arXiv:2606.16282v1 Announce Type: new Abstract: This paper presents a geometry-driven detection and fault-classification framework for grid-forming (GFM) inverters based on normally hyperbolic invariant manifolds (NAIM) and stochastic hypothesis testing. The GFM droop manifold $\mathcal{M}_0$ is identified as a NAIM of the closed-loop dynamics. Transverse fluctuations under grid noise are modeled as an Ornstein--Uhlenbeck process, and the long-run covariance is obtained from the algebraic Lyapunov equation. The detection statistic $D_t=T_w\bar{\xi}_{\perp}^{\top}\Sigma_{\mathrm{long}}^{-1}\bar{\xi}_{\perp}$ converges to $\chi^2(2)$ under the null hypothesis, yielding the tuning-free threshold $D_{\alpha}=-2\ln\alpha$ and an asymptotically exact false-alarm rate $\alpha$. A factor-of-2 error in earlier formulations is corrected and validated using 8,000 Monte Carlo realizations over nine window lengths and three significance levels. The Berry--Esseen bound $d_{\mathrm{KS}}\leq1.6704/(\beta T_w)$ is confirmed empirically. The minimum window condition $T_w\geq10/\beta_{\min}\approx1.0$ s, where $\beta_{\min}=\min(\omega_f,\omega_v)$, satisfies the IEEE 1547-2018 two-second detection requirement. A co-design theorem shows that increasing $(\omega_f,\omega_v)$ simultaneously enlarges the Fenichel spectral gap, tightens the null covariance, and reduces the false-alarm rate. Modal decomposition separates frequency and voltage contributions, enabling classification of islanding and voltage faults without additional sensors. Case studies confirm correct acceptance of normal operation, rapid detection of soft islanding, and accurate identification of a 10\% voltage sag.
Science Journals
arXiv:2606.16273v1 Announce Type: cross Abstract: We introduce, to our knowledge, the first deep generative modeling framework for probability distributions continuously supported on compact metric graphs. Given source and target measures on a metric graph, our method embeds the graph into a smooth ambient space, solves an entropic Kantorovich problem via a neural semidual parameterization, and projects generated samples back onto the original graph. We study two embedded geometries: an extrinsic Euclidean realization and the intrinsic tropical Abel--Jacobi embedding into the Jacobian torus. In both cases, the resulting generator is graph-supported by construction. We prove that, in the joint limit of increasing neural expressivity, the learned generator converges weakly to a valid transport coupling between the original graph measures. Empirically, across a range of geometrically distinct graphs, our method matches or improves upon heuristic transport baselines based on discrete graph OT, while scaling more favorably. Finally, we demonstrate scalability on real-world urban mobility data by training our model on one million Uber pickup locations in Manhattan, New York City.
arXiv:2605.29641v2 Announce Type: replace-cross Abstract: In data centers, tasks are dispatched to various servers to evenly distribute the workload. When a data center considers implementing a new scheduling algorithm, it typically conducts an A/B test prior to deployment to assess the real-world impact of this new method. However, a straightforward A/B test might be interfered with so-called ``Markovian'' interference. We utilized the Differences-in-Q estimator, as developed by Farias et al. (2022), and introduced mixed Differences-in-Q estimators grounded in Little's Law. We show that our A/B testing methods significantly reduce bias and variance when testing various scheduling policies. Extensive simulations were conducted under scenarios like non-stationary arrival rates, heterogeneous service rates, and communication delays. These simulations highlight the robustness and efficacy of our A/B testing approach.
