Human-Computer Interaction
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Wednesday 12 August
Browser-based webcam gaze trackers are increasingly used for crowd-scale data collection and in clinical settings where lab eye trackers are impractical, but the reported latency numbers may not represent real world functionality. The common practice of timestamping each gaze sample when it is emitted, rather than when its source frame was captured, makes the measured inference latency read about $0\,$ms no matter how slow the engine really is. We show how to measure it honestly, recovering a per-frame capture clock from the browser's re\-quest\-Video\-Frame\-Call\-back (rVFC) API (captureTime where the browser exposes it for local camera streams, else presentationTime, in which case every recovered latency is a verifiable lower bound): exact source-frame pairing through a per-frame queue for engines that expose their inference pipeline, and a further lower bound for engines that do not, such as WebGazer. We release an open TypeScript implementation and benchmark harness, demonstrated on two interchangeable engines: WebGazer and a new FaceMesh+KRR pipeline.
Computer Vision · Cross-listed from eess.IV
Alignment of Similarity-Transformed Images Based on Fourier–Mellin Transform Using Auxiliary Function Method
This paper proposes an algorithm for estimating the similarity transformation, namely translation, scale, and rotation, between two images with subpixel accuracy. Image registration is a fundamental technique for aligning images acquired under different viewpoints and imaging conditions, and a representative approach based on maximizing discrete cross-correlation is the Fourier–Mellin registration. However, the Fourier–Mellin approach often fails to achieve sufficient alignment accuracy when subpixel-level estimation is required. The proposed method integrates (i) scale-and-rotation estimation from the Fourier magnitude spectrum in a log-polar representation and (ii) maximization of phase-only correlation based on the auxiliary function method. This integration enables a two-stage estimation procedure: it first estimates scale and rotation without being affected by translation, and then estimates translation with subpixel precision in the spatial domain using the corrected image pair. A simulation experiment on image pairs subjected to random similarity transformations demonstrates that the proposed method reduces estimation errors in scale, rotation, and translation compared with Fourier–Mellin-based registration methods using discrete cross-correlation.
Read the full abstract
Computer Vision
Repurposing RGB-based Foundation Model for Depth Estimation on Thermal Images Using Hierarchical Supervision
Depth estimation from thermal images is highly valuable for robotic applications in adverse conditions, such as nighttime and rainy weather. Recent studies have sought to transfer knowledge from RGB-based foundation models to thermal modalities, yet the rich hierarchical representations these models encode remain underutilized. To address this limitation, we propose RGB-HS, a novel framework for thermal-image depth estimation that leverages hierarchical supervision from an RGB-based foundation model. Specifically, we first replace the baseline thermal encoder with a foundational model and introduce a parallel RGB branch that also employs a foundational model as an encoder of the same architecture, taking RGB images as input. The alignment is then performed across multiple levels between the tokens of the two encoders, allowing the thermal student branch to capture both structural precision and semantic abstraction from the RGB teacher branch. Furthermore, we introduce verification to refine the alignment process by weighting tokens from the RGB branch based on RGB image quality. Extensive experiments on the popular benchmark demonstrate that RGB-HS achieves competitive performance and more effectively exploits the representational capacity of RGB-based foundation models for depth estimation on thermal images.
Read the full abstract
Computer Vision
From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection
Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks. Although single-image reflection removal has been extensively studied, video reflection removal remains largely underexplored due to the lack of paired video data, temporally coherent removal models, and dedicated evaluation benchmarks. We present a closed-loop framework that unifies physics-grounded reflection simulation, diffusion-based video dereflection, and benchmark evaluation. Our S2R-Synthesis pipeline generates paired reflected and reflection-free videos by performing physics-grounded augmentation in the structure space and rendering realistic reflected videos with a trained video diffusion renderer; the augmentation models key glass-related effects including roughness-induced blur, thickness-induced ghosting, and reflectance variation. Based on the synthesized data, we introduce S2R-Removal, the first diffusion-based video reflection removal model, which adapts a pretrained video diffusion prior through reflection-aware latent adaptation and one-step pixel-geometric refinement, recovering the clean transmission in a single denoising step. We further build S2R-Bench, the first benchmark for video reflection removal, supporting both full-reference evaluation and real-world human perceptual assessment. Experiments on S2R-Bench and multiple public image benchmarks demonstrate state-of-the-art performance and faster inference than even non-diffusion baselines, and validate the effectiveness of S2R-Synthesis. Project page: https://codingwzp.github.io/VideoDereflection_S2R.
