arXiv:2607.04353v1 Announce Type: new Abstract: Hierarchical structure is common in image data, where fine-grained clusters often merge into larger, coarser semantic groups. In biological cell images, current self-supervised learning models often suppress this hierarchy, as coarse factors such as imaging modality can obscure finer morphological attributes in the latent space. We propose a hierarchy-aware self-supervised training framework to address this problem. Our method combines two components: a distillation framework with a segmentation teacher to improve morphological awareness in the latent space, and a hierarchy-aware contrastive loss based on HDBSCAN to improve decision boundaries between closely related subtypes at different hierarchical levels. Together, these components reduce the tendency of self-supervised learning to overemphasize coarse factors and instead align embeddings with semantic and morphological cues. This yields biologically meaningful sub-clusters driven by fine morphological detail. We train and evaluate our method on a curated corpus of 2.3 million single cells aggregated from 20 microscopy datasets, both labeled and unlabeled, covering 208 cell classes. Our method improves over baseline and counterpart methods, increasing average top-K accuracy by 2.8%, top-9 retrieval on the dataset with the deepest hierarchy by 6.3%, and downstream F1-score for biologically relevant drug classification from perturbed cell morphology by 7.8%.
Science Journals
arXiv:2607.04335v1 Announce Type: new Abstract: Time-frequency orthogonality has been a foundational principle in the historical development of optical communications, whether in dense wavelength division multiplexing (WDM) within long-reach high-capacity coherent optical transmission or in time-frequency division multiple access within short-reach dense passive optical networks. Towards next-generation agile optical networks, jointly programmable orthogonal and non-orthogonal regulation offers flexible spectral allocation, ultra-dense packet distribution, and increased capacity. For bridging the fundamental differences of physical implementation, we propose and demonstrate a versatile orthogonal to non-orthogonal multiplexing format converter, with application to high-speed coherent optical transmission network enabled by a Talbot-based processor. The programmable Talbot-processed pumps coherently transfer and superpose optical signals of distinct wavelength channels onto a single channel through cross-phase modulation. We first demonstrate flexible conversion of two 80-Gbps WDM QPSK channels separated by 200-250 GHz into a non-orthogonal power-division multiplexing channel, while maintaining the high-quality encoded information in the digital domain. We then validate a digital-subcarrier-multiplexing dense access scenario in which eight 20-Gbps sub-channels are combined, converted, transmitted, and successfully decoded over a field-deployed fiber. The multiplexing format converter promises potential for applications in next-generation optical systems and networks with complex topologies and dense populations.
arXiv:2603.29499v2 Announce Type: replace Abstract: Classical proportional--integral--derivative (PID) control remains widely used in industrial control systems, while model predictive control (MPC) is actively studied to achieve higher performance for systems with nonlinear dynamics. Model predictive path integral (MPPI) control is a sampling-based MPC method that optimizes control inputs without gradient calculations and can handle non-differentiable models and objective functions. However, conventional MPPI directly samples control-input sequences, which can produce large temporal input increments and causes the optimization dimension to grow with the prediction horizon. This study proposes MPPI--PID control, which uses MPPI to optimize PID gains online instead of directly optimizing the control-input sequences. By replacing high-dimensional input-sequence optimization with low-dimensional gain-space optimization while retaining the PID structure, the proposed formulation improves sampling efficiency and promotes smoother control inputs. Theoretical analyses are provided for a unified path-integral update, the relation between optimization dimension and effective sample size, and the temporal correlation of input perturbations induced by the PID structure. The method is evaluated on a learning-based path following of a mini forklift using a residual-learning dynamics model that combines a physical model and a neural network identified from real-machine driving data. Numerical results show that MPPI--PID improves tracking performance over fixed-gain PID, yields smaller input increments than conventional MPPI, and maintains favorable performance under reduced sampling budgets.
