arXiv:2607.06082v1 Announce Type: cross
Abstract: We study a generalization of the star coloring problem on hypergraphs. For a family of connected subhypergraphs $\mathcal{F}$, we define an $\mathcal{F}$-coloring of a hypergraph as a coloring avoiding monochromatic hyperedges and any 2-colored member of $\mathcal{F}$. We let $\chi^r_{\mathcal{F}}(d)$ be the maximum of the minimum number of colors needed for an $\mathcal{F}$-coloring of an $r$-uniform hypergraph with maximum degree $d.$ We show bounds for $\chi^r_{\mathcal{F}}(d)$, that also yield results on star and acyclic coloring problem on hypergraphs.
Science Journals
arXiv:2607.05679v1 Announce Type: new
Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes. Effectively analyzing and mitigating such biases requires accurate and generalizable evaluation methods of the underlying associations. Some existing approaches focus on downstream metrics that analyze associations in generated text. Since generated text content can vary drastically across LMs, such metrics often require specialized evaluation datasets, which limits the generalization of such downstream metrics. In contrast, upstream metrics examine LMs at the fundamental level of embeddings or continuation probabilities, enabling principled association analyses across LMs. Yet, to date, no upstream metric for generative LMs has uncovered a strong relationship with real-world associations, including those measured in generated text. To address this gap, we introduce the Relative Probability Association Metric (RPAM), an association evaluation metric for generative LMs. For three LMs of different quality of language generation and purpose (Mistral-7B-Instruct, Mistral-7B, and GPT-2) and well-studied evaluation datasets (WEAT-WS, Bellezza, WS-353, and SST2), we find a strong relationship between upstream RPAM measurements and corresponding implicit and explicit associations observed in humans, as well as biases measured downstream with LM-specific tasks, outperforming prior record values where applicable.
arXiv:2607.06371v1 Announce Type: new
Abstract: Chatbots powered by generative AI (e.g., OpenAI's ChatGPT and Google's Gemini) are increasingly being appropriated for emotional support and companionship. These tools offer a suite of security and privacy (S&P) controls, including model training opt-outs and memory toggles, yet how the presence of these controls influences users' attitudes toward emotionally sensitive disclosure remains understudied. We conducted a mixed-methods vignette study with 354 U.S. participants to examine how S&P controls influence users' willingness to engage with generative AI chatbots for emotional support, their perceptions of how protected they are when using these systems, and their perceptions of how effective the chatbots are for providing support. Controls enabling deletion of disclosures had the largest positive impact: these offerings outperformed technically sophisticated controls such as local-only processing and model training opt-outs, where participants expressed difficulty understanding the underlying mechanisms. Yet trust remains fragile, and participants often doubted S&P controls would function as promised. We conclude with actionable recommendations informed by our results to bridge users' comprehension gaps, build credible assurances, and properly calibrate barriers for users in distress.
arXiv:2607.05492v1 Announce Type: cross
Abstract: Quantum information theory is built on entropic quantities; among them, the sandwiched R\'enyi relative entropy is a fundamental divergence with various applications, and its data processing inequality (DPI) under quantum channels is a cornerstone result. In this work, we present a Lean 4 library for quantum information, designed as a reusable formal infrastructure for theoretical analysis. As a central demonstration of the library, we formalize the DPI for the sandwiched R\'enyi relative entropy for positive semidefinite operators on finite-dimensional quantum systems. The library provides a basis-independent operator-theoretic framework for finite-dimensional quantum mechanics compatible with the standard mathematical library Mathlib, including reusable interfaces for finite-dimensional systems, states, channels, tensor products, partial traces, Choi operators, Kraus representations, and Stinespring representations. It also builds infrastructure for noncommutative trace inequalities, including operator monotonicity and convexity via the real continuous functional calculus, block-operator positivity, Hilbert-Schmidt operator spaces, Jensen's operator inequality, generalized perspectives, operator power means, and Lieb-Ando trace inequalities. On top of this framework, we formalize entropy-specific ingredients for the DPI: variational formulas for the sandwiched quasi-entropy via Young and reverse-Young inequalities, tensor-product compatibility of real powers, and Haar measures on unitary groups. Together, these components yield a Lean formalization of the DPI, give strong subadditivity as a corollary, and provide the last missing component needed to complete the Lean formalization of the generalized quantum Stein's lemma. More broadly, the development provides machine-checkable foundations for future formalized and AI-assisted research in quantum information theory.