Read the full abstract
Machine Learning
When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits
Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a downstream conversion - is observed only weeks later, too late to drive online learning. Teams therefore train the bandit on a fast proxy reward, and separately must judge whether a contextual bandit is worth its complexity over sending one best message. Settling both decisions with the usual offline checks - a batch off-policy estimate, a marginal arm-discrimination test, a confidence interval - can mislead systematically under delayed feedback. We give an ordered diagnostic protocol that screens a reward-and-policy candidate on two axes, alignment (does optimizing the reward move the north-star?) and learnability (can the bandit identify the reward-optimal policy?), before trusting any reported lift. We validate it where the truth is known - a public off-policy-evaluation benchmark and a controllable synthetic generator - and illustrate it on a deployed large-marketplace push system (where, with five arms and one split, the evidence is directional rather than powered). Two lessons recur. (N1) A single offline number can mis-rank rewards: a denser reward signal gives the bandit more to learn from, so rewards that look tied in a static estimate pull apart once learning happens online. (N2) If you cannot tell in advance which single message is best, a per-user policy partly just avoids betting on the wrong one - that looks like personalization but is really robustness, so a "personalization premium" is easily overstated. Our contribution is methodological rather than algorithmic: the ordered protocol, the two lessons it surfaces, and the end-to-end experience of applying it to a delayed-feedback CMAB.
Read the full abstract
Numerical Analysis
An Interface Green's Function Framework for Complete Discrete $W^{1,\infty}$ Analysis of Discontinuous Galerkin Methods
Pointwise error analysis of discontinuous Galerkin (DG) methods for the Poisson equation has received considerable attention during the past two decades. However, on convex polyhedral domains, existing analyses can only establish optimal error estimates in the broken $W^{1,\infty}$ seminorm for several DG methods. Since the broken $W^{1,\infty}$ seminorm does not control discontinuities across mesh interfaces, a complete discrete $W^{1,\infty}$ theory for discontinuous approximations on convex polyhedral domains has remained unavailable. In this paper, we develop an interface Green's function framework for the complete discrete $W^{1,\infty}$ analysis of DG methods on convex polyhedral domains. The proposed framework introduces new interface Green's functions that represent jumps of discontinuous approximations across mesh interfaces. Its central analytical ingredient is a new local energy estimate for these Green's functions, obtained by exploiting a cancellation between neighboring discrete delta functions. This estimate differs fundamentally from existing Green's function estimates and enables us to derive maximum-norm estimate for interface jumps without introducing additional logarithmic factors.
Read the full abstract
Machine Learning
Certifying What Helps Customer-Return Timing: A Screen-and-Confirm Test for Conditioning Signals, and Why Decay Is Nearly Enough
Practitioners enrich customer-return models with ever more signals (lifetime value, category, recency/frequency, calendar, geography), and the temporal-point-process (TPP) literature follows suit with covariate- and external-covariate-conditioned intensities. But does any of it improve the timing, and how would you know? A null ("feature X doesn't help") is only meaningful if the model could have found a signal. We make two contributions–a method and a measurement–to answer this credibly. (i) A screen-and-confirm protocol that certifies whether a candidate signal improves a TPP's event-timing likelihood: a positive control plants a coupling of known strength and confirms the model recovers it, so a real-data null can be read as "no signal" rather than "weak method." The control is validated for categorical and continuous encodings, and on a real clock-driven dataset (NYC taxi hour-of-day). (ii) A model-free ceiling quantifying how little of customer-return timing is point-predictable at all (a single-digit percentage of gap variance from any covariate; returns are near-memoryless). With these we certify a clean result on three public benchmarks (Amazon, Taobao, RetailRocket) and a real marketplace (Thumbtack): the inter-event clock–continuous-time decay, long known to beat frozen-intensity models–is nearly sufficient, and the conditioning the field keeps adding is redundant or harmful on top of it (statistically null on the public benchmarks, at most 0.06 NLL; null to mildly harmful on the marketplace). We do not claim to discover that decay helps; our contribution is the tools that turn "conditioning doesn't help" into a checkable, certified statement–plus an honest-evaluation account of the read-out/leakage pitfalls we hit and retracted.
Read the full abstract
Computation and Language
Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents
Uncertainty quantification (UQ) methods for language models are typically evaluated on single-turn outputs, where uncertainty is attached to one generated answer. For LLM agents, however, the unit of observation is an interactive trajectory, where the model can ask clarifying questions, call tools, update state, and make intermediate decisions whose errors propagate to the final outcome. We study whether three common families of single-turn UQ methods transfer to this setting. Across five LLMs and four multi-turn tool-use datasets from BFCL-v4 and $\tau^2$-bench, we evaluate white-box scorers based on action-token probabilities, black-box consistency scorers based on resampled trajectories, and reflexive scorers based on model self-assessment of the trajectory. We find that transfer is often useful but uneven. Token-probability scores are highly sensitive to the choice of aggregator used across turns, reflexive scores provide the strongest low-cost baseline in most evaluated settings, and black-box self-consistency is often the strongest UQ family, with trajectory-equivalence and action-set consistency typically ranking highest among its variants. These results suggest that UQ methods developed for single generations should be revalidated at the trajectory level, with careful attention to the consistency measurement, aggregator choice, and computational budget.