arXiv:2604.03553v2 Announce Type: replace Abstract: AI is increasingly supporting, accelerating, and automating scientific discovery across subjects. Yet, the adoption of AI in historical research remains limited due to the lack of specialised solutions for historians. To change this, we introduce Chronos, an AI Co-Historian designed to support historians. It allows researchers to create and customize research workflows through natural-language interaction and share these as Chronos-Extensions with others. Chronos specifically addresses the need of historians for a tool that is specialised, non-technical, highly customizable, and facilitates extensive task evaluation. As a first extension, we introduce Chronos-Extract, which enables researchers to automate the targeted extraction of information from image scans of historical sources. We benchmark Chronos-Extract on three historical source corpora and find that it achieves high task-accuracy across primary sources spanning three centuries and diverse languages, layouts, and typefaces. Chronos is openly available and ready for historians to use on their own primary and secondary sources.
arXiv:2606.20659v2 Announce Type: replace Abstract: Agent skills encode reusable procedural knowledge for large language model (LLM) agents, and existing benchmarks show that such skills can improve task-level performance. However, a task outcome does not reveal which parts of a reusable skill were exercised, nor whether the agent followed the relevant skill instructions when those parts were exercised. This gap makes it unclear whether a skill has been adequately tested, or whether observed task failures provide actionable evidence for improving agent skill effectiveness. To fill this gap, we introduce skill coverage, a trajectory-based test-adequacy metric for reusable agent skills. Our framework extracts skill behavior constraints from each skill, translating natural-language skill instructions into semi-structured constraints that specify the expected agent behavior under particular conditions. It then determines whether each constraint is covered by an agent trajectory and, for covered constraints, assigns a Pass or Fail verdict according to the agent behavior. We apply this framework to SkillsBench. The results show that agent trajectories on the benchmark leaderboard cover only 38.66 to 45.51% of the extracted skill behavior constraints on average. We then use Fail verdicts to strengthen the corresponding skill content only by emphasizing the original instructions that the agent failed to follow, and run the same tasks with the strengthened skills. This emphasis yields an average 16.0% recovery rate of the failed tasks across the five agent-model rows. These results show that skill coverage is both a test-adequacy metric and a fine-grained signal for observing skill-use behavior. In failed tasks, failed constraint labels provide actionable evidence for improving agent skill effectiveness. A project website accompanies the paper.
arXiv:2606.20742v2 Announce Type: replace Abstract: UAV-based pavement inspection can reduce the cost and risk of road-surface monitoring, but real-world deployment remains difficult when traffic, pedestrians, and temporary occlusions affect defect visibility. This paper presents a Unity-based digital twin framework for traffic-aware UAV pavement monitoring in open-traffic conditions. The proposed environment integrates procedurally generated road defects, dynamic traffic agents, autonomous UAV navigation, and a multitask YOLOv8n perception module for detecting road defects, pedestrians, and vehicles while classifying road-defect subtypes. After synthetic-domain fine-tuning, the perception model achieved 0.959 mAP@0.5 and 0.940 macro F1-score on a held-out synthetic test set generated from the simulator. The digital twin was then used to evaluate hover-and-recheck, micro-repositioning, and skip-and-revisit recovery strategies across different traffic densities and flight altitudes. Results show that flight altitude strongly affects inspection coverage, while recovery strategies introduce different trade-offs between coverage, mission duration, energy consumption, and revisit behaviour. These findings demonstrate that digital twins can support the development and evaluation of traffic-aware UAV inspection strategies before real-world deployment. The full implementation and trained models are available at https://github.com/EdwinTSalcedo/RDMO-DigitalTwin.
