arXiv:2605.18529v1 Announce Type: new Abstract: The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, standard algorithms like GRPO apply sequence-level rewards uniformly to all tokens, creating a severe credit-assignment bottleneck. While on-policy self-distillation attempts to resolve this by conditioning a self-teacher on privileged contexts, direct exposure to raw oracle solutions often induces over-conditioned teacher distributions, implicit answer leakage, and late-stage training collapse. To overcome these limitations, we propose Asymmetric Meta-Reflective Self-Distillation (AMR-SD). Instead of conditioning directly on raw reference traces, AMR-SD inserts a reflection bottleneck: it compresses diagnostic signals -- from verifier outcomes, peer rollouts, or reference feedback -- into concise, self-generated Socratic hints and critiques. Furthermore, we introduce Causal Information Gain (CIG) with an asymmetric, ReLU-gated threshold to translate these reflections into sparse, highly precise token-level advantage modulations. Combined with temporal annealing, this mechanism preserves the base environmental reward while filtering out distributional noise. Experiments across scientific, mathematical, and tool-use benchmarks demonstrate that AMR-SD significantly outperforms existing baselines, achieving robust long-horizon stability and successfully preventing late-stage collapse.
Science Journals
arXiv:2605.18523v1 Announce Type: new Abstract: The intertropical convergence zone (ITCZ) is a central component of tropical climate, but the conditions under which a tropical rain belt remains zonally extended or becomes unstable to zonal organization are not well understood. We investigate this problem using idealized nonrotating kilometer-scale simulations forced by a prescribed sea surface temperature (SST) distribution that varies only in the meridional direction. This setup produces an ITCZ-like rain belt while allowing spontaneous zonal convective self-aggregation (ZCSA) to emerge. A parameter sweep shows that ZCSA occurs preferentially when both the peak SST and the meridional SST amplitude are large. ZCSA cases exhibit a temporary weakening of the meridional near-surface convergence. Boundary-layer momentum and thermodynamic analyses link this weakening to enhanced lower-tropospheric stability over the cool subsiding region, a shallower boundary layer, and stronger effective frictional damping of the meridional inflow. However, weak convergence alone is not sufficient for ZCSA. Aggregating cases also have a large meridional contrast in moist static energy forcing, implying a strong demand for meridional energy transport. Consistently, ZCSA reorganizes meridional moist static energy transport, including enhanced stationary eddy export from the warm region, and is accompanied by growing zonal moisture variability and weakening meridional moisture contrast. These results suggest that zonal symmetry breaking of an ITCZ-like rain belt is favored when weakened meridional inflow coincides with a large imposed meridional MSE-forcing contrast.
arXiv:2605.18517v1 Announce Type: new Abstract: Data center electricity consumption reached 4.4% of U.S. total in 2023 and is projected to grow to 6.7--12% by 2028, imposing increasing stress on transmission networks while representing a largely untapped source of controllable demand-side flexibility. This paper proposes a modular security-constrained unit commitment (SCUC) framework that coordinates flexible data center workloads with system-level scheduling to reduce renewable curtailment, alleviate congestion, and lower operating costs. Three mixed-integer linear programming (MILP) models are formulated: the Data Center Spatial model (DC-S), enabling instantaneous workload redistribution across geographically distributed sites; the Data Center Temporal model (DC-T), permitting each site to shift its deferrable load across time while preserving the daily energy balance; and the Data Center Spatio-Temporal model (DC-ST), jointly activating both mechanisms and spanning the largest feasible operating region. Case studies on a modified IEEE 24-bus reliability test system show that DC-ST eliminates all base-case and post-contingency transmission violations at a flexibility ratio of 40%, and reduces renewable curtailment by up to 84.4% at 30% relative to the inflexible baseline. Sensitivity analysis further reveals that moderate flexibility levels of 20%--30% already capture most of the achievable benefits, supporting practical deployment with limited operational burden on data center operators.
