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.
Science Journals
arXiv:2601.05569v3 Announce Type: replace
Abstract: Distributed AI systems face critical memory management challenges across computation, communication, and deployment layers. RRAM based in memory computing suffers from scalability limitations due to device non idealities and fixed array sizes. Decentralized AI frameworks struggle with memory efficiency across NAT constrained networks due to static routing that ignores computational load. Multi agent deployment systems tightly couple application logic with execution environments, preventing adaptive memory optimization. These challenges stem from a fundamental lack of coordinated memory management across architectural layers. We introduce Self Evolving Distributed Memory Architecture for Scalable AI Systems, a three layer framework that unifies memory management across computation, communication, and deployment. Our approach features (1) memory guided matrix processing with dynamic partitioning based on device characteristics, (2) memory aware peer selection considering network topology and computational capacity, and (3) runtime adaptive deployment optimization through continuous reconfiguration. The framework maintains dual memory systems tracking both long term performance patterns and short term workload statistics. Experiments on COCO 2017, ImageNet, and SQuAD show that our method achieves 87.3 percent memory utilization efficiency and 142.5 operations per second compared to Ray Distributed at 72.1 percent and 98.7 operations per second, while reducing communication latency by 30.2 percent to 171.2 milliseconds and improving resource utilization to 82.7 percent. Our contributions include coordinated memory management across three architectural layers, workload adaptive resource allocation, and a dual memory architecture enabling dynamic system optimization.
arXiv:2605.17704v1 Announce Type: new
Abstract: The lottery ticket hypothesis posits that dense networks contain sparse subnetworks, ``winning tickets,'' that, when rewound to their initial weights and retrained in isolation, match the performance of the full model. We ask a more mechanistic question: what internal object does a winning ticket preserve? We work in a combinatorial, clause-structured toy setting that admits an interpretable feature-space representation with well-defined combinatorial distances between features. We show that winning tickets in weight space correspond to precursor locations in feature space that are already near, at initialization, to the final feature-channel codes. Dense SGD resolves these locations through structured selection: proximal locations either converge to final codes or are rejected, with rejection concentrated at more crowded neurons, implicating competition under superposition. A winning ticket is thus a family of compatible code locations that jointly balance proximity to final codes with low inter-feature interference. Sparse retraining often re-expresses the same clause/template family on a different row, so the preserved object is family-level rather than microscopic row identity. We validate this account with lightweight probes based on feature-space distance and motion; in our setting, these probes frequently outperform established weight-based ticket discovery methods in both accuracy and exact code recovery. Although these findings are grounded in a toy setting, they suggest that the lottery ticket structure is governed by hidden feature-space geometry rather than weight-space subnetwork identity.
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:2508.15878v2 Announce Type: replace
Abstract: Formal theorem proving (FTP) has emerged as a critical foundation for evaluating the reasoning capabilities of large language models, enabling automated verification of mathematical proofs at scale. However, progress has been constrained by limited datasets due to the high cost of manual curation and the scarcity of challenging problems with verified formal-informal correspondences. We propose leveraging theoretical computer science (TCS) as a scalable source of rigorous proof problems, where algorithmic definitions enable automated generation of arbitrarily many challenging theorem-proof pairs. We demonstrate this approach on two TCS domains: Busy Beaver problems, which involve proving bounds on Turing machine halting behavior, and Mixed Boolean Arithmetic problems, which combine logical and arithmetic reasoning. Our framework automatically synthesizes problems with parallel formal (Lean4) and informal (Markdown) specifications, creating a scalable pipeline for generating verified proof challenges. Evaluation on frontier models reveals substantial gaps in automated theorem proving: while DeepSeekProver-V2-671B achieves 57.5\% success on Busy Beaver problems, it manages only 12\% on Mixed Boolean Arithmetic problems. These results highlight the difficulty of long-form proof generation even for problems that are computationally easy to verify, demonstrating the value of TCS domains for advancing automated reasoning research.