arXiv:2606.20971v2 Announce Type: replace Abstract: We introduce UNITY, a Universal-to-Specialized adapter for efficient and scalable composite conditioning in diffusion based image generation. Unlike prior methods that train separate adapters for each conditioning modality, UNITY jointly learns shared semantics across multiple conditioning types and subsequently specializes without modifying the underlying architecture. The proposed two stage training paradigm consists of a Universal Stage that captures cross modal representations across all conditioning modalities using half of the total training steps, followed by a Specialization Stage that refines modality specific features using the remaining training budget. At the core of UNITY are the Morphable Attention Flow (MAF) Network and Morph Wrapper modules, which enable channel aware and spatially adaptive feature alignment through learnable flow fields and attention based fusion. This constant complexity formulation supports flexible operation under both single and composite conditioning settings while significantly reducing inference latency and memory consumption. Extensive experiments across multiple datasets demonstrate that UNITY achieves state of the art image fidelity while maintaining superior memory efficiency. Code: https://github.com/arya-domain/UNITY
arXiv:2606.21883v2 Announce Type: replace Abstract: In this paper, we propose a modified projected Walk on Spheres method (MPWoS) for screened Poisson equations on embedded manifolds. The method employs local extensions together with the Green representation in local Euclidean balls, coupled with a closest-point projection that maps the boundary samples back to the manifold. This formulation yields a meshfree and highly parallelizable stochastic recursion in the ambient Euclidean space, rather than a direct discretization of the Laplace-Beltrami operator on the manifold. The proposed approach can be viewed as a high-dimensional extension and modification of the projected Walk on Spheres method introduced for surface PDEs in [Sugimoto et al., SIGGRAPH Asia 2024 Conference Papers, pp. 1-10], with three main distinctions: a compensation term that corrects the discrepancy between the ambient Laplacian applied to the closest-point extension and the intrinsic Laplace-Beltrami operator on the manifold, an adaptive radius strategy determined by local geometric and boundary information, and a rigorous error analysis for the proposed algorithm. Under assumptions on the geometric projection and the prescribed compensation accuracy, we establish mean-square error estimates for the proposed Monte Carlo method in both the boundary and closed-manifold settings. Extensive numerical examples on parametrized, implicit, high-dimensional (up to 1000 dimensions), and point-cloud manifolds are presented to illustrate the convergence and efficiency of the proposed method across different geometries.
arXiv:2604.09544v2 Announce Type: replace Abstract: Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly. Whether this brittleness reflects a fundamental lack of coherent internal organization for harmfulness remains unclear. Here we use targeted weight pruning as a causal intervention to probe the internal organization of harmfulness in LLMs. We find that harmful content generation depends on a compact set of weights that are general across harm types and distinct from benign capabilities. Aligned models exhibit a greater compression of harm generation weights than unaligned counterparts, indicating that alignment reshapes harmful representations internally--despite the brittleness of safety guardrails at the surface level. This compression explains emergent misalignment: if weights of harmful capabilities are compressed, fine-tuning that engages these weights in one domain can trigger broad misalignment. Consistent with this, pruning harm generation weights in a narrow domain substantially reduces emergent misalignment. Notably, LLMs harmful generation capability is dissociated from how they recognize and explain such content. Together, these results reveal a coherent internal structure for harmfulness in LLMs that may serve as a foundation for more principled approaches to safety.
arXiv:2604.10062v3 Announce Type: replace Abstract: We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives. Prior works on reward poisoning mainly focused on sufficient conditions to design a successful attacker, while only a few studies discussed the infeasibility of targeted attacks. This paper provides the first precise necessity and sufficiency characterization of the attackability of a linear MDP under reward poisoning attacks. Our characterization draws a bright line between the vulnerable RL instances, and the intrinsically robust ones which cannot be attacked without large costs even running vanilla non-robust RL algorithms. Our theory extends beyond linear MDPs -- by approximating deep RL environments as linear MDPs, we show that our theoretical framework effectively distinguishes the attackability and efficiently attacks the vulnerable ones, demonstrating both the theoretical and practical significance of our characterization.
arXiv:2606.21942v2 Announce Type: replace Abstract: Spanwise wall oscillation can enhance convective heat transfer disproportionately to its drag penalty, a departure from the Reynolds analogy termed dissimilar heat transfer (DHT). The companion study of Gu'erin et al. (2026) established that an optimised quasi-plateau waveform attains an analogy factor $\overline{A}n \approx 1.09$ at $Pr = 1$ and attributed this preferential thermal enhancement to the absence of a pressure-strain redistribution channel in the temperature variance equation, but the mechanism had not been quantitatively verified. The present study addresses this gap through phase-resolved variance transport budget analysis from direct numerical simulation of turbulent channel flow at $Re\tau = 200$, $Pr = 1$. Two complementary pressure-mediated mechanisms are identified. At the Stokes-strain reversal, the pressure-strain redistribution $\Pi_{uu}$ imposes a pronounced drain on the streamwise velocity variance with no counterpart in the temperature variance equation: the divergence-free constraint redistributes momentum variance among velocity components but has no scalar analogue. During the quasi-steady plateau phases, the pressure-temperature-gradient correlation $\Pi_{v\theta}$ preferentially enhances the wall-normal scalar flux relative to the momentum flux. The concentration of both mechanisms within the reversal and plateau phases, rather than at the Stokes-layer penetration maxima, identifies the duration of the quasi-steady phases as the controlling parameter for DHT enhancement, resolving the paradox whereby increased penetration depth does not produce increased dissimilarity.
