arXiv:2607.11300v1 Announce Type: new
Abstract: Moir\'e structure emerging in photonic bilayers stacked with a twist enables the controllable frequency selective resonant response. Here, we employ twist tunable resonances to boost second harmonic generation (SHG) at a desired frequency in twisted photonic bilayers integrated with two-dimensional nonlinear crystals. We develop an analytical theory relating the resonance frequencies and the SHG enhancement factor to the material parameters of the dielectric layers and the twist angle. The theory reveals a critical twist angle separating two distinct regimes of photonic bilayer operation: with open and closed moir\'e diffraction channels. Above the critical angle, the photon leakage from the guided mode is suppressed and the SHG enhancement factor rises by orders of magnitude. The paper offers a compact route to nonlinear conversion in moir\'e photonic structures efficient and tunable over a wide spectral range.
Science Journals
arXiv:2607.10400v1 Announce Type: new
Abstract: Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such as length, layout complexity, modality, and question difficulty, which makes it difficult to attribute model failures to specific causes. We introduce SynthDocBench, a fully synthetic benchmark for long-context visual document understanding that systematically controls factors including document length, layout structure, modality composition, and question type. The benchmark is constructed using a combinatorial design, each factor is varied independently across generated documents, enabling controlled analysis of model behavior. Documents are generated end to end using an LLM pipeline across six layout archetypes, with a 40 percent random override to prevent models from exploiting spurious correlations. Additionally, SynthDocBench spans long-context documents with substantially greater length and structural diversity than existing benchmarks. Evaluating seven frontier VLMs, we uncover three failure modes that existing benchmarks cannot surface: sharp degradation with document length, a systematic positional sensitivity in which the middle third of a document is hardest for five of six models and five of six models show a negative Early-to-Late trend (steepest decline: 8.3 percentage points), and breakdown of chart comprehension in long-document settings. These results suggest that current models may be overfitting to benchmark artifacts rather than achieving robust long-context visual document understanding.
arXiv:2607.11070v1 Announce Type: new
Abstract: Modern large language models (LLMs) operate in interactive multi-turn settings, making multi-turn jailbreaking a realistic threat model and an important setting for automated red teaming. A core challenge in learning multi-turn jailbreak attackers is credit assignment: different turns contribute differently to the final outcome, yet existing learning signals are often too coarse to identify their individual contributions. We propose decomposed credit GRPO (DC-GRPO), a unified turn-level credit assignment framework for Group Relative Policy Optimization in multi-turn jailbreak learning. DC-GRPO assigns a separate group-relative learning signal to each turn by combining immediate and future credit, avoiding the credit misassignment induced by broadcasting a single trajectory-level score across the dialogue. We instantiate this framework with static and dynamic weighting rules that differ in how the two credit sources are balanced while sharing the same turn-level structure. Across multiple victim LLMs and benchmarks, the dynamic- and static-weighted variants achieve average ASR5@3 scores of 98.26% and 97.88%, respectively, substantially outperforming the state-of-the-art methods, including SEMA (86.58%) and TROJail (86.23%). Their consistently strong performance indicates that the central empirical benefit comes from turn-level group-relative credit assignment rather than a particular weighting rule. Warning: This paper contains examples of harmful content.
arXiv:2607.11087v1 Announce Type: new
Abstract: Energy is a binding constraint for AI scaling, yet it lacks the formal treatment that computation, communication, and learning have long enjoyed. Recent systems demonstrate large energy savings, but each targets a specific granularity and structure; one cannot combine frequency scaling from one system with critical-path analysis from another and reason about their joint effect on total energy. Energy remains a monolithic scalar that is measured after the fact and optimized with point solutions that do not generalize.
