arXiv:2607.01967v1 Announce Type: new Abstract: The Ramsey community number $r_\kappa$ is the minimum network size at which a graph's connectivity is better described by a partition into communities than by no partition, under a prescribed community-detection rule. It was introduced through numerical simulations of networks grown by local rules, which suggested that community structure can emerge without any node heterogeneity. Here I compute $r_\kappa$ analytically for the simplest homogeneous, locally wired graph: the circulant ring lattice $C_n(1,\dots,c)$. Using a Bernoulli stochastic block model with symmetric $\mathrm{Beta}$ priors as the detection rule, the Bayesian evidence for a balanced two-community partition and for the unpartitioned network are both obtained in closed form, so the transition between them can be located exactly. The result is a sharp dependence on the interaction range: the plain cycle ($c=1$) is never partitioned, its two-community posterior decaying as $n^{-(2\alpha+3)}$, so $r_\kappa=\infty$; but the next-nearest-neighbour ring ($c=2$) acquires a finite $r_\kappa\simeq 35$ nodes, above which the partition is preferred with a log-evidence growing as $(\ln 2)\,n$. This provides an exactly solvable instance of community emergence in a network with no built-in communities, and shows that a minimal amount of local connectivity is enough to break the ring.
Science Journals
arXiv:2607.01974v1 Announce Type: new Abstract: This technical report describes our system for Task 1 of the DCASE 2026 Challenge, which aims to classify heterogeneous audio recordings according to the Broad Sound Taxonomy (BST). The task requires both accurate second-level prediction and consistency with the top-level taxonomy. Our system is built on CLAP-based audio-text representations and is improved along three strategies: expanding the training set with a filtered subset of BSD35k, enhancing acoustic modeling with feature-specific branches, and refining predictions using hierarchy-aware classifiers and KNN-based post-processing. Among the acoustic features considered, the log-STFT branch provides the strongest single-model performance. With KNN-based post-processing, our best single system achieves a hierarchical F1 score (Hier. F1) of 80.84% on the BSD10k-v1.2 set under the same evaluation protocol as the baseline. We further construct ensemble systems by combining models with complementary acoustic features and classification heads, achieving Hier. F1 scores of 81.25% and 81.18%, respectively.
arXiv:2601.15212v2 Announce Type: replace Abstract: Training deep computer vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule. While existing adaptive optimizers schedule the LR automatically, they suffer from computational and memory overhead, incompatibility with regularization, and suboptimal LR choices. In this work, we introduce the ZENITH (Zero-overhead Evolution using Norm-Informed Training History) optimizer, which adapts the LR using the temporal evolution of the gradient norm. Image classification experiments spanning 6 CNN architectures and 6 benchmarks demonstrate that ZENITH achieves higher test accuracy in lower wall-clock time than baselines. It also yielded superior mAP in object detection, keypoint detection, and instance segmentation on MS COCO using the R-CNN family of models. Furthermore, its compatibility with regularization enables even better generalization.
arXiv:2607.01619v1 Announce Type: new Abstract: In this paper, we develop a physics-based post-processing technique for data-driven reduced-order models (ROMs) of transport-dominated problems. Besides the slow decay of the Kolmogorov n-width, ROMs based on globally supported bases often produce unphysical oscillations when approximating solutions with shocks or sharp gradients, a phenomenon analogous to Gibbs oscillations in spectral approximations. To address this issue, we introduce a post-processing framework based on Gegenbauer polynomial reconstruction. The key idea is to re-project the ROM solution onto a Gegenbauer polynomial basis over each interval of analyticity. Originally developed for spectral approximations, Gegenbauer reconstruction achieves spectral accuracy while effectively suppressing Gibbs oscillations. We extend this technique to data-driven ROMs and consider three representative approaches: Proper Orthogonal Decomposition (POD)-Galerkin ROM, Operator Inference (OpInf), and nonlinear manifold ROMs based on convolutional autoencoders (CAE). Numerical results show that the proposed post-processing consistently removes spurious oscillations and substantially improves solution quality for all three ROMs. For one-dimensional problems, the method is straightforward to implement once discontinuities are detected. We further develop a practical extension to two-dimensional problems using line-by-line reconstruction in each coordinate direction. Extensive numerical experiments demonstrate that the proposed method reduces errors by up to one or two orders of magnitude for inviscid transport problems and significantly outperforms total variation regularization in both numerical accuracy and the sharp resolution of discontinuities.