arXiv:2606.22005v3 Announce Type: replace Abstract: We present InstructFX2FX, a system for sequential audio effect refinement through multi-turn natural-language instructions. Existing text-to-effect systems are largely single-shot, mapping one textual descriptor to one preset. Real audio engineering is instead sequential: engineers refine an existing effect chain through successive instructions. This poses a stateful problem that single-shot systems do not address: given the current effect parameters state and a new instruction, update the sound while preserving what earlier instructions already achieved. InstructFX2FX addresses this with a hybrid architecture that divides labor between a language model and CLAP-guided optimization. The LLM serves as a high-level planner that selects effects and proposes the initial parameter state, motivated by recent evidence that LLMs can outperform CLAP-based optimization for single-turn text-to-effect mapping; CLAP-guided optimization then refines the existing parameter state, providing a more stable and robust refinement mechanism than LLM reprompting. In the demo, attendees drive a dry recording through successive natural-language instructions: after each turn, they choose how strongly the effect is applied, then issue the next instruction based on what still differs from the sound they intend. In a preliminary evaluation on SocialFX-derived descriptor pairs, CLAP-guided refinement achieves lower DSP-feature MMD than an LLM+LLM initialize-then-reprompt baseline on 9 of 10 pairs. Trajectory analysis further shows that, for differentiable effects, optimization tends to gradually move the audio toward the new target while retaining the effects of the previous instruction, highlighting the potential for gradual refinement.
arXiv:2606.22047v2 Announce Type: replace Abstract: Guided acoustic wave Brillouin scattering (GAWBS) is a major obstacle in fiber-based quantum and high-speed classical communication systems as well as in interferometry. The transverse phonons driving it modulate the light field in the fiber core, adding thermal noise to the signal. To this day, there is no known method to eliminate GAWBS from the fiber or to compensate its effects completely. In this letter, we present twisted photonic crystal fibers (t-PCF) as the first-ever fiber system allowing a complete removal of mixed torsional radial GAWBS in a Stokes basis. The torsional radial modes modulate the fiber asymmetrically in the transverse direction, resulting in linear birefringence. While pure phase modulation is added as common noise in the guided fiber modes and can be easily removed through self-referencing, linear birefringence induces polarization modulation, which cannot be counteracted. In t-PCFs, the transverse symmetry of the geometry translates to multiple symmetries in the acoustic and optical domains in the circular basis. This enables equal phase accumulation in certain orientations in the two optical modes. Through experiments and theory, we show that the GAWBS-induced phase can be compensated down to the quantum-noise limit by self-referencing in a symmetric interferometer with Stokes detection.
arXiv:2606.22574v2 Announce Type: replace Abstract: While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables. This paper presents a systematic study analyzing the impact of lighting configurations and background complexity on object detection performance. We introduce SmartSDG, an automated, reproducible pipeline built on NVIDIA Isaac Sim using Physically-Based Shading (PBS), alongside ILLUM\_INTRUCK, a new multi-object industrial benchmark dataset. Through 18 controlled experiments utilizing a state-of-the-art YOLOv12 framework, we demonstrate that complex, indirect lighting configurations paired with domain-relevant background variability significantly increase visual cue richness. Our quantitative findings show that avoiding direct specular peaks preserves crucial surface textures, mitigates the domain gap, reduces false positives, and accelerates model convergence compared to using conventional direct-light synthetic data. Ultimately, we provide actionable virtual scene design guidelines to maximize object detection robustness in industrial automation.
