Cryptography and Security
An Evidence Model for Agentic Processes: Evidence Claims, Trust Assumptions, and Policy Assessment
Arslan Brömme
Agentic AI systems increasingly exchange messages, invoke tools, request approvals, hold structured decision sessions, and modify shared artifacts. Logs and anchors can make selected records tamper-evident, but they can also mislead if their evidentiary meaning is implicit: a hash does not establish semantic truth, a signature does not establish authorization, and an external anchor does not establish capture completeness. This paper proposes an evidence claim model for agentic processes. It distinguishes artifact integrity, temporal existence, provenance, approval evidence, declared ordering, capture claim, relevance claim, deliberation traceability, monitoring claim, anchoring authorization claim, policy assessment claim, risk treatment claim, mitigation implementation claim, and management response claim. Semantic validity is treated as a recurring limitation. The model maps these claims to mechanisms, assumptions, limitations, and threats, and situates them in an
agent organization with functional CEO
agent, executive, operational, evidence, and audit roles, plus a plan-do-check-act-inspired management response loop. The contribution is conceptual: it does not validate a particular implementation, prevent all failures, or automate legal compliance. It provides a vocabulary for stating which claims an agentic black box can support, which claims it cannot establish, and which controls are required around it.
Read the full abstract ▾
Numerical Analysis
Cahn-Hilliard phase-field modeling of tumor growth via locally adaptive isogeometric analysis with THB-splines
Dhiraj S. Bombarde, Carlotta Giannelli, Alessandro Reali et al. (+1 more)
Predicting tumor dynamics in biological systems under physiologically relevant conditions using mathematical and computational models remains a challenging problem. Continuum models based on phase-field (diffuse-interface) formulations have proven to be an effective modeling strategy to govern tumor dynamics and interactions of multiple species. Within this framework, the present work investigates a tumor growth model based on the Cahn-Hilliard (CH) equation. The formulation involves a fourth-order differential operator that imposes higher continuity requirement on approximation spaces for a well-defined primal variational formulation. To address this challenge, we use isogeometric analysis (IGA), which inherently satisfies this requirement through spline-based basis functions and eliminates the need for mixed or auxiliary-variable approaches commonly used in standard finite element discretizations. Additionally, a locally adaptive IGA scheme with truncated hierarchical B-splines (THB-splines) is used to reduce computational cost while maintaining accuracy. The model is first evaluated on standard
benchmark cases and then applied to an organ-scale, patient-specific
geometric model of the breast reconstructed from
magnetic resonance imaging (MRI) data. Our results show that the model reproduces known tumor morphologies, ranging from a spheroidal pattern to fingered growth. A series of numerical experiments further shows the diversity of tumor dynamics produced by different model parameter choices. Our findings demonstrate the predictive potential of the CH-based phase-field tumor growth model integrated with a locally adaptive IGA framework.
Read the full abstract ▾
All authors Dhiraj S. Bombarde, Carlotta Giannelli, Alessandro Reali, Guillermo Lorenzo
Cryptography and Security
When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning
Wenrui Yu, Changlong Ji, Johannes Bjerva et al. (+1 more)
Secure Aggregation (SA) is widely regarded as a strong defense against model-update leakage in
Federated Learning (FL), as it reveals only aggregate results while hiding individual updates. In Decentralized
Federated Learning (DFL), SA is commonly instantiated as local neighborhood aggregation, where each node obtains a weighted aggregate over its neighbors. We show that this locality creates a structural leakage surface: sparse decentralized
topologies provide colluding semi-honest nodes with asymmetric aggregate views, exposing multiple hidden linear combinations of honest participants' private states. Reconstructing private states from these aggregate views is fundamentally challenging, as both the private states and the aggregation coefficients are hidden. We tackle this challenge by establishing a formal connection to the Hidden Subset Sum Problem, a long-studied problem in cryptography. Building on this formulation, we design a
lattice-based reconstruction approach that combines
lattice reduction with structural filtering to reconstruct protected model states. We evaluate our attack on image, tabular, and text tasks under sparse DFL
topologies. Our results show that colluding semi-honest nodes can recover the original local updates of honest nodes, enabling downstream reconstruction of private training data. These findings demonstrate that SA alone does not guarantee
privacy in DFL when local aggregation induces asymmetric observations.