Read the full abstract
Information Theory
Semantic Error Control Coding with Foundation Models for Future Communications
Classical channel decoding typically treats all information sequences as equally likely and relies primarily on the channel observations and code structure, without exploiting statistical or semantic structure in the source data. Although source compression is designed to remove redundancy, practical source coding can leave substantial residual structure that conventional channel decoders do not exploit. Modern multimodal data sources, including text, speech, and images, exhibit rich statistical and semantic dependencies that foundation models can learn and exploit to improve channel decoding. This article introduces semantic error control coding (SECC), which seamlessly integrates the semantic structure of the source into encoding and decoding through a foundation model. The semantic source prior, represented by the model's a priori probability of the source content, directs code redundancy toward semantically important content at the encoder, and improves reliability estimation, candidate search, and error detection/correction at the decoder. The channel code keeps its algebraic structure, and its constraints ensure that the semantic suggestions from the foundation model comply with this structure. We describe the SECC framework, classify its design methods into three approaches, and demonstrate representative schemes on text sources. The demonstrated schemes show several decibels of coding gain over conventional decoding on AWGN channels, and reach error rates below the normal approximation bound. Finally, we identify several open challenges.
Read the full abstract
Systems and Control
Poisson Tangent Limits and Critical Policy Switching for Sampled Bellman Operators
Consider a discounted Markov decision process with continuous action space in which, at each state visit, the controller draws a random pool of $N$ candidate actions and selects among them. When the optimal action set has zero mass under the sampling distribution, the value of this random-candidate model converges to the optimal value as $N$ grows, but the rate of convergence and the asymptotic selection rule are governed jointly by the geometry of the optimal set and by the transition kernels of the near-optimal candidates. This paper develops an exact first-order theory of both. The rescaled near-optimal candidates converge to a marked Poisson point process, and the leading term of the value gap is the fixed point of a nonlinear tangential Bellman operator, a stochastic generalization of the classical resolvent that emerges when several optimal actions compete. The asymptotic selection at exact ties is genuinely dynamic, driven by the transition kernels through the fixed point, and admits an explicit Mecke integral formula at the limiting Poisson level; perturbing the tie at the critical rate yields a switching layer in which the value gap and the selection interpolate continuously between the branch regimes, and in the unique-optimum heterogeneous case the critical class is propagated at the slowest global scale through the discounted reachability of the limit policy. Numerical experiments confirm the predicted rates, constants, and selection probabilities.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
Boundary-Continuous Cross-Camera RGB Mapping via Hue-Split Model Trees
We propose a hue-split model-tree method for boundary-continuous cross-camera RGB mapping. Cross-camera RGB mapping aims to produce consistent color representations across cameras whose recorded RGB values differ due to sensor spectral sensitivities and image-signal processing pipelines. A common chart-based remedy is to estimate a single global affine color correction matrix (CCM), but such a global model cannot capture hue-specific discrepancies between cameras. To capture that behavior, we recursively partitions the source-camera color space along a scalar hue coordinate and builds an model tree that stores an affine CCM at every node. For fitting the node CCMs, we utilize a log-domain error objective. To prevent false contours that arise from hard hue splits, we further introduce a boundary-continuous formulation in which the prediction is obtained by blending the log-domain outputs of all node CCMs along the root-to-leaf path. The path-wise blending weights are optimized under a simplex constraint using both a chart-pair fitting loss and an explicit continuity regularizer defined on deterministic boundary prototype pairs placed just on either side of each learned hue threshold. We conducted an experiment on a Canon EOS-1Ds Mark II to Canon EOS 20D mapping using the Middlebury Registered Color Checker dataset. The results show that hue splitting substantially reduces log-RMSE over a single global affine CCM and that the proposed path blending with boundary prototype regularization simultaneously improves accuracy and suppresses chromaticity gaps at the learned hue thresholds across two illuminants and multiple exposure conditions.