arXiv:2605.07961v2 Announce Type: replace Abstract: Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapting large language models (LLMs). Built upon federated learning, FFT enables distributed agents to jointly refine a shared pretrained LLM by aggregating local LLM updates without sharing local raw data. However, FFT-based LLMs remain vulnerable to model manipulation threats, in which adversarial participants upload manipulated LLM updates that corrupt the aggregation process and degrade the performance of the global LLM. In this paper, we propose an Augmented Model maniPulation (AugMP) strategy against FFT-based LLMs. Specifically, we design a novel graph representation learning framework that captures feature correlations among benign LLM updates to guide the generation of malicious updates. To enhance manipulation effectiveness and stealthiness, we develop an iterative manipulation algorithm based on an augmented Lagrangian dual formulation. Through this formulation, malicious updates are optimized to embed adversarial objectives while preserving benign-like parameter characteristics. Experimental results across multiple LLM backbones demonstrate that the AugMP strategy achieves the strongest manipulation performance among all competing baselines, reducing the global LLM accuracy by up to \(26\%\) and degrading the average accuracy of local LLM agents by up to \(22\%\). Meanwhile, AugMP maintains high statistical and geometric consistency with benign updates, enabling it to evade conventional distance- and similarity-based defense methods.
arXiv:2605.08307v2 Announce Type: replace Abstract: Triplet formation and its regulation have always been of central interest in understanding the photophysical behavior of living systems. In organic systems, excessive triplet formation poses significant challenges, as it can promote photochemical damage and reduce the efficiency of charge separation processes, making its regulation critically important.Here, we present a theoretical investigation of the intrinsic quantum spin dynamics governing triplet formation in the heliobacterial reaction center, a system that operates without any internal magnetic field. Using an open quantum systems approach based on the Lindblad formalism, we simulate the spin-correlated radical pair dynamics occurring during charge separation in the heliobacterial reaction center. The study systematically examines how triplet formation is regulated by variations in two key parameters, hyperfine coupling strengths and recombination rates, and how this regulation is further influenced by the inclusion of chirality-induced spin selectivity (CISS) in conjunction with the radical pair mechanism (RPM). Our results demonstrate that the CISS effect significantly suppresses triplet formation across the parameter space relevant to the heliobacterial molecular environment, revealing an intrinsic quantum protective mechanism operating through spin control in heliobacterial photosynthesis.
arXiv:2606.24107v2 Announce Type: replace Abstract: Short dramas, with their rapid shot rhythms, dialogue-driven focus shifts, and demanding cinematographic grounding, pose challenges that prompt-level or text-only video generation pipelines struggle to meet. We study plot-to-short-drama generation, where a global plot and local context are transformed into visually grounded multi-shot videos. We propose DramaDirector, a geometry-grounded framework that lets the planner borrow cinematographic geometry from a gallery of real short-drama shots indexed by depth and pose. DramaDirector decouples each shot into static visual and dynamic narrative conditions, trains the planner with schema-constrained SFT and GRPO under a learned text-visual alignment reward, and retrieves depth-pose references to guide first-frame generation and image-to-video synthesis. We also introduce DramaBoard, a benchmark built from 35 live-action dramas, 2.8K episodes, and 81K shots, with structured storyboards and multi-dimensional evaluation protocols. Experiments show that DramaDirector improves over representative multi-agent and video generation baselines on faithfulness, consistency, and controllability. Our code is released at: https://github.com/iLearn-Lab/DramaDirector
arXiv:2606.24155v4 Announce Type: replace Abstract: Existing medical AI benchmarks lack process visibility, atomic skill evaluation, and integrated hallucination detection. We introduce MedBench v5, a redesigned benchmark for clinical multimodal models (language, vision-language, and agent systems) that moves from static QA to dynamic, process-oriented evaluation. MedBench v5 features: (1) a dual-dimensional framework combining Clinical Cognitive Responsiveness (13 sub-dimensions) and Medical Atomic Skills (4 agent environments), covering 63 tasks; (2) three switchable information-flow stressors (omission, contradiction, evidence delay) for factorized degradation analysis; (3) a dynamic process audit protocol with five reasoning nodes that produces model-specific failure fingerprints; (4) hallucination propagation monitoring across initiation, propagation, anchoring, and contradiction interaction-capturing silent hallucination. Experiments on frontier models show that strong overall task performance does not guarantee process stability: stressors mainly disrupt contradiction detection, diagnosis updating, hallucination propagation, and contradiction-based self-correction, while final evidence grounding can remain superficially stable. MedBench v5 provides a unified infrastructure for capability profiling, controllable stress testing, process auditing, and hallucination trajectory analysis in clinical AI evaluation.