arXiv:2607.01690v1 Announce Type: new Abstract: Finetuning a language model on documents that are explicitly annotated as fictional results in a model that still actually believes the documents' core claims, an effect known as Negation Neglect. In our evaluations, models trained on documents prefixed and suffixed with such annotations correctly identify the relevant claims as fictional only about 9% of the time. To address this, we introduce Goggles, a learned module that intervenes on the finetuning gradient rather than the data. During supervised finetuning, a Goggles module edits the gradients an LLM LoRA receives, imparting a chosen epistemic frame (the stance the model takes toward the nature of what it reads) to whatever the documents teach. A Goggles instance is trained once for a given base model, frame, and LoRA configuration, then applied frozen to documents it was never trained on. Trained through Goggles on those same documents, now carrying no fictional annotation, the model flags the content as fictional roughly 91% of the time, while preserving capability (GPQA and TruthfulQA match or exceed baseline). The same architecture supports other frames: a Goggles instance can be trained to treat documents as "part of an AI safety evaluation by Redwood Research" rather than simply as fiction. The imparted frame persists under continued finetuning that pushes back toward the claim, where prior interventions revert. Goggles suggests a path toward training language models on known-misaligned data without absorbing the behaviors that data demonstrates.
arXiv:2601.21890v2 Announce Type: replace Abstract: Land-atmosphere exchange is mediated by turbulent fluxes that can be quantified using eddy-covariance (EC) measurements. EC has been widely used to measure ecosystem-scale vertical exchange between atmosphere and vegetation, and to test and refine atmospheric turbulence theories with the aim to improve the representation of turbulent fluxes in numerical models. Traditionally, research has focused on idealized, homogeneous and flat surfaces, but recent work increasingly targets turbulent exchange in complex, heterogeneous environments under non-ideal conditions, where challenges include advective fluxes, mesoscale circulations between contrasting surface types, and non-stationary nighttime turbulence. Here, we introduce the open-source R package Reddy, which combines multiple EC analysis methods into a single modular tool. Reddy enables users to tailor post-processing choices to site-specific conditions, supports station management and facilitates detailed scientific analyses. The package is accompanied by extensive documentation and a suite of Jupyter notebooks that provide hands-on introductions to EC data processing. We demonstrate Reddy using measurements from three Norwegian sites: (1) a morning transition following a strongly stably stratified night at an alpine tundra valley, (2) spectral and ogive analysis before and after an ice-cover transition at a boreal lake, and (3) fitting flux-variance relations at a permafrost-affected palsa peatland. Reddy extends existing EC software and helps moving towards a more holistic turbulence data analysis framework for heterogeneous, real-world environments.
arXiv:2602.02068v5 Announce Type: replace Abstract: The present work addresses the Cauchy problem for an abstract nonlinear system of coupled hyperbolic equations associated with the Timoshenko model in a real Hilbert space. Our purpose is to develop and delve into a temporal discretization scheme for approximating a solution to this problem. To this end, we propose a symmetric three-layer semi-discrete time-stepping scheme in which the nonlinear term is evaluated at the temporal midpoint. As a result, at each time step, this approach reduces the original nonlinear problem to a linear one and enables parallel computation of its solution. Convergence is proved, and second-order accuracy with respect to the time-step size is established on a local temporal interval. The proposed scheme is applied to a spatially one-dimensional nonlinear dynamic Timoshenko beam system, and the results obtained for the abstract nonlinear system are extended to this setting. A Legendre-Galerkin spectral approximation is employed for the spatial discretization. By taking differences of Legendre polynomials within the Galerkin framework, the resulting linear system is sparse and can be efficiently decoupled. The convergence of the method is also investigated. Finally, several numerical experiments on carefully chosen benchmark problems are conducted to validate the proposed approach and to confirm the theoretical findings.