Read the full abstract
Computer Vision
Through Van Gogh's Eyes: Global Style Transfer with Diffusion Model
Artistic image synthesis aims to recreate the expressive visual identity of a target artist, yet existing methods often fail to capture an artist's global style. Conventional style transfer methods transfer the style of one or a few reference artworks to a content image in a One-to-One manner, making them effective for artwork-level stylization but limited in representing the broader stylistic distribution of an artist. Text-to-image diffusion models conditioned on artist names, such as '~ in Van Gogh style', offer greater flexibility, but they often suffer from text-induced bias and reproduce patterns from only a few iconic works. To address these limitations, we introduce Global Style Transfer (GST), an artistic image synthesis paradigm, in a Many-to-One manner, that aggregates multiple artworks from a target artist and transfers their shared global style to a single content image. For GST, we propose Global Style Guidance (GSG), which learns a residual global style offset in the intermediate feature space, or h-space, of a diffusion model under a fixed prompt. By learning artist-level style semantics purely from visual statistics, GSG mitigates text-dependent artistic bias. We further propose Content Alignment Guidance (CAG), a training-free perceptual guidance mechanism that preserves the semantic structure of the content image while allowing artist-specific geometric deformation. Experiments on WikiArt demonstrate that GST achieves superior stylistic fidelity, content preservation, and output diversity compared to existing style transfer and diffusion-based artistic synthesis methods.
Read the full abstract
Machine Learning · Cross-listed from stat.ML
Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows
In many high-stakes domains, extreme events carry substantial consequences, yet learning the heavy-tailed distributions that govern them from finite samples remains challenging: the quantities of interest are driven by a few extreme observations, so the tail is under-sampled relative to its importance. Even generative models tailored for heavy tails capture the tail region inadequately in practice. We propose the Conditional Value-at-Risk (CVaR)-penalized Generative Particle Algorithm (CVaR-GPA), a tail-agnostic algorithm for fine-tuning generative models toward heavy-tailed targets, built as a time discretization of the Wasserstein gradient flow of the Lipschitz-regularized KL divergence penalized by a CVaR discrepancy term. Such a flow can be initialized from the output samples of the pre-trained model, which are then transported along the gradient descent of the loss functional, without requiring access to the pre-trained model's internal architecture. The Lipschitz-regularized KL divergence requires minimal assumptions on the target, while the CVaR penalty focuses the flow on the tail. The CVaR penalty depends on the target only through a scalar tail statistic, inducing a velocity field that remains active in the under-sampled tail region at a dimension-free estimation cost. The resulting velocity field, and hence the depth of the transport map, implicitly adapts to the target, without target-specific modifications. Across four targets, including two real-world, high-dimensional datasets (daily streamflow in the Ohio River basin ($d=64$) and the Fama-French portfolios ($d=25$) with tail indices ranging from $1.05$ to $3.34$), fine-tuning with CVaR-GPA reduces global and tail errors by geometric-mean factors of $14.0 \times$ and $9.8 \times$, respectively, across seven pre-trained models spanning GANs, diffusion models, and other generative flows, with a single set of hyperparameters.
Read the full abstract
Machine Learning
Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistency
Machine learning models should be robust, in the sense of remaining predictively consistent under permissible variations. A model's predictions should ideally remain unchanged when it is replaced by a functionally equivalent one, or when its inputs are subject to minor, admissible perturbations. If such changes alter a prediction significantly, then the prediction is "ambiguous" with respect to the model. Models should abstain from making such ambiguous predictions and/or should flag them for human inspection, especially in high-stakes decision-making scenarios. However, in practice, such ambiguity is not easy to identify once a model is deployed. Here, the Robust Ambiguity Detection (RAD) framework is advanced for quantifying predictive ambiguity using two complementary metrics: Model-Space Consistency and Feature-Space Consistency. These two scores, the RAD Score-Pair, visualised through the RAD Plot, provide an interpretable characterisation of the sources of ambiguity and the actions a user may consider in response. RAD is evaluated on synthetic datasets with systematically controlled overlap, as well as several real-world datasets where the level of ambiguity cannot be directly inspected. Finally, we demonstrate a downstream application of RAD where samples are ranked by their RAD Pareto-Rank and the most ambiguous are abstained from prediction, achieving performance comparable to existing rejection-based approaches.
Read the full abstract
Systems and Control
A Conceptual Framework for Enhancing Workforce Readiness for Smart Manufacturing in the AI Era
The convergence of artificial intelligence (AI), Industrial Internet of Things, cyber-physical systems, and advanced robotics is reshaping manufacturing faster than engineering curricula can adapt, widening the gap between the competencies required on the shop floor and those delivered by traditional engineering and technology education. This paper proposes a Workforce Readiness Level (WRL) framework, which adapts the Technology Readiness Level scale into nine progressive competency stages and a four-pillar rubric, digital and AI literacy, cyber-physical systems fluency, human-machine collaboration, and data-driven decision making, aggregated through a composite stage score and a cohort-level workforce-readiness index under a “no-thin-pillar” rule. The framework is instantiated at a university smart-manufacturing teaching laboratory and draws on 89 sponsored capstone projects delivered over four semesters, four of which are analyzed in depth. Four pillars jointly span the relevant ABET student outcomes. Across the highlighted cohorts the workforce-readiness index ranged from 5.2 to 6.4, and the no-thin-pillar rule was diagnostically informative in three of the four cases and the binding certification constraint in one, repeatedly surfacing cyber-physical and data-driven-decision gaps concealed behind strong analytics profiles; advancement to the highest stages was gated by industry-embedded experience rather than additional coursework. WRL offers educators, accreditation bodies, and regional workforce systems a common, evidence-based instrument for diagnosing and advancing workforce readiness; future work will calibrate pillar weights and test reliability and predictive validity.