Read the full abstract ▾
All authors Wenrui Yu, Changlong Ji, Johannes Bjerva, Qiongxiu Li
Computation and Language
Do Reviewers Still Reward Lexical Complexity? A Frozen-Rater Study of Preference Drift in 124K ICLR Reviews
Jiabin Zheng
Large
language models have collapsed the cost of producing lexically elaborate prose, and whether peer reviewers still reward it is a question about the evaluator, not about the text. When the association between a writing cue and review scores moves across years, the reviewers may have changed, the submissions may have changed, or both, and a regression of scores on text cannot say which. We separate the two with a frozen rater: 81,850 machine reviews of ICLR submissions from 2018 to 2025, all generated in one February-April 2025 window with one model family and one
prompt, so that its year-to-year coefficients track submission composition alone and the human-minus-frozen trend difference identifies reviewer preference drift. On 32,638 submissions with 124,615 human reviews, the human coefficient on non-domain lexical complexity falls from +0.142 to -0.015 while the frozen rater moves from +0.080 to +0.082; the three-way difference-in-differences is -0.0100 (q=0.013), and forty random-wordlist placebos through the same specification centre on zero. Humans still reward sentence-length variability, which the frozen rater never registers, while the frozen rater still pays for lexical complexity at its earlier rate. Every claim is held to a double gate of false-discovery control and interval exclusion, and the findings that failed
adversarial re-testing are reported. Reviewers discounted a cue whose production cost collapsed, as models of manipulable signals prescribe; an LLM judge calibrated to historical human preferences inherits the earlier schedule and drifts out of
alignment while its agreement with humans on totals stays ordinary.
Read the full abstract ▾
Multiagent Systems
From Evidence to Effect: Authority Semantics and Runtime Infrastructure for Stateful Agents
Yang Li, Zongsi Xu, Sergey Volkov et al. (+7 more)
Stateful
agents reuse artifacts after producing executions and permissions change. We formalize authority-sufficient observations and durable effects bound to execution and material identities. WTB implements this interface through runtime adapters, shared evidence, and transactional publication/recovery. Six study families separate the mechanism from its integration. Raw and typed evidence both solve 32/32 authority cases, with model-dependent planning effects. Fixed-intent enforcement blocks six unsafe proposals and executes 12 eligible authorized intents. Complete controls match WTB's capability. Paid integration yields 176/210 accepted
benchmark-source stages, including 19/30 publication stages, recovery on 8/8 primary SWE repositories, and the most complete continuous trajectories on each of three source tasks. The findings connect authority information, effect admission, and infrastructure reuse in stateful
agents.
Read the full abstract ▾
All authors Yang Li, Zongsi Xu, Sergey Volkov, hai liu, Tuo Zhou, Xiyu Chen, Di Wan, Dian Shao, Ye Luo, Hao Sun
Social and Information Networks
The conservative turn in science: The changing character of knowledge recombination
Cheng Zhang, Xinkun Liang, Yi Bu et al. (+1 more)
This study examines how the dominant mode of cross-disciplinary knowledge combination has changed over time. It addresses a limitation of existing studies that document declining disruptiveness at the level of individual works but do not reveal whether the mechanisms of cross-disciplinary knowledge flow have themselves shifted. Drawing on 56 million publications and 816 million citations from OpenAlex (1960-2025), the study classifies cross-disciplinary citations into five types based on the set relationship between the subfield portfolios of citing and cited publications and introduces a semantic-distance measure derived from SPECTER-v2
embeddings of publication abstracts. It subsequently demonstrates that cross-disciplinary citations have shifted markedly away from configurations with no shared disciplinary ground toward types built on partially overlapping knowledge bases, a reorientation further reflected in a steady decline in average semantic distance between citing and cited fields. This shift co-occurs with a
diffusion of brokerage positions across the network and a greater reliance on older literature, consistent with a system that has become broader and more decentralized in its interdisciplinary reach. Finally, this study discusses the implications of these findings for science policy and for the design of cross-disciplinary funding mechanisms.
Read the full abstract ▾
All authors Cheng Zhang, Xinkun Liang, Yi Bu, Hongkan Chen
Machine Learning · Cross-listed from hep-ph
Inclusive electron-nucleus cross section models from domain adaptation
Krzysztof M. Graczyk, Beata E. Kowal, Rwik Dharmapal Banerjee et al. (+3 more)
We apply transfer learning (TL) to construct data-driven models of inclusive electron-
nucleus cross sections. Starting from an ensemble of deep neural networks pretrained on \(^{12}\)C data, we fine-tune the models separately for \(^{3}\)He, \(^{6}\)Li, \(^{16}\)O, \(^{27}\)Al, \(^{40}\)Ca, and \(^{56}\)Fe. The resulting models improve for all targets, marginally so for oxygen, where the carbon baseline is already adequate, although their predictive robustness depends on the amount, coverage, and precision of the available target data. We systematically study how model performance depends on the number of fine-tuned layers, on the fraction and selection of the training data, and on the overlap between the source and target kinematic domains. The layer-wise analysis shows that oxygen requires only shallow adaptation, whereas helium, calcium, and iron require substantially deeper fine-tuning. Lithium represents the least robust case because of its limited
dataset, while aluminum demonstrates a strong sensitivity to a small subset of highly constraining measurements. For selected kinematic configurations outside the coverage of the carbon training data, the adapted models remain consistent with the measurements within their estimated uncertainties. Finally, we compare the resulting predictions with those of the phenomenological F1F2 model.