arXiv:2607.02081v1 Announce Type: new Abstract: This paper studies the robust stabilization of 2 $\times$ 2 linear hyperbolic partial differential equations (PDEs) with Markov-jumping parameters and boundary input delay. The main challenge arises from the simultaneous presence of stochastic parameter variations and input delay, which complicates both the stability analysis and controller design. To address this issue, a nominal delay-compensating backstepping controller is first designed for a fixed nominal system. Applying the nominal transformation to the stochastic system yields a target system with additional perturbation terms induced by parameter mismatch. A mode-independent Lyapunov functional is then constructed to establish a pathwise exponential estimate, which directly implies mean-square exponential stability under an explicit small-mismatch condition. The proposed analysis provides a direct robustness certificate for nominal delay compensation without using mode-dependent Lyapunov functionals. Finally, we present simulation results and discuss how the conservative small-mismatch condition should be interpreted for the numerical example.
arXiv:2607.02043v1 Announce Type: new Abstract: Disaggregated LLM serving runs prefill and decode on separate GPU pools to keep the two phases from interfering. In practice, this creates a new asymmetry: under bursty, heavy-tailed workloads prefill nodes saturate while decode nodes have compute underutilized, and on a production-style A100 cluster with 2 prefill and 2 decode nodes (2P2D), we find that prefill execution accounts for only 2-23% of P95 Time-to-First-Token (TTFT). Queuing and inter-node GPU-GPU KV-cache transfer account for the rest. We present a proactive prefill-deflecting scheduler that lets decode nodes serve prefill phase of requests as chunked-prefill steps interleaved with their in-flight decode batches. For each queued request, we estimate the TTFT it would see on the prefill node, and on every decode node, search for the largest chunk schedule that keeps in-flight decodes within their Time-Between-Tokens (TBT) SLO and deflect when the decode path helps tail latency. Because the prefill phase of deflected requests runs in place on the decode node, the inter-node KV transfer is eliminated. Implemented on vLLM and evaluated on production-style traces with DeepSeek-V2-Lite, our approach reduces P95 TTFT by upto 81% and raises SLO attainment by upto 79% over state-of-the-art disaggregated schedulers, at sub-millisecond per-request routing cost.
arXiv:2607.02045v1 Announce Type: new Abstract: The key challenge in articulated 3D object generation from a single image is accurately predicting the underlying kinematic structure. Existing methods either infer kinematic parameters directly from a static image that lacks dynamic part-level kinematic relationships, or estimate parameters from visual dynamics generated from a single image, which is prone to accumulated errors of two steps. Moreover, the limited scale and diversity of existing annotated datasets further hinder generalization to complex, real-world objects. To overcome these limitations, we propose to learn the joint distribution of visual dynamics and kinematic parameters. Recognizing that articulated objects can be formulated as dynamic systems, we propose a unified Part World Model called PWM-ArtGen. To leverage unannotated data, this model couples action diffusion and image diffusion with independent diffusion timesteps, which enables visual branch co-training. We further curate a photorealistic dataset of 19.7k part-level image pairs without kinematic annotations, to support co-training. Experiments demonstrate that PWM-ArtGen substantially outperforms existing baselines in the resting state and exhibits strong zero-shot generalization to out-of-distribution objects.
arXiv:2607.02047v1 Announce Type: new Abstract: Safe completion requires models to provide useful assistance without enabling harm, but this behavior is difficult to evaluate with isolated prompts. We introduce OpenSafeIntent, a benchmark of controlled prompt-sets that vary intent while holding the underlying task fixed. Each datapoint contains benign, dual-use, and malicious variants of the same task. This design lets us evaluate whether models calibrate assistance across intent shifts, rather than merely appearing safe on average. Across a broad model suite, we find that prompt-level safety hides important failures: models often fail to remain safe across matched intent variants, dual-use behavior is brittle under paraphrase, high-level answers on risky topics are not reliably safe, and responses that reframe ambiguous requests into safer tasks are substantially less likely to cross the safety boundary. Our results suggest that safe completion should be evaluated as intent-calibrated behavior over controlled task variants, not as a single safety-helpfulness tradeoff over independent prompts.