Read the full abstract
Human-Computer Interaction
Player Perceptions of Generative AI in Games: A Steam Review Analysis
The rapid adoption of generative AI in game development has created large discussions among players, yet little empirical work has examined how players actually perceive AI-generated content. Employing quantitative methods, we study the adoption of generative AI in games in the Steam marketplace, using procedural content generation (PCG) as a baseline of a generative technology that was successfully integrated into games over several decades. Furthermore, using qualitative methods, we study player reception of generative AI by analyzing 508,192 English-language reviews. We found that games disclosing generative AI use receive lower recommendation rates and more negative overall sentiment than PCG games. Thematic analysis of 600 reviews shows that players perceive the use of generative AI in games as low developer investment in the game. Drawing on human-centered AI frameworks, we argue that successful generative AI adoption requires deploying generative AI for what players need, not for what makes development cheaper.
Read the full abstract
Computer Vision
Generative Semantic Segmentation via an Observable Semantic-Image Interface and Hierarchical Generator Evidence Alignment
Generative semantic segmentation exposes structured predictions as images, but direct color decoding is susceptible to color drift and boundary mixing, whereas latent-feature decoders that predict a separate output distribution may relegate the rendered image to an intermediate visualization. We present Semantic Prism, a conditional semantic-image generation-and-refinement framework with deterministic inference. A diffusion-distilled one-step generator renders a semantic RGB image; per-pixel distances from the rendered colors to a fixed class-color codebook define an explicit probabilistic interface. Hierarchical Generator Evidence Alignment spatially aligns multi-level generator features and uses a zero-initialized output projection to predict an additive residual in the interface logit space, retaining the image-defined interface as the reference for the final distribution. The interface and refined distributions further enable Contextual Interface–Hierarchy Disagreement (C-IHD), a fixed readout for ranking remaining pixel errors without an auxiliary predictor or additional forward pass. On the 500-image Cityscapes validation set, Semantic Prism achieves 72.07% mean intersection over union, 11.39 mIoU points above direct-interface decoding, with 0.41% expected calibration error. Matched-capacity ablations over three seeds support the benefit of jointly aligned multi-level evidence. A separately trained model attains 62.22% mIoU on BDD100K, while the Cityscapes-trained model reaches 46.89% mIoU under source-frozen transfer to the Adverse Conditions Dataset with Correspondences, without target-domain adaptation. Across all three datasets, C-IHD consistently improves the area under the precision–recall curve for pixel-error ranking over maximum softmax probability on the same segmentation predictions; on ACDC, it raises AUPR from 0.6580 to 0.7557.
Read the full abstract
Computation and Language
CT-$\Delta$Bench: A Benchmark for Longitudinal 3D Medical Imaging Difference Reporting with Vision-Language Models
In medical imaging, the clinical value of Computed Tomography (CT) lies not only in depicting current disease status, but crucially in enabling longitudinal comparison of serial scans to determine disease evolution, a process that underpins response assessment, recurrence detection, and ongoing patient management. Yet, despite this central role of temporal comparison in clinical decision-making, existing medical foundation models remain largely confined to single-study understanding, leaving temporally grounded cross-examination insufficiently addressed. To address this gap, we study longitudinal imaging difference reporting, a task in which a model takes two temporally separated scans from the same patient and generates a clinically meaningful report describing interval changes between them. We introduce CT-$\Delta$Bench, a dedicated benchmark for this task with patient-level splitting to prevent information leakage. To better evaluate this task beyond surface-level text similarity, we further develop change-aware metrics specifically designed to capture clinically meaningful longitudinal changes, and conduct an independent physician validation to assess the reliability of the synthesized references and event extraction pipeline. We also compare direct paired-CT reasoning with an indirect two-stage pipeline that first generates single-timepoint reports and then performs textual differencing. Finally, we propose DeltaMed, a baseline model for direct paired-CT difference reporting, and train it on the benchmark training set. Together, these contributions lay the groundwork for temporally aware medical foundation models that better reflect real-world longitudinal clinical reasoning.