Read the full abstract ▾
All authors Krzysztof M. Graczyk, Beata E. Kowal, Rwik Dharmapal Banerjee, Jose Luis Bonilla, Hemant Prasad, Jan T. Sobczyk
Numerical Analysis
Selective boundary condition reduction via learned error gating
Daniel Fernández, Dominik Penk and Dominik Riedelbauch
Parametric PDEs can admit different boundary conditions with different accuracy and computational cost. We introduce a framework for learning when one reduced boundary condition can replace another: paired solutions train a neural network to estimate the resulting domain and boundary errors, and the simpler condition is used only when both predicted errors meet prescribed tolerances. We focus on singular limits in applications, in which a stiff Robin or nonlinear boundary law is replaced by its limiting Dirichlet form. We evaluate the method on a galvanic corrosion problem and other nonlinear stationary and
evolution problems.
Read the full abstract ▾
Computation and Language
Detecting Authorship in Political Texts with Inductive Stylometry
Gennadii Iakovlev and Levente Littvay
Political texts are rarely authored by the nominal speaker alone. Tweets,
speeches, reports, and official statements are drafted, edited, or harmonized by staff, yet political science has paid limited
attention to the stylistic traces these hidden authors leave behind. This paper develops and stress-tests an inductive stylometric approach for recovering latent authorship structure in political communication, combining character 3-gram features with UMAP dimensionality reduction, and Burrows' Delta. We apply the approach to six corpora that vary in length (from tweets to long documents), in mode (written and oral), and in
language (English and Hungarian). The approach recovers near-disjoint analyst fingerprints in formal legal prose in both
languages, sorts a politician's tweets into validated subsets while uncovering additional insights, and distinguishes scripted from improvised
speech. It fails, however, to resolve individual speechwriters within scripted corpora. Frequency-based stylometry is thus a powerful tool that, depending on authorial signal strength and institutional editing, can uncover authorship traces relevant to legislative studies, political communication, and policy research.
Read the full abstract ▾
Artificial Intelligence
SRPO: Setwise Relative Policy Optimization for Multi-Agent Systems
Shengtian Yang, Ziyu Xiong, Yu Li et al. (+3 more)
Multi-
agent systems enable complex
reasoning and tool use by coordinating
agents that divide roles and refine candidate solutions. Existing methods typically update individual
agent responses or treat a complete trajectory as one training example. However, these methods may produce misleading policy updates because they assign the same final outcome to responses or trajectory segments that may play different roles in different team decisions. This is because treating each response as an independent update may separate outputs that jointly determine the next action, while treating an entire trajectory as one update may combine decisions made after different observations. These limitations call for a policy update defined at the level of a team decision, outputs that lead to the same state transition are optimized under a shared objective. In this paper, we propose Setwise Relative Policy Optimization (SRPO) for multi-
agent systems. We represent the outputs used together to produce one state transition as an active set. A singleton set covers division of labor, while a larger set covers joint co-
evolution, and the set composition can change across decisions. SRPO assigns a shared advantage to each active set, clips the combined policy change, and normalizes its scale according to the set size. This ties each update to the decision that produced the next state. Experiments on mathematical
reasoning and multi-turn search demonstrate the effectiveness of SRPO across both tasks. Additional ablation studies analyze the normalization choice and training behavior under changing active-set sizes.
Read the full abstract ▾
All authors Shengtian Yang, Ziyu Xiong, Yu Li, Yewen Li, Qingpeng Cai, Lei Feng
Distributed Computing
Sample-Guided Exact Top-K Selection for Long-Context Sparse Attention
Siran Liu, Yang Xue, Theo Tang et al. (+11 more)
Sparse
attention bounds downstream
attention work by retaining a fixed-size subset of indexed
tokens, but its standalone exact Top-$K$ stage must still process materialized score rows whose length grows with context. Production radix selectors discover their first actionable boundary only after a complete-row pass, forcing another row-scale traversal before exact refinement. We observe that locating a compact upper tail requires substantially less resolution than identifying the exact rank boundary, and that fixed-stride partial views of the current row remain calibrated to the corresponding complete-row rank across ragged lengths. We present HPC-Ops Top-K, a sample-guided exact selector for ragged sparse-
attention score rows. A fixed-stride view proposes a row-local coarse boundary; the mandatory complete-row pass certifies its sufficiency, forms the admitted candidate set, and initializes exact FP32 refinement over the unresolved frontier. A nested secondary boundary and exact recovery handle underfilled proposals before any output is committed, so sampling controls common-path work but never correctness. The GPU implementation fuses complete-row certification and candidate formation, and combines persistent, KV-split, and direct-exact execution behind graph-capturable ragged-row dispatch. We evaluate HPC-Ops Top-K on indexer scores from Hy4-Preview. It outperforms the fastest verified external exact baseline by $1.29$–$1.75\times$ across 20 operator configurations, with a $1.55\times$
geometric-mean speedup. It further achieves $1.36\times$ and $1.48\times$ speedups on two framework-derived sparse-
attention traces. The implementation is available in HPC-Ops, Tencent's open-source high-performance operator library for LLM inference, at https://github.com/Tencent/hpc-ops.
