic scatter-gather traffic generated by input-dependent token routing, and the tail-latency dependency imposed by synchronous expert output aggregation. To address these challenges, we propose ThAME, a three-dimensional (3D) heterogeneous multi-chiplet architecture for MoE inference. ThAME employs Ferroelectric Field-Effect Transistor (FeFET)-based non-volatile and DRAM-based volatile memory chiplets with a co-designed compute mapping strategy that aligns the distinct computational profiles of attention mechanisms and expert routing. Furthermore, we design a specialized Network-on-Chip communication backbone optimized to mitigate the bottlenecks associated with non-deterministic token routing traffic across the combinatorial space of input-dependent MoE traffic patterns. Experimental results demonstrate that ThAME outperforms state-of-the-art counterparts by up to 15.7x in terms of speedup and improves energy efficiency by up to 9.8x.
arXiv:2607.16254v1 Announce Type: new
Abstract: FFNs are often treated as parametric memories. In long-context retrieval, however, the sharper question is not only what they store, but whether their native residual writes push the current retrieval state toward or away from the correct answer. We test this by scaling the model's own FFN write one layer at a time, without editing weights or injecting external steering vectors.
Across controlled literal and semantic retrieval suites, native FFN response surfaces are signed, layer-specific, and task-conditioned: the final FFN is a suppressor in 7 of 8 model-suite cases, and 60% of layers switch role between retrieval modes (95% CI [50%, 69%]). A local directional derivative along the native write separates the two monotone roles: suppressors have negative derivative in 34/35 cases, and amplifiers have positive derivative in 18/18 cases, so the roles are not reducible to write size. On a safety-filtered LongBench retrieval-QA probe, the same diagnostic predicts attenuation damage with raw R^2=0.796 on Qwen2.5-7B and 0.791 on Qwen3.5-9B; a held-out suppressor-attenuation policy improves retrieval margins over random and norm-matched controls. These results show that native FFN scaling exposes a signed, task-conditioned residual-write structure in retrieval, and that write-gradient alignment is a compact diagnostic for the two monotone roles.
arXiv:2607.17025v1 Announce Type: new
Abstract: Drone swarms are increasingly deployed in critical applications such as surveillance, disaster response, and infrastructure monitoring. However, their reliance on open communication channels and their limited computational resources make them vulnerable to a wide range of cyber-threats. There is a growing interest in intrusion detection systems (IDS) specifically designed for drone environments and operations. However, the conventional solutions including Machine Learning (ML)-based approaches require collecting all data from heterogeneous drones in the swarm and processing on a central server may not be always feasible. Federated Learning (FL) has emerged as a promising distributed solution with an additional privacy-preserving feature. Even though potential studies exist, conventional FL-based IDS frameworks still face communication and computational overhead challenges, while achieving a balance between efficiency and effective detection under practical resource constraints remains a challenge. Therefore, we propose a lightweight FL-based IDS tailored for drone swarm networks using deep neural networks (DNN) enhanced with knowledge distillation (KD) to reduce model complexity and communication costs without sacrificing detection performance. We evaluate our framework using Raspberry Pi 4 devices and a real-world drone network dataset. Our approach demonstrates a detection accuracy of approximately 98.6% while reducing overall communication cost by around 70% and computational overhead by 29%. These results show that FL combined with KD is a practical and suitable solution for secure and efficient deployment in resource-constrained drone networks.
arXiv:2607.17876v1 Announce Type: new
Abstract: We provide a novel end-to-end framework for the execution of an assembly operation by two robotic arms, given the digital CAD models of the parts and their desired relative placement in their assembled state. We analyze and demonstrate the advantages of using two robotic arms simultaneously in tight assembly operations, compared to single-arm systems. Our method is implemented in both simulation and using physical robots. It provides theoretical guarantees on execution time and trajectory accuracy, supported by empirical evidence. In particular, we show that coordinated movement of two arms reduces average execution time by more than 50% compared to using a single arm only, produces higher-quality trajectories, and accelerates the search for valid robot placements. Furthermore, we establish bounds on the required dimensions of the robotic cell. Our open source software together with real-life video demonstrations are available in our project page.