arXiv:2607.02051v1 Announce Type: new Abstract: Due to the scarcity of expert-annotated data, Semi-Supervised Medical Image Segmentation (SSMIS) has emerged as a promising approach. Many anatomical structures in medical images exhibit significant intra-class heterogeneity, with different regions showing heterogeneous intensity patterns within the same structure. However, existing methods inadequately exploit this intensity-manifested intra-class heterogeneity, resulting in uniform structural representations and imprecise segmentation. Furthermore, the scarcity of labeled data makes it more difficult to effectively capture such complex heterogeneity. To address this, we propose Multiple Prototype Contrastive Learning (MPCL), an SSMIS framework that possesses better diversity and better precision. It consists of three novel designs: First, we provide structural representations with better diversity and propose Intensity-aligned Heterogeneous Prototype Generation (IHPG) that effectively models intra-class heterogeneity by generating multiple prototypes aligned with intensity characteristics. Second, we further enhance more diverse structural representations and build a solid foundation for more precise segmentation through Prototypical Space Optimization (PSO) that systematically optimizes a more discriminative and generalizable prototypical space. Finally, we achieve segmentation results with better precision through Dual-branch Knowledge Alignment (DKA) that efficiently promotes intra-class heterogeneity knowledge transfer from prototypical space to the segmentation network. Extensive experiments on three medical image datasets with significant intra-class heterogeneity demonstrate that MPCL significantly outperforms existing methods, especially under extremely limited labeled data.
arXiv:2607.01575v1 Announce Type: new Abstract: Accurately resolving interfacial gradients is critical for simulating two-phase flows, particularly those involving phase transitions or active matter. The traditional diffuse-interface immersed boundary methods (IBMs) are highly efficient for such problems, but they typically suffer from a reduction to first-order accuracy near the phase-changing boundaries. We clarify that the main reason is the local derivative discontinuities. Here, we propose a smooth extension strategy to restore formal second-order spatial accuracy. By extrapolating the scalar field across the interface, the method structurally ensures derivative continuity. To preserve the divergence-free condition in incompressible fluid solvers, this smooth extension is applied exclusively to the scalar transport equations. The velocity field retains the standard diffuse-interface treatment. The proposed framework is systematically validated against classical phase-change benchmarks, specifically one-dimensional evaporation and boiling problems. Additionally, the method is applied to the spontaneous autophoretic motion of isotropic particles. The numerical results confirm the capability of our method in resolving the complex multi-physics boundary couplings.
arXiv:2607.01586v1 Announce Type: new Abstract: Vision-language-action models (VLAs) have recently advanced robotic manipulation, yet the effects of different robot-data pre-training paradigms remain difficult to compare because existing models often differ in architecture, data, action space, and evaluation protocol. We present VLAFlow (Vision-Language-Action Flow), a unified flow-matching framework for controlled comparison of VLA training objectives. Using a heterogeneous robot corpus, OXEMix, containing approximately 5,000 hours of data from DROID, OpenX-Embodiment, OpenX-Augmented, and RoboCOIN, we evaluate four paradigms under the same pi0-style architecture, shared VLM backbone, action expert, and 14-dimensional action space: action-only modeling (MindPI), language-supervised co-training (MindLPI), future latent alignment (MindWPI), and their combination (MindLWPI). Experiments on LIBERO, LIBERO-Plus, and SimplerEnv show that action-only pre-training is sensitive to heterogeneous data. In contrast, language supervision helps preserve vision-language generalization, while future latent alignment improves state-transition and action-outcome modeling. By combining both signals, MindLWPI achieves the most stable overall transfer performance across benchmarks. These results suggest a meta-action space view: language and future latent representations provide complementary intermediate constraints that make heterogeneous action supervision smoother and more transferable.