Read the full abstract ▾
All authors Siran Liu, Yang Xue, Theo Tang, Changxu Shao, Qian Cheng, Haimeng Ren, Donghua Jiang, Haipeng Ming, Lehua Ding, Zhonghan Lin, Shengying Wei, Wei Liu, Kai Liu, Jianchen Zhu
Computer Vision
GSComplete: Gaussian Splat Completion with 2D Diffusion Priors
Elias Brugger, Philipp Erler, Stefan Ohrhallinger et al. (+1 more)
Gaussian splats provide a fast, high-fidelity representation for 3D objects but are often constructed from incomplete input data in practice, leaving missing regions. Existing completion methods either do not preserve the original splats or require scarcely available 3D training data. We propose GSComplete, which combines 3D generation based on Score
Distillation Sampling with a novel preservation loss that encourages the original splats to be preserved where they should be visible. This effectively completes the Gaussian splat object using only 2D
diffusion priors while fully preserving existing splats and generating new splats only in missing regions, without occluding the input. To evaluate our approach, we introduce a new
dataset of partial Gaussian splat objects and show that GSComplete achieves significantly more accurate preservation of the input than existing methods with comparable plausibility of the completed result. Our code and
dataset will be made available upon acceptance.
Read the full abstract ▾
All authors Elias Brugger, Philipp Erler, Stefan Ohrhallinger, Paul Guerrero
Hardware Architecture
FlexSpIM: An Event-Based Digital Compute-In-Memory Accelerator with Flexible Operand Resolution and Layer-Wise Hybrid Stationarity
Nicolas Chauvaux, Adrian Kneip and Charlotte Frenkel
Compute-in-
memory (CIM) accelerators for spiking neural networks (SNNs) offer a promising solution for achieving $\mu$s-level inference latency and ultra-low energy in edge
vision applications. However, their limited flexibility at both
circuit and system levels restricts their deployment across diverse workloads. This work introduces FlexSpIM, a digital CIM architecture supporting arbitrary operand resolution and shape within a unified storage for weights and
neuron states (i.e., membrane potentials). These
circuit-level capabilities enable a layer-level hybrid weight- and output-stationary dataflow, maximizing operand reuse and reducing costly on- and off-chip data movement during SNN execution. Measurement results from a fabricated FlexSpIM prototype in 40-nm CMOS demonstrate competitive 1-bit-normalized energy efficiency and higher throughput compared with prior fixed-precision digital CIM-based SNN accelerators, while providing bitwise resolution reconfiguration. Evaluated on the IBM DVS gesture
dataset, FlexSpIM achieves 95.8% accuracy while enabling up to 45% energy and 52% latency reductions in large-scale systems compared with fixed stationarity approaches.
Read the full abstract ▾
Machine Learning
Topological Fraud Detection in Latent Transaction Spaces
Avraham Bourla
Working entirely on topologically anonymized
embeddings, we perform fraud detection using iterative rounds of unsupervised filtering followed by supervised sniping. The result is an ultra-low latency
privacy–preserving triage that allows institutions to flag suspicious activity without compromising Personally Identifiable Information.
Read the full abstract ▾
Robotics
Safe Task Planning with Long-Term Graph Memory for Embodied Agents
Siyuan Li, Taiyan Lang, Aoqi Yan et al. (+6 more)
Large
language models (LLMs) and
vision-
language models (VLMs) have significantly advanced zero-shot task planning for
embodied agents. However, most LLM- and VLM-driven methods struggle to generate safe high-level actions due to a lack of physical risk awareness, particularly under partial observability, where hazards lie outside the immediate field of view. To address this challenge, we propose a novel safe task-planning framework, SafeMem, which constructs and maintains a long-term semantic graph
memory of the open and dynamic environment. Based on
egocentric observations, the proposed framework incrementally accumulates knowledge about surrounding objects and their relationships with a graph. Then, an LLM-based risk predictor evaluates candidate actions using the graph
memory, triggering a conservatism-modulated replanning loop with explanations for detected hazards. Extensive experiments on the IS-Bench
benchmark and a real-world
robot platform demonstrate that the SafeMem framework substantially improves safe success rates compared to state-of-the-art VLM-driven task planners.
Video results are available on our webpage: https://sites.google.com/view/safemem.
Read the full abstract ▾
All authors Siyuan Li, Taiyan Lang, Aoqi Yan, Jia Yu, Feifan Liu, Yihan Du, Yu Zheng, Xun Wang, Peng Liu
Information Retrieval
SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching
Lin Guan, Jia-Qi Yang, Zhishan Zhao et al. (+15 more)
Modeling long-term user behavior is central to sequential recommendation and billion-scale industrial recommender systems, yet production ranking models operate under strict latency,
memory, communication, and training-throughput constraints. At the 100K scale, the challenge extends beyond
attention complexity: raw sequence features must be stored, transferred, and repeatedly processed during training and online serving. Existing approaches based on history truncation, multi-stage behavior
retrieval, compressed lifelong histories, or train-short/infer-long extrapolation either weaken end-to-end optimization or retain substantial length-dependent cost. We present SequenceO1, an end-to-end framework for ultra-long user behavior sequence modeling, deployed at full traffic on Douyin with histories of up to 100K interactions. SequenceO1 follows a compress-then-reason design. Its Sketch
Attention (SA) uses learnable prototypes and prototype-wise normalization to compress the raw history into a fixed-size, target-agnostic user representation. Target-conditioned Stacked Target-to-History Cross
Attention (STCA) then models complementary time scales: a recent 10K suffix for short-term interests and the compact sketch for long-term preferences. To make training and inference practical, SequenceO1 combines low-rank user representation caching, multi-request user-level batching, pipeline lift, and a fused FlashSA kernel to amortize feature storage, communication, and computation across targets, training instances, and consecutive requests. Production experiments show consistent offline and online gains, while the compact cached sketch retains most of the benefit of directly scaling end-to-end sequence ranking to 100K. These results provide a practical model-system approach to efficient
attention, sequence compression, and scalable long-sequence and long-context recommendation systems.