Read the full abstract
Performance
Testing the EPYC Conjecture on Real Hardware: MoA-Guided Dense Matrix Multiplication on NCSA Delta (AMD EPYC 7763 Milan)
A companion empirical study conjectured that MoA-guided dense matrix multiplication would need per-CCD recalibration on AMD EPYC Bergamo; allocation access to that machine was declined, and this paper reports the resulting test on NCSA Delta, an architecturally related chip. Its central claim: every result here traces to shape, not architecture in the abstract – cache shape, access-pattern shape, and co-tenancy itself treated as a shape parameter. The corrected block size M_C = 256 follows directly from Delta's real 512 KB L2 divided by the data type's own byte width, no parameter fit after the fact, and outperforms the M1-Pro-inherited M_C = 64 by 30–59% – a block's shape finally matching the cache shape it was always meant to occupy. The same reasoning extends to a shared level: co-tenancy treated as raw capacity fails by an order of magnitude, while co-tenancy treated as a shape parameter – capacity divided by concurrent consumers – survives. A controlled NUMA experiment isolates a third shape: GEBP and MoA-pipelined compute the identical result at identical achieved bandwidth, yet GEBP loses 13.9% of its throughput to remote memory while MoA-pipelined loses only 2.4% – not a speed difference, a difference in the shape each kernel's access pattern traces through memory. The headline result reproduces the M1 Pro's exact three-of-four win over a Strassen-GEBP hybrid, a pattern AWS Graviton4 did not achieve. One question is named rather than resolved: whether Delta's larger MoA-over-GEBP margin reflects genuine speed or an unmatched utilization fraction. Every result here was predicted before it was measured, not fitted after.
Read the full abstract
Machine Learning
Hierarchical Federated Transfer Learning in Digital Twin-Based Vehicular Networks
In recent research on the Digital Twin-based Vehicular Ad hoc Network(DT-VANET), Federated Learning (FL) has shown its ability to provide data privacy. However, Federated learning struggles to adequately train a global model when confronted with data heterogeneity and data sparsity among vehicles, which ensure suboptimal accuracy in making precise predictions for different vehicle types. To address these challenges, this paper combines Federated Transfer Learning (FTL) to conduct vehicle clustering related to types of vehicles and proposes a novel Hierarchical Federated Transfer Learning (HFTL). We construct a framework for DT-VANET, along with two algorithms designed for cloud server model updates and intra-cluster federated transfer learning, to improve the accuracy of the global model. In addition, we developed a data quality score-based mechanism to prevent the global model from being affected by malicious vehicles. Lastly, detailed experiments on real-world datasets are conducted, considering different performance metrics that verify the effectiveness and efficiency of our algorithm.
Read the full abstract
Computation and Language
On Weak Bisimilarities in CCSK
In the context of CCSK, a reversible extension of CCS, we study different notions of bisimilarity (strong/weak, forward-only/reversible) and highlight their differences and commonalities. In particular, for the weak reversible case, not previously studied in the literature, we propose two variants, dubbed directional and mixed bisimilarity, depending on whether $\tau$ actions should be in the same direction (forward/backward) as the action being matched or not. We show, in particular, that mixed bisimilarity is a congruence and completely abstracts away from $\tau$ actions.
Read the full abstract
Computation and Language
Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment
Group alignment adapts a language model to a demographic group to produce responses that reflect the group's opinions, values, and preferences. Sycophancy, a well-documented by-product of alignment, causes the model to over-agree with the user regardless of factual and objective information. However, existing group alignment methods and evaluations focus only on how closely the model matches the group's opinions, overlooking the induced change in sycophantic behaviour. To bridge this gap, we introduce Group Alignment-induced Sycophancy (GAS) and systematically evaluate alignment across 3 methods, 4 models and 13 demographic groups, on both the intended gain in opinion alignment and the unintended shift in sycophancy. We find that gain and shift are non-uniform across groups: under an identical budget, some groups receive larger gains in opinion alignment than others, and the induced sycophancy shift forms a group-specific profile rather than a single-dimensional change. These results suggest that group alignment should be reported as a two-sided, multi-dimensional profile rather than a single fit score that accounts for per-group differences when adapting LLMs to diverse populations.