We propose energy calculus, a compositional algebra that treats energy as a first-class primitive. It builds on energy elements, units of computation whose energy we can reliably measure, each carrying an energy signature that comprises its time, its static and dynamic energy, the hardware operating point and execution context under which we measured it, and the associated measurement uncertainty. Three operators (sequential, same-device parallel, and cross-device parallel) compose signatures along the same structure as the computation itself, covering arbitrary DAG-structured executions. The algebra rests on seven axioms that capture how hardware consumes energy, and it exhibits two properties distinctive to energy among computing resources: sequential composition commutes only when elements are mutually context-insensitive, and sequential composition does not distribute over parallel composition. We also present a Reduction Theorem that recovers simple context-independent algebra whenever interactions fall below measurement uncertainty, so practitioners pay for context dependence only where the physics demands it. Uncertainty propagates through every composition, so each prediction carries an error bound. Finally, we show that the same operators extend from energy totals to time--energy Pareto frontiers, so reasoning about tradeoffs composes with the same algebra.
arXiv:2607.11072v1 Announce Type: new
Abstract: The double-sided power supply railway system increases the simultaneous operation of vehicles on the grid, potentially causing system instability and oscillation overvoltage issues. As vehicles frequently switch operating points during operation, it is essential to analyze system stability across a wide range of conditions. Therefore, accurately identifying the black-box impedance of vehicle converters at multiple operating points is crucial for studying railway vehicle-grid system stability. However, traditional impedance identification methods require extensive data and lack interpretability, leading to significant computational and data burdens. This study introduces an interpretable residual feedforward neural network (ResFNN) combined with SHapley Additive exPlanations for training vehicle impedance models, reducing data requirements while maintaining accuracy. Additionally, a component connection method is proposed for deriving the impedance matrix of a multivehicle railway system under the double-sided feeding mode. This method incorporates the dynamic mobility of vehicles and their positional distribution, and it utilizes the ResFNN to identify impedance for stability analysis. Real operational data from actual railway lines is used as case study to analyze the stability of the double-sided power supply railway system. The results demonstrate that this approach accurately assesses both lowfrequency and high-frequency instability issues.
arXiv:2607.11208v1 Announce Type: new
Abstract: The VeloAlpha System Code (VSC) is a computational framework for zero-dimensional fusion power-balance studies across five magnetic-confinement configurations: tokamaks, magnetic mirrors, field-reversed configurations (FRCs), dipoles, and stellarators. A common power-balance formulation connects fusion production, charged-particle deposition, radiation, transport loss, external heating, and fusion gain, while each configuration retains its own geometry, profile weights, confinement model, and operating constraints. The same solver interface supports both single-point calculations and two-dimensional plasma operating contour (POPCON) scans, producing fusion and heating powers, gain, radiation and transport losses, geometry quantities, and configuration-specific validity indicators. VSC therefore makes it possible to study how assumptions about density, temperature, magnetic field, confinement, and geometry shape the accessible operating space of different fusion concepts within one traceable framework. By combining reduced-order physics models with a unified computational platform, VSC enables rapid assessment and comparative analysis of candidate fusion reactor concepts during the early design stage.
arXiv:2607.11472v1 Announce Type: new
Abstract: Perceptual hash algorithms (PHAs) are widely deployed to detect image forgery under benign transformations, yet their robustness against adversarially chosen perturbations remains poorly understood and rarely comes with provable guarantees. We propose a novel evolutionary framework based on GigaEvo and OpenEvolve for targeted second-image attacks on perceptual hash algorithms. We assess attack performance using a composite score that jointly accounts for the fraction of adversarial images whose normalized Hamming distance to the target hash falls below threshold p (Attack Success Rate), the number of queries issued to the hash function, and the L2 distortion relative to the original image. Experiments on four deployed PHAs (pHash, PDQ, PhotoDNA, NeuralHash) across 30 ImageNet image pairs demonstrate that our evolutionary approach achieves comparable or better ASR than existing black-box baselines using substantially fewer queries to the hash function, while simultaneously producing adversarial images with lower L2 distortion relative to the originals. The best evolved programs reduce the pre-defined composite attack score relative to the best optimized seed by 41.2% for NeuralHash, 38.3% for PDQ, 34.0% for pHash, and 8.1% for PhotoDNA. Unlike gradient-based methods, our framework requires no internal knowledge of PHA architectures and naturally handles the non-differentiable, discretized nature of hash outputs. These results reveal previously unreported vulnerabilities in widely deployed content-moderation pipelines and motivate the development of provably robust perceptual hashing 1schemes.