arXiv:2508.16438v4 Announce Type: replace
Abstract: Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG). However, existing approaches face significant challenges in complex reasoning-oriented multi-hop retrieval tasks: 1) Ineffective reasoning-oriented planning: Prior methods struggle to generate robust multi-step plans for complex queries, as rule-based decomposers perform poorly on out-of-template questions. 2) Suboptimal reasoning-driven retrieval: Related methods employ limited query reformulation, leading to iterative retrieval loops that often fail to locate golden documents. 3) Insufficient reasoning-guided filtering: Prevailing methods lack the fine-grained reasoning to effectively filter salient information from noisy results, hindering utilization of retrieved knowledge. Fundamentally, these limitations all stem from the weak coupling between retrieval and reasoning in current RAG architectures. We introduce the Orchestrated Planner-Executor Reasoning Architecture (OPERA), a novel reasoning-driven retrieval framework. OPERA's Goal Planning Module (GPM) decomposes questions into sub-goals, which are executed by a Reason-Execute Module (REM) with specialized components for precise reasoning and effective retrieval. To train OPERA, we propose Multi-Agents Progressive Group Relative Policy Optimization (MAPGRPO), a novel variant of GRPO. Experiments on complex multi-hop benchmarks show OPERA's superior performance, validating both the MAPGRPO method and OPERA's design.
arXiv:2605.18680v1 Announce Type: new
Abstract: Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoes, accessories) under strict category and topology constraints. While users increasingly expect free-form text control, text-only retrieval is brittle: natural language is ambiguous with respect to platform taxonomies, metadata is often noisy or informal, and independently retrieved components can be stylistically inconsistent or geometrically incompatible. We propose \textbf{CMAG}, a concept-scaffolded retrieval and verified composition framework for marketplace avatar generation. Given a prompt, CMAG first synthesizes an intermediate 3D concept scaffold that disambiguates intent beyond text by providing global spatial and stylistic context. In parallel, a view-aware part discovery module extracts localized visual evidence via prompt decomposition and text-grounded segmentation. A prompt-conditioned taxonomy router enforces category coverage and resolves semantic-to-taxonomic mismatch, after which a hybrid category-wise retriever combines part-based fusion with a concept-residual fallback using feature suppression. Finally, an agentic vision--language model filters and re-ranks candidates across categories and drives an iterative verification loop to assemble prompt-faithful, topologically consistent avatars from catalog assets. We evaluate CMAG on diverse compositional prompts and demonstrate improved retrieval robustness and compositional correctness compared to strong baselines, highlighting the importance of 3D concept scaffolding under prompt ambiguity.
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:2605.17707v1 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:2605.18491v1 Announce Type: new
Abstract: Methods: Nine SSL methods spanning four pretext-task families were pretrained from scratch using the same 10{,}412 3D CT scans (1.89~M 2D axial slices) covering varied disease sites. The pretrained Swin Transformer encoder from each method was integrated into a SwinUNETR-style segmentation network (Swin encoder with a 3D CNN decoder and skip connections) and fine-tuned on nine public segmentation tasks of varying complexity, including large abdominal organs, head-and-neck structures, and tumors from CT and MRI. Performance was assessed using Dice similarity coefficient (DSC). Fine-tuning convergence speed, transferability across modalities (CT-to-MRI), and feature-reuse patterns between few- and many-shot fine tuning were further analyzed using centered kernel alignment.
Results: Self-distilled masked image transformer (SMIT), which combines masked image modeling (MIM) with local and global self-distillation, achieved the highest overall segmentation accuracy across the nine tasks, the fastest fine-tuning convergence, and the smallest few-shot-to-many-shot performance gap, indicating the strongest data efficiency. SMIT also showed the most consistent feature-reuse patterns between few- and many-shot fine tuning. MIM-based SimMIM and self-distillation methods (DINO, iBOT) outperformed contrastive learning and rotation prediction, which rely on image-level global representations. Differences between SSL methods were largest in the few-shot setting and narrowed as the size of the labeled fine-tuning dataset increased, indicating that the choice of SSL pretraining matters most under limited annotation budgets.
arXiv:2508.17431v4 Announce Type: replace
Abstract: Person re-identification (re-ID) is a fundamental task in intelligent surveillance and public safety. Federated learning (FL) provides a privacy-preserving paradigm for collaborative model training without centralized data collection. However, deploying FL in real-world re-ID systems remains challenging due to statistical heterogeneity caused by non-IID client data and the substantial communication overhead incurred by frequent transmission of large-scale models. To address these challenges, we propose FedKLPR, a lightweight and communication-efficient federated learning framework for person re-ID. FedKLPR consists of three key components. First, KL-Divergence-Guided training, including the KL-Divergence Regularization Loss (KLL) and KL-Divergence-aggregation Weight (KLAW), is introduced to mitigate statistical heterogeneity and improve convergence stability under non-IID settings. Second, unstructured pruning is incorporated to reduce communication overhead, and the Pruning-ratio-aggregation Weight (PRAW) is proposed to measure the relative importance of client parameters after pruning. Together with KLAW, PRAW forms KL-Divergence-Prune Weighted Aggregation (KLPWA), enabling effective aggregation of pruned local models under heterogeneous data distributions. Third, Cross-Round Recovery (CRR) adaptively controls pruning across communication rounds to prevent excessive compression and preserve model accuracy. Experiments on eight benchmark datasets demonstrate that FedKLPR achieves substantial communication savings while maintaining competitive accuracy. Compared with state-of-the-art methods, FedKLPR reduces communication cost by 40\%--42\% on ResNet-50 while achieving better overall performance.