arXiv:2605.18512v1 Announce Type: new Abstract: In-context learning (ICL) is highly sensitive to which demonstrations appear in the prompt, but selecting them is expensive because the space of possible demonstration contexts and combinations is enormous. We argue that demonstration selection is \emph{easier to judge than to find}: predicting whether a specific query--context pair $(q,D)$ will succeed is cheaper and more general than searching for an optimal $D^\star$. Based on this insight, we propose DiSP, a sample-and-judge framework that stratifies queries by difficulty. DiSP runs random demonstration trials to estimate success rate of each training query, trains a lightweight router to predict difficulty from the query, and trains level-specific judges for sampled demonstrations. At inference, DiSP performs stop-on-acceptance judging under an explicit budget, emitting diagnostic risk tags when no suitable context is found. Across five classification datasets with Llama~3--8B and Qwen~2.5--7B, DiSP achieves the best average accuracy, improving over strong learned selection baselines by up to 3.4\%, while achieving up to $23\times$ end-to-end wall-clock speedup.
arXiv:2605.18503v1 Announce Type: new Abstract: Low-altitude economy (LAE) is transforming low-altitude airspace into a new cyber-physical infrastructure. Although air-ground communications have been widely studied, LAE is fundamentally different in the sense that it is mission-centric with diverse requirements, such as stringent safety and compliance constraints not be effectively addressed with a communication-centric design alone, which makes air-ground collaboration indispensable: Only through effectively coordinating air-ground infrastructure and resources can LAE missions be fulfilled. Consequently, LAE calls for task-driven, closed-loop, multi-resource orchestration of Sensing, Communication, Computing, Storage, and Intelligence (SCCSI), where key decisions must be co-designed under mobility and uncertainty. In this paper, we first present a novel framework that connects (i) LAE scenarios and a requirement--resource coupling matrix, (ii) an air--ground collaborative architecture, and (iii) methodological toolboxes for SCCSI co-optimization and online decision-making. We then systematically review enabling technologies for collaborative SCCSI resources and capabilities, emphasizing their coupling and end-to-end tradeoffs. Finally, we summarize testbeds, datasets, and evaluation metrics, and provide representative use cases to illustrate how the proposed framework translates application requirements into practical task-driven optimization designs, together with open challenges and a roadmap toward scalable and trustworthy LAE deployment.
arXiv:2605.18496v1 Announce Type: new Abstract: We introduce a dialect of the Asynchronous pi-calculus, called AWpi, in which (1) an input name may be owned, at any time, by at most one process; (2) each name has either only the input or only the output capability. As a result, special processes called wires (aka forwarders, that is, processes that receive values at one name and re-transmit) behave as substitutions when composed with any AWpi process. Thus AWpi naturally yields a category, whose morphisms are AWpi processes (modulo the reference behavioural equivalence, barbed congruence) and whose objects are types; and where wires act as identity morphisms. We show that the category of processes can be further organised into (sub)categories with the structures needed for the interpretation of common higher-order language features in the literature by drawing on insights from game semantics; notably, we construct a relative Seely category, the categorical structure that concurrent game semantics has. At the same time, AWpi follows the tradition of ordinary pi-calculi in that expressiveness is preserved and the operational and algebraic theory are developed in a similar manner, notwithstanding substantial technical differences in their development and proofs. In short, the goal of AWpi is to remain faithful to the operational and algebraic tradition of the pi-calculi while connecting to the tradition of denotational models for programming languages.
arXiv:2605.18437v1 Announce Type: new Abstract: Vehicular edge computing (VEC) enables latency-sensitive vehicular applications by offloading computation-intensive tasks to nearby edge servers. However, real-world vehicular workloads are typically modeled as heterogeneous directed acyclic graph (DAG) tasks with complex dependency structures, making joint offloading and resource allocation highly challenging. Moreover, distributed MEC deployment raises privacy concerns when collaboratively training learning-based policies. In this paper, we propose a Federated Meta Deep Reinforcement Learning framework with GAT-Seq2Seq modeling (FedMAGS) for heterogeneous task offloading in VEC systems. The proposed approach leverages Graph Attention Networks to capture DAG dependencies, a Seq2Seq-based policy to generate structured offloading decisions, and federated meta-learning to enable fast adaptation across distributed MEC servers without sharing raw data. Extensive simulations demonstrate that FedMAGS achieves faster convergence, lower execution delay, and better scalability compared with state-of-the-art baselines. In addition, the federated design preserves data privacy while reducing communication overhead, making the framework well suited for dynamic and large-scale VEC environments.