arXiv:2607.05501v1 Announce Type: cross
Abstract: Pipe diagrams have emerged as a powerful framework for flexible lattice surgery compilation and spacetime optimization for the surface code. In contrast, analogous compilation techniques for color code architectures remain largely unexplored, despite the color code's favorable properties, including reduced qubit overhead and transversal single-qubit Clifford gates. In this work, we develop a pipe diagram representation for the triangular color code on the 6.6.6 lattice and establish its correspondence to ZX-diagrammatic descriptions of computation. We present distance-independent constructions of color code pipe diagrams together with explicit realizations of correlation surfaces, stabilizers, and syndrome extraction circuits. This framework enables both macroscopic optimization of logical computations in spacetime and microscopic compilation to executable syndrome extraction circuits. We demonstrate the potential for compact spacetime embeddings with the color code's geometry. These results provide a foundation for automated lattice surgery compilation and diagrammatic optimization in color code architectures.
arXiv:2607.05539v1 Announce Type: cross
Abstract: Bregman Proximal Gradient methods (BPGM) exploit the underlying geometry of the objective function through a carefully chosen mirror map. In this work, we introduce a novel notion of strong convexity, termed Restricted Relative Strong Convexity, and establish linear convergence rates for BPGM under this condition. We then exploit the proposed theoretical framework to provide an in-depth analysis of the convergence of BPGM for (regularized) Kullback--Leibler regression problems, covering scenarios with both unique and non-unique minimizers, as well as regularized and unregularized formulations. Specifically, we demonstrate that using the popular Burg's entropy as a distance-generating function may only yield linear convergence for certain KL regression problems. In contrast, we show that employing a smoothed version of the Burg's entropy induces the suitable geometry required to guarantee linear convergence. We conclude with numerical experiments that nicely align with our theoretical findings.
arXiv:2308.16041v2 Announce Type: replace
Abstract: Talking head generation has progressed rapidly from landmark- and GAN-based facial animation to diffusion models, neural rendering, 3D-aware avatars, and foundation-model-assisted systems. This progress has enabled increasingly realistic audio-, image-, and video-driven talking heads, but it has also made the field difficult to navigate because methods differ substantially in their inputs, assumptions, controllability, temporal stability, computational cost, and risks of misuse. This survey provides a critical review of talking head generation techniques, organizing the literature into four broad families: image-driven, audio-driven, video-driven, and 3D/neural-rendering-based approaches. For each family, we discuss the underlying technical ideas, representative methods, strengths, limitations, datasets, and evaluation practices. Beyond cataloguing prior work, we analyse the persistent gap between commonly reported quantitative metrics and perceptual quality, and compare publicly available models in terms of inference time, memory requirements, and human-rated visual quality. We also examine emerging trends, including diffusion-based generation, 3D-aware representation learning, controllable emotional expression, real-time deployment, and the growing importance of provenance, watermarking, and deepfake detection. Finally, we identify open challenges around robust evaluation, identity preservation, lip synchronisation, temporal consistency, demographic fairness, computational efficiency, and responsible use. This review aims to provide researchers and practitioners with a structured and up-to-date map of the talking head generation landscape, while highlighting the technical and societal questions that should shape future work.
