Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Thursday 20 August

Information Theory

Tri-Hybrid Beamforming for T-RIS-Enabled Base Station

Transmissive reconfigurable intelligent surfaces (T-RISs) integrated into the transmitter provide a viable realization of tri-hybrid multiple-input multiple-output (MIMO), where spatial processing is distributed across the digital, analog radio-frequency (RF), and electromagnetic (EM) domains. However, unlike conventional RIS-assisted links, a transmitter-native T-RIS directly participates in radiation formation, making T-RIS front-end modeling and weighted sum-rate (WSR)-oriented joint precoding challenging under practical hardware constraints. This paper develops a unified modeling and precoding framework for transmitter-native T-RIS tri-hybrid multi-user (MU) downlink transmission. Specifically, starting from a continuous-field description, the received field is characterized by the interaction among the feed array, the programmable T-RIS aperture, and the user-side propagation, leading to a cascaded baseband input-output model for MU precoding. Furthermore, the same representation is instantiated in the Fresnel, Fraunhofer, and mixed-field regimes, so that near-field focusing and far-field angular steering can be handled within one front-end model. Additionally, a WSR maximization problem is formulated over the digital precoder, analog network, and T-RIS coefficients under power and quantization constraints. A two-level solver is then developed by coupling outer weighted minimum mean-square error (WMMSE) updates with WMMSE-induced aperture-field shaping and hardware projection. Simulations validate the modeling accuracy and convergence, and show that the proposed full tri-hybrid design improves WSR over baselines while suppressing mixed-field cross-regime leakage.
Read the full abstract

Machine Learning

RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations

We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic clickstream environments sampled from a broad structural causal prior, enabling it to amortize Bayesian-style inference from a small support set. At inference, a lightweight decoder-only transformer conditions on a handful of domain sequences and produces next-item predictions for queries in a single forward pass, without any weight updates. Across eight public benchmarks, RecPFN achives state-of-the-art zero-shot performance while remaining strongly competitive with supervised methods in low-compute and low-data regimes. It is deployment-efficient and robust to domain shift, outperforming strong zero-shot baselines that rely on large real-interaction corpora. RecPFN provides a practical path toward generalizable, data-efficient recommenders and opens avenues for richer priors, longer-context ICL, and multimodal extensions. Code for training and evaluation is publicly available at https://github.com/SAP-samples/tabular-ai-recpfn/.
Read the full abstract

All authors En Zhi Tan, Jia Xiang Lim, Bryan Lijie Chew, Tze Minh Ng, Benjamin Yan Han Yap

Networking

Proper Sea Surface Roughness Enhances the Performance of Near-Shore Maritime Networks

Accurate performance analysis for near-shore maritime wireless communication is essential for ensuring robust and reliable operations. However, existing analytical models often rely on oversimplified propagation assumptions, such as a perfectly smooth sea surface, which fail to capture the full dynamics of the maritime channel. In this paper, we develop a physically grounded analytical framework using stochastic geometry that bridges this gap. The spatial distribution of vessels is modeled as a non-homogeneous Poisson point process to reflect realistic near-port densities. We replace the idealized smooth-sea assumption by deriving a novel reflection coefficient from the classical Rayleigh criterion, which explicitly links the path loss to the significant wave height. Integrating this roughness-aware channel model into the stochastic geometry framework, we derive new analytical expressions for the uplink coverage probability and average ergodic rate, providing the first tractable characterization of aggregate interference under such dynamic conditions. The analysis reveals a sea-state-dependent reliability–capacity trade-off: roughness-induced attenuation of the coherent specular reflection can suppress destructive-interference nulls and improve reliability-oriented coverage, while reducing high-SINR and average-rate performance. Available measurements support the underlying roughness-sensitive reflection mechanism, but direct VHF validation under rough sea conditions remains unavailable; the corresponding rough-sea results are therefore interpreted as model-based predictions. A cross-frequency ablation further confirms the wavelength dependence of the roughness effect and shows that the reflection coefficient must be evaluated for the operating frequency.
Read the full abstract

All authors Wen-Yu Dong, Shaoshi Yang, Song Zhao, Jinyang Yu, Weiliang Xie, Rui-Si Han, Qi Bi, Sheng Chen

Artificial Intelligence

SafeBranch: Branch-Pair Safety Alignment for Embodied Agents

Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed as interactive safety. Training such agents to act safely is difficult, since safety and task success are distinct objectives, and safety arises only at a small number of safety-critical steps within a trajectory. Standard supervision is insufficient: imitating safe trajectories teaches behavior without explaining why it is safe, and contrasting arbitrary safe and unsafe trajectories mixes the safety signal with unrelated differences. We propose SafeBranch, a framework that aligns an embodied actor on safety through branch pairs constructed from the actor's own unsafe rollouts via environment rollback. SafeBranch rolls each unsafe rollout back to the safety-critical step that caused the violation, queries the actor for a safe alternative, and pairs the original action with the alternative so that the two branches differ only at that step. The trained actor acts safely at deployment with no critic in the loop. On IS-Bench, SafetyALFRED, and out-of-distribution variants with unseen tasks and objects, it improves safe task completion, achieving roughly ten times more safe successes than the untrained baseline on the unseen-object variant. Project page: https://github.com/98hyunse/SafeBranch.
Read the full abstract