arXiv:2605.17707v1 Announce Type: new Abstract: AI Accelerator (AIA) are specialized hardware e.g., Tensor Processing Unit (TPU), that enable optimal and efficient execution of AI applications and on-device inference. The growing demand for AI applications has led to the widespread adoption of AIAs on Edge or embedded devices on Edge or embedded devices. Unlike applications, AIAs are not bound by Operating System (OS) restrictions and have limited visibility into Application Processor (AP) security mechanisms (e.g., kernel vs. application memory, process isolation). This semantic gap can lead to confused deputy vulnerabilities, i.e., AIA can be tricked by a malicious application to perform privileged operations on their behalf. In this paper, we conducted the first in-depth study of Confused Deputy Attacks (CDAs) using AIA. We design DeputyHunt, a Large Language Model (LLM) assisted framework to extract CDA relevant information for a given AIA through a combination of dynamic and static analysis. We used this information to explore the feasibility of CDA on seven different AIAs from popular vendors, i.e., Google, NVIDIA, Hailo, Texas Instruments, NXP, AWS, and Rockchip. Our analysis revealed that CDA is feasible on six out of the seven AIAs, impacting over 128 System On Chips (SOCs) and over 100 million devices. Our findings highlight critical security risks posed by AIA on system security. Our work has been acknowledged by the corresponding vendors and assigned the CVE-2025-66425. We propose an on-demand validation defense against CDA, and evaluation on the Gem5- salam simulator shows that it incurs minimal runtime overhead (i.e., ~15%).
arXiv:2604.07292v2 Announce Type: replace Abstract: Real-time supervisory control of advanced reactors requires accurate forecasting of plant-wide thermal-hydraulic states, including locations where physical sensors are unavailable. Meeting this need calls for surrogate models that combine predictive fidelity, millisecond-scale inference, and robustness to partial observability. In this work, we present a physics-informed message-passing Graph Neural Network coupled with a Neural Ordinary Differential Equation (GNN-ODE) to addresses all three requirements simultaneously. We represent the whole system as a directed sensor graph whose edges encode hydraulic connectivity through flow/heat transfer-aware message passing, and we advance the latent dynamics in continuous time via a controlled Neural ODE. A topology-guided missing-node initializer reconstructs uninstrumented states at rollout start; prediction then proceeds fully autoregressively. The GNN-ODE surrogate achieves satisfactory results for the system dynamics prediction. On held-out simulation transients, the surrogate achieves an average MAE of 0.91 K at 60 s and 2.18 K at 300 s for uninstrumented nodes, with $R^2$ up to 0.995 for missing-node state reconstruction. Inference runs at approximately 105 times faster than simulated time on a single GPU, enabling 64-member ensemble rollouts for uncertainty quantification. To assess sim-to-real transfer, we adapt the pretrained surrogate to experimental facility data using layerwise discriminative fine-tuning with only 30 training sequences. The learned flow-dependent heat-transfer scaling recovers a Reynolds-number exponent consistent with established correlations, indicating constitutive learning beyond trajectory fitting. The model tracks a steep power change transient and produces accurate trajectories at uninstrumented locations.
arXiv:2605.18498v1 Announce Type: new Abstract: Expert specialization in Mixture-of-Experts (MoE) models remains poorly understood, with traditional evaluations conflating architectural load-balancing with functional specialization. We introduce DBES, a comprehensive diagnostic framework combining a multi-domain benchmark with five theoretically grounded metrics: Routing Specialization, Normalized Effective Rank, Domain Isolation, Routing Stiffness Score, and N-gram Expertise measures. Critical findings demonstrate distinct specialization paradigms across models: Qwen-series exhibit modular specialization with high domain isolation, while DeepSeek and GLM employ distributed collaboration. However, we emphasize that specialization is a diagnostic dimension, necessary but not sufficient for downstream performance. Most crucially, interventional evidence validates the actionability of these metrics: by using DBES to identify high-specialization expert paths during domain-specific post-training, we achieved 66% to 94.48% improvement in specialized domains with only 15% of original training resources, demonstrating that these diagnostic tools can be converted into concrete optimization operators. This work provides the first systematic methodology for evaluating expert specialization independently of accuracy metrics, offering crucial insights for the design and post-training optimization of next-generation MoE systems.