Read the full abstract ▾
All authors Lin Guan, Jia-Qi Yang, Zhishan Zhao, Jiaqi Huang, Hangyu Wang, Longbin Li, Beichuan Zhang, Haonan Jiang, Jinan Ni, Xiangyu Fan, Xiaowen Li, Ziyao Ren, Yuhang Qi, Xiaolong Zhu, Xuanyuan Luo, Qiwei Chen, Yi Cheng, Lele Yu
Computer Vision
AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation
Shanwei Fan, Bin Zhang, Zhiwei Xu et al. (+4 more)
Aerial
Vision-and-
Language Navigation requires drones to follow natural-
language instructions and navigate through complex urban environments. Accurate
navigation relies on both local and global spatial information, which support immediate action grounding and long-horizon path planning, respectively. However, existing zero-shot methods typically operate at a single spatial scale, relying either on local representations constructed online from current observations or on global
memories built offline from historical experience. To address this limitation, we propose AirAnchor, a new paradigm that bridges local and global spatial information through spatial anchors and integrates both into a shared
navigation framework, enabling comprehensive spatial grounding for decision-making. AirAnchor consists of three core components: (1) Query-Driven Spatial Anchor Grounding, which identifies decision-relevant anchors from visual observations and organizes them into local spatial representations; (2) Persistent Object Spatial
Memory, which incrementally maintains an object knowledge base as persistent global spatial
memory and retrieves landmark-related spatial priors; and (3) a Spatially-Informed
Navigation Agent, which explicitly integrates both local and global spatial information into an agentic framework for decision-making. Extensive experiments on AerialVLN demonstrate that AirAnchor substantially outperforms existing zero-shot baselines, validating the effectiveness and efficiency of the proposed paradigm.
Read the full abstract ▾
All authors Shanwei Fan, Bin Zhang, Zhiwei Xu, Yingxuan Teng, Siqi Dai, Lin Cheng, Guoliang Fan
Networking
AI-Native Orchestration in the 6G Continuum: Evolving Operator Platforms with Agentic AI
Claudia Carballo González, Hatim Chergui, Sergio Giménez-Antón et al. (+5 more)
As Sixth-Generation (6G) networks evolve towards a seamless Cloud-Edge-Internet of Things (IoT) continuum, autonomous orchestration across distributed compute and network domains becomes critical. Future 6G services will span multiple administrative and operator domains, making federation essential for ubiquitous, ultra-low-latency service continuity beyond individual footprints. This complexity demands AI-native mechanisms supporting intent-driven automation and closed-loop management. While the GSMA Operator Platform (OP) provides the architectural blueprint for multi-operator federation and network capability exposure, and the ETSI Software Development Group OpenOP (SDG OOP) offers a primary open-source reference implementation, current frameworks are limited by stateless API interactions and lack native intelligence. This paper proposes an Agentic-driven Intelligence extension for the GSMA OP architecture, using the OOP as the reference framework. We introduce an AI-native orchestration layer where autonomous
agents manage persistent service contexts and enable closed-loop control via CAMARA APIs. By integrating a Declarative Monitoring and Alerting System (DeMAS) into the OOP stack and establishing a decentralised
agent negotiation protocol, the proposed architecture enables real-time, intent-driven resource optimisation and autonomous cross-domain conflict resolution across
federated domains. We validate our approach through a representative 6G use case involving Ultra-Reliable Low-Latency Communication (URLLC) and enhanced Mobile Broadband (eMBB) coexistence, demonstrating that an agentic OP framework autonomously reconciles stringent Service Level Agreements (SLAs) while enhancing infrastructure energy efficiency. Our findings establish a scalable blueprint for cross-domain Network-as-a-Service (NaaS) models that align standardised exposure with 6G autonomous requirements.