arXiv:2606.24530v2 Announce Type: replace Abstract: We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move beyond reproduction toward discovery on real scientific problems. NatureBench is built on NatureGym, an automated pipeline that constructs a standardized, per-task containerized environment from a source paper, addressing the environment-fragmentation problem that has limited the credibility of prior agent-on-research benchmarks. Evaluating ten frontier agent configurations under a strict web-search-disabled protocol, we find that the strongest model surpasses SOTA on only 17.8% of tasks under the g>0.1 criterion. Analysis of method pathways reveals that agents succeed primarily through methodological translation, converting scientific tasks into familiar supervised prediction problems, rather than through genuine scientific invention. Failures are dominated by wrong method choice and insufficient compute budget, not by task misunderstanding. We release the benchmark, the NatureGym pipeline, and a public leaderboard with maintainer-side reproduction. Code: https://github.com/FrontisAI/NatureBench
arXiv:2602.12940v2 Announce Type: replace Abstract: This work presents a comprehensive framework for capturing bifurcating phenomena and detecting bifurcation curves in nonlinear multiparametric partial differential equations, where the system exhibits multiple coexisting solutions for given values of the parameters. Traditional continuation methods for one-dimensional parameterizations employ the previously computed solution as the initial guess for the next parameter value. These are usually very inefficient, since small step sizes increase computational cost, while larger steps could jeopardize the method convergence jumping to a different solution branch or missing the bifurcation point. To address these challenges, we propose a novel framework that combines: (i) arclength continuation, adaptively selecting new parameter values in higher dimension, and (ii) the deflation technique, discovering multiple branches to construct complete bifurcation diagrams without requiring a costly spectral analysis of the system. In particular, the arclength continuation method is designed to handle multiparametric scenarios, where the parameter vector $\lambda \in \mathbb{R}^p$ traces a curve $g(\lambda)$ within a $p$-dimensional parameter space. In addition, we introduce a zigzag path-following strategy to robustly track the bifurcation curves and surfaces, respectively, for two- and three-dimensional parametric spaces. Finally, we demonstrate its performance on three benchmark problems of increasing complexity: from the 1D/2D Bratu and Allen--Cahn equations to the 2D/3D Rayleigh--Benard convection problem.
arXiv:2602.21009v2 Announce Type: replace Abstract: Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors and loss of long-tail preferences. To alleviate these issues, we propose Hierarchical Sparse Activation Compression (HiSAC), an efficient framework for personalized sequence modeling. HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook. A hierarchical voting mechanism sparsely activates personalized interest-agents as fine-grained preference centers. Guided by these agents, Soft-Routing Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error and retain long-tail behaviors. Deployed on Taobao's "Guess What You Like" homepage, HiSAC achieves significant compression and cost reduction, with online A/B tests showing a consistent 1.65% CTR uplift -- demonstrating its scalability and real-world effectiveness.
arXiv:2605.01989v2 Announce Type: replace Abstract: Distributed machine learning (ML) training has become a necessity with the prevalence of billion to trillion-parameter-scale models. While prior work has improved training efficiency from the ML perspective at the application layer, it often fails to address transient congestion events at the network layer that introduce severe tail latency and training-time variability, thereby undermining the quality of service of distributed ML training systems. Existing network optimizations treat all gradients equally and thus fail to integrate sufficient model-training insights into communication protocol design. In this paper, we present Dynamic Bounded-Loss Protocol (DBLP), a burst-resilient, training-phase-aware, and hardware-agnostic transport protocol that incorporates model-level tolerance properties into gradient communication. By dynamically adjusting gradient loss tolerance across training phases, DBLP reduces overall training time and mitigates tail-latency collapse during transient high-loss events (i.e., microbursts). Compared to the current state-of-the-art solution (baseline), DBLP tolerates significantly higher loss while achieving comparable test accuracy, and reduces end-to-end training time by an average of 24.4% and a maximum of 33.9%. At microburst events, DBLP achieves up to 5.88x single-round communication latency speedups over the baseline, preventing burst-induced tail-latency spikes and maintaining stable training performance.