arXiv:2604.02511v2 Announce Type: replace Abstract: Public pooled single-cell perturbation atlases are valuable resources for studying transcription factor (TF) function, but downstream re-analysis can be limited by incomplete deposited metadata and missing internal controls. Here we re-analyze the human TF Atlas dataset (GSE216481), a MORF-based pooled overexpression screen spanning 3,550 TF open reading frames and 254,519 cells, with a reproducible pipeline for quality control, MORF barcode demultiplexing, per-TF differential expression, and functional enrichment. From 77,018 cells in the pooled screen, we assign 60,997 (79.2\%) to 87 TF identities. Because the deposited barcode mapping lacks the GFP and mCherry negative controls present in the original library, we use embryoid body (EB) cells as an external baseline and remove shared batch/transduction artifacts by background subtraction. This strategy recovers TF-specific signatures for 59 of 61 testable TFs, compared with 27 detected by one-vs-rest alone, showing that robust TF-level signal can be rescued despite missing intra-pool controls. HOPX, MAZ, PAX6, FOS, and FEZF2 emerge as the strongest transcriptional remodelers, while per-TF enrichment links FEZF2 to regulation of differentiation, EGR1 to Hippo and cardiac programs, FOS to focal adhesion, and NFIC to collagen biosynthesis. Condition-level analyses reveal convergent Wnt, neurogenic, EMT, and Hippo signatures, and Harmony indicates minimal confounding batch effects across pooled replicates. Our per-TF effect sizes significantly agree with Joung et al.'s published rankings (Spearman $\rho = -0.316$, $p = 0.013$; negative because lower rank indicates stronger effect). Together, these results show that the deposited TF Atlas data can support validated TF-specific transcriptional and pathway analyses when paired with principled external controls, artifact removal, and reproducible computation.
arXiv:2605.18068v1 Announce Type: new Abstract: Residual error propagation remains a fundamental problem in recurrent models, where small prediction inaccuracies compound over time and degrade long-horizon performance. Accurately modeling the correlation structure of such residuals is critical for reliable uncertainty quantification in probabilistic multivariate timeseries forecasting. While recent time-series deep models efficiently parametrize time-varying contemporaneous correlations, they often assume temporal independence of errors and neglect spatial correlation across the observed network. In this paper, we introduce Teger, a structured uncertainty module that overcomes the spa- tial and temporal limitations of error-correlated autoregressive forecasting. Teger proposes a spatial curvature-aware graph rewiring mechanism explicitly strengthening information-bottleneck edges identified by discrete Forman curvature. The component is integrated into a low-rank-plus-diagonal covariance head, preserving tractable inference via the Woodbury identity. Teger is backbone-agnostic, requiring only the latent state produced by any autoregressive encoder. We provide theoretical evidence of Teger, and experimentally evaluate it on LSTM, Transformer, and xLSTM backbones across four real-world spatio-temporal datasets, showing consistent improvement in Continuous Ranked Probability Score (CRPS). We further provide a formal theoretical analysis connecting curvature-aware rewiring to (i) oversquashing alleviation, (ii) improved spectral connectivity, (iii) reduced effective resistance, and (iv) improved covariance calibration bounds
arXiv:2605.18337v1 Announce Type: new Abstract: Large-scale news corpora support a wide range of research in Computational Social Science and NLP, yet access remains constrained: commercial archives impose prohibitive costs and licensing restrictions, while open alternatives like Common Crawl's CC-News require terabyte-scale storage and computationally intensive processing. We present Infini-News, a retrieval toolkit and index for the entire CC-News archive from August 2016 to the latest available snapshot. Our contributions are threefold. First, we extract, clean the text, and parse the structured metadata of over 1.35B articles. Second, we enrich the corpus with language detection using three frontier language classifiers (GlotLID, lingua, and CommonLingua), and with multi-source geographic attribution that resolves a country of origin for 83.4% of articles across 222 countries. Third, we construct Infini-gram indexes: suffix-array structures that let researchers search the full archive for arbitrary text patterns in sub-second time. Together, these resources lower the barrier to longitudinal, cross-national media research.