Read the full abstract ▾
All authors Claudia Carballo González, Hatim Chergui, Sergio Giménez-Antón, Mohammadreza Mosahebfard, Juan Sebastián Camargo, Pouria Sayyad Khodashenas, Vasileios Theodorou, Christos Verikoukis
Systems and Control
A Two-Stage, Model-Based Reinforcement Learning Approach for Active Flow Control of Bluff Body Wakes
Aayushman Sharma and Suman Chakravorty
This paper develops a data-driven, output-feedback approach to the infinite-horizon optimal control of high-dimensional nonlinear systems with unknown and unstable
equilibria, using sparse partial observations. The approach builds on the transfer-plus-regulation decomposition of the infinite-horizon problem: a finite-horizon nonlinear transfer drives the system into a region where the dynamics are well-approximated by a linear model about the unknown operating point, and an infinite-horizon linear regulator identified within that region completes stabilization. We extend this framework to the partially observed setting by combining an ARMA-based information-state construction with a two-stage control architecture: an iterative linear quadratic regulator (iLQR) approach on the information state drives the system to the
equilibrium neighborhood, discovered implicitly without prior knowledge of the target, and a locally identified time-invariant ARMA model provides the infinite-horizon regulator for asymptotic stabilization. The method requires no adjoint solver, reduced-order model, or full-state access. We validate the approach on high-fidelity Navier-Stokes simulations of the cylinder wake at $\mathrm{Re}=100$ using only eight surface pressure sensors, an order of magnitude fewer than recent model-based RL methods. The controller achieves complete suppression of
vortex-shedding-induced lift oscillations and a $44\%$ reduction in total drag relative to the uncontrolled baseline.
Read the full abstract ▾
Artificial Intelligence
EvolveScaler: Synthesizing Information-Evolution Contexts via Executable State Machines and Natural-Language Rendering
Ziliang Zhao, Zenan Xu, Shuting Wang et al. (+6 more)
In persistent interactions, long contexts may encode an evolving process rather than a fixed record: later events can revise or revoke earlier information, changing what remains valid and what conclusions follow. We call this setting information
evolution (IE). Solving IE requires identifying valid records, applying updates in order, and reconstructing the query-relevant state from the event history. Existing text-first synthesis pipelines make such data difficult to verify because state transitions and answer logic remain implicit. We introduce EvolveScaler, a code-driven framework that defines information
evolution before rendering it as natural
language. Human-authored operational specifications define state transitions, record validity, difficulty controls, and executable answer logic; a strong LLM then synthesizes a self-contained simulator from each specification. Executing validated simulators produces natural-
language multi-turn event histories, while deterministic replay computes reference answers and atomic checklists. We instantiate EvolveScaler with 117 task prototypes and 159 final-question operators across five difficulty levels spanning approximately 7 to 1,200 events per instance, yielding about 35,100 training examples and 585 validated evaluation instances. On the very_long tier, the strongest model reaches 59.3% avg@5, while six models score below 10%. Training an internal A3B model on 6,000 EvolveScaler examples improves performance over its base checkpoint on all eight independently constructed out-of-distribution
benchmarks, with a 5.25-point average gain. These results show that code-driven IE synthesis provides both challenging evaluation and transferable training supervision.
Read the full abstract ▾
All authors Ziliang Zhao, Zenan Xu, Shuting Wang, Zhao Wang, Bowen Cao, Minda Hu, Lincheng Li, Pluto Zhou, Zhicheng Dou
Sound · Cross-listed from eess.AS
Semantic Refinement of Universal Audio Representations through Audio-Description Alignment
Lejun Min, Junyu Dai, Ruichen Zheng et al. (+7 more)
Universal audio representations must preserve acoustic detail while making high-level concepts accessible across
speech, music, environmental sound, and downstream models of different capacities. We study semantic refinement of an acoustically pretrained encoder by adding audio-description
alignment to a foundation of BEST-RQ, reconstruction, and CTC. We compare matched control, shuffled-description, and correctly paired trajectories to distinguish correct correspondence from an extra contrastive objective. Each endpoint is frozen and evaluated with a temporal-mean linear probe and a sequence-aware LLM readout, testing whether the refined information is directly accessible and remains useful to a stronger model. Across three paired seeds, correct
alignment improves domain-balanced classification by 4.66 points with the linear probe and 2.59 points with the sequence-aware LLM, with positive changes in every domain. Correct pairing accounts for 87% of the linear-probe gain, while the LLM shows its clearest correspondence-specific benefit in captioning. Dense acoustic objectives provide complementary gains under both readouts. A separate 24-layer continuation remains competitive with leading public encoders under the shared evaluator, supporting the recipe beyond the controlled study.
Read the full abstract ▾
All authors Lejun Min, Junyu Dai, Ruichen Zheng, Xinyue Fan, Yang Xiang, Huaichen Zhang, Xingchen Song, Yufei Shi, Han Zhao, Xiangang Li
Networking
Toward Fully Autonomous 6G Networks: AI-driven Operational Efficiency and Optimization
David Reiss, Oriol Sallent, Miguel Catalan-Cid et al. (+1 more)
Mobile networks
evolution is characterized by a substantial increase in system complexity, driven by the need to accommodate a growing number of heterogeneous services on top of the digital infrastructure. This growth in service accommodation is expected to accelerate with the adoption of the Network as a Service (NaaS) paradigm, which has emerged as a promising approach to accelerate network innovation while enabling new revenue streams for operators. Although it is fundamental to abstract network capabilities for third-party developers, it poses significant challenges in terms of efficient network operation. To address this increased complexity, future mobile networks are envisioned to be inherently Artificial Intelligence (AI)-native. In particular, the integration of AI within the
Radio Access Network (RAN) becomes a key enabler for optimizing operation, energy consumption, and autonomous network control. In this context, this research explores the convergence of AI-native RAN and NaaS ecosystems to enable autonomous 6G RAN management. We propose an Agentic-based orchestration framework capable of interpreting intent-based policies. The proposed framework becomes key to integrate external NaaS requests with internal network management policies.