arXiv:2607.05888v1 Announce Type: new
Abstract: i-EXAM is a planning-powered tool that helps system administrators to create security profiles of complex networks and perform what-if analyses to identify network hardening strategies. It leverages planning compilation that provides soundness and completeness guarantees to identify attack paths, evaluate security metrics, generate diverse hardening strategies, and explain these strategies in natural language using Large Language Models.
arXiv:2607.05773v1 Announce Type: new
Abstract: As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution. By moving to verifiable execution outcomes, the platform generates high-fidelity traces and applies multi-dimensional reward shaping. Critically, our framework mitigates reward hacking through rigorous internal state validation and testing. This work provides a first look at our platform's core capabilities through a Customer Support Agent case study demonstrating a consistent closed-loop feedback for model optimization. Future work will focus on advanced features such as Computer Use, Tool Use, automated "stumping", and edge-case generation.
arXiv:2607.05845v1 Announce Type: new
Abstract: Soccer is widely popular for its simple rules and complex yet coordinated play that unfolds on the pitch. Nevertheless, the fundamental mechanisms governing such play are not well understood: what shapes player interactions on the pitch? What short-term goals guide players' decisions about their movements over the next few seconds? We address these questions by focusing on one-on-one settings in open play, in which the attacker, in possession of the ball and typically dribbling, faces a defender aiming to stop or delay the attacker's actions over a short period. Here we develop a mathematical model of attacker-defender interactions and analyze 306 professional soccer games. Synthesizing the large-scale dataset with an analysis of the model reveals a simple behavioral principle that may underlie these interactions: the defender seeks to minimize their future relative speed to the attacker, whereas the attacker initiates their movements to preempt the defender's objective. This principle, relative-speed minimization, provides a consistent and unified account of the empirical data. Since our framework depends little on soccer-specific details, this principle may govern diverse pursuit-evasion scenarios as well as other invasion team sports.
arXiv:2607.05785v1 Announce Type: new
Abstract: Recent advances in coding agents have enabled the generation of increasingly complex software systems. While existing evaluations primarily focus on functional correctness, production systems must expose failure evidence to support observability. In this paper, we present a systematic study of observability in agent-generated systems. We examine whether agents can reconstruct source-level diagnostic semantics by restoring observability artifacts in 10 open-source and 8 industrial repositories. We also evaluate whether these artifacts translate into effective fault signals at runtime through 200 generated microservice systems deployed on Kubernetes with 13 injected faults. Our results reveal a consistent gap between diagnostic semantics at the source level and fault signals (i.e., explicit, fault-specific evidence) at runtime. At the source level, agents partially recover observability artifacts but struggle to capture key diagnostic semantics. At runtime, generated systems expose fault signals for only a small fraction of failures (up to 13.99\%), despite the presence of logging, suggesting that the generated observability artifacts may lack the failure-specific semantics needed to effectively expose faults. We further introduce an observability-oriented skill, which can serve as a guidance to improve both diagnostic semantics and fault-signal exposure, but the gains remain limited, indicating that the gap is not easily addressed. More broadly, our findings suggest that current evaluations focusing primarily on functional correctness may overlook observability as an important dimension of practical software quality.
arXiv:2607.05546v1 Announce Type: cross
Abstract: We develop a unified function space theory of deep fully connected neural networks. Functions in our spaces are defined recursively as $\ell^1$-bounded linear combinations of activated functions from preceding layers, with a dictionary of affine functions at the first layer. Unlike existing theories that are largely specialized to homogeneous activations such as the ReLU, our framework provides a meaningful notion of functional complexity for deep networks with a broad range of homogeneous and non-homogeneous activation functions commonly used in practice. This simple construction unites several seemingly disparate ideas from the literature, including norm-based complexity bounds and variational characterizations of depth, and facilitates novel analyses of what kinds of functions deep norm-constrained networks can represent. To this end, we prove a novel representer theorem for our spaces and establish novel function-space complexity bounds showing that the associated function classes remain qualitatively small at arbitrary depth. In the univariate ReLU case, we prove a "depth saturation" result: depth in this setting yields only a small constant rescaling of the function class, with no added functional diversity. As a consequence, we show that deep norm-controlled ReLU functions in any dimension cannot exhibit high frequencies along any direction. This finding reveals that some commonly cited expressivity benefits of depth disappear once network complexity is controlled by an appropriate function space norm, rather than parameter count or other representational costs that permit compounded rescaling across layers. Overall, our results illustrate how a function space perspective yields new structural insights into the relationship between depth and complexity.