All authors Hyunse Lee, Jiwoo Jeong, Haneul Lee, Kyochul Jang, Youngjae Yu, Woojin Lee

Programming Languages

Hippogriff: a semantic approach to uniting core and modules

In this paper we introduce Hippogriff, a language with a module system that unifies syntax between the core level and the module level. Hippogriff's type theory is dependent, with modularity features enabled via a universe of small types, but Hippogriff still supports general recursion without making typechecking nonterminating. This paper contains two halves. In the first half, we describe Hippogriff and its implementation. In the second half, we build categorical semantics for our use of dependent types that justify the use of general recursion at the value level. Specifically, we use an extension of the second-order generalized algebraic theory framework to include a synthetic phase distinction, and this allows us to make a mathematical connection between dependent type theories and split-context type theories (like System F). Included as supplements are a Haskell implementation of Hippogriff and an appendix describing the full type theory of Hippogriff using a second-order generalized algebraic theory with phase distinction.
Read the full abstract

Machine Learning

A Locally Tokenized Generative Model for Robust Time-Series Watermarking

Watermarking is a central tool for provenance in generative models, yet its application to multivariate time series remains hindered by reliability failures under post-editing attacks. We show that existing detectors, which rely on globally coupled re-encoding, suffer from bidirectional drift of the null distribution: post-editing attacks can shift the $z$-score of non-watermarked samples in either direction, invalidating clean-calibrated thresholds. We argue that this instability is a property of the re-encoding, and that reliable detection requires each recovered unit to depend only on a bounded temporal neighborhood. Guided by this principle, we propose L-VQVAE, a generative model in which each discrete token is produced from a short contiguous window, and LVQMark, a watermarking method over this token space that combines logit-bias injection with robust re-encoding for attack-time detection. Experiments on four benchmarks spanning finance, energy, and neuroimaging show that our approach preserves generation quality while stabilizing both detection power and false-positive behavior under post-editing attacks.
Read the full abstract

All authors Dongbin Kim, Geonwoo Shin, Yujin Choi, Soyeon Park, Jaewook Lee

Computation and Language

Projector Is All You Train

The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a modality-specific encoder. We ask whether fine-tuning the backbone of an MLLM is necessary to adapt it to a new modality. Through experiments on 3D MLLMs, we find that training only the projector is sufficient to achieve strong multimodal performance relative to existing baseline models and our jointly trained MLLMs with the same encoder and backbone. We also show that joint training leads to undesirable drift in existing capabilities of the language model, which projector-only training avoids by definition. Furthermore, projector-only training has approximately twice the training sample throughput of joint training. We validate our findings across different language model backbones via 3D classification and captioning benchmarks as well as standard benchmarks evaluating language, vision, and spatial reasoning capabilities.
Read the full abstract

Computer Vision

StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary

Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be recalled under bounded computation and memory. This challenge is pronounced in live soccer commentary, where a system must describe completed events, summarize recent play, recall earlier events, or remain silent using only information available before each utterance. We present StreamSoccer, an event-driven system that uses event memory as its intermediate representation. A fixed-budget active memory integrates the stream; completed event states are retained locally and consolidated into retrievable historical records. A unified generator uses current, recent, and historical context to produce three commentary modes, while a rule-assisted scheduler selects a mode or silence. Unlike streaming video-language models organized around frames, visual tokens, or caches, and soccer-commentary methods based on predefined clips or output timestamps, StreamSoccer explicitly models event lifecycles. We construct a three-track streaming soccer commentary dataset and a layered evaluation protocol. At common reference anchors, StreamSoccer obtains CIDEr scores of 38.62, 23.96, and 17.39 for current-event, recent-window, and historical-memory commentary, ranking first on the current-event and historical-memory tracks and second on recent-window. Controlled ablations show that local completed events improve all tracks and that the full system performs best on all three. Across 174 raw-video runs on 58 matches, per-minute RTF p95 ranges from 0.10 to 0.22 without sustained growth with match history. These results indicate that event memory supports streaming soccer commentary across temporal scopes while controlling long-history computation.
Read the full abstract

All authors Chenxi Shao, Bozhong Wang, Jiaxin Huang, Zhao Liu, Sunwei Zhu, Tianxin Hang, Gaoqi He, Yang Li, Changbo Wang