arXiv:2605.14987v2 Announce Type: replace Abstract: Positronium-based imaging requires realistic modelling of positronium (Ps) decay in matter. We introduce a modular Ps decay model implemented in GATE 9.4 and GATE 10, enabling the definition of an arbitrary number of decay channels characterised by lifetime, branching fraction, annihilation multiplicity (2g/3g), and optional prompt photon emission. The model is validated through analytical and numerical benchmarks, including lifetime distributions, branching fraction consistency, photon kinematics, and prompt photon emission. Its practical applicability is demonstrated using simulations of mixed annihilation scenarios and the NEMA IEC phantom with a large field-of-view PET system. The proposed model accurately reproduces input lifetime distributions as weighted sums of exponential components and correctly samples decay channel fractions. Simulated two- and three-photon annihilation kinematics are consistent with theoretical expectations. Complex mixtures of decay channels, including varying 3g-to-2g ratios and multi-component ortho-positronium lifetimes, are correctly modelled, with observable signatures reflected in both temporal and energy distributions. Phantom simulations demonstrate the capability to generate realistic positronium-sensitive datasets. This work provides the first general-purpose, multi-channel positronium decay model integrated into GATE, enabling realistic simulations of positronium behaviour in complex media. The model supports the development and optimisation of positronium-based imaging techniques, including PLI and multi-photon PET, and applies to medical imaging, industrial tomography, and fundamental physics studies. Its public availability and compatibility with standard GATE workflows make it a valuable tool for the broader research community.
arXiv:2604.16030v4 Announce Type: replace Abstract: The k-Visits problem is a recently introduced finite version of Pinwheel Scheduling [Kanellopoulos et al., SODA 2026]. Given the deadlines of n tasks, the problem asks whether there exists a schedule of length kn executing each task exactly k times, with no deadline expiring between consecutive visits (executions) of each task. In this work we prove that 2-Visits is strongly NP-complete even when the maximum multiplicity of the input is equal to 2, settling an open question from [Kanellopoulos et al., SODA 2026] and contrasting the tractability of 2-Visits for simple sets. On the other hand, we prove that 2-Visits is in RP when the number of distinct deadlines is constant, thus making progress on another open question regarding the parameterization of 2-Visits by the number of numbers. We then generalize all existing positive results for 2-Visits to a version of the problem where some tasks must be visited once and some other tasks twice, while providing evidence that some of these results are unlikely to transfer to 3-Visits. Lastly, we establish bounds for the density thresholds of k-Visits, analogous to the $(5/6)$-threshold of Pinwheel Scheduling [Kawamura, STOC 2024]; in particular, we show a $\sqrt{2}-1/2\approx 0.9142$ lower bound for the density threshold of 2-Visits and prove that the density threshold of k-Visits approaches $5/6\approx 0.8333$ for $k \to \infty$.
arXiv:2604.16084v2 Announce Type: replace Abstract: Traffic forecasting is a challenging spatio-temporal modeling task and a critical component of urban transportation management. Current studies mainly focus on deterministic predictions, with limited considerations on the uncertainty and stochasticity in traffic dynamics. Therefore, this paper proposes an elegant yet universal approach that transforms existing models into probabilistic predictors by replacing only the final output layer with a novel Gaussian Mixture Model (GMM) layer. The modified model requires no changes to the training pipeline and can be trained using only the Negative Log-Likelihood (NLL) loss, without any auxiliary or regularization terms. Experiments on multiple traffic datasets show that our approach generalizes from classic to modern model architectures while preserving deterministic performance. Furthermore, we propose a systematic evaluation procedure based on cumulative distributions and confidence intervals, and demonstrate that our approach is considerably more accurate and informative than unimodal or deterministic baselines. Finally, a more detailed study on a real-world dense urban traffic network is presented to examine the impact of data quality on uncertainty quantification and to show the robustness of our approach under imperfect data conditions. Code available at https://github.com/Weijiang-Xiong/OpenSkyTraffic