arXiv:2607.16787v1 Announce Type: new
Abstract: Surgical video phase recognition is a fundamental task in computer-assisted intervention, supporting workflow understanding, intraoperative guidance, and surgical quality assessment. Although recent visual-temporal models have achieved promising progress, accurate and temporally coherent phase recognition remains challenging due to local visual ambiguity, transient prediction noise, and insufficient use of procedural semantics. To address these challenges, we propose HTT-Net, a Hierarchical Text-guided Transition modeling Network for surgical video phase recognition. The key idea is to introduce structured surgical semantic knowledge into phase-aware segment construction and semantic refinement. Specifically, we construct a hierarchical surgical semantic memory with intra-phase descriptions, inter-phase transition descriptions, and fine-grained semantic units. Based on this memory, the proposed Transition-Aware Segment Construction (TAS-Con) organizes frame-level evidence into coherent segment representations and handles boundary clips with inter-phase transition descriptions. Furthermore, we introduce Transition-Aware Segment Calibration (TAS-Calib), which calibrates phase-aware segment representations through hierarchical surgical semantics and improves discrimination under visual ambiguity without dense frame-level vision-language fusion. Experiments on Cholec80 and LCRS-100 demonstrate the effectiveness of HTT-Net for robust surgical video phase recognition.
arXiv:2607.16255v1 Announce Type: new
Abstract: A crucial step in machine learning pipelines is to present each entity with features or attributes that are representative of the characteristics of the processed entities. Feature engineering is an important step in finding a relation among attributes that otherwise may not be processed by the ML algorithms. Meanwhile, Large Language Models have shown promising abilities in coding, mathematical reasoning, and processing world knowledge. In this work, we utilize an LLM for the problem of feature generation from tabular data based on the previously given features. We have created a pipeline that takes a set of attributes and a prompt to generate new features. Then, our selection algorithm selects the best-performing sets of attributes. We apply our method to eight datasets from different domains and data types. Our results show that, in most cases, the language model can produce new features based on mathematical and logical operators that are useful for the given tasks and can improve classification results.
arXiv:2607.17314v1 Announce Type: new
Abstract: The transcorrelated (TC) method dramatically accelerates the convergence of correlated calculations toward the complete-basis-set (CBS) limit by folding a Jastrow correlator into the Hamiltonian via a similarity transformation, incorporating the electron--electron cusp into the effective interaction. We make the TC framework practical for large systems and flexible, multi-center correlators by compressing the grid-evaluated TC integrals with the interpolative separable density-fitting (ISDF) approximation, combined with the effective two-body (xTC) treatment of the three-body operator. This low-rank representation reduces storage and integration costs by orders of magnitude, and a multi-GPU implementation with automatic differentiation of the correlator makes the construction routine for large basis sets. We demonstrate the resulting ISDF-xTC-CCSD method on the linear hydrogen chain, reaching the joint thermodynamic and CBS limits with basis sets up to cc-pV5Z in agreement with state-of-the-art many-body references to within about 1~mHa/atom, and on the benzene ground-state energy with up to 1200 orbitals (cc-pCV5Z), where the method attains state-of-the-art accuracy at the coupled cluster singles and doubles level and its CBS extrapolation is markedly more robust than that of conventional coupled-cluster methods.
arXiv:2607.16257v1 Announce Type: new
Abstract: Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face challenges in training agents with longer-horizon interactions. One major bottleneck is distinguishing the contribution of different actions in long-horizon interaction, leading to high optimization variance. To address this, we introduce a novel policy gradient method, Hindsight Policy Optimization (HPO), that projects both the current policy distribution and the hindsight distribution into an intent space and extracts low-variance learning signals from the Wasserstein distance between them. We theoretically and empirically show that aggregating semantically similar states and actions in the intent space yields a bounded-variance estimator and improves policy performance stably. Our code is available online.