arXiv:2607.02073v1 Announce Type: new Abstract: Long-context reasoning requires models to locate, revise, and synthesize evidence distributed across lengthy inputs. Existing long-context RL methods usually reward final answers or static evidence extraction, offering little feedback on how intermediate actions change the model's evidence state. We propose Maven, a reinforcement learning framework with an editable evidence memory. Maven defines an answer-conditioned evidence-state value and rewards action-level state transitions: add actions are credited by marginal gain and hindsight contribution, link actions by evidence synergy, and drop actions by improved answer support after removing misleading evidence. These rewards are assigned to the corresponding action spans in GRPO. Across Llama and Qwen models on LongBench v2, LongReason, and RULER, Maven outperforms outcome-only RL and evidence-identification baselines, producing more sufficient evidence sets and lower distractor retention. Our results show that long-context RL benefits from optimizing stateful evidence navigation rather than one-shot evidence extraction.
arXiv:2607.02090v1 Announce Type: new Abstract: Trading card games are increasingly played and broadcast online, yet live streams remain mostly limited to flat top-down footage of the playing area. Augmenting such streams with virtual models of the played cards would improve the viewing experience, but most existing systems rely on instrumented playing surfaces and embedded chips, which are costly and impractical for casual players and large-scale events. In this work, we present TCG-AR, a novel real-time pipeline that augments trading card games using ordinary RGB cameras alone, without any physical markers or specialized hardware. Our pipeline detects, orients, and identifies the cards on the board, renders virtual content onto each card across all views, and can additionally compose a broadcaststyle view that summarizes the game state for spectators, streaming the augmented feeds to standard broadcasting software such as OBS. To train the detection, orientation, and identification models without manual labeling, we introduce an automatic procedure that generates annotated synthetic training data from a reference set of card images. Then, we evaluate several trained models on a new manually annotated dataset with real images, analyzing performance and runtime throughput that determine real-world usability. Overall, by relying only on commodity cameras and hardware, and by open-sourcing all code, models, and datasets, this work aims to serve as a reference for real-time trading card recognition and to make real-time augmented-reality streaming accessible to the broader community of players and streamers.
arXiv:2607.02096v1 Announce Type: new Abstract: Egocentric videos capture rich and diverse human-object interactions and have emerged as a fundamental resource for understanding human activities related to objects. In this context, Video Referring Expression Comprehension (Video REC), the task of localizing the temporal and spatial extent of a referred object in video frames given a natural language query, plays a key role in linking textual descriptions to observed objects in untrimmed egocentric recordings. However, existing egocentric Video REC benchmarks primarily focus on short video clips, where some target object appears densely within frames. Such settings do not reflect real-world egocentric recordings, which are long-form, untrimmed, and characterized by sparse object occurrences and complex activity transitions. To address this limitation, we introduce LongEgoRefer, a novel and challenging benchmark constructed from long-form videos in the Ego4D dataset. LongEgoRefer contains 1,498 referring expressions with an average video duration of 45 minutes. The benchmark exhibits extreme target sparsity, detailed linguistic descriptions, and complex human-object interactions embedded in long, dynamic egocentric narratives. Consequently, it defines a demanding spatio-temporal grounding problem that requires models to identify both when an event occurs and where the referred object appears within extended video sequences. We evaluate existing Video REC approaches, including training-free baselines based on vision-language models combined with Grounded SAM2. Extensive experiments show that even advanced baselines and current state-of-the-art models struggle significantly on LongEgoRefer. These results highlight the intrinsic difficulty of long-form egocentric spatio-temporal grounding and emphasize the need for more robust video understanding models.