arXiv:2602.01394v2 Announce Type: replace-cross Abstract: This paper addresses the challenge of audio-visual single-microphone speech separation and enhancement in the presence of real-world environmental noise. Our approach is based on generative inverse sampling, where we model clean speech and ambient noise with dedicated diffusion priors and jointly leverage them to recover all underlying sources. To achieve this, reformulate a recent inverse sampler to match our setting. We evaluate on mixtures of 1, 2, and 3 speakers with noise and show that, despite being entirely unsupervised, our method consistently outperforms leading supervised baselines in WER across all conditions. We further extend our framework to handle off-screen speaker separation. Moreover, the high fidelity of the separated noise component makes it suitable for downstream detection of the acoustic scene. Code and pretrained models will become available upon acceptance. Demo page: https://ssnaps2026.github.io/ssnaps2026/
arXiv:2602.11547v4 Announce Type: replace-cross Abstract: Existing H.265/HEVC video steganalysis research mainly focuses on detecting the steganography based on motion vectors, intra prediction modes, and transform coefficients. However, there is currently no effective steganalysis method capable of detecting steganography based on Coding Unit (CU) block structure. To address this issue, we propose, for the first time, a H.265/HEVC video steganalysis algorithm based on CU block structure gradients and intra prediction mode mapping. The proposed method first constructs a new gradient map to explicitly describe changes in CU block structure, and combines it with a block level mapping representation of IPM. It can jointly model the structural perturbations introduced by steganography based on CU block structure. Then, we design a novel steganalysis network called GradIPMFormer, whose core innovation is an integrated architecture that combines convolutional local embedding with Transformer-based token modeling to jointly capture local CU boundary perturbations and long-range cross-CU structural dependencies, thereby effectively enhancing the capability to perceive CU block structure embedding. Experimental results show that under different quantization parameters and resolution settings, the proposed method consistently achieves superior detection performance across multiple steganography methods based on CU block structure. This study provides a new CU block structure steganalysis paradigm for H.265/HEVC and has significant research value for covert communication security detection.
arXiv:2602.02773v2 Announce Type: replace Abstract: Mobile manipulators in the home can enable people with cervical spinal cord injury (cSCI) to perform daily physical household tasks that they could not otherwise do themselves. However, paralysis in these users often limits access to traditional robot control interfaces such as joysticks or keyboards. In this work, we introduce and deploy the first system that enables a user with quadriplegia to control a mobile manipulator using intent from paralyzed parts of their body, using bimanual high-density electromyography (HDEMG). We develop a pair of custom, fabric-integrated HDEMG forearm sleeves, worn on both arms, that capture residual neuromotor activity from clinically paralyzed degrees of freedom and support real-time gesture-based robot control. We achieve high classification accuracies based on motor intent across (n = 2) users with cSCI, achieving up to 98.0%. Second, by integrating vision, language, and motion planning modules, we introduce a shared autonomy framework that supports robust and user-driven teleoperation, with particular benefits for navigation-intensive tasks in home environments. Finally, to demonstrate the system in the wild, we present a twelve-day in-home user study evaluating real-time use of the wearable EMG interface for daily robot control. Together, these system components enable effective robot control for performing activities of daily living (ADLs) and other household tasks in a real home environment.
arXiv:2603.27450v2 Announce Type: replace Abstract: Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation. However, efficient reinforcement learning (RL) upon these policies remains a challenge due to the lack of explicit log-probabilities for vanilla policy gradient estimators. While numerous attempts have been proposed to address this, the field lacks a unified perspective to reconcile these seemingly disparate methods, thus hampering ongoing development. In this paper, we bridge this gap by introducing a comprehensive taxonomy for RL algorithms with diffusion/flow policies. To support reproducibility and agile prototyping, we introduce a modular, JAX-based open-source codebase that leverages JIT-compilation for high-throughput training. Finally, we provide systematic and standardized benchmarks across Gym-Locomotion, DeepMind Control Suite, and IsaacLab, offering a rigorous side-by-side comparison of diffusion-based methods and guidance for practitioners to choose proper algorithms based on the application. Our work establishes a clear foundation for understanding and algorithm design, a high-efficiency toolkit for future research in the field, and an algorithmic guideline for practitioners in generative models and robotics. Our code is available at https://github.com/typoverflow/flow-rl.