arXiv:2605.18693v1 Announce Type: new Abstract: As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, reusable, and executable skills from repositories and documents. Existing benchmarks primarily evaluate the efficacy of given skills or the ability of agents to solve downstream tasks from raw context, but they do not isolate skill generation itself as the object of study. We introduce SkillGenBench, a benchmark for evaluating skill generation pipelines under a unified and controlled protocol. In SkillGenBench, a generator receives raw corpora and produces standardized skill artifacts, which are then executed under fixed harnesses and assessed with unified evaluation procedures. The benchmark covers two generation regimes: task-conditioned generation, where a task-specific skill is synthesized after the task is revealed, and task-agnostic generation, where a reusable skill library must be distilled before downstream tasks are known. It also spans two complementary procedural sources: repository-grounded instances, where procedures are distributed across code, configuration, and scripts, and document-grounded instances, where procedures and constraints must be distilled from long-form text. We provide standardized task specifications, pinned environments, and evaluation protocols centered on deterministic execution-based checks, supplemented by auxiliary signals for diagnosis. Experiments across a range of skill-generation methods and backbones show substantial performance variation, highlight the difficulty of reusable skill distillation, and reveal distinct failure modes in skill generation from software repositories versus long-form documents. SkillGenBench establishes a reproducible testbed for studying skill generation as an independent research problem in agent systems.
arXiv:2605.01815v2 Announce Type: replace Abstract: Generative Adversarial Networks (GANs) can help overcome data scarcity in computer vision tasks by generating additional training samples. In this work, we explore generative data augmentation in two low-resource domains: Bangla handwritten character recognition and chest X-ray image analysis. We use DCGAN-based models trained on 64x64 images to generate synthetic samples and evaluate their quality using Inception Score (IS), Fr\'echet Inception Distance (FID), and visualization methods such as t-SNE and UMAP. To measure practical usefulness, we train image classifiers using real data and a combination of real and synthetic data. Experimental results show that synthetic augmentation improves data diversity and consistently increases classification performance in limited-data settings. We also investigate training stability techniques, including gradient penalty and spectral normalization, and perform ablation studies on synthetic-to-real data ratios and sample filtering strategies. In addition, we discuss challenges related to medical image evaluation, dataset licensing, and privacy concerns of synthetic data. Our approach is simple, reproducible, and provides a strong baseline for generative augmentation in resource-constrained imaging applications.
arXiv:2605.12445v2 Announce Type: replace Abstract: Scalable vector instruction sets such as Arm SVE enable vector-length-agnostic (VLA) execution, allowing a single implementation to adapt across hardware with different vector lengths. However, they complicate compiler code generation, as tiling and data layout decisions can no longer be fixed at compile time. We present an approach for enabling VLA code generation in an end-to-end ML compilation pipeline through vector-length-aware packed data layouts and corresponding compiler extensions. We integrate these mechanisms into MLIR/IREE and extend tiling, fusion, and vectorization to operate with scalable vector lengths. Evaluated on real-world ML workloads on Arm CPUs, our approach generates SVE code that is competitive with, and often outperforms, existing NEON-based code generation within IREE, achieving up to $1.45\times$ speedup. We also outperform PyTorch ecosystem frameworks, including ExecuTorch, TorchInductor, and eager execution, demonstrating the effectiveness of scalable vectorization in a production compiler setting. A simulator-based study further shows that the generated code scales with increasing SVE vector length on compute-bound workloads, supporting performance portability across hardware configurations.
arXiv:2605.18033v1 Announce Type: cross Abstract: Autonomous labs enable the integration of automated experiment execution, data analysis and decision making. The main challenge remains the integration of diverse data streams from multiple instruments, where the data is often heterogeneous and unsynchronized. The standard learning process of undetermined synthesis-process-structure-property relationships (SPSPR) usually relies on post-experiment analysis after data is fully collected, not during live experiments, and decision making is carried out independently across characterization equipment. Here, we demonstrate the Multi-instrument Autonomous Discovery (MAD) framework -- combining structural property mapping and functional property optimization simultaneously in a closed-loop manner. As an example, we applied MAD to phase change memory (PCM) materials, and, in particular on the Mn-Sb-Te ternary, a previously unexplored materials system for PCM. A multi-output model is employed to merge data from x-ray diffraction (XRD) and electrical resistance measurements simultaneously through a co-regionalization kernel that models the relationship between them. The output probabilistic posterior and uncertainty quantification facilitate decision making with shared knowledge, while the goals are different across tasks. We aimed to maximize the knowledge of crystal structure distribution using non-negative matrix factorization (NMF), while in parallel, we find the composition with the maximum resistance value, an important figure of merit for PCM. Leveraging MAD, we found promising electrical PCMs and identified the SPSPR within 25 closed-loop iterations, corresponding to a seven-fold speed-up. The framework opens a new path of study in large-scale autonomous facilities, where future experiments can be run in parallel together, not independently.