arXiv:2607.17075v1 Announce Type: new
Abstract: The advent of LLMs has significantly changed the research on privacy policy and data compliance analysis by enabling tasks that previously required specialized, domain-specific tools. However, it remains unclear to what extent LLMs can truly replicate the diverse functionalities, and the wide range of methodologies and analysis offered by prior work. In this paper, we conduct the first systematic evaluation of whether off-the-shelf LLMs can replace specialized privacy analysis tools. We study six representative tools spanning three major functionalities: contradiction detection, regulatory compliance analysis, and privacy policy summarization and aggregation, and across three intermediate tasks: structured data extraction using tuples, Semantic Role Labeling (SRL) and manual privacy policy labeling. We compare the performance of two state-of-the-art LLMs (GPT-5.2 and Gemini-2.5 in various configurations) against the tools by directly prompting the models to perform corresponding functionalities and tasks on a custom dataset of 10 privacy policies, allowing us to assess whether off-the-shelf models can produce tool-specific functionalities without further engineering or domain-specific training, major limitations in prior work. Our results show that LLMs consistently match or exceed the capabilities of existing tools across the functionalities. In manual labeling of first-party collection entities, LLMs achieved an average precision of 81.8% and recall of 70.9%, while for labeling of third-party sharing entities, they achieved an average precision of 91.4% and recall of 70.8% compared to the OPP-115 dataset. Overall, our findings indicate that LLMs can effectively perform a broad range of functionalities and tasks in privacy policy and regulation analysis that previously required specialized tools.
arXiv:2607.16649v1 Announce Type: new
Abstract: Magnetic Resonance Imaging (MRI) is often acquired with anisotropic resolution to reduce scan time, producing stair-step artifacts along the through-plane direction. In through-plane MRI super-resolution, an efficiency-fidelity trade-off arises: feed-forward regressors are fast but oversmooth at large slice-thicknesses, while sampling-based methods improve fidelity at high inference cost. We propose DRIFT, a two-stage thickness-conditioned rectified flow framework for through-plane MRI super-resolution with continuous input slice-thickness. Stage 1 employs an Anatomical Projection Network (APN) to map low-resolution patches to a coarse high-resolution manifold, providing a deterministic anatomical initialization that shortens the residual transport of Stage 2 and stabilizes slice-wise refinement. Stage 2 refines details via rectified flow and introduces a Physics-Aware Difficulty (PAD) metric derived from slice-thickness induced through-plane bandwidth deficit to guide an Adaptive Integration Scheduler (AIS), allocating ODE steps by thickness. A Consistent Endpoint Trajectory Alignment (CETA) loss enforces thickness-consistent reconstructions. Experiments show that DRIFT outperforms super-resolution baselines while reducing inference cost. Code, models, and interactive demos are available at https://yoonseokchoi-ai.github.io/drift-eccv2026/.
arXiv:2607.16347v1 Announce Type: new
Abstract: We study the classical single-machine deadline problem $1 \mid\mid \sum U_j$, in which each task has a deadline and an execution requirement and the goal is to select as many on-time tasks as possible. The standard Moore-Hodgson algorithm processes tasks by deadline and may later delete a previously accepted task. We study the insertion-only shortest-job-first rule of Lin and Wang: process the tasks in nondecreasing execution requirement, and accept a task exactly when doing so preserves feasibility. We give a direct $O(n\log n)$-time implementation using a balanced augmented BST keyed by deadline. Unlike the previous $O(n\log n)$ implementation of this SJF rule, our implementation needs neither a pre\"emptive schedule nor an amortized analysis of interval changes.