arXiv:2607.06445v1 Announce Type: new
Abstract: Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimodal reasoning capabilities. While standalone VLMs demonstrate strong localization capabilities, editing pipelines frequently struggle to maintain this accuracy, particularly in complex, multi-entity scenes. In this work, we investigate this performance gap, hypothesizing that it stems from treating the VLM as a condition encoder. In this role, the model is restricted to a single forward pass, preventing the autoregressive generation process for which it was optimized, thereby failing to fully expose its capabilities. To investigate whether this spatial understanding persists when the VLM is used as a condition encoder, we introduce Analysis-by-Proxy. In this framework, we train a lightweight, interpretable proxy model on the VLM's intermediate representations using an auxiliary localization task. By analyzing the VLM through this proxy, we uncover the specific VLM representations that encode localization information. Our findings expose a fundamental mismatch between how spatial knowledge is represented within a VLM condition encoder and how it is extracted by current editing pipelines. We reveal that under single-pass constraints, the localization signal does not reliably propagate to the predefined layer configurations commonly used for conditioning. Instead, this crucial signal remains hidden within intermediate representations, at locations that vary depending on the input prompt. Using our introduced Analysis-by-Proxy framework, we reveal the fundamental failures of existing condition extraction strategies in editing pipelines, opening the door to more principled design of conditioning architectures.
arXiv:2607.05869v1 Announce Type: new
Abstract: Robust robotic grasping of novel objects requires datasets that simultaneously provide photorealistic RGB-D observations, physically validated grasp quality annotations, and a principled bridge between simulation and the real world, which existing datasets lack to provide jointly. \textbf{GraspIT} addresses this gap: tabletop scenes in NVIDIA Isaac Sim are annotated via a four-stage physical slip-test on parallel Franka Panda instances, producing trajectory-reachability checks and continuous quality scores beyond force-closure.Of ${\sim}$2.3M candidates, 83% pass as \emph{good} ($s{\geq}0.50$); the 17% that passed force-closure but failed the slip-test provide graded hard negatives. A Real$\leftrightarrow$Sim loop back-projects these labels onto 100 real-world scenes. The release provides ${\sim}$316k annotated RGBD frame sets across 1035 sim and 100 real scenes, with instance masks, 6-DoF poses, physical object properties, and scored 6-DoF grasps. All tools are open-source and Docker-containerized. The trajectory planning within Isaac Sim further allows streaming of high resolution demonstrations for tabletop manipulation policy learning and behavior cloning.
arXiv:2607.06468v1 Announce Type: new
Abstract: We introduce EgoPolice, a carefully curated dataset of real, egocentric police-civilian interactions, sourced from publicly available body-worn camera videos. We select police-civilian action labels that are critical for police behavioral research and annotate them at a second-by-second granularity. The videos feature rapid and irregular camera motion, dense human interactions, and rare high-stakes events, making the dataset a challenging benchmark for motion-robust and context-aware egocentric perception. We provide two different tasks, classification and multiple-choice question-answering, and benchmark both open-source and closed-source models. We find that even the best video models like Gemini 2.5 Pro still struggle to accurately predict high-risk actions such as "Weapon Out". Beyond serving as a benchmark, EgoPolice provides a foundation for developing models capable of identifying events of interest in large-scale body-worn camera video repositories, enabling more efficient downstream human review.