arXiv:2606.16607v1 Announce Type: cross Abstract: This paper considers neural channel state information (CSI) compression for time-varying massive multiple-input multiple-output (MIMO) channels in frequency division duplex (FDD) systems with limited feedback resources. The main challenge lies in obtaining a compact and efficient representation of the CSI given that it exhibits strong temporal correlation across successive snapshots. Existing memoryless compression models do not exploit this property, while simple temporal extensions often incorporate multiple observations without explicitly modeling the latent dynamics. We propose a context-aware compression framework based on a k-memory Markov variational autoencoder (k-MMVAE), which uses a finite temporal window to capture the evolution of CSI in the latent space. The model introduces Markov-structured latent dynamics with finite memory, enabling efficient use of temporal dependencies for compression. Simulation results show that the proposed approach improves target CSI reconstruction performance compared to memoryless and weakly sequential baselines, particularly at low and moderate compression rates. These results suggest that explicit latent temporal modeling can provide an effective mechanism for CSI compression under limited feedback constraints.
arXiv:2504.17547v2 Announce Type: replace Abstract: Knowledge-based Vision Question Answering (KB-VQA) extends general Vision Question Answering (VQA) by not only requiring the understanding of visual and textual inputs but also extensive range of knowledge, enabling significant advancements across various real-world applications. KB-VQA introduces unique challenges, including the alignment of heterogeneous information from diverse modalities and sources, the retrieval of relevant knowledge from noisy or large-scale repositories, and the execution of complex reasoning to infer answers from the combined context. With the advancement of Large Language Models (LLMs), KB-VQA systems have also undergone a notable transformation, where LLMs serve as powerful knowledge repositories, retrieval-augmented generators and strong reasoners. Despite substantial progress, no comprehensive survey currently exists that systematically organizes and reviews the existing KB-VQA methods. This survey aims to fill this gap by establishing a structured taxonomy of KB-VQA approaches, and categorizing the systems into main stages: knowledge representation, knowledge retrieval, and knowledge reasoning. By exploring various knowledge integration techniques and identifying persistent challenges, this work also outlines promising future research directions, providing a foundation for advancing KB-VQA models and their applications.
arXiv:2606.16303v1 Announce Type: new Abstract: This paper introduces a learning-based control framework for real-time constrained optimal control of nonlinear systems with safety guarantees based on the Pontryagin's Minimum Principle. The approach learns a neural co-state (adjoint) policy that encodes optimality through the system Hamiltonian, rather than directly approximating a control law. Feasibility is enforced separately at runtime through an efficient convex projection that incorporates actuator limits and safety constraints expressed as control barrier functions. We refer to this framework as an adjoint-based neural regulator (ANR) as it yields a controller that satisfies constraints while retaining the optimality structure encoded by the learned adjoint. We demonstrate the effectiveness of the proposed framework on nonlinear constrained control tasks using a unicycle model. The ANR achieves performance at par with nonlinear model predictive control at more than two orders of magnitude lower computational cost, while exhibiting near-invariant performance across unseen scenarios, thus, significantly outperforming reinforcement learning methods in out-of-training-distribution regimes.
arXiv:2606.16668v1 Announce Type: cross Abstract: This paper introduces CraBERT, a pre-trained phoneme encoder (PPEnc) designed for efficient pre-training in text-to-speech (TTS). CraBERT employs a cascade-fusion architecture and a subword-phoneme alignment algorithm to integrate representations from a pre-trained subword-level BERT into a phoneme-level BERT. This design provides prior word- and sentence-level information, reducing the amount of pre-training required by the phoneme encoder. Subjective listening evaluations show that CraBERT achieves MOS values comparable to existing PPEncs after approximately one epoch of pre-training, whereas the baselines in our comparison are pre-trained for approximately ten epochs. These results demonstrate that CraBERT can efficiently learn representations suitable for improving the perceived naturalness and prosody of synthesized speech.
arXiv:2505.08461v3 Announce Type: replace Abstract: An optimal and robust low-order nonconforming finite element method is developed for the strain gradient elasticity (SGE) model in arbitrary dimensions. An $H^2$-nonconforming quadratic vector-valued finite element in arbitrary dimensions is constructed, which together with the Nitsche's technique, is applied for solving the SGE model. The resulting nonconforming finite element method is optimal and robust with respect to the Lam\'{e} coefficient $\lambda$ and the size parameter $\iota$, as confirmed by numerical results. Additionally, nonconforming finite element discretization of the smooth Stokes complex in two and three dimensions is devised.