Our analysis gives an explicit threshold form of the rule's lexicographic (\emph{lex-first}) optimality: for every threshold~$e$, its outputs maximize the number of selected tasks whose execution requirement is at most~$e$. The analysis also reveals additional combinatorial structure. After the shorter tasks have been greedily fixed, the feasible choices within a single execution-requirement tier form a nested matroid. These tier matroids assemble, as a direct sum, into an overall laminar matroid whose bases are exactly the greedy outputs. Finally, a flow network encoding the deadline-prefix constraints gives a polymatroid rank function for the underlying scheduling feasibility structure. This flow view also recovers the nested matroids that govern the equal-execution tiers.
arXiv:2607.17076v1 Announce Type: new
Abstract: Routing quantum keys over low-earth-orbit (LEO) satellite constellations is harder than classical routing: satellite handovers couple consecutive scheduling decisions, stochastic cloud cover can silently zero a ground link, and finite-key effects eliminate short, low-elevation passes entirely. We present SATLOCK, a handover-aware Quantum Key Distribution (QKD) routing framework that combines (i) a composite channel model incorporating atmospheric loss, pointing jitter, Markov cloud cover, decoy-state estimation, and finite-key correction; (ii) an integer linear program (ILP) giving a provable handover-aware throughput upper bound; and (iii) a decentralized deep Q-network (DQN) baseline for weather-adaptive online routing. We evaluate two contention regimes on a Walker constellation serving intercontinental demands. In low contention (16 satellites, 6 demands), the ILP delivers 1,311 Mbit while the strongest heuristics reach 95--96\% of ILP. In high contention (8 satellites, 12 demands), where handovers become binding, heuristics drop to 89.5\% of ILP. The DQN agent reaches 91.8\% and 84.6\% of ILP in the two regimes; it learns effective per-demand weather policies but is limited in aggregate by the lack of cross-demand coordination.
arXiv:2607.16654v1 Announce Type: new
Abstract: We present a combined experimental and numerical investigation of the preferential alignment of Kolmogorov-size, high-aspect-ratio fibers in turbulent channel flow at friction Reynolds numbers $\mathit{Re}_{\tau}=300$ and $550$. Time-resolved volumetric measurements in the TU Wien Turbulent Water Channel are used to simultaneously track fibers and surrounding tracer particles, enabling the reconstruction of fiber trajectories together with a coarse-grained estimate of the local velocity-gradient tensor (VGT). Complementary direct numerical simulations (DNS) of channel flow laden with prolate ellipsoids provide a reference point-particle description. The analysis focuses on the channel core, where the experimental data recover the canonical alignment of vorticity with the intermediate strain-rate eigenvector, thereby supporting the reliability of the reconstructed VGT. We show that fibers preferentially align with the local vorticity direction, while weaker but still non-random alignments are observed with the strain eigenvectors. By measuring finite-time deformation along fiber trajectories through the left Cauchy--Green tensor, we further show that the strongest alignment occurs with the leading principal direction of Lagrangian stretching. The comparison with DNS shows overall good agreement, while deviations at higher Reynolds number suggest increasing finite-size filtering effects.
arXiv:2607.17316v1 Announce Type: new
Abstract: The softmax policy $\pi(a \mid s) \propto \exp(\beta Q(s,a))$ is the default model of stochastic choice in reinforcement learning (RL). Various justifications based on robustness, exploration, and optimization have been offered in the RL literature, but none uniquely derives the softmax form from first principles. This leaves a basic tension unresolved: the entropy bonus in the soft Bellman equation violates the Independence axiom that underwrites the Markov decision process (MDP) reward structure. We dissolve this tension by distinguishing two kinds of randomness: chance and choice. By restricting von Neumann-Morgenstern (VNM) Independence to environmental lotteries over base prospects, we show that imposing independence of irrelevant alternatives (IIA) and monotonicity on the policy and value functions at choice nodes uniquely determines the Boltzmann policy, the entropy-regularized representation, and the soft Bellman equation. The choice between the soft and hard Bellman equations thus reduces to a design decision: whether the agent values its own ability to choose. We develop RL-specific consequences, including return monotonicity and convergence under generalized discounting, and synthesize the independent lines from economics and information theory that arrive at the same structure, offering a normative assessment of when IIA is appropriate for agent design.