arXiv:2607.05891v1 Announce Type: new
Abstract: Coreset selection aims to identify a small and highly representative subset of a massive dataset for efficient model training. The problem remains challenging even in the few-shot knowledge distillation (KD) setup, where a full-scale pre-trained teacher informs the student network. Typical sample selection strategies often struggle to surpass the random selection baseline. In this paper, we showcase few-medoids, an embarrassingly simple coreset selection strategy that chooses the samples closest to the centroid (average image) of each class. We present extensive KD experiments on four datasets, covering a wide range of image classification problems, and three teacher-student model pairs, comprising both convolutional and transformer networks. Although the proposed method is embarrassingly simple, our empirical results indicate that few-medoids is able to consistently surpass the random selection baseline, as well as the other coreset selection strategies. We therefore consider that few-medoids can be used as a drop-in replacement for commonly-used baselines (e.g. herding or k-center Greedy), in future research on coreset selection. To reproduce the reported results, we publicly release our code at https://github.com/CemilAndreiDilmac/Few-Shot-KD-Coreset.
arXiv:2607.06393v1 Announce Type: new
Abstract: We give faster exponential-time randomised approximation algorithms for counting problems where polynomial-time approximation is unavailable and exact exponential-time counting remains expensive. For general \(n\)-vertex graphs, our independent-set counter runs in \(O^{\ast}(1.1869^{n})\) time, improving the previous \(O^{\ast}(1.2041^{n})\) general-graph bound. For \(n\)-variable \#\textsc{2-SAT}, we obtain an \(O^{\ast}(1.2373^{n})\)-time approximation algorithm, narrowly below Wahlstr{\"o}m's currently cited \(O^{\ast}(1.2377^{n})\) variable-parameter exact bound.
The new algorithmic point is to take the square root after decomposition. For a single bounded unweighted self-reduction with \(f(x)\) positive leaves and recursion-compatible upper bound \(b(x)\), an enumerate-or-sample estimator gives an \((\varepsilon,\delta)\)-approximation in \[
O^{\ast}\!\left(\sqrt{b(x)}\,\varepsilon^{-2}\log \tfrac1\delta\right) \] time. After preprocessing decomposes an input into many bounded cores, the combined estimator pays \[
O^{\ast}\!\left(\sqrt{\sum_i b_i(x_i)}\,\varepsilon^{-2}\log \tfrac1\delta\right), \] rather than estimating the cores separately at cost \(\sum_i \sqrt{b_i(x_i)}\).
The same conversion improves the bases for counting maximal cliques, minimal separators, and perfect matchings in subcubic graphs. Bounded unweighted self-reductions provide the formal language; at the level of counting classes, the resulting unweighted formulation has the same Karp closure as TotP. With explicit recursion-tree access, the framework yields black-box quantum speed-ups.
arXiv:2607.05994v1 Announce Type: new
Abstract: Human-Object Interaction (HOI) video generation aims to synthesize realistic videos of humans manipulating diverse objects, serving as a promising avenue for AI-driven live streaming e-commerce. A primary obstacle in this domain lies in the complexity of modeling fine-grained physical dynamics and the intricate spatial-temporal coordination between human hands and objects. Existing approaches to this problem typically rely on dense temporal guidance, e.g., frame-wise hand-object pose sequences, to strictly control the interaction process. However, such dense guidance incurs high annotation costs and affects motion synthesis diversity. To overcome these limitations, we introduce SparseCtrl-HOI, a novel sparse temporal control framework for HOI video generation. It requires only a few keyframes that capture interaction states at designated timestamps. Specifically, we employ a Time-Controlled Rotary Positional Embedding (TiRoPE) mechanism to temporally anchor these keyframes while preserving their spatial integrity. Subsequently, to govern the dynamics across intermediate frames, we propose a Motion Prior Injection Module that leverages Multimodal Large Language Models (MLLMs) to extract high-level motion priors. This empowers the model to hallucinate logically and physically plausible transitions. Furthermore, we build SparseHOI-5K, a high-quality and richly annotated dataset for HOI video generation with sparse temporal control. Comprehensive evaluations confirm that our method substantially reduces annotation overhead while synthesizing superior live-streaming e-commerce videos. Both our code and dataset are publicly available at https://mpi-lab.github.io/SparseCtrl-HOI.