arXiv:2602.09329v3 Announce Type: replace Abstract: Quality benchmarks are essential for fairly and accurately tracking scientific progress and enabling practitioners to make informed methodological choices. Outlier detection (OD) on tabular data underpins numerous real-world applications, yet existing OD benchmarks remain limited. The prominent OD benchmark AdBench is the de facto standard in the literature, yet comprises only 57 datasets. In addition to other shortcomings discussed in this work, its small scale severely restricts diversity and statistical power. We introduce MacrOData, a large-scale benchmark suite for tabular OD comprising three carefully curated components: OddBench, with 790 datasets containing real-world semantic anomalies; OvrBench, with 856 datasets featuring real-world statistical outliers; and SynBench, with 800 synthetically generated datasets spanning diverse data priors and outlier archetypes. Owing to its scale and diversity, MacrOData enables comprehensive and statistically robust evaluation of tabular OD methods. Our benchmarks further satisfy several key desiderata: We provide standardized train/test splits for all datasets, public/private benchmark partitions with held-out test labels for the latter reserved toward an online leaderboard, and annotate our datasets with semantic metadata. We conduct extensive experiments across all benchmarks, evaluating a broad range of OD methods comprising classical, deep, and foundation models, over diverse hyperparameter configurations. We report detailed empirical findings, practical guidelines, as well as individual performances as references for future research. All benchmarks containing 2,446 datasets combined are open-sourced, along with a publicly accessible leaderboard hosted at https://huggingface.co/MacrOData-CMU.
arXiv:2606.06646v2 Announce Type: replace Abstract: Formalizing complex reasoning from natural text is one of the central challenges in computational linguistics. It requires systems to understand not just keywords but also the context and complex reasoning embedded in a text. Current Argument Mining (AM) techniques identify basic claims and premises, yet they often struggle to capture the richer structural information required by advanced schemas such as the Carneades Argumentation Framework (CAF), which incorporates features such as premise types, proof standards, and argument schemes. We address this limitation by introducing CAF-Gen, an automated multi-agent framework designed to enrich shallow argument structures into CAF-compliant argument models. By employing an iterative Creator-Reviewer pipeline, a creator agent's output is validated by a critical agent to ensure structural integrity. This multi-agent collaboration is crucial for mitigating the structural instability typical of single-pass generative models. Our experiments demonstrate that the iterative feedback loop improves the quality of the resulting data and achieves strong alignment with the original annotations, while producing structurally richer models. Our findings show that the multi-agent system can overcome the limitations of single-pass generation, providing a robust methodology for the automated modeling of formal argumentation.
arXiv:2606.15442v1 Announce Type: cross Abstract: We design a new unconstrained coordinate system where a $p\times p$ symmetric positive definite (SPD) matrix $\Theta$ is represented by a reverse telescoping map $\Theta(x)=\rm{RT}(x)$, with $x=(v,d,r)\in\mathbb{R}\times\mathbb{R}^{(p-1)}\times\mathbb{R}^{p(p-1)/2}$, representing respectively the log volume or log determinant; and the shape, as encoded by log relative diagonal scales and partial covariances among the nodes. This construction results in important properties not available in other charts, e.g., matrix logarithm, such as Jacobian depending on only the log-determinant. A useful feature of our construction is $x$ contains a lossless symbolic representation of both the matrix and its inverse. Many important computations involving a matrix and its inverse can be performed in $O(p^2)$ in the transformed domain, while it is the rendering of results in matrix forms (on demand) that must incur an $O(p^3)$ cost. Moreover, two unit-determinant matrices in the transformed domain can be joined by a straight line with pathwise unit determinant. For generative modeling, this allows designing a split volume-shape flow model trained by conditional flow matching for transporting the shape over the unit-determinant path, with a separate one-dimensional flow for transporting the volume or the determinant. The forbidding SPD constraint, tamed thus into a powerful guiding force, leads to the surprising insight that it is in some sense easier to design a volume-normalized shape flow for SPD compared to the unconstrained $\mathbb{R}^{p\times p}$, with no intrinsic notion of volume to aid normalization, unlike the determinant of SPD matrices. We apply our construction for up to $p=200$ in generative modeling of SPD matrices on a difficult synthetic bimodal target, and in generating brain connectivity networks by models trained on fMRI data; as well as in intrinsic diffusion on the SPD manifold.