Read the full abstract ▾
All authors David Reiss, Oriol Sallent, Miguel Catalan-Cid, Daniel Camps-Mur
Hardware Architecture
PENDA: An Efficient Processing Element via Norm-of-Difference for Deep Learning Accelerators
Kai-Chieh Hsu and Tian-Sheuan Chang
Inner product computation dominates the computational cost of deep learning models; thus, accelerating this primitive is key to improving hardware efficiency. However, most existing techniques rely on approximations, which can degrade model accuracy. To preserve exactness while optimizing hardware, this paper presents PENDA (processing element via norm-of-difference architecture), which leverages the law of cosines to recast multiplications as squared-difference operations. Replacing multiply-accumulate units with the proposed norm-of-difference units yields 11~36%, 5~48%, and 11~19% reductions in area, energy, and clock period, respectively, for the PE array of a deep learning accelerator.
Read the full abstract ▾
Numerical Analysis · Cross-listed from gr-qc
Picard Iteration for the Characteristic Initial Value Problem in Einstein Equations
Shengrong Wu
We present an iteration
algorithm for
vacuum and Einstein scalar-field equations in double-null gauge, which transform the non-linear PDE into systems of ODE. The numerical realization combines characteristic constraint solves, LGL spectral elements, pole-free spherical operators, Galerkin projection, and independent first-order residual and consistency checks.
Read the full abstract ▾
Computer Vision
CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learning
Imane Chraki, Pierre Marza, Stergios Christodoulidis et al. (+1 more)
Multiple Instance Learning (MIL) is widely used for weakly supervised learning, particularly in digital pathology, where fine-grained annotations are costly. Most MIL methods aggregate instance features via
attention mechanisms. However,
attention weights do not always faithfully reflect instance importance and may focus on spuriously correlated regions. In this work, we propose CAR-MIL, a framework that explicitly guides
attention learning through a counterfactual
attention regularization objective inspired by counterfactual explanations. Built on a standard
attention-based MIL architecture, our approach introduces a lightweight counterfactual
attention branch trained to produce an alternative prediction while remaining close to the factual
attention distribution. This encourages prediction changes to arise from minimal, structured redistributions of
attention, leading to more informative evidence allocation. The resulting factual and counterfactual
attention maps capture complementary evidence: the former highlights regions supporting the prediction, while the latter reveals regions whose reweighting would challenge it. We evaluate our method on synthetic MIL
benchmarks with instance-level ground truth enabling controlled analysis of
attention behavior and on five digital pathology
datasets across four tasks. CAR-MIL maintains competitive classification performance, with the largest gains observed on more challenging tasks, while improving
attention reliability, demonstrating the benefits of integrating counterfactual explainability
reasoning into
attention learning. Code is available at: https://github.com/ImaneCR/CAR-MIL/.
Read the full abstract ▾
All authors Imane Chraki, Pierre Marza, Stergios Christodoulidis, Maria Vakalopoulou
Artificial Intelligence
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Zongjie Li, Alan Z. W, John Nicolas J et al. (+4 more)
Training capable cyber
agents is often treated primarily as a problem of model scale, yet open-weight post-training is constrained more directly by the cost of executable environments, reliable multi-turn supervision, and access to strong teachers. We present a data-centric framework that addresses these bottlenecks through five complementary systems: Choulea analyzes hidden
reasoning signatures, SkyReal reduces teacher-sampling cost, Hongzwang bypasses API restrictions on teacher execution, PSBreakup restores capabilities weakened by model merging, and Kreator converts expert interventions into trainable
reasoning. Our data engine constructs resettable coding, vulnerability, CTF, kernel-history, full-exploit, firmware, and device-backed environments. Candidate trajectories are retained only after execution verification and evidence
auditing, yielding 164,269 trajectories for long-context supervised fine-tuning. The three checkpoints improve over their starting models by an average of 23.76% on the full CyberGym suite and 10.49% across the pooled CTF suites. As of September 1, 2026, Feyospace-s1 achieves a verified success rate of 63.24% and ranks 10th on the official CyberGym leaderboard, while all three checkpoints rank 1st among models at comparable parameter scales. To our knowledge, this is the first end-to-end demonstration that a seven-person independent team can train open-weight models with leading agentic cyber capability.