arXiv:2607.05998v1 Announce Type: new
Abstract: We present a unified finite element method for the dynamics of fluidic biomembranes. The model is governed by the Navier--Stokes equations in the bulk coupled to the surface Navier--Stokes equations on the evolving biomembrane surface, with bending forces arising from the Willmore energy. By allowing the bulk mesh velocity to be independent of the fluid velocity and permitting a free tangential surface velocity, we are able to derive a unified weak formulation of the coupled bulk-surface Navier--Stokes system. To address the bending force, we consider an evolution equation for the curvature and propose a surface arbitrary Lagrangian--Eulerian (ALE) weak formulation. Discretization with either fitted or unfitted finite elements leads to well-posed fully discrete linear schemes that are unconditionally energy stable. We present a variety of numerical examples to demonstrate the favourable properties of the proposed methods.
arXiv:2607.06023v1 Announce Type: new
Abstract: Visual SLAM is a well-established technology utilized in a wide range of real-world applications. However, its performance still degrades under challenging visual conditions, such as low texture, severe motion blur, and poor illumination. Systems based on deep learning outperform classical geometry-based ones and achieve state-of-the-art results by combining learned 2D data association and uncertainty with differentiable geometric optimization in recurrent architectures. Still, it remains unclear exactly which components are fundamentally responsible for this success. In this paper, we ask: Is the superior performance of deep learning-based systems driven primarily by learned 2D data association, the combination of learned 2D data association and uncertainty, or the recurrent architecture itself? We investigate this question empirically by conducting a controlled study. Our findings reveal that the success of DL-based V-SLAM systems hinges on learned 2D data association and uncertainty rather than their recurrent architecture, underscoring the necessity of learning-based paradigms for the design of these components. Upon acceptance, the code will be released as open source.
arXiv:2607.06037v1 Announce Type: new
Abstract: A shared electrocardiogram (ECG) is itself a biometric fingerprint that can re-identify a patient and reveal personal information. Recent ECG anonymizers transform the signal before sharing to reduce privacy leakage. However, existing methods still face a privacy--utility trade-off, in which preserving privacy often compromises utility while preserving utility reveals personal information. We propose \emph{REAN} (\emph{RE}construction-aware ECG \emph{AN}onymizer), a raw ECG signal anonymizer, to address this privacy--utility trade-off. REAN reconstructs the signal using a 1-D U-Net trained with losses from frozen privacy and utility classifiers to reduce privacy leakage while preserving utility. The privacy and utility gradients are near-orthogonal ($\approx$93.8$^\circ$), so reducing privacy leakage leaves utility almost unchanged. On four public PhysioNet databases, REAN achieves the strongest privacy--utility balance among raw ECG signal baselines. It drives re-identification to chance (0.96$\to$0.00), keeps arrhythmia macro-AUROC at the clean level (Clean 0.9982 vs.\ REAN 0.9991), and maintains re-identification protection under unseen privacy-classifier architectures.
arXiv:2607.06039v1 Announce Type: new
Abstract: High-integrity systems, such as autonomous vehicle fleets and large-scale energy infrastructures, rely on structured assurance cases to justify safety claims. To remain valid under evolving operational conditions, such cases must be examined against potential challenges, known as defeaters. While large language models (LLMs) can support the scalable generation of candidate defeaters, assessing their quality remains largely manual and subjective process. This paper presents an automated approach for supporting the assessment of LLM-generated defeaters using natural language processing techniques. The method combines structural features from assurance case graphs with semantic embeddings and meta-classifiers trained on expert-assessed defeater annotations. We evaluate the approach through two case studies in the automotive and energy domains. The results show substantial human reviewer dissensus, with Cohen's kappa values below 0.442, highlighting the difficulty of consistent manual assessment. Against this background, the proposed classifiers achieve an average F1-score of 0.84 in validation and show improved alignment with individual expert ratings. The findings suggest that automated assessment can help reduce subjective variance and provide scalable decision support for assurance case review, while leaving final judgment to domain experts.