arXiv:2607.11197v1 Announce Type: new
Abstract: When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-level variation may reflect distinct latent planning competencies rather than differences along a single ability spectrum. We study this question on ACPBench-Hard by evaluating multiple LLM families under varying test-time reasoning budgets and applying a multidimensional item response theory model to uncover the latent competency structure underlying LLM planning. The analysis reveals two principal dimensions that shape planning performance: operational reasoning, the ability to evaluate local action applicability and immediate state transitions, and structural enumeration, the ability to reason about goal reachability and landmark structure. Operational reasoning improving under model scaling and longer reasoning traces, while structural enumeration remains comparatively insensitive. Our findings motivate competency-level evaluation of LLM planning, shifting the focus from whether models improve overall to which planning competencies improve, under what conditions, and why.
arXiv:2607.11205v1 Announce Type: new
Abstract: Image matting is highly ill-posed, especially when both the foreground and background are richly textured. While single-image matting methods learn strong priors from data, they often struggle on these challenging cases. Existing approaches improve results by requiring additional signals such as green screens, polarized lighting, or clean background images, but these typically rely on specialized capture setups. We present Parallax Portrait Matting, a practical two-frame matting method that uses a second image captured with slight viewpoint change. Such a setting arises naturally in burst photography, where small camera motion induces foreground-background parallax and provides complementary observations for matting. Our pipeline estimates trimaps and foreground/background motion, then constructs aligned views for prediction. To handle imperfect motion estimation, the network uses the background-aligned pair for direct fusion and the foreground-aligned cue through cross-attention for error compensation. Experiments show that our method recovers finer details and more accurate foreground colors than strong single-image matting baselines on challenging portrait cases.
arXiv:2607.11615v1 Announce Type: new
Abstract: Runtime logs are an important source of information that supports software maintenance. To obtain useful logs, developers spend significant effort identifying appropriate log locations, assigning correct severity levels, and writing concise yet informative messages. Therefore, end-to-end automated log statement generation can help reduce this burden, and prior work has proposed many methods for this task. However, existing methods still exhibit limited accuracy. To address this problem, we propose ThinkLog, an LLM-based end-to-end log statement generation method. The core idea of ThinkLog is to incorporate reasoning that helps LLMs make decisions about log insertion, severity level assignment, and message generation, thereby improving log statement generation accuracy. ThinkLog injects reasoning into prompts as few-shot examples and guides LLMs to generate appropriate log statements. Evaluated on 9,619 Java methods extracted from public GitHub repositories, ThinkLog achieves 20.55% log statement generation accuracy, representing a 15.4% improvement over the best existing method. Moreover, these improvements were achieved at approximately 50% of the inference cost (USD) compared to the best existing method. These results show that leveraging reasoning is an effective and cost-efficient way to improve the accuracy of end-to-end log statement generation.
arXiv:2607.11635v1 Announce Type: new
Abstract: In fixed-budget best-arm identification, also known as ranking and selection, an algorithm has a sampling budget to distribute across $K$ arms. Each sample provides noisy feedback about that arm's mean, and the goal is to identify the arm with the largest mean. A common performance benchmark is the static oracle: a non-adaptive strategy that knows the means in advance and chooses fixed sampling proportions to maximize the exponential decay rate of the probability of incorrect identification. Several adaptive algorithms have been constructed such that their sampling proportions converge to the static oracle proportions. However, it has remained open whether any algorithm could match the static oracle's error decay rate uniformly across all problem instances. We answer this in the negative. For any $K\ge 3$ and for rewards drawn from any one-parameter natural exponential family, we show that for any algorithm, there is at least one instance where the error decay rate is at most $\left(1 + \frac{\log(K)}{8}\right)^{-1}$ times that of the static oracle. This also answers the open question posed by Qin (2022), showing that fixed-budget best-arm identification does not admit a complexity.