arXiv:2606.15454v1 Announce Type: cross Abstract: Speech deepfake detection is predominantly treated as an opaque classification task where all temporal frames are aggregated equally. This ignores that different phonetic categories carry vastly different amounts of discriminative information. To address this, we propose a phoneme-guided cross-attention framework that transforms detection into an interpretable, phonetically grounded process. We factorize the spoofing posterior $P(\text{spoofed}\mid X, W)$, conditioned on the acoustic representation $X$ and the phonetic posteriorgram $W$. The resulting factorization can be written as $P(\text{spoofed} \mid X, W) = \sum_{i=1}^{M} w_i \cdot P(\text{spoofed} \mid X, Z = z_i)$, where $M$ denotes the number of phonetic classes, $P(\text{spoofed} \mid X, Z = z_i)$ is the spoofing probability for the $i$-th phonetic class $z_i$ conditioned on $X$, and each $w_i$ is the prevalence of phonetic class $z_i$ in the utterance. Our transformer-based architecture instantiates this through a cross-attention block in which phonetic queries selectively probe information in acoustic keys and values, with softmax-normalized pooling supplying explicit phone-presence weights. Unlike prior approaches that rely heavily on post-hoc explainability methods, our framework offers phonetic-explainability-by-design. We evaluate the framework on an LJSpeech-derived corpus, ASVspoof 2019 LA, and ASVspoof 5 Track 1. Per-phone importance rankings reveal that discriminative power concentrates on articulatory categories that generative models struggle to reproduce faithfully. Stops, fricatives, affricates, nasals, and silence-boundary closures rank most discriminative, while periodic vowels and semivowels rank lower. Beyond competitive performance, our model provides structural interpretability, yielding an inspectable per-articulatory category breakdown of the final verdict.
arXiv:2405.07636v3 Announce Type: replace-cross Abstract: We derive conditions for the identifiability of nonlinear networks characterized by additive dynamics at the level of the edges when all the nodes are excited. In contrast to linear systems, we show that the measurement of all sinks is necessary and sufficient for the identifiability of directed acyclic graphs, under the assumption that dynamics are described by twice continuously differentiable functions without constant terms (i.e., $f(0)=0$). But if constant terms are present, then the identifiability is impossible as soon as one node has more than one in-neighbor. In the case of general digraphs that may contain cycles, we consider additively separable functions for the analysis of the identifiability, and we show that the measurement of one node of all the sinks of the condensation digraph is necessary and sufficient. Several examples are added to illustrate the results.
arXiv:2606.15459v1 Announce Type: cross Abstract: The DART impact on Dimorphos produced a large population of low-velocity ejecta, likely containing most of the excavated mass, whose early fate remains poorly constrained. We investigate the first 22 h evolution of ejecta launched at 1-9 cm/s with RAVEL, a custom-developed code that couples three dimensional orbital dynamics in the Didymos-Dimorphos system with post-impact surface transport, including re-impact, rebound, frictional sliding, and detachment. Re-accretion is rapid and asymmetric: more than 99% of the re-accreted mass returns to Dimorphos within 5 h. The slowest ejecta remain concentrated near the DART crater and dominate the primary ejecta blanket, whereas faster particles undergo orbital transport and preferentially populate antipodal and trailing regions. Surface motion strongly modifies the first-contact pattern, and the DART-derived rough terrain model produces ray-like deposits controlled by local topography and dominated by the slowest ejecta. These results provide testable predictions for ESA's Hera mission and link ejecta-blanket morphology to orbital dynamics and surface mechanical response.