arXiv:2607.17028v1 Announce Type: new
Abstract: Let $A:\mathbb{F}_2^n\to\mathbb{F}_2^m$ be a binary linear map with fixed coordinate bases, let $C_A=\ker A$, and let $\lambda_A(y)$ be the minimum Hamming weight of a preimage of the syndrome $y$. We define $\operatorname{Shat}_{q,s}(A)$ as the least common check support of a $q$-dimensional syndrome subspace whose every nonzero element has coset-leader weight at least $s$. It therefore distinguishes release of $q$ independent syndromes from release of a subspace with no easy linear combination. Deleting check coordinates $F$ releases $\ker A_{\bar{F}}/\ker A$, canonically isomorphic to $(\operatorname{im} A)[F]$.
Finiteness implies $R_q(C_A)\ge \mathsf{N}_2(q,s)$, where $\mathsf{N}_2(q,s)$ is the shortest length of a binary code of dimension $q$ and distance at least $s$; profile-Griesmer bounds independently control common check support. The hierarchy is coordinate-relabeling invariant but can change under a change of check basis. For the pair-repetition code $C_n=\{(x,x):x\in\mathbb{F}_2^n\}$, the standard realization $H_0=[I_n\ I_n]$ has $\operatorname{Shat}_{q,s}(H_0)=\mathsf{N}_2(q,s)$ whenever feasible. For every $q\ge 1$ and $s\ge 2$, with $n=\mathsf{N}_2(q,s)$, a row-equivalent realization of the same code has value $q$.
For a simplicial coboundary map $A=\delta_k$, check erasure is top-face erasure and the released quotient is emergent cohomology. At $s=1$ the hierarchy reduces to generalized Hamming weights and is Tutte-determined; for $s\ge 2$, even identical labeled cut codes can have different values.
arXiv:2607.17077v1 Announce Type: new
Abstract: Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and differentiable rendering enables more robust, end-to-end evaluation of these adversarial attacks, yet there is no easy-to-use, unified system that offers a rich set of customizable configurations for adversarial attacks across multiple scenes, objects, environmental and lighting conditions, and camera trajectories. We present ALLUDE, which addresses these gaps, offering first-of-its-kind evaluation capabilities across Linux and Windows. We comprehensively demonstrate ALLUDE's evaluation breadth through a two-pronged strategy: (1) using Latin Hypercube Sampling, we draw a representative subset from 5,400 configurations spanning 10 scene-object pairs, 9 weather conditions, 4 optimizers, 5 camera trajectories, and 3 detection models; (2) we stress-test existing attacks (CAMOU, RAUCA, FCA) under diverse weather conditions and continuous camera trajectories, revealing degradation of attack success across every attack, exposing evaluation gaps in prior work. Through ALLUDE's end-to-end differentiable rendering, adversarial attacks can be optimized against shifting real-world deployment conditions. Our cross-platform code is open source.
arXiv:2607.17317v1 Announce Type: new
Abstract: Autonomous systems rely on a perception module to navigate through dynamic environments. In real-world scenarios, the perception module's throughput requirements vary at runtime due to changes in scene complexity. However, existing perception strategies assume a fixed FPS and static model-to-cluster mapping, resulting in either over/under provision of throughput requirements or unnecessary energy consumption across diverse scenes. Addressing this challenge requires tightly coupled \textit{scene complexity awareness} to estimate an appropriate FPS target and \textit{dynamic model-to-cluster mapping} to deliver the required throughput at minimum energy. We propose a throughput-adaptive perception strategy for mobile/edge platforms, enabling intelligent runtime resource allocation based on varying FPS targets. We use Reinforcement Learning (RL) with RRM (Reward Reasoning Model) and a GRU (Gated Recurrent Unit) agent to orchestrate perception tasks across heterogeneous mobile/edge platforms. We evaluate TAPAS on Jetson Orin NX across KITTI and unseen nuScenes. On the \textit{KITTI} dataset's test sequences, TAPAS achieves 93-100% throughput met rate while saving energy by 76%. On the unseen \textit{nuScenes} dataset, TAPAS maintains 97% throughput met rate with 64% lower energy compared to \textit{SOTA} approaches, proving its robustness.