arXiv:2607.10684v1 Announce Type: new
Abstract: Few-shot spheroid segmentation must adapt to new cell lines, microscopes, and illumination conditions from only a small set of annotated images. While foundation few-shot segmenters can be accurate, their large opaque backbones make it difficult to understand which visual cues drive success or failure. We study this question with HyperBank, a differentiable bank of classical image-processing operators combining Frangi vesselness, a Sauvola threshold pyramid, structure-tensor responses, gradient magnitude, and Laplacian-of-Gaussian filters. HyperBank is fitted on the annotated support images and evaluated on disjoint held-out images across three independently acquired spheroid datasets. We treat it not as a general replacement for foundation models, but as a compact, interpretable few-shot microscopy pipeline and an analytic-prior probe of which classical cues carry the few-shot signal. The results show that, adapted on the same few annotated support images, a compact bank of analytic priors is competitive with, and on small-cluster, contrast-driven data can outperform, much larger foundation models, while those models remain stronger on externally sourced, texture-dominated spheroids. Leave-one-family-out ablations indicate that the useful few-shot signal is distributed across operator families and strengthened by support-set-tuned morphology.
arXiv:2607.11230v1 Announce Type: new
Abstract: Recently, Bumpus, Downey, Eagling-Vose, Enright, Fellows, Kutner, Larios-Jones, Martin, Rosamond, and Yates defined Truly Linear FPT (TLFPT) to be the class of parameterized problems with algorithms running in time $O(n) + f(k)$, where $n$ is the input size and $k$ the parameter [arXiv:2606.02492]. They gave several algorithmic techniques for designing TLFPT algorithms, but left parameterization by treewidth open.
In this paper, we give a general method for designing TLFPT algorithms parameterized by treewidth, solving three open problems posed by Bumpus et al. In particular, we give a TLFPT algorithm for Courcelle's theorem: We show that given an $n$-vertex $m$-edge graph $G$, an integer $k$, and a $\mathsf{CMSO}_2$-formula $\varphi$, we can in time $O(n+m) + f(k, \varphi)$ either conclude that the treewidth of $G$ is more than $k$, or check whether $G$ satisfies $\varphi$. As a part of our algorithm, we give an approximation algorithm for treewidth that runs in time $O(n+m)$ and returns a tree decomposition whose width is at most $2^{O(k)}$ times the optimum. Our result also implies a TLFPT algorithm for computing the value of treewidth exactly.
arXiv:2607.11653v1 Announce Type: new
Abstract: Black-box conditional quantile forecasts are widely used for sequential decisions under asymmetric costs, such as inventory planning in supply chain management. Once deployed, such forecasters must be monitored continuously as data streams drift and regimes change; this invalidates standard, fixed-horizon backtests for calibration. Further, existing backtests do not take into account that the notion of calibration is, in fact, information-dependent: forecasts can look calibrated to an auditor with coarse information while being miscalibrated to an auditor with richer information. We develop a distribution-free and game-theoretic testing framework for continuously auditing black-box conditional quantile forecasters with non-i.i.d. losses, such that the resulting evidence process is powerful against predictably chosen alternatives specified by the features available to the auditor. We first formalize notions of conditional quantile calibration when different sets of features are available to the auditor, establishing that the coarseness of the auditor's information set determines the hardness of the testing problem. We then identify the sets of alternatives for which the auditor can achieve power, and focusing on contextual bets linear in the features, we derive finite-time detection guarantees for such alternatives, all without an i.i.d. assumption. The resulting evidence processes are interpretable at the feature level, as they quantify fine-grained, "feature-aware" evidence for miscalibration. We empirically validate these methods on simulated and real data, finding that a popular time series forecaster (Chronos-2) is highly miscalibrated w.r.t. multiple relevant features.