arXiv:2607.05672v1 Announce Type: cross
Abstract: More than 80 years ago Kramers published a paper calculating how fast a Brownian particle escapes from a potential well over an activation barrier. Since then Kramers' model has been widely adopted by nuclear physics, biophysics and chemical physics communities as a description of activated barrier crossing. From a chemical kinetics perspective, Kramers' theory provides a mapping from continuous dynamics to discrete-state chemical kinetics. Motivated by recent developments, this Perspective provides a rigorous way of performing such a mapping, explaining why and how Kramers' theory works from several points of view. Specifically, we consider transitions of a Brownian particle between two potential wells corresponding to the ``reactant'' and the ``product'' of a chemical reaction. A central unifying idea is to divide the equilibrium ensemble of possible states of the system into two sub-ensembles corresponding to the reactant and product states and then to consider fluxes between these sub-ensembles. Importantly, naive separation based on the location measured relative to the barrier top does not result in a mapping that is physically tenable, and instead the past of the trajectory should be considered. Thus constructed reactant and product ensembles provide an internally consistent description of the problem when also viewed from two different perspectives: one based on the definition of the rate as a conditional transition probability per unit time and the other based on the relaxation modes of the time-evolution operator governing the dynamics.
arXiv:2607.06408v1 Announce Type: new
Abstract: Robust remote verification of identity documents relies on analyzing faint, transparent security features like Optically Variable Devices (OVDs), or "holograms", within user-captured videos under uncontrolled conditions. Current systems, however, face critical limitations: existing methods often treat video frames in isolation, neglecting the intrinsic dynamic nature of OVDs and leaving systems vulnerable to swapping attacks, or focus on general holographic presence and lack the ability to verify specific OVD types. Moreover, the economic infeasibility of frame-by-frame video annotation makes supervised training impractical. In this work, we introduce two novel approaches for verifying the dynamic behavior of transparent OVDs protecting the holder's portrait, specifically designed for open-set scenarios where attack types are unknown during training. We demonstrate that these approaches can be trained without any attack samples in a self-supervised setting, surpassing previous state-of-the-art methods on public datasets while adhering strictly to industrial constraints. Our results confirm that modeling temporal dynamics is essential for defeating sophisticated attacks under realistic conditions, and underscores the promise of sequence modeling and anomaly detection for OVD verification. Code is available at https://github.com/EPITAResearchLab/pouliquen.26.icdar.
arXiv:2607.06054v1 Announce Type: new
Abstract: Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their accent defaults to other Mandarin variants, their tokenizers over-segment common Taiwanese text, and their pronunciation degrades at code-switching boundaries where Chinese and English alternate within one utterance. These problems share one root: the text side lacks adaptation to the Taiwanese context. We address the text side from the bottom up. PangolinTokenizer, a byte-level BPE tokenizer trained on Taiwan-context data, reaches the lowest token rate (0.485 tokens/character) with the smallest vocabulary among nine tokenizers. Barbet, a billion-parameter Traditional-Chinese language model trained on PangolinTokenizer, serves as the text-semantic frontend and ranks first among comparable public models on a 14-task evaluation. BlueMagpie-TTS attaches Barbet to the pretrained acoustic stack of VoxCPM2 through a learned bridge, keeping the acoustic stack fixed. On a 1000-sentence Taiwan-localized test set, it lowers CER from 11.45% to 4.81% and WER from 14.83% to 5.36%, relative reductions of 58.0% and 63.9%. In a blind listening study on 500 of these sentences with ten listeners, 65.6% of majority votes prefer BlueMagpie-TTS.