arXiv:2604.04931v2 Announce Type: replace Abstract: Local feature matching has long been a fundamental component of 3D vision systems such as Structure-from-Motion (SfM), yet progress has lagged behind the rapid advances of modern data-driven approaches. The newer approaches, such as feed-forward reconstruction models, have benefited extensively from scaling dataset sizes, whereas local feature matching models are still only trained on a few mid-sized datasets. In this paper, we revisit local feature matching from a data-driven perspective. In our approach, which we call LoMa, we combine large and diverse data mixtures, modern training recipes, scaled model capacity, and scaled compute, resulting in remarkable gains in performance. Since current standard benchmarks mainly rely on collecting sparse views from successful 3D reconstructions, the evaluation of progress in feature matching has been limited to relatively easy image pairs. To address the resulting saturation of benchmarks, we collect 1000 highly challenging image pairs from internet data into a new dataset called HardMatch. Ground truth correspondences for HardMatch are obtained via manual annotation by the authors. In our extensive benchmarking suite, we find that LoMa makes outstanding progress across the board, outperforming the state-of-the-art method ALIKED+LightGlue by +18.6 mAA on HardMatch, +29.5 mAA on WxBS, +21.4 (1m, 10$^\circ$) on InLoc, +24.2 AUC on RUBIK, and +12.4 mAA on IMC 2022. We release our code and models publicly at https://github.com/davnords/LoMa.
Science Journals
arXiv:2607.04170v1 Announce Type: new Abstract: Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization, and sharp minima compared to centralized training. Sharpness-Aware Minimization (SAM) has emerged as a promising approach to improve generalization, yet its application in federated learning still suffers from divergence problems, since perturbations are computed locally and reflect client-specific loss geometries. To better understand this issue, we provide experimental evidence from a new perspective, the frequency domain, for SAM perturbations in federated settings, revealing that inter-client perturbation inconsistencies are predominantly concentrated in the low-frequency spectrum. Motivated by this insight, we propose Federated learning with Frequency-domain Filtering of SAM perturbations (FedFFT). It is a lightweight and plug-and-play method that filters out low-frequency components of SAM perturbations without requiring additional communication, thereby suppressing inconsistent components in client updates while preserving consistent learning signals. Extensive experiments across multiple benchmarks and diverse backbones demonstrate that FedFFT consistently outperforms SAM-based FL methods, particularly under severe non-IID distributions. These results highlight the effectiveness, scalability, and general applicability of our frequency-domain perspective for sharpness-aware federated optimization.
arXiv:2607.04172v1 Announce Type: new Abstract: This paper investigates the causal rate-distortion function for networked control systems with multiple encoders and a single decoder, a longstanding open problem in information and control theory. While previous work has explored the causal rate-distortion function for single-encoder and feedback-enabled networked settings, the case of networks without feedback remains unaddressed. We establish a novel directed information lower bound, the first derived for the networked control setting. We further demonstrate the optimality of linear, independent encoders and linear decoders for optimizing this lower bound for Linear Quadratic Gaussian (LQG) plant and quadratic cost, with the condition that the full plant state is observed when sensors are sitting together. By reducing the original infinite-dimensional optimization problem to a finite-dimensional one, our approach simplifies the analysis. Additionally, our directed information lower bound provides an alternate proof for the sufficiency of linear encoders in the single encoder and single decoder setting with side information, extending prior results in the literature. We present Semidefinite Programming formulations for the causal rate distortion function of Gaussian-Markov sources with linear side information and the singular noise matrix.
arXiv:2506.16995v4 Announce Type: replace Abstract: Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games. However, recent advancements in game AI based on reinforcement learning have predominantly focused on improving proficiency, whereas methods based on evolution algorithms generate agents with diverse play styles but exhibit subpar performance compared to RL methods. To address this gap, this paper proposes Mixed Proximal Policy Optimization (MPPO), a method designed to improve the proficiency of existing suboptimal agents while retaining their distinct styles. MPPO unifies loss objectives for both online and offline samples and introduces an implicit constraint to approximate demonstrator policies by adjusting the empirical distribution of samples. Empirical results across environments of varying scales demonstrate that MPPO achieves proficiency levels comparable to, or even superior to, pure online algorithms while preserving demonstrators' play styles. This work presents an effective approach for generating highly proficient and diverse game agents, ultimately contributing to more engaging gameplay experiences.
arXiv:2506.15199v4 Announce Type: replace Abstract: While there are many applications of ML to scientific problems that look promising, visuals can be deceiving. Using numerical analysis techniques, we rigorously quantify the accuracy, convergence rates, and generalization bounds of certain ML models applied to linear differential equations for parameter discovery or solution finding. Beyond the quantity and discretization of data, we identify that the function space of the data is critical to the generalization of the model. A similar lack of generalization is empirically demonstrated for commonly used models, including physics-specific techniques. Counterintuitively, we find that different classes of models can exhibit opposing generalization behaviors. Based on our theoretical analysis, we also introduce a new mechanistic interpretability lens on scientific models whereby Green's function representations can be extracted from the weights of black-box models. Our results inform a new cross-validation technique for measuring generalization in physical systems, which can serve as a benchmark.