arXiv:2607.10223v1 Announce Type: new
Abstract: Plug-and-Play (PnP) methods have emerged as a highly effective paradigm for solving imaging inverse problems by replacing traditional proximity operators of regularization terms with highly expressive deep denoisers. While empirically successful, establishing rigorous convergence guarantees for PnP algorithms remains a major challenge. Existing provable approaches based on the Gradient-Step (GS) denoiser suffer from theoretical and practical limitations, such as restrictive bounds on the regularization parameter, rigid step-size rules, and the inability to handle nonconvex data-fidelity terms. In this paper, we introduce PnP-IPA (Plug-and-Play Inexact Proximal Algorithm), a novel optimization scheme that overcomes these bottlenecks. We propose a new splitting strategy that evaluates the proximal operator of the scaled implicit regularizer inexactly. To enable adaptive step-size selection without exact objective evaluations, we design a novel surrogate merit function that successfully drives an Armijo-like backtracking line-search. Relying on the Kurdyka-Lojasiewicz property, we establish global convergence to a stationary point of the nonconvex objective without imposing any assumption on the regularization parameter. Extensive numerical experiments on image deblurring under both Gaussian and Cauchy noise demonstrate the practical advantages of PnP-IPA. By effectively lifting previous theoretical constraints, our method allows for optimal parameter tuning, yielding state-of-the-art restoration quality and robust convergence even in nonconvex regimes.
arXiv:2607.10695v1 Announce Type: new
Abstract: The rapid advancement of generative artificial intelligence (AI) has made synthetic images remarkably realistic, posing security threats such as misinformation and fraud. It is significant to detect the synthetic image in the manner of passive and blind image authentication. Most existing detectors rely on supervised training with large labeled datasets, leading to high costs and degraded performance on unknown generative models. To attenuate such deficiencies, we propose a training-free detection method. Specifically, noise residual fingerprints are first extracted by a simple yet effective pre-trained Noiseprint++ model. Then multi-scale features are further extracted from such residual by a frozen Vision Transformer (ViT), followed by adaptive weighted fusion. Only a few real image samples are used needed to initialize the clustering centers for unsupervised K-Means, distinguishing real and synthetic images without training. Extensive evaluations on four benchmark datasets show that our proposed scheme achieves an average accuracy of 82.2%, outperforming the state-of-the-art detectors on generalization ability. Superior performance is gained on the popular diffusion type of synthetic images, and the effectiveness of each module is validated by ablation studies. Source code will be publicly available at https://github.com/multimediaFor/NoiseCluSID.
arXiv:2607.10752v1 Announce Type: new
Abstract: Simultaneous detection of the spectral and polarization properties of light is highly desirable for integrated imaging and photonic technologies but typically requires complex multi-component architectures. Here, we demonstrate that the intrinsic dielectric anisotropy of layered insulating CrCl3 enables ultrabroadband polarization-resolved photodetection spanning wavelengths from 300 to 1700 nm. The photoresponse is governed by long-lived ligand-field excitons, whose microsecond-scale lifetime produces a photoconductive gain exceeding 4.5 x 10^4. By combining wavelength-, polarization-, and angle-resolved optoelectronic measurements, we reveal that distinct ligand-field and higher-energy excitonic transitions possess different optical dipole orientations, leading to excitation-energy-dependent rotation of the in-plane polarization axis. Furthermore, oblique illumination activates out-of-plane optical dipoles, while competing excitonic transitions with distinct dipole orientations drive wavelength-dependent rotation and reversal of the polarization anisotropy. Together, these effects produce a highly tunable degree of polarization ranging from -90% to +75%, establishing intrinsic three-dimensional vectorial light-matter interactions in a layered magnetic van der Waals insulator. These findings establish dielectric anisotropy and excitonic dipole engineering as powerful design principles for compact ultrabroadband polarization-sensitive photodetectors and multifunctional van der Waals photonic systems.