arXiv:2605.17849v1 Announce Type: new Abstract: LLM pretraining is shifting from a compute-bound to a data-bound regime, where available human (organic) text falls far short of scaling demands. However, reaching the data-bound regime does not mean the model has fully utilized its organic corpus. In this paper, we introduce SynPro, a synthetic data generation framework that helps LLMs more thoroughly learn from limited organic data. SynPro applies two operations, rephrasing and reformat, that present the same organic source in diverse forms to facilitate deeper learning without introducing external information. Both generators are optimized via reinforcement learning with quality, faithfulness, and data influence rewards, and are continuously updated as pretraining plateaus to target content the model has yet to absorb. We pretrain 400M and 1.1B models with 10% of their Chinchilla-optimal tokens (0.8B and 2.2B) from DCLM-Baseline, reflecting a realistic data-bound regime in frontier pretraining. Our results reveal that organic data is significantly underutilized by standard repetition: SynPro unlocks 3.7-5.2x the effective tokens of repetition, even surpassing the non-data-bound oracle that trains on equivalent unique data at the 1.1B scale. Analyses confirm that faithful, model-aware synthesis sustains data-bound scaling without causing distribution collapse. We open-source our code at https://github.com/cxcscmu/SynPro.
arXiv:2605.11854v2 Announce Type: replace Abstract: Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generation. However, post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient: training reconstructs randomly masked tokens in a single step, whereas inference follows a confidence-guided, multi-step easy-to-hard denoising trajectory. Recent trajectory-based self-distillation methods exploit such inference trajectories mainly for sampling-step compression and acceleration, often improving decoding efficiency without substantially enhancing the model's underlying capability, and may even degrade performance under full diffusion decoding. In this work, we ask whether self-distilled trajectories can be used not merely for faster inference, but for genuine knowledge acquisition. Although these trajectories lie on the pretrained DLM's own distributional manifold and thus offer a potentially lower optimization barrier, we find that naively fine-tuning on them with standard NELBO objectives yields only marginal gains. To address this limitation, we propose \textbf{T}rajectory-\textbf{A}ligned optimization via \textbf{Bo}ltzmann \textbf{M}odeling (\textbf{TABOM}), a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference. TABOM models the inference unmasking preference as a Boltzmann distribution over predictive entropies and derives a tractable pairwise ranking objective to align the model's certainty ordering with the observed decoding trajectory. Empirically, TABOM achieves substantial gains in new domains, expands the effective knowledge boundary of DLMs, and significantly mitigates catastrophic forgetting compared with standard SFT.
arXiv:2605.17927v1 Announce Type: new Abstract: In various surgical procedures, regions of interest (ROIs) such as organs or lesions are often occluded by overlying tissues, requiring surgeons to achieve adequate exposure for precise intervention. However, the irregular geometry, nonlinear biomechanical properties of overlying tissues, and limited intraoperative visibility of the ROI pose significant challenges to the autonomous execution of tissue retraction. To address this, we formulate a realistic model of the tissue retraction task and propose a learning-based adaptive control framework for achieving ROI exposure. The method optimizes control inputs online by monitoring changes in the visual boundary of the tissue, while leveraging a deep deformation estimation model trained on simulation data to identify the optimal grasping point and ensure the convergence and safety of the adaptive controller. Through simulations and real-world experiments on different deformable materials, it has been demonstrated that this framework exhibits zero-shot adaptation to similar tasks and can complete the autonomous retraction process, from initial grasp selection to full ROI exposure. Therefore, it has the potential to be applied in actual surgical assistance scenarios.