arXiv:2308.06035v4 Announce Type: replace Abstract: Humans routinely draw on visual context to predict upcoming words. To what extent current vision-language models produce comparable behaviour is unclear. Here we placed five state-of-the-art pretrained systems side-by-side with 600 human participants in a web-based Visual-World Paradigm. On each of 100 six-second movie clips, models and participants received either text only or synchronised video and text and judged how likely a specified target word was to appear next; human eye movements were tracked throughout. Adding visual context increased model-human alignment in predictability ratings across all architectures (average Delta r = 0.18) with no impact of parameter size. When visual context was informative, transformer attention significantly increased alignment. Attention maps from two transformer models corresponded with human gaze, explaining up to 70% of the inter-participant variance when the scene contained informative cues. Notably, cross-modal attention reliably tracked anticipatory human fixations on semantic cues. These results suggest that current transformer-based vision-language models can approximate human behaviour exploiting visual context during language prediction - and that selective attention to informative cues, not sheer model scale, is the principal driver of this alignment.
arXiv:2606.15522v1 Announce Type: cross Abstract: Self-driving laboratories (SDLs), where artificial intelligence proposes subsequent experiments and robotic systems execute them, are rapidly becoming the vanguard of materials discovery. A critical bottleneck, however, lies in seamlessly bridging diverse AI algorithms tailored for specific exploration goals with the heterogeneous robotic hardware found across different laboratories. Here, we present NIMO, an open-source software platform designed to dissolve this barrier through three core paradigms: a modular AI-robot decoupling mediated via simple CSV file exchange, a discrete candidate-pool architecture that seamlessly absorbs domain knowledge, and a unified Python interface pre-loaded with twelve distinct AI algorithms. In this Perspective, we review the operational principles of each algorithm alongside six diverse SDL implementations driven by NIMO, covering electrolyte discovery, organic synthesis, thin-film exploration, fuel-cell process informatics, coffee-ring phase exploration, and legacy liquid-handling automation. One of these also demonstrates NIMO's seamless interoperability with the IvoryOS orchestration framework. To democratize autonomous science, we also introduce a no-code desktop application that enables intuitive, human-in-the-loop exploration for non-programmers. NIMO is freely available at https://github.com/NIMS-DA/nimo, offering a versatile, plug-and-play foundation to accelerate autonomous materials exploration across diverse experimental landscapes.
arXiv:2606.15555v1 Announce Type: cross Abstract: In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with every generated token. Under high concurrency, aggregate memory usage therefore increases endogenously over time: the service process itself creates future capacity pressure. When memory capacity is exceeded, systems evict active requests, discarding cached state and restarting them later, which wastes computation and reduces throughput. We develop a discrete-time dynamical model of memory-constrained LLM inference that captures admission, memory growth, and eviction under continuous batching. In the saturated-input regime, the system admits both eviction-free fixed points and limit cycles with evictions. For homogeneous workloads, we show that the eviction-free equilibrium is unstable and that, except for a Lebesgue-measure-zero exact-capture set, the system converges to a unique worst-case limit cycle that is asymptotically stable outside this exceptional set, with throughput losses as large as 50%. For heterogeneous workloads, we prove a stability criterion in the two-class common-input setting and explain how the survival-polynomial mechanism generalizes to multiple classes and heterogeneous-input lengths. Under an input-dominated scaling regime, coprime decoding lengths stabilize the eviction-free equilibrium, while non-coprime lengths create synchronized modes that drive instability. These results characterize when workload heterogeneity desynchronizes completions and helps stabilize memory-constrained serving. More broadly, we identify service-induced congestion as a structural instability mechanism and derive scheduling design principles for sustaining high throughput.
arXiv:2606.15580v1 Announce Type: cross Abstract: Block copolymers self-assemble into ordered nanostructures whose geometry is governed by a competition between interfacial energy and chain conformational entropy. While this competition produces a rich sequence of morphologies, topologically complex ``frustrated'' phases such as the primitive cubic ($Im\bar{3}m$) network incur severe packing penalties and are difficult to access in neutral systems. Here we show that ions functionalized at the termini of one block in an AB diblock copolymer melt introduce a qualitatively new stabilization mechanism. Strong ion correlations drive chain-end association and generate a curvature preference toward the charged domain; the resulting tendency of end-localized ion clusters to adopt compact, curved geometries selectively favors the highly frustrated $Im\bar{3}m$ single-network over the classical phases, in a region of parameter space lying below the order-disorder transition of the neutral system. Free energy decomposition reveals that the electrostatic energy, arising almost entirely from beyond-mean-field ion correlations, becomes increasingly negative with increasing interfacial curvature. In the primitive cubic network, pronounced local segregation of ions into the cylindrical struts generates compact curved clusters whose correlation energy gain more than offsets the enhanced packing frustration, so the very geometry that is the source of packing frustration in neutral systems becomes the source of its stability here. Increasing ion size weakens correlations and suppresses the $Im\bar{3}m$ phase, consistent with experimental observations. Our results establish curvature-selective end-group association as a general principle for accessing frustrated topologies in block copolymer systems.