arXiv:2607.10887v1 Announce Type: new
Abstract: Machine learning interatomic potentials (MLPs) have revolutionized atomistic modeling, offering the potential to replace traditional methods like Density Functional Theory (DFT). However, inference time of MLPs is orders of magnitude slower than that of classical force fields, hindering real-world applications for biomolecular systems that require timescales of microseconds and beyond. Implicit solvent MLPs can address this issue, but are faced with data challenges associated with coarse-grained modeling. Consequently, previous approaches relied on empirical force field data, thereby inherently limiting the MLP's accuracy. Here, we introduce the Transferable Water Implicit Network (TWIN), an implicit water MLP parametrized entirely by an Equivariant Graph Neural Network and trained solely on ab initio and experimental labels. We demonstrate TWIN's transferability across drug-like molecules, peptides, and proteins, achieving excellent results on ab initio and experimental crystallographic and NMR benchmarks, consistently outperforming previous machine-learning-based implicit solvent or coarse-grained models. Furthermore, TWIN closely matches DFT-based explicit solvent MLPs while providing a two-order-of-magnitude faster timestep evaluation, paving the way for efficient ab initio-level modeling of biomolecular systems in aqueous environments.
arXiv:2607.10898v1 Announce Type: new
Abstract: Self-supervised data splitting has emerged as a promising paradigm for sparse-view CT reconstruction, enabling training from incomplete measurements without fully sampled ground truth. However, the influence of key design choices, including partitioning strategy, preprocessing, and inference, remains insufficiently understood. In this work, we introduce a unified framework that decomposes splitting-based reconstruction into these three components, enabling controlled comparison of existing methods and two incremental extensions: multi-partition splitting and an alternative inference strategy. Experiments on simulated LoDoPaB-CT data under independent and correlated noise, together with validation on the real-world 2DeteCT dataset, show that the optimal partitioning strategy strongly depends on the measurement noise structure. Lattice-based splitting performs favorably under independent noise, whereas angular masking is more robust under correlated noise and real measured data. Multi-partition splitting consistently improves over pure projection-wise splitting in several settings. Complementary perceptual and structural metrics, including LPIPS and HaarPSI, reveal differences between masking strategies that are less apparent from PSNR and SSIM alone. These results provide practical guidelines for designing self-supervised sparse-view CT reconstruction methods and highlight the limitations of common independence assumptions in realistic imaging environments.
arXiv:2607.10909v1 Announce Type: new
Abstract: Recently, large pretrained multimodal embedding models such as Qwen3-VL Embedding have shown strong promise for sequential recommendation, as they provide reusable semantic item representations across modalities and domains. However, directly using these embeddings often leads to suboptimal performance because of domain misalignment. Efficient side adaptation is therefore an attractive solution. Although adapting all backbone layers should help, existing side adapters often degrade with depth, prompting layer dropping despite the loss of useful hidden states. This is due to two major challenges: (1) the lack of modeling in selecting fused representations during residual addition, and (2) the insufficient preservation of earlier representations during progressive sigmoid fusion. This paper therefore asks a practical question: How can we design a side adaptation approach that effectively unlocks the potential of large pre-trained multimodal embedding models?
To address this question, we propose Stresa, a stream-aware side-adaptation framework for frozen large pre-trained multimodal embedding models in sequential recommendation. Stresa introduces Stream-aware Hidden-Adapter Fusion (SHAF) to preserve historical side memory during fusion and Residual Stream Adapter (ReSA) to produce selective residual updates across layers. Empirically, Stresa consistently outperforms standard side adapters and state-of-the-art baselines on public datasets across multiple backbone embedding models. These results highlight the promise of adapting large embedding models for sequential recommendation. Our code is publicly available at https://github.com/GAIR-Lab/Stresa.
arXiv:2607.11004v1 Announce Type: new
Abstract: We present a manipulation planning system based on affordance recognition and action effect prediction. The system reasons through possible futures in visual form, and evaluates candidate plans by agreement of predicted outcomes with text-based goals set at run-time, using a multi-modal goal-matching module. Positions of objects named in the goal text are tracked through predictions even when occluded, making it possible to generate action plans even when objects become occluded, or when their initial descriptors cease to identify them in future states. We further expand the system with an image conversion module for translating real-world state images with objects of varied shapes and visual appearances into a consistent visual appearance, to facilitate manipulation planning in a physical robot setup. We evaluate performance of the system's modules in isolation and demonstrate the integrated system's manipulation planning capabilities on a set of challenging tasks in both simulation and on hardware.