Read the full abstract
Cryptography and Security
Towards Scalable Fuzzy PSI via Efficient Fuzzy Matching
In this paper, we present scalable fuzzy PSI protocols for general $L_{p \in [1, \infty]}$ distance, supporting both low- and high-dimensional sets. The core technique is two efficient fuzzy matching protocols. The first is built from a role-reversed oblivious PRF (OPRF) and realizes $O(d\log \delta)$ overhead, compared to $O((\log \delta)^d)$ in previous works. The second leverages customized oblivious transfer (OT) with $O(d\ell)$ overhead, where $\ell$ is the bit length of inputs, which is particularly suitable for short inputs. With these new techniques, we further propose a new dual-layer hashing framework for fuzzy PSI over low-dimensional sets, instantiated with our OT-based fuzzy matching and enhanced with a domain reduction optimization. The protocols achieve an overhead linear with $n, m, \log \delta, 2^d$, without the $O((\log \delta)^d)$ or $O(\delta)$ factors present in prior works. {For high-dimensional sets, we construct fuzzy PSI protocols based on our OPRF- and OT-based fuzzy matching, which achieve an asymptotic overhead linear with $n, m, d$, and $\log \delta$ but rely on the strong globally disjoint assumption.} Extensive evaluations demonstrate that our protocols achieve up to a $145\times$ speedup in running time and a $20\times$ reduction in communication cost compared to van Baarsen and Pu~(ASIACRYPT'25), and achieve up to a $25\times$ speedup in running time and up to a $17\times$ reduction in communication cost compared to Piske et al.~(CCS'25).
Read the full abstract
Distributed Computing
Descriptive Dispatch of Computational Work
Agents powered by AI/ML are becoming ingrained in orchestration. Dispatch of work is the task of receiving a request, transforming it for a workload manager, and successfully submitting it. Running scientific workflows across multi-cluster environments introduces substantial challenges of dynamic job transformation, dispatch, and submission to heterogeneous clusters. These tasks are well-suited to agents, which can receive textual instructions for work, prepare job specifications, and dispatch. In this work, we assess the reliability of a dispatch agent across 432 runs, testing all possible combinations of five feature dimensions across four prompt styles. The agent is highly reliable (97.9% success). We test a full orchestration to submit, queue, match, score, select, transform, and dispatch in a multi-cluster experiment. We find that descriptive metadata increases successful execution from 48% to 87% of 220 submitted jobs, eliminating architecture mismatch, and improving performance for five of ten measurable applications by up to 3.3x.
Read the full abstract
Robotics
Keep the Future, Drop the Rollout: RIFT for World Action Models
World action models (WAMs) condition robot actions on predicted futures, but iterative video rollout increases deployment latency. We ask whether action generation requires the evolving rollout trajectory or only its future representation. Across four WAMs on 40 simulated robotic manipulation tasks, paired closed-loop interventions show that blocking access to the future cache or reassigning its values changes execution and reduces success. Yet in the evaluated co-denoising settings, reusing one fixed final-clean key/value (K/V) cache throughout action denoising nearly preserves unmodified execution, with $1.7$–$1.9$ cm end-effector average displacement error. Obtaining this cache still requires iterative video generation. We therefore propose RIFT (Rollout-free Imagination via Future Tokens), which uses learned anticipation tokens to construct a complete future K/V cache in one backbone pass. On LIBERO, RIFT achieves $98.8\%$ overall success, outperforming all evaluated rollout-based methods while yielding a $3.1$–$9.2\times$ inference speedup. Without further training, it achieves $81.1\%$ overall success on the out-of-distribution LIBERO-Plus benchmark, a $+9.7$ percentage-point improvement over the strongest evaluated baseline. On RoboTwin, it achieves $92.9\%$ and $92.6\%$ success on clean and randomized scenes, respectively, the highest among the evaluated methods. On real-world manipulation tasks, RIFT achieves $45.3\%$ average success, a $+6.0$ percentage-point improvement over Fast-WAM-Joint. These results support rollout-free future conditioning without iterative video generation at deployment.
Read the full abstract
Numerical Analysis
Contour Hankel dynamics and indicator fields for the Riemann $\Xi$-function
We develop a moving-contour Hankel framework for encoding local zero configurations of the Riemann $\Xi$-function. Weighted contour integrals of the logarithmic derivative $\Xi'/\Xi$, expressed in a holomorphic coordinate associated with the contour, are identified with the power moments of a finite atomic measure supported at the coordinate images of the enclosed zeros. This representation yields exact zero-free and rank criteria and, for conjugation-compatible contour-coordinate pairs, an inertia formula: once the matrix order is at least the number of distinct coordinate nodes, the negative index equals the number of distinct nonreal conjugate pairs. Consequently, the Riemann hypothesis admits a local finite-dimensional Hankel-positivity formulation, although establishing this positivity independently of the zero set remains unresolved. As the contour moves, the Hankel matrix evolves by a continuous congruence flow between zero crossings and undergoes finite-rank jumps at crossing events. An isolated zero produces a signed rank-one jump, whereas a nonreal conjugate pair produces a rank-two indefinite event in a real-axis circular scan that meets the pair. Removing the continuous coordinate drift yields a piecewise-constant matrix process from which crossing coordinates, multiplicities, and zero locations can be recovered. Numerical experiments validate the contour quadrature, indicator fields, continuous flow, crossing signatures, and recovery procedure.