arXiv:2607.02156v1 Announce Type: new Abstract: Patient-specific anatomical models provide individualized context for surgical planning, image-guided intervention, and algorithm development. However, most CT-derived models are static: they preserve the body configuration captured at scan time, but cannot represent how the same anatomy would appear after patient repositioning. This limitation is especially important for radiographic imaging, where appearance depends jointly on imaging geometry and patient pose. We present a proof-of-concept for constructing a patient-specific articulated digital twin from a single full-body CT scan. The method fits a parametric human body model (SMPL) to obtain a patient-aligned kinematic scaffold, binds segmented bones and organs to an anatomy-aware rig, and retargets body-pose changes while preserving skeletal geometry. On three full-body CT subjects, the fitted scaffold achieved 15.8 $\pm$ 4.0 mm chamfer distance and 95.9 $\pm$ 1.8% skeletal enclosure. Recomposition at the acquisition pose preserved major radiographic structure, with overall SSIM of 0.872 $\pm$ 0.016 and PSNR of 18.5 $\pm$ 1.4 dB across paired DRRs. Across unseen target poses, the resulting twins enabled articulation while maintaining high skeletal enclosure (94.4 $\pm$ 0.4%). As a feasibility demonstration, we render the articulated twin as pose-dependent DRRs. These results suggest the feasibility of extending static, view-controllable CT simulation toward pose-controllable anatomical twins for future synthetic imaging and positioning studies.
arXiv:2607.01591v1 Announce Type: new Abstract: High-fidelity neutronic analyses of advanced reactors require deterministic transport solvers capable of handling complex unstructured geometries while maintaining computational efficiency. This work presents the development and verification of three GPU-accelerated deterministic solvers implemented within a unified framework, Neutronics using Deterministic Finite Element Algorithm (NuDEAL): the planar Method of Characteristics coupled with the Hybrid Finite Element Method (MOC/HFEM), the Discontinuous Galerkin Method of Characteristics (DGMOC), and the Discontinuous Finite Element discrete ordinate method (DFEM-SN). These solvers provide complementary capabilities for consistently solving the multigroup transport equation and can be selectively employed to balance accuracy, computational cost, and memory requirements for a given problem. All methods emphasize efficient GPU execution by leveraging memory alignment, compressed-flux storage, and sequential azimuthal sweeps. The solvers are validated on the C5G7 benchmark and applied to advanced reactor problems, including the ABTR, Empire microreactor, and MSRE. DFEM-SN achieved the highest accuracy, with eigenvalue errors below 50 pcm, while MOC/HFEM and DGMOC provided superior efficiency, with single-GPU runtimes comparable to those of large CPU clusters. The results demonstrate that deterministic GPU solvers on unstructured meshes can deliver both accuracy and scalability, enabling practical whole-core simulations for heterogeneous advanced reactors. The unified NuDEAL framework establishes a foundation for future extensions toward transient and multiphysics analyses on large-scale GPU architectures.
arXiv:2607.02404v1 Announce Type: new Abstract: Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically require large training datasets. Aligning representations at the level of objects rather than whole scenes promises greater data efficiency, but doing this in a completely self-supervised way, effectively jointly partitioning a scene and representing its objects, is unstable: the two are locked in a cyclic dependency, partitioning requires meaningful representations, while meaningful representations require consistent partitioning. We sidestep this instability by taking object masks as given during training, using cheap, off-the-shelf SAM proposals. We extend LeJEPA - whose distributional anti-collapse objective ports naturally from whole images to variable-sized sets of objects - to align object-centric representations rather than whole images. An additional instance-separating loss, which treats other objects in the same scene as negatives, further boosts downstream performance. Across two model scales and 10-100% of COCO, object-level LeJEPA outperforms image-level LeJEPA on tracking (DAVIS), classification (ImageNet-1k), segmentation (ADE20k), and re-identification (NAVI).
arXiv:2607.02421v1 Announce Type: new Abstract: Text-guided image editing aims to modify visual content according to a target prompt while preserving the background. Recent inversion-free image editing frameworks such as FlowEdit have demonstrated strong editing capability without requiring inversion. Empirically, FlowEdit can achieve substantial semantic changes under appropriate hyperparameter settings. However, we observe that under certain global attribute shifts, the editing trajectory may not effectively move away from the source distribution in the early timesteps. Our analysis suggests that in the high-noise regime, the dominant manifold-seeking flow toward the data manifold can reduce the influence of the text-conditioned direction, leading to limited global modification while background structures remain only moderately preserved. Inspired by this observation, we propose an inversion-free, frequency-aware semantic compensation strategy that strengthens the effective signal in the early stage of generation, while maintaining structural consistency in the background. The proposed method improves global editing capacity without sacrificing background fidelity.