arXiv:2606.07176v2 Announce Type: replace Abstract: We provide the spectral decompositions of $(\star,\epsilon_1,\epsilon_2)$-structured matrix polynomials $P(\lambda)$ in the unified form by a standard pair $(X, J)$ and a parameter matrix $\Gamma$. Using the recursive relationship between the coefficient matrices of $P(\lambda)$, equivalent expressions of these coefficient matrices are provided. When $J$ is assumed to be a block diagonal matrix, we show that the parameter matrix $\Gamma$ has a special structure.
arXiv:2607.04188v1 Announce Type: new Abstract: Intelligent industrial maintenance critically relies on reliable fault diagnosis of rotating machinery. However, it faces formidable challenges from unknown fault types and domain shifts induced by varying operating conditions, which is formally formulated as the open-set domain generalization (OSDG) problem. Existing methods are mainly data-driven, thereby overlooking the cascaded propagation of uncertainty across feature extraction, topological learning, and decision-making stages.To tackle this challenge, we propose PGU-OD, a novel Physics-Informed Graph Learning framework with Uncertainty Awareness for Open-set Domain generalization. First, it designs a physics-informed spectral attention module to extract condition-robust fault features, thereby suppressing perceptual uncertainty caused by frequency shifts. Further, it constructs an uncertainty aware adaptive graph learning mechanism to dynamically adjust the edge weights of the sample graph guided by class-scale Gaussian distribution parameters, which mitigates the structural propagation of uncertainty. Finally, a Gaussian-distribution-based adaptive boundary loss function and a dual-criteria open-set inference strategy are developed to optimize decision boundaries and reliably reject unknown faults. Extensive experimental evaluations on two public and widely used rotating machinery fault datasets demonstrate that the proposed PGU-OD outperforms state-of-the-art baselines in both known fault classification and unknown fault rejection under domain shifts.
arXiv:2603.22116v2 Announce Type: replace Abstract: In this study, we report direct experimental observations of self-sustaining CH4-air rotating flames formed spontaneously in an unheated, open, circular Hele-Shaw cell. These flames are observed under fuel-rich conditions and exhibit stable traveling-wave patterns, with edge velocities that can significantly exceed the nominal flame speed of the unburned mixture. PLIF measurements across the central plane reveal that the flame front consists of a bibrachial structure, with a diffusion branch gliding along the side edges of the cell and a premixed branch extending into the interior. Complementary numerical simulations suggest that the formation of rotating flames is driven by a dynamic balance between local flame speed and unburned-gas velocity near the cell edges, where both wall heat loss and flow expansion play critical roles in stabilizing the rotation pattern. A parametric study is conducted for various equivalence ratios, flow rates, and gap distances, from which the regime diagrams of flame modes and rotation frequencies are obtained. At low flow rates, the rotating state is characterized by a single rotating flame wave, whose rotation frequency increases with flow rate. For this type of flames, a semi-empirical model is established to predict their rotation frequencies and shapes as functions of mass flow rate and surface temperature. At elevated flow rates, multiple rotating waves appear with approximately equal azimuthal spacing, and the product of the wave number and rotation frequency increases with flow rate. Mode transition from rotating flames to steady ring-shaped flames anchored at the burner edges occurs at sufficiently high flow rates, while at sufficiently low flow rates, flame extinction occurs due to thermal quenching. These findings can provide useful guidance for the advancement of micro-combustion technologies.
Generation of Polarized Overdense Pair-photon Fireball via Laser-Driven Nonlinear-linear QED Cascade
arXiv:2603.26383v2 Announce Type: replace Abstract: Relativistic, polarized pair-photon fireballs are central to understand the microscopic energy transfer of high-energy astrophysical outflows, yet generating an overdense fireball in the laboratory, especially via an ultraintense laser, remains a formidable challenge. Here, we propose a novel method of laser-driven nonlinear-linear quantum electrodynamics (NL-QED) plasma, that dramatically lowers the laser intensity threshold for dense pair-photon fireball creation. By coupling polarization-resolved linear Breit-Wheeler and Compton processes with strong-field nonlinear radiation, we find that a self-organized NL-QED cascade is ignited in the laser-driven hole boring at intensities of $\sim 10^{22}~\mathrm{W/cm^2}$, accessible with current 10-PW-class laser facilities. Consequently, we demonstrate the generation of a pair-photon fireball with an overdense gamma-ray bath (maximum average density $\overline{n_\gamma} \approx 3 \times 10^{22}~\mathrm{cm^{-3}}$) and a pair plasma reaching collective regime (maximum average density $\overline{n_\pm} \approx 3 \times 10^{17}~\mathrm{cm^{-3}}$), which is highly polarized. Our method provides a comprehensive framework for studying laser-driven QED plasma and its application in laboratory astrophysics, probing multi-process QED physics.