arXiv:2607.11654v1 Announce Type: new
Abstract: Direct human interaction with autonomous UAV systems can be enabled through modalities such as speech, gestures, and graphical interfaces. However, interpreting such inputs as directly executable commands introduces safety risks in dynamic environments. Operator requests may conflict with terrain constraints, inter-UAV separation requirements, or flight-envelope limitations. In this paper, we present a requirements-governed maneuver-response model that mediates multi-modal human intent into safe UAV maneuvers by treating operator inputs as bounded maneuver requests rather than direct commands. Requested maneuvers are mapped to constrained motion primitives and processed through a structured request-evaluate-execute pipeline. Each request is interpreted with associated confidence, validated against terrain, separation, workspace, and flight-envelope constraints, and either constrained, rejected, or executed under continuous runtime monitoring. We further formalize the approach as a requirements-based specification model in which maneuver primitives are associated with explicit preconditions, invariants, guard conditions, and postconditions governing admissibility, execution safety, and emergency handling. These requirements support runtime verification and future reactive synthesis approaches. We present an initial lab-based validation demonstrating that voice and GUI-based inputs can be reliably interpreted and safely executed as constrained maneuver requests.
arXiv:2607.10661v1 Announce Type: new
Abstract: Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically relies on auxiliary draft modules, incurring significant training and communication overhead. Although recent methods attempt to generate drafts within the target model itself, they often fail to fully exploit its latent parallel capacity due to a lack of structural coordination. In this paper, we propose \textbf{Progressive Tree Drafting (PTD)}, which employs a structured, guided parallel drafting strategy to harness the model's parallel potential. By coupling a progressive tree structure with a stepwise pruning mechanism, PTD actively guides the LLM to explore multiple semantic paths in a single forward pass, ensuring both draft diversity and coherence. Experiments demonstrate that PTD achieves up to $2\times$ decoding speedup across various benchmarks while remaining training-free and model-agnostic. Our code is available at: https://github.com/MINE-USTC/PTD.
arXiv:2607.11140v1 Announce Type: new
Abstract: Determining whether one finite group is isomorphic to a subgroup of another is a fundamental problem in computational group theory. In this work, we propose a Siamese Graph Neural Network (Siamese GNN) for subgroup prediction using Cayley graph representations of finite groups. Each input group is represented by its undirected Cayley graph and encoded by one branch of a Siamese GNN to produce a graph embedding. The resulting graph embeddings are combined with algebraic features derived directly from the input groups to construct a joint feature vector, which is processed by a fully connected classifier to predict subgroup relations between finite groups. By integrating graph-based structural representations with algebraic features, the proposed framework provides a unified approach for learning subgroup relations from finite groups. Experimental results demonstrate the effectiveness of the proposed architecture, achieving a test accuracy of 95.9% (47/49) on an independent test set and illustrating the potential of geometric deep learning for subgroup prediction.
arXiv:2607.10800v1 Announce Type: new
Abstract: Editing images with pre-trained text-to-image flow models typically requires carefully balancing target alignment with the desired prompt and source consistency with the original image. Existing approaches either rely on inversion-based pipelines or heuristic source-to-target trajectory constructions, which often depend on architecture-specific designs or are sensitive to hyperparameters. In this paper, we propose h-Flow, a training-free and theoretically grounded flow-based editing framework. Inspired by Doob's $h$-Transform, we reformulate image editing as conditional generation under multiple terminal events corresponding to source consistency and target alignment. We first extend the classical $h$-Transform from SDE-based models to the deterministic RF framework by constructing an equivalent SDE with identical marginals. Within this formulation, we design dedicated $h$-functions for source consistency and target alignment, yielding closed-form reconstruction guidance and velocity-based semantic editing signals. We further introduce a velocity orthogonal decomposition to decouple reconstruction and editing directions, enabling a controllable trade-off between the two objectives. Extensive experiments demonstrate that h-Flow achieves effective, robust, and flexible editing across diverse scenarios. The code will be released soon.