arXiv:2602.12279v2 Announce Type: replace Abstract: Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especially those involving complex spatial compositions, multiple interacting objects, or evolving instructions, require decomposing instructions, verifying intermediate results, and making iterative corrections. While test-time scaling (TTS) has demonstrated that allocating additional inference compute for iterative reasoning substantially improves language model performance, extending this paradigm to unified multimodal models remains an open challenge. We introduce UniT, a framework for multimodal chain-of-thought test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds. UniT combines agentic data synthesis, unified model training, and flexible test-time inference to elicit cognitive behaviors including verification, subgoal decomposition, and content memory. Our key findings are: (1) unified models trained on short reasoning trajectories generalize to longer inference chains at test time; (2) sequential chain-of-thought reasoning provides a more scalable and compute-efficient TTS strategy than parallel sampling; (3) training on generation and editing trajectories improves out-of-distribution visual reasoning. These results establish multimodal test-time scaling as an effective paradigm for advancing both generation and understanding in unified models.
arXiv:2606.15581v1 Announce Type: cross Abstract: We study the graph alignment problem for correlated Gaussian Orthogonal Ensemble (GOE) matrices, where the goal is to recover a hidden vertex permutation given two correlated symmetric Gaussian matrices $(A, B)$ with correlation $1/\sqrt{1+\sigma^2}$. While the maximum likelihood estimator is information-theoretically optimal, its computation, which reduces to a quadratic assignment problem, is intractable. Motivated by this, we analyze convex relaxations based on minimizing $\|AX - XB\|_F$ over the set of doubly stochastic matrices and the unit hypercube. We show that when the correlation parameter satisfies $\sigma = o(n^{-1/2}/\log^4 n)$, the solution of either relaxation $(X^\star)$ concentrates around the ground-truth permutation matrix $(\Pi^\star)$, i.e., $\|X^\star-\Pi^\star\|_F^2 = o(n)$, implying recovery of all but a vanishing fraction of vertices after simple post-processing. Combined with existing lower bounds, our results precisely characterize that $\|X^\star-\Pi^\star\|_F^2$ transitions from $o(n)$ for $\sigma = \tilde{o}(n^{-1/2})$ to $\Omega(n)$ for $\sigma = \tilde{\Omega}(n^{-1/2})$. In doing so, our analysis significantly tightens prior results and extends them beyond doubly stochastic relaxations.
arXiv:2606.15586v1 Announce Type: cross Abstract: Quantum illumination provides a quantum advantage in detecting weakly reflecting objects embedded in a noisy environment, even when environmental noise destroys most of the initial entanglement. We investigate this advantage using Haar-random probe states constrained to symmetry-resolved subspaces. Employing tools from quantum channel discrimination and asymptotic hypothesis testing, we derive the discrimination exponents associated with Haar-random probe ensembles and identify the role of symmetry in determining their performance. We show that typical states drawn from fixed-charge sectors achieve the same asymptotic quantum-illumination advantage as maximally entangled probes. In particular, we show that the effective thermal-noise suppression and the corresponding Chernoff exponent are governed by the dimension of the accessible symmetry sector. Our results reveal that the operational resource underlying quantum illumination can be generalized from fine-tuned structure of a specific probe state to the existence of a large symmetry-protected correlation subspace. These findings establish a direct connection between quantum illumination, symmetry-resolved typicality, and quantum channel discrimination, and demonstrate that near-optimal quantum hypothesis testing resources can emerge naturally from generic many-body quantum states constrained by conservation laws.