arXiv:2604.15579v2 Announce Type: replace Abstract: There is increasing interest in integrating AI agents that invoke tools into domain-specific commercial software, where unintended tool calls can cause serious security and safety incidents. This has drawn growing research attention, and many agent security and safety benchmarks have emerged. They implicitly shape how the community approaches security and safety. Yet existing work exhibits a blind spot: it emphasizes training-based methods and neural guardrails, which reduce the likelihood of insecure or unsafe actions but cannot guarantee their prevention. It generally overlooks opportunities for deductive, symbolic guardrails grounded in standard software engineering practices, which can provide guarantees for some security and safety requirements. Our study has three parts: (1) a systematic review of 80 agent security and safety benchmarks finding that that 85\% of benchmarks do not state verifiable requirements (61\% provide none, and 24\% give only high-level goals); (2) an applicability analysis of which security and safety requirements symbolic guardrails can and cannot enforce on $\tau^2$-Bench, CAR-bench, and MedAgentBench, finding that 74\% of requirements are symbolically enforceable and 95\% of these need only simple, low-cost checks; and (3) an empirical evaluation of symbolic guardrails on the same three benchmarks, finding that symbolic guardrails improve security and safety without sacrificing utility, and often improve it. Our work draws attention to the potential for symbolic guardrails for AI agents, suggesting them as an overlooked but practical path toward deploying domain-specific AI agents in risk-averse commercial software. We release all codes and artifacts at https://github.com/hyn0027/agent-symbolic-guardrails.
arXiv:2607.04260v1 Announce Type: new Abstract: Aerial physical interaction represents a promising direction for next-generation unmanned aerial vehicles (UAVs), but it requires an aerial platform that can exert contact forces while maintaining stable flight. For close-proximity tasks, this translates into three coupled design requirements: multidimensional wrench generation for stable contact, compactness for maneuverability and safety in confined spaces, and reduced lateral airflow toward the target when generating horizontal force. This article presents FLOAT Drone, a fully actuated coaxial UAV with servo-driven control surfaces for close-proximity physical interaction. The coaxial dual-rotor layout provides a compact propulsion layout, while the control surfaces, immersed in the rotor downwash, generate lateral forces and moments for 6-DoF wrench generation. A force-matched computational fluid dynamics (CFD) comparison with a tilted-rotor alternative quantifies the reduction in target-facing lateral airflow. To account for nonlinear rotor--control-surface coupling in the rotor wake, a high-fidelity polynomial aerodynamic wrench model is identified from precision force measurements and embedded in a constrained nonlinear allocator for real-time wrench tracking. Comparative flight and interaction experiments show that the proposed framework improves control accuracy over linear allocation baselines, rejects ground-effect and payload disturbances, and enables close-proximity drawer push--pull manipulation through a $2~\mathrm{cm}$ handle clearance.
arXiv:2603.28981v3 Announce Type: replace Abstract: We develop a conservative finite-volume Buckley--Leverett solver equipped with a bounded-interval multiwavelet state-analysis layer. Because non-capillary Buckley--Leverett transport is a nonlinear hyperbolic conservation law with entropy-admissible shocks, the saturation equation is advanced by a conservative finite-volume method with monotone numerical fluxes. The accepted finite-volume state is then embedded in a bounded-domain multiwavelet hierarchy, reconstructed back to cell averages, and used for multiresolution diagnostics. The formal transport accuracy is therefore governed by the underlying finite-volume discretization, while the multiwavelet layer is used for representation, compression, and front-localization diagnostics. Its purpose is instead to quantify whether the deterministic physical-space saturation state can be represented faithfully, compressed in a controlled manner, and used to identify dynamically active front regions. Validation against reference Buckley--Leverett profiles for a Berea benchmark shows accurate saturation histories, spatial profiles, front-position diagnostics, and mass balance. The multiwavelet reconstruction tracks the internal finite-volume state with essentially exact fidelity. Additional thresholding tests show that a substantial fraction of detail coefficients can be discarded while maintaining small reconstruction errors and negligible global mass defect, and fine-level detail activity localizes the moving displacement front. The resulting formulation provides a conservative and reproducible first stage toward future transport-active adaptive multiwavelet solvers for porous-media flow.
arXiv:2603.29278v2 Announce Type: replace Abstract: There have been various attempts at token standards on numerous blockchain platforms today to fundamentally change the way assets are traded in the traditional capital markets, but there is a lack of research and resolution on regulatory issues that become the common foundation for interoperability and reusable standards. Our proposal, Regulatory Compliance Protocol (RCP), is based on the regulations and reports of 15 global financial institutions and standardizes recommendations and guidelines involving the overall asset tokenization of TradFi and DeFi into five regulatory groups: Traceability, Privacy, Enforceability, Finality and Tokenizability, compiling them into 31 items and presenting a benchmark for technology and standards as an underlying protocol. To review the legality and effectiveness of RCP, it was validated based on three tokenization and trading scenarios, and by benchmarking existing asset-tokenization standards (ERC-20, ERC-7943, ERC-1400, and ERC-3643) against RCP, it makes explicit which regulatory requirements each standard addresses at the token level and which remain inherently off-chain.
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%.
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: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: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: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.