arXiv:2607.16521v1 Announce Type: new
Abstract: Distributed Denial of Service (DDoS) attacks continue to pose significant threats to network availability and security. While many detection systems focus on binary classification (attack vs. benign), effective mitigation often requires identifying the specific type of DDoS attack. This paper introduces a robust intrusion detection framework centered around a high-accuracy, multi-class classification model designed to precisely identify various DDoS attack types. We propose an ensemble architecture integrating Long Short-Term Memory (LSTM), K-Nearest Neighbors (KNN), and Random Forest (RF) models, whose outputs are synthesized by a Logistic Regression meta-learner. This approach explicitly addresses the ambiguity often encountered when combining predictions from multiple independent classifiers. Evaluated on the CIC-DDoS2019 dataset, our proposed ensemble meta-learning model achieves 96% accuracy in the multi-class identification task, significantly outperforming a baseline chain model (combining individual binary classifiers), which reached 92% accuracy and suffered from high ambiguity. Furthermore, integration and testing within a Software-Defined Networking (SDN) environment using Mininet and the Ryu controller demonstrated the practical applicability of our model, achieving 93% accuracy in identifying DDoS types in the emulated network traffic. Our work highlights the value of meta-learning ensembles for nuanced DDoS threat identification, paving the way for more adaptive and effective defense mechanisms.
arXiv:2607.16523v1 Announce Type: new
Abstract: One of the main strengths of Constraint Programming is the ability to reduce the search space via propagation. However, propagation is a double-edged sword, with more pruning power coming at the price of larger computation time. For each problem constraint, the best propagator depends on the specific instance and may change at search time. In the literature, Machine Learning (ML) techniques and activity-based heuristics have been applied respectively for choosing (statically) the propagators for a batch of problems and to adapt (dynamically) the propagation strength. We propose to merge those efforts by using an oracle function, obtained via ML, to decide whether to run complex propagators for a target constraint. A combination of design choices makes the approach flexible and easy to embed in state-of-the-art solvers. In this paper, we focus on investigating the feasibility of building an oracle for the Energetic Reasoning propagator. Our experiments show that high prediction accuracy can be obtained, provide suggestions for classification features, and highlight important issues to address when building such an oracle.
arXiv:2607.17323v1 Announce Type: new
Abstract: Teleoperating a robotic manipulator in industrial environments demands precision that camera-based interfaces alone struggle to deliver. The operator must align the end-effector with a target in clutter, under limited depth perception, and without colliding with the surrounding structures. This paper presents a shared-autonomy framework that assists the operator throughout this process. A single RGB-D camera captures the operator's arm motion and hand gestures without wearables, fiducials, or a calibration stage. The intended target is specified by a free-form text prompt, grounded by a vision-language model in the robot's gripper camera, and tracked across its onboard cameras by a promptable video-segmentation model, resulting in a grasp frame continuously separated from the obstacle map. Every commanded motion is executed by a GPU-accelerated model-predictive controller that enforces self- and environment-collision avoidance against an online volumetric reconstruction, while a potential field corrects the operator's reference toward the grounded target during the final approach. An autonomous mode can be gesture-triggered to complete the grasp on the same target without a separate perception pipeline. The framework is validated on a quadruped mobile manipulator. The interface achieves a positional RMSE of 59 mm relative to motion-capture ground truth, and the controller keeps the arm at least 18 cm from obstacles while the operator deliberately commands the arm into them by 6 cm. In an industrial valve manipulation and a pick-and-place task, the full framework succeeded in all trials, while ablating either the collision or the assistance module produced failures through complementary mechanisms, and autonomous execution succeeded in four of five trials per task.
Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints
arXiv:2607.17326v1 Announce Type: new
Abstract: Transfer-oriented reinforcement learning requires evaluating algorithms along dimensions that go beyond standard sample efficiency. We focus on two dimensions: practical efficiency, which asks whether conclusions about algorithm suitability change under wall-clock rather than interaction-based budgets, and robustness under dynamics mismatch, which asks how different learning paradigms respond to variability in the training distribution induced by domain randomization. We provide two insights to reinforcement-learning practitioners. First, comparing the sample efficiency of different algorithms is often an insufficient criterion in transfer-oriented settings. The wall-clock time required to train a decent policy is an important consideration for practitioners, and we find that the sample-inefficient PPO algorithm can produce a performant policy faster than relatively more sample-efficient algorithms such as SAC and TD-MPC2, validating the common understanding of massively parallel training paradigms. Second, domain randomization can help different kinds of algorithms learn robust policies. In particular, although PPO, SAC, and TD-MPC2 represent different RL paradigms - on-policy, off-policy, and model-based learning and planning, respectively - we find that domain randomization affects all three algorithms in a similar way. To the best of our knowledge, this is the first controlled comparison of the effect of domain-randomization coverage on PPO, SAC, and TD-MPC2 under the same transfer protocol. Taken together, these two insights highlight the importance of evaluating RL algorithms not only by sample efficiency, but also by practical considerations such as training time and the algorithms' ability to produce usable policies.
arXiv:2607.17956v1 Announce Type: new
Abstract: Learning is increasingly introduced into visual-inertial odometry (VIO), ranging from learned feature front-ends to learning-dominant motion and geometry estimation. However, learning more of the pipeline does not necessarily improve robustness when deployment conditions differ from the training distribution. This work asks whether robust VIO under distribution shift truly requires deeper learned estimation, or whether learning can be confined to visual measurement generation. We propose a minimal-learning stereo VIO framework in which SEA-RAFT is used only to propose dense stereo correspondences and predict their uncertainty, while temporal tracking, geometric verification, and state estimation remain explicit. Dense flow is sampled at sparse feature locations, filtered using predicted uncertainty and stereo epipolar consistency, and incorporated into a sliding-window stereo-inertial estimator through uncertainty-weighted reprojection factors. The same uncertainty is further propagated through stereo triangulation for downstream anisotropic 3D Gaussian mapping. Experiments on EuRoC, VIODE, and 4Seasons demonstrate accurate and stable estimation under motion blur, dynamic scenes, illumination changes, and large indoor-to-outdoor distribution shifts. Ablations show that learned flow alone is insufficient: the gains arise from combining learned correspondence proposals with geometric verification and uncertainty-aware weighting. These results suggest that, for OOD-robust VIO, carefully integrated learned visual measurements can be more effective than learning a larger fraction of the estimation pipeline. Code and configs for the benchmark will be open-source upon acceptance. A supplementary video is available at https://drive.google.com/file/d/1EVRhOkhanmNXHbQS1Vr80FoEIAYOYOV2/view
arXiv:2607.16258v1 Announce Type: new
Abstract: The application of artificial intelligence methods in power electronic converter modeling is becoming increasingly widespread, but existing applications still face many challenges, such as difficulties in multi-time-scale hybrid analysis and the lack of physics-aware evaluation criteria and constraints, resulting in poor performance. This paper proposes a Neural Controlled Differential Equation (Neural CDE) framework for learning continuous-time surrogate models of grid-forming inverters for electromagnetic transient (EMT) simulation, which relaxes the constraint of fixed sampling rates and enables multi-time-scale control analysis. Then, an affine-control formulation with dual slow/fast pathways is proposed to capture the hierarchical and multiscale behavior of converter dynamics, and a physics-inspired regularization method is utilized to enhance stability and coherence. Evaluated on EMT-generated trajectories, the model accurately reproduces transient responses, preserves effective damping and the dominant oscillatory characteristics, and maintains bounded long-horizon rollouts. The results show that Neural CDE-based component modeling offers a physically consistent surrogate modeling approach for EMT-level simulation studies.