Read the full abstract
Machine Learning
FLARE++: Low-rank attention with dynamic attention routing
Full self-attention is a strong token mixer for PDE surrogates on irregular domains, but its quadratic cost limits its use on large problems. Latent-space attention methods such as PerceiverIO, Transolver, and FLARE (Fast Low-rank Attention Routing Engine) avoid that cost by routing attention among $N$ tokens through $M\ll N$ learned latents. They compress by dot-product matching of the input tokens against $M$ learned query tokens or projection weights: once trained, the same learned templates serve every input. We remove this restriction with FLARE++, a low-rank attention architecture with input-conditioned routing queries. FLARE++ uses FLARE's own encoder to map the $N$ input tokens to $M$ query tokens, which correct the learned queries. The adapted queries then determine how that same input is compressed and redistributed. This preserves FLARE's explicit low-rank factorization and linear $\mathcal O(NM)$ complexity, and expresses the complete routing operation with standard scaled dot-product attention (SDPA) calls alone. We also provide a multi-GPU context-parallel implementation that shards input tokens across devices without ever gathering the full token sequence on one of them. FLARE++ reduces FLARE's error by $25\%$ on average across five standard PDE benchmarks, achieving the lowest errors among the efficient models compared. The gains persist on industrial-scale DrivAerML aerodynamics and on Long Range Arena, where average accuracy rises by $3.5\%$ over fixed-query FLARE. Code is available at https://github.com/vpuri3/FLARE.py.
Read the full abstract
Computer Vision
New Orthogonal Multiwavelet Filters Derived by Matrix Spectral Factorization
The paper considers the construction of two new orthogonal multiwavelets with supercompact support by using the Fast Bauer's method for matrix spectral factorization on the matrix product filter of the orthogonal CL multiwavelet filter. The new multiwavelets possess orthogonality, symmetry/antisymmetry, and one of them provides better coding and smoothness than other supercompact multiwavelets. The performance of the new multiwavelet filters in subband-based edge detection, grayscale and color image compression and 1D and 2D signal denoising is compared with the GHM, SA4, CL, Integer Haar and Alpert multifilters. The comparative analysis shows that new multiwavelets can provides better human visual measures, SSIM and MS-SSIM in image compression and denoising applications.
Read the full abstract
Tuesday 11 August
Operating Systems
MobiInfer: Accelerating On-Device GUI Agents with Workload-Aware Inference
Mobile GUI agents assist users in executing phone tasks through iterative observe-reason-act loops. However, deploy ing multimodal GUI agents directly on smartphones is challenging due to strict end-to-end latency requirements and significant memory overhead. We observe that GUI-agent work loads exhibit recurring workflows and structured I/O: their prompts contain reusable context, while their outputs follow fixed schemas with phase-dependent predictability. Based on this observation, we present MobiInfer, a workload-aware inference engine for on-device multimodal GUI agents. MobiInfer combines trajectory-aware prefix reuse, phase-indexed vocabulary specialization, and schema-guided speculative decoding to eliminate redundant prefill computation and reduce structured-generation overhead. We implement MobiInfer on top of MNN and evaluate it on AndroidWorld and a real world dataset using three real Android devices. Across the four model-benchmark settings, MobiInfer achieves average speedups of 2.6x in prefill and 2.5x in decoding, reduces end-to-end task latency by 2.4x on average, and cuts total deployment storage by 30%, while limiting task-success degradation to less than one percentage point.
Read the full abstract
Sound
TTS-Q: Speaker-Aware Post-Training Quantization of Text-to-Speech Diffusion Transformers
Zero-shot text-to-speech (TTS) can clone a voice from seconds of audio. Yet the quality comes from billion-parameter diffusion transformers whose size and multi-step sampling put them out of reach of the on-device, assistive, and real-time applications that need them most. Post-training quantization (PTQ) shrinks such models without retraining, but it has been built for language and vision, not speech. At 4 bits, a strong quantizer leaves intelligibility close to full precision but consistently erodes speaker timbre, so error rates stay low while the voice drifts from the target speaker. We ask why quantization hurts speech, where the damage lives, and whether it can be repaired without retraining. To find out, we run the first 4-bit weight-and-activation (W4A4) PTQ study of a TTS diffusion transformer at 1B and 3.5B. The timbre cost comes from both the weight and the activation quantization, but only the activation part has the timestep structure a precision schedule can exploit. We therefore introduce TTS-Q, which selects hard-to-quantize items from task-matched calibration candidates and applies a budget-balanced mixed-precision schedule that assigns higher precision to late-step feed-forward activations. TTS-Q recovers timbre best at both scales, at no cost to intelligibility. Separately, the deployed calibrated-W4A4 reference reduces peak memory on GPU, providing a practical reference for resource-constrained TTS deployment.