Computer Vision

Scale-Separated Conditioning for Style-Encoder-Free Diffusion Stylization

Reference-based diffusion stylization requires separating target geometry from transferable appearance. Existing tuning-based methods often rely on aligned content-style-target triplets or auxiliary visual encoders, which increases data cost and can transfer unintended scene structure from the style reference. We propose SEFS (Style-Encoder-Free Stylization), a style-encoder-free conditioning framework for diffusion transformers. SEFS forms style tokens from stochastic low-resolution crops of single training images. This crop bottleneck preserves local appearance statistics such as palette, stroke, texture, and material, while reducing access to global layout cues. Target content is encoded by edge and segmentation cues and fused with the noisy latent through parameter-efficient trainable projections. We add style-to-denoising re-normalization for token-statistic alignment and cross-block skip fusion for spatial detail. SEFS trains on unpaired single images; the frozen diffusion VAE is used only to place image conditions in the latent space. On artistic stylization benchmarks, SEFS improves content consistency and leakage diagnostics while retaining reference-style affinity, and ablations support the crop-resolution, re-normalization, and skip-fusion choices. The code of SEFS will be made publicly available.
Read the full abstract

All authors Jingtao Zhang, Haorui Gao, Youqing Liang, Zeming Liu

Computer Vision

Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions

Reliable underwater robotic perception remains difficult because optical imagery degrades under turbidity, wavelength-dependent attenuation, low illumination, scattering, and blur. Although sonar provides complementary information that is less affected by optical visibility, prior visual-sonar research has largely focused on feature alignment and nominal detection performance. We investigate cross-modal robustness as visual reliability deteriorates and assess whether pretrained visual foundation-model representations can be complemented by sonar under severe degradation. We use frozen DINOv2 as the visual encoder and construct a controlled five-level benchmark ranging from clean to extreme visual conditions. We compare conventional visual detection, frozen foundation-model representations, sonar context, fixed multimodal fusion, clean-trained adaptive gating, and degradation-aware gated fusion. Our method trains the fusion mechanism across the full range of degradation while keeping the visual and sonar encoders frozen, allowing modality contributions to adapt without fine-tuning the pretrained backbone. Under extreme combined degradation, the DINOv2 baseline achieves 0.4610 balanced accuracy, while degradation-aware visual-sonar fusion reaches 0.6152, a 33.5% relative improvement. The learned sonar contribution increases from 14.2% under clean conditions to 41.3% under extreme degradation, demonstrating adaptive redistribution of cross-modal reliance. Fusion provides the largest gains under severe turbidity and blur, whereas color attenuation alone yields little additional benefit. These results show that foundation-model representations remain valuable but insufficient under severe information loss, and that explicitly adapting fusion to modality reliability can improve robust underwater multimodal perception.
Read the full abstract

Networking

RFWM: Physics-Guided World Model for Dynamic Wireless Radiance Field Generation

Radio-frequency (RF) radiance-field modeling is essential for wireless network optimization and sensing, yet remains challenging in dynamic and unseen environments. Existing learning-based methods synthesize RF fields from sparse measurements, but most struggle to generalize to dynamic and unseen environments. To address this limitation, we propose RFWM, a physics-guided RF world model that maps multimodal physical conditions like visual dynamics and AP configurations to spatiotemporal RF fields. RFWM adopts a two-stage training strategy with physics-guided priors and constraints. In the first stage, RFWM adapts a pretrained visual diffusion backbone to RF trajectories to predict RF sequences from a few past RF inputs, while conditioning the backbone on a Friis-guided prior for coarse attenuation guidance. In the second stage, RFWM learns the physical-to-RF mapping by training a ControlNet from scratch and fine-tuning the RF-adapted backbone, while six physics-guided regularizers enforce fine-grained propagation consistency. Cross-height heads then jointly generate RF trajectories at queried receiver heights in one forward pass. We construct a new benchmark of 7,715 sequences averaging 33 frames across 115 environments for dynamic RF-field generation. Experimental results show that RFWM improves MSE by approximately 7 dB and 3 dB over the state of the art under in-distribution and out-of-distribution settings, respectively.
Read the full abstract

Computers and Society

ChatGPT Solves All Tested Qiskit Homework Assignments

Generative AI creates an assessment challenge in quantum software education: a student can provide a homework notebook to ChatGPT and request a completed submission. This study examined whether introductory Qiskit homework could remain autogradable while requiring students to run, review, and discuss results rather than banning AI. Three packages were tested: seeded basis-state circuits with bit flips and customized measurement mappings; Quantum Fourier Transform followed by inverse-transform recovery; and seeded Deutsch-Jozsa with customized oracle masks. The designs used personalization, simulator execution, JSON submissions, hidden references, circuit metrics, reflections, and optional IBM Quantum execution. For each package, one student-visible instance was tested in 50 separate ChatGPT sessions, yielding 150 sessions overall. Every final artifact was executed and passed its grader. Nine sessions were fully archived; none required operator code changes or correction of quantum logic. Under the study's operational definition, each tested instance had zero observed ChatGPT-resiliency. Seeds changed parameters rather than task structure, expected results remained derivable from visible assignment logic, scaffolding exposed key solution steps, and hidden grading verified output consistency without establishing independent authorship or understanding. Because one instance was repeated for each package, the results do not establish