arXiv:2605.17693v1 Announce Type: new Abstract: Structure-based drug design has been accelerated by pocket-aware 3D generative models, yet most methods primarily fit the training distribution and may fall short of satisfying multiple properties required in real-world therapeutic drug discovery. Recently, increasing attention has focused on structure-based molecule optimization (SBMO), which targets fine-grained control over multiple specified molecular properties. In this paper, we present DEPPA, a novel SBMO approach building upon Denoising Diffusion Policy Optimization for fine-tuning a pre-trained pocket-aware diffusion model via reinforcement learning. DEPPA enables optimization over multiple properties, including binding affinity, drug-likeness, synthesizability and diversity. We formulate the reverse denoising process of the pretrained pocket-aware diffusion model as a multi-step Markov Decision Process, where the desired properties that serve as reward signals are evaluated on the final generated ligand molecules. DEPPA incorporates a coarse denoising scheduler during the RL fine-tuning to achieve efficient and effective molecule optimization. Experimental results on the CrossDocked2020 benchmark demonstrate that DEPPA outperforms baselines in binding affinity (Vina Score -8.5 kcal/mol), drug-likeness and diversity while exhibiting competitive performance in synthesizability. The source code is available at https://github.com/xy9485/DePPA .
arXiv:2605.18420v1 Announce Type: new Abstract: In contrast to dyadic interactions, higher-order interactions may contain one another, with subgroups naturally embedded within larger groups. These containment patterns arise empirically in ecology, sociology, computer science and the science of science, and have been studied under the names nestedness, simpliciality, encapsulation, and inclusion. In this chapter, we review each of these measures and unify them through a mathematical object known as the encapsulation directed acyclic graph, formulating each measure as a function of its properties. We demonstrate that nested structure is prevalent in social systems across several domains, show that different measures capture complementary aspects of this structure, and find that the absence of nestedness can itself be a powerful indicator of the mesoscale organization of a system.
arXiv:2605.18415v1 Announce Type: new Abstract: This paper presents a novel method to compare two numbers in Residue Number System (RNS) using an additional modulus, which is often already available because it is required in modular computations and digital signal processing scaling.Our method provides the comparison of two integers in the full range of the RNS base. It does not require moduli of a special form, unlike other state-of-the-art methods that are restricted to specific RNS bases or require bounds on input numbers. Our approach only requires one single conversion to a mixed radix representation with a complexity of O(n2), which can be reduced to O(log(n)) in time with parallelization. This provides a significant advantage over classical methods and more recent competitive methods which work under restrictions. This opens perspectives for advancements in challenging RNS operations such as division, scaling, and cryptographic applications.
arXiv:2605.18414v1 Announce Type: new Abstract: Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial scenarios -- even when explicitly instructed otherwise. We propose a governed MCP proxy that enforces attribute-based access control (ABAC) at two points: tool discovery, where unauthorized tools are removed from the model's context window, and tool invocation, where a second check blocks any unauthorized call. Across three models (Qwen 2.5 7B, Llama 3.1 8B, Claude Haiku 3.5) and 150 adversarial tasks spanning four attack categories, our proxy reduces unauthorized invocation rate (UIR) to 0% while adding under 50ms median latency. Prompt-based restrictions reduce UIR by only 11--18 percentage points, leaving substantial residual risk. Our results show that architectural enforcement -- not prompting -- is necessary for reliable tool access control in deployed agentic systems.
arXiv:2605.17759v1 Announce Type: new Abstract: To circumvent the inherent fidelity bottlenecks and optimization misalignment of VAE-based latent diffusion, pixel-space diffusion models have emerged as a compelling end-to-end paradigm. However, existing pixel diffusion models often struggle to balance computational efficiency with the preservation of high-frequency details. They frequently resort to patch-based compression or restricted local decoding, leading to a "spectral compromise" where high-frequency and fine-grained pixel information are suppressed. To address these challenges, we propose \textbf{FrequencyBooster}, a novel framework designed to empower pixel diffusion with full-frequency modeling capabilities without prohibitive overhead. The core of our method is a high-capacity decoder that specializes in extracting exhaustive high-frequency details and low-frequency semantics, the latter of which is derived from a Diffusion Transformer (DiT) backbone. Unlike prior works that sacrifice global context for local refinement, FrequencyBooster leverages high-dimensional feature representations to maintain global structural integrity while achieving superior pixel-level precision. Extensive experiments on ImageNet demonstrate the effectiveness of our approach: our model achieves a state-of-the-art FID of \textbf{1.60} at $256 \times 256$ resolution within only 320 epochs. Furthermore, at $512 \times 512$ resolution, FrequencyBooster attains an FID of \textbf{1.69}, significantly outperforming existing pixel-space and latent-space generative models.