Read the full abstract ▾
All authors Zongjie Li, Alan Z. W, John Nicolas J, Walter H. F, Scott Donald L, Gordon Y. P, Deke X Jr
Machine Learning
Stochastically Perturbed Weights: Ensembles from Deterministic Machine-Learning Weather Models
Simon Adamov, Oliver Fuhrer, Reto Knutti et al. (+1 more)
Machine-learning weather models (MLWMs) now match or outperform operational numerical weather prediction (NWP) at global medium-range
forecasting, at far lower inference cost. Many deployed MLWMs are deterministic, producing a single forecast with no estimate of its own uncertainty, whereas a growing family of trained-probabilistic models generate calibrated ensembles directly, at the price of a dedicated training run. We ask instead how much uncertainty can be extracted from a deterministic checkpoint that already exists, without retraining it. Where physical ensembles represent model uncertainty by stochastically perturbing parametrisation tendencies, we perturb the network's raw weight tensors at inference time, a scheme we call stochastically perturbed weights (SPW). We also ask whether it works, where and on which scales to inject the noise, and where it fails. A three-phase ablation across four deterministic backbones, Aurora, GraphCast, SFNO, and AIFS, selects one production baseline per model, benchmarked against the trained-probabilistic AIFS-ENS, FourCastNet 3 and Atlas as well as the operational ECMWF ensemble (IFS-ENS) over 112 initialisation times. At a 240 h (10-day) lead time the SPW ensembles reach continuous ranked probability skill scores (CRPSS) between 0.04 and 0.13 below the best trained-probabilistic baseline, at zero marginal training cost. No injection site works across models: the productive tensor group is architecture-specific, so SPW is at present a tuning procedure rather than a plug-and-play recipe. Its main failure mode is a coherent whole-field offset that overdisperses the domain mean, and restricting the noise to coarse scales or perturbing the initial conditions each repair part of it.
Read the full abstract ▾
All authors Simon Adamov, Oliver Fuhrer, Reto Knutti, Sebastian Schemm
Computation and Language
Compositional Multilingual and Behavioral Attribute Steering
Hyun Gu Kang, Daniil Gurgurov, Tanja Baeumel et al. (+2 more)
This study examines the compositionality of steering vectors for
language and behavioral control in large
language models. Focusing on
language, jailbreak, and conciseness, we investigate whether additive, training-free composition of attribute steering vectors can preserve the intended steering effect of each attribute, across four instruction-tuned models from two model families and two size scales. We find that single-attribute steering is reliable for all three attributes, but only within an appropriate combination of intervention layer and steering strength, with abstract behaviors (jailbreak, conciseness) favoring middle layers and
language favoring earlier layers. We show that additive composition of two attribute vectors succeeds in steering both attributes simultaneously when each is injected at its own best-performing layer, and that this partially extends to three simultaneously composed attributes, addressing an inconsistency left open by prior work on training-free composition. We further analyze the
geometric properties of these steering vectors, finding that they are approximately orthogonal in the residual stream, consistent with their compositional behavior.
Read the full abstract ▾
All authors Hyun Gu Kang, Daniil Gurgurov, Tanja Baeumel, Josef van Genabith, Simon Ostermann
Robotics
Coverage Path Planning for Redundant Manipulators using Generalized Spanning Trees
Raksi Kopo and Kostas J. Kyriakopoulos
Surface coverage with task-redundant manipulators is challenging because each surface point may admit multiple inverse kinematics (IK) solutions, and configuration choices strongly affect motion quality. This paper extends the classical Spanning Tree Coverage (STC) method to redundant manipulators through offline and online Joint Spanning Tree Coverage (JSTC)
algorithms. Offline JSTC samples multiple Inverse Kinematics (IK) solutions per grid
cell and formulates the problem as a Generalized Minimum Spanning Tree (GMST), selecting one configuration per
cell and tracing the resulting tree to obtain a non-revisiting coverage path. Online JSTC incrementally expands and backtracks a spanning tree with feasibility and cost evaluation while handling dynamic grid updates. Simulation results show that offline JSTC reduces computation time, reconfigurations, and joint motion compared to other methods, while online JSTC achieves fast per-step planning in dynamic scenarios.
Read the full abstract ▾
Robotics
Localized Visual Feature Aggregation via Focus Pooling for Visuomotor Policies
Ruiyu Wang, Zheyu Zhuang, Danica Kragic et al. (+1 more)
Focusing on spatially localized, control-relevant visual cues has been shown to improve data efficiency in visuomotor policies by reducing the need to model task-irrelevant visual variation. Existing methods often impose this focus through input preprocessing, such as cropping control- or object-centric regions in RGB images or point-clouds. However, it remains underexplored whether such localized features can be exposed directly from commonly used convolutional neural network (CNN) encoded features. In this paper, we show that intermediate CNN features preserve localized visual context for control, but existing pooling methods fail to aggregate it effectively. We introduce FocusPool, an
attention pooling module that selectively aggregates intermediate visual features according to their relevance to the
robot's current proprioceptive context. The resulting pooled representation captures task-progressive, control-relevant local information and is used directly for policy learning. Across simulation and real-world experiments, FocusPool improves policy success rates over pooling and explicit local focus methods by 36.2% and 41.2%, with training only 5.8% of encoder parameters.
Read the full abstract ▾
All authors Ruiyu Wang, Zheyu Zhuang, Danica Kragic, Florian T. Pokorny