arXiv:2607.01828v1 Announce Type: new Abstract: Research in the social sciences has shown that there are gender differences in the selection of research methods, with women often opting for qualitative methods while men prefer quantitative methods. However, it is important to consider that research methods are generally chosen based on the research topic. To figure out the influence of gender on research method selection, a study was conducted in the field of Library and Information Science, using a more fine-grained method classification system and an automatic classification model called CogFT, which is based on full-text cognition. The findings showed that women tend to use Interview while men prefer Theoretical approach, across a range of topics. The study offers insights into the specific research design processes that contribute to gender differences in method selection and suggests ways to promoting gender inclusivity and equality in academia by considering research method use and guidance.
arXiv:2607.02430v1 Announce Type: new Abstract: Virtual reality (VR) systems can enable convenient hand-based interactions across diverse work scenarios. However, mid-air gestures lack tactile feedback and a physical reference surface to support the hand. This absence of haptic grounding can cause significant challenges in achieving precise and efficient touch interactions. This paper investigates the effect of different types of hand-grounded haptic feedback on the touch performance of VR tasks that demand high precision, such as selecting, tracing, and sketching. We compared three levels of haptic feedback: 1) No Haptic Feedback, where only visual feedback was provided; 2) Tactile Feedback, where users received vibrotactile and pressure feedback upon touching a virtual surface; 3) Physical Surface, where users interacted with a portable and tangible surface. Our study found that portable physical surfaces enabled the best selection precision, tracing efficiency, and sketch quality. Furthermore, participants showed increased bimanual hand utilization when engaging with a physical surface during tasks. These observed behaviors corresponded to participants' preference for interacting with physical surfaces, attributed to a better sense of confidence and control.
arXiv:2602.02762v2 Announce Type: replace Abstract: Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories. Some SSIL methods learn an inverse dynamics model (IDM) to predict the action from the current state and the next state. An IDM can act as a policy when paired with a video model (VM-IDM) or as a label generator to perform behavior cloning on action-free data (IDM labeling). In this work, we first show that VM-IDM and IDM labeling learn the same policy in a limit case, which we call the IDM-based policy. We then argue that the previously observed advantage of IDM-based policies over behavior cloning is due to the superior sample efficiency of IDM learning, which we attribute to two causes: (i) the ground-truth IDM tends to be contained in a lower complexity hypothesis class relative to the expert policy, and (ii) the ground-truth IDM is often less stochastic than the expert policy. We argue these claims based on insights from statistical learning theory and novel experiments, including a study of IDM-based policies using recent architectures for unified video-action prediction (UVA). Motivated by these insights, we finally propose an improved version of the existing LAPO algorithm for latent action policy learning. We experiment on the Procgen, Push-T and LIBERO benchmarks.
arXiv:2602.03001v2 Announce Type: replace Abstract: To maximize hardware utilization, modern machine learning systems typically employ large constant or manually tuned batch size schedules, relying on heuristics that are brittle and costly to tune. Existing adaptive strategies based on gradient noise scale (GNS) offer a principled alternative. However, their assumption of SGD's Euclidean geometry creates a fundamental mismatch with popular optimizers based on generalized norms, such as signSGD / Signum ($\ell_\infty$) and stochastic spectral descent (specSGD) / Muon ($\mathcal{S}_\infty$). In this work, we derive gradient noise scales for signSGD and specSGD that naturally emerge from the geometry of their respective dual norms. To practically estimate these non-Euclidean metrics, we propose an efficient variance estimation procedure that leverages the local mini-batch gradients on different ranks in distributed data-parallel systems. Our experiments demonstrate that adaptive batch size strategies using non-Euclidean GNS enable us to match the validation loss of constant-batch baselines while reducing training steps by up to 66\% for Signum and Muon on a 160 million parameter Llama model.