arXiv:2605.18490v1 Announce Type: new
Abstract: We preregistered a comparison of two ways to help an LLM answer questions over a small research corpus: a single-round Vector RAG system and an LLM-compiled markdown wiki. Both systems answered the same 13 questions over 24 papers using the same answer-generating model, and their answers were scored by blinded LLM judges.
The wiki scored much better at connecting findings across papers, but its advantage in answer organization was not strong after judge adjustment. RAG met the preregistered test for single-fact lookup questions. The clean query-side cost result went against the expected wiki advantage: under the tested setup, the wiki used far more query tokens than RAG, so it could not recover any upfront build cost through cheaper queries.
Two exploratory analyses changed how we interpret the result. First, claim-level citation checking favored the wiki: its cited pages more often supported the exact claims being made, even though RAG scored better on the overall groundedness rubric. Second, a decomposition-based RAG variant recovered most of the wiki's advantage on cross-paper synthesis at lower LLM-token cost, but it did not recover the wiki advantage in claim-by-claim citation support.
The main conclusion is that grounded research synthesis is not a single capability. Systems can differ in how well they organize evidence, how well their citations support each claim, and how much they cost to run. In this study, no architecture was best on all three.
arXiv:2605.18488v1 Announce Type: new
Abstract: We present SPARC-atomSFE, a spectral finite-element package for accurate and efficient atomic structure calculations within the framework of Kohn-Sham density functional theory. The package supports both all-electron and norm conserving pseudopotential calculations across a comprehensive hierarchy of exchange-correlation approximations, spanning local, semilocal, and nonlocal functionals. The latter includes hybrid functionals and the many-body random phase approximation, for which we implement both the generalized Kohn-Sham approach and the optimized effective potential (OEP) method, with OEP necessary for eigenvalue-dependent functionals. Spatial discretization is based on an adaptive grid with element nodes distributed according to the Legendre--Gauss--Lobatto scheme, high-order $C^{0}$-continuous Lagrange polynomial basis functions, and Gauss--Legendre quadrature for numerical integration. We present systematic convergence studies and identify the computational parameters required to achieve target accuracies. We validate the accuracy of SPARC-atomSFE through representative calculations spanning the various exchange-correlations approximations, obtaining results that generally agree with values in the literature to within $1~\mu\text{Ha}$ or better.
arXiv:2605.18480v1 Announce Type: new
Abstract: The computation of chance constraints in stochastic model predictive control is often numerically challenging due to the non-Gaussian nature of the disturbances. To overcome this problem, we propose an optimization computational framework applicable to non-Gaussian disturbances. This framework employs a numerical inversion method, utilizing the characteristic function of the disturbance distribution to compute the probability in the chance constraint as well as its gradient. To improve efficiency, it vectorizes integral points and reuses intermediate computations in Gauss-Kronrod quadrature. The framework is implemented within the YALMIP toolbox to perform chance constraint calculations for arbitrary non-Gaussian disturbances, applicable to both single-component distributions and mixture models. It allows the user to simply specify a distribution type and its parameters for the disturbance and directly compute the probability and its gradient to solve the optimization problem. The method is validated through a numerical example of a stochastic model predictive control application.
arXiv:2605.17545v1 Announce Type: cross
Abstract: We give a large family of almost perfect nonlinear (APN) permutations of finite vector spaces of every odd dimension divisible by three. We also give APN functions that are not bijective on even dimensions and related highly nonlinear functions. The functions we provide admit a so-called triprojective structure induced by the general linear group $\mathrm{GL}(3,2^m)$.
arXiv:2511.04472v3 Announce Type: replace
Abstract: Malware analysis systems, including dynamic-analysis sandboxes and digital forensics and incident response (DFIR) platforms, rely on telemetry pipelines comprising collection agents, serializers, and database backends to capture and present program behavior to analysts. We show that these data-handling components constitute an exploitable attack surface that can lead to denial-of-analysis (DoA) states without disabling sensors or requiring elevated privileges. We present Telemetry Complexity Attacks (TCAs), a new class of vulnerabilities that exploit mismatches between unbounded collection mechanisms and bounded processing capabilities. Our method recursively spawns child processes to generate deeply nested and oversized objects that stress serialization and storage boundaries, as well as visualization layers, e.g., JSON/BSON depth and size limits. Depending on the product, this leads to truncated or missing behavioral reports, rejected database inserts, serializer recursion and size errors, and unresponsive dashboards, with some cases also exhibiting normal malicious execution that was not recorded or presented to analysts. We evaluate our technique against 18 commercial and open-source malware analysis platforms and endpoint detection and response (EDR) solutions. Seven products fail at different stages of the telemetry pipeline; two CVE identifiers have been assigned (CVE-61301 and CVE-61303); one more is pending; one has been assigned to an underlying library, and others have issued patches or configuration changes. We discuss root causes and propose mitigation strategies to prevent DoA attacks triggered by adversarial telemetry.
arXiv:2509.16391v3 Announce Type: replace
Abstract: Machine unlearning (MU) aims to remove the influence of specific "forget" data from a trained model while preserving its knowledge of the remaining "retain" data. Existing MU methods based on label manipulation or model weight perturbations often achieve limited unlearning effectiveness. To address this, we introduce CoUn, a novel MU framework inspired by the observation that a model retrained from scratch using only retain data classifies forget data based on their semantic similarity to the retain data. CoUn emulates this behavior by adjusting learned data representations through contrastive learning (CL) and supervised learning, applied exclusively to retain data. Specifically, CoUn (1) leverages semantic similarity between data samples to indirectly adjust forget representations using CL, and (2) maintains retain representations within their respective clusters through supervised learning. Extensive experiments across various datasets and model architectures show that CoUn consistently outperforms state-of-the-art MU baselines in unlearning effectiveness. Additionally, integrating our CL module into existing baselines empowers their unlearning effectiveness.
arXiv:2605.17723v1 Announce Type: new
Abstract: Residential batteries increasingly serve two roles: they can earn money by arbitraging wholesale prices and providing grid services, and they provide backup power during outages. This dual use creates a basic tradeoff between earning market value and preserving outage readiness. Coordination across many batteries can help, but a provider cannot treat the fleet as a single virtual battery when each household is promised its own backup protection.
We compare standalone control, in which each home is dispatched independently, with pooling, in which homes are coordinated while each battery retains its own state of charge and household-specific backup requirement. Both regimes are implemented as model predictive control problems with 15-minute decision intervals and evaluated using household telemetry together with ERCOT market inputs. The empirical design focuses on the 543 homes in our sample that can support at least one backup product in standalone operation and studies backup caps ranging from 2 to 24 hours. Lower caps relax backup obligations, while the 24-hour cap coincides with assigning each home its own longest feasible backup tier.
Pooling remains beneficial in this service-constrained setting, but its value declines smoothly as backup obligations tighten. Standalone firm margin ranges from \$11.06 per home per week at the 2-hour cap to \$10.79 at the 24-hour cap, while pooling benefit falls from \$1.49 to \$1.27 per home per week. Relative to standalone firm margin, pooling is worth about 13.5% at the 2-hour cap and about 11.8% at the 24-hour cap. Coordination therefore still helps after preserving household-level backup guarantees, but its value declines as backup obligations tighten.
arXiv:2605.17727v1 Announce Type: new
Abstract: Frozen vision-language embeddings contain signals at multiple semantic resolutions, from object identity to attributes, relations, and full-caption meaning, but they expose these signals through a fixed-length vector interface. We study whether embedding length can be turned into a controllable semantic access interface. We propose \textbf{GraSP-VL}, which learns a shared near-orthogonal prefix transform over frozen VLM embeddings. GraSP-VL instantiates a \textbf{Semantic Matryoshka} interface: short prefixes are assigned coarse semantic roles, while longer prefixes progressively expose finer language-grounded distinctions. Because the transform is shared across image and text embeddings and preserves full-dimensional geometry, prefix behavior changes without rewriting the original VLM space. On a 20,147-example COCO/Flickr30K annotation pool, GraSP-VL reaches a staircase score of 53.01 and hard-negative selectivity of 89.76, while keeping full-space drift below $10^{-6}$. It also transfers to SugarCrepe-clean with 86.03 object accuracy and 11.96 mean external emergence, and preserves full-dimensional zero-shot CIFAR-100 accuracy. These results show that frozen VLM embeddings can be reorganized into a truncatable semantic prefix interface rather than merely compressed.
arXiv:2512.02617v2 Announce Type: replace
Abstract: Laminar set systems consist of non-crossing subsets of a universe with set inclusion essentially corresponding to the descendant relationship of a tree, the so-called laminar tree. Laminar set systems lie at the core of many graph decompositions such as modular decompositions, split decompositions, and bi-join decompositions. We show that from a laminar set system we can obtain the corresponding laminar tree by means of a monadic second order logic (MSO) transduction. This resolves an open question originally asked by Courcelle and is a satisfying resolution as MSO is the natural logic for set systems and is sufficient to define the property ``laminar''. Using results from Campbell et al. [STACS 2025], we can now obtain transductions for obtaining modular decompositions, co-trees, split decompositions and bi-join decompositions using MSO instead of CMSO. We further gain some insight into the expressive power of counting quantifiers and provide some results towards determining when counting quantifiers can be simulated in MSO in laminar set systems and when they cannot.
arXiv:2512.02691v3 Announce Type: replace
Abstract: Consider a high-multiplicity Bin Packing instance $I$ with $d$ distinct item types. In 2014, Goemans and Rothvoss gave an algorithm with runtime ${{|I|}^2}^{O(d)}$ for this problem~[SODA'14], where $|I|$ denotes the encoding length of the instance $I$. Although Jansen and Klein~[SODA'17] later developed an algorithm that improves upon this runtime in a special case, it has remained a major open problem by Goemans and Rothvoss~[J.ACM'20] whether the doubly exponential dependency on $d$ is necessary.
We solve this open problem by showing that unless the ETH fails, there is no algorithm solving the high-multiplicity Bin Packing problem in time ${{|I|}^2}^{o(d)}$. To prove this, we introduce a novel reduction from 3-SAT. The core of our construction is efficiently encoding all information from a 3-SAT instance with $n$ variables into an ILP with $O(\log(n))$ variables and constraints.
This result confirms that the Goemans and Rothvoss algorithm is essentially best-possible for Bin Packing parameterized by the number $d$ of item sizes in the context of XP time algorithms.
arXiv:2605.17732v1 Announce Type: new
Abstract: In this paper, we consider the non-Hermitian quaternion linear systems arising from color image restoration and three-dimensional signal filtering problems. For exploring to solve such systems, we present two innovative structure-preserving conjugate gradient-type methods, QNHERLQ and QNHERQR, which are based on the unitary equivalence transformations of the non-Hermitian quaternion matrices to tridiagonal forms, called quaternion Saunders-Simon-Yip tridiagonalization procedure. The proposed tridiagonalization procedure for non-Hermitian quaternion matrices is closely related to the quaternion Lanczos process for Hermitian matrices, and is very different from the quaternion Lanczos biorthogonalization process for non-Hermitian matrices. The convergence of QNHERLQ and QNHERQR is discussed, which depends on the singular values of the coefficient matrix. Also we show that both algorithms have the finite termination property and constant costs per iteration step. Numerical results illustrate that the proposed algorithms are with the robustness and effectiveness compared with QGMRES and QQMR.
arXiv:2605.17734v1 Announce Type: new
Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains largely advisory, lacking explicit mechanisms for when and how to intervene in the agent loop. To bridge the gap, we introduce HASP(Harnessing LLM Agents with Skill Programs), a new framework that upgrades skills into executable Program Functions (PFs). Rather than offering passive advice, PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context. HASP is highly modular: it can be applied at inference time for direct agent-loop intervention, during post-training to provide structured supervision, or for self-improvement by evolving validated, teacher-reviewed PFs. Empirically, HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks. For example, on web-search reasoning, inference-time PFs alone improve the average performance by 25% compared to (multi-loop) ReAct Agent, while post-training and controlled evolution achieve a 30.4% gain over Search-R1. To provide deeper insights into HASP, our mechanism analysis reveals how PFs trigger and intervene, how skills are internalized, and the requirement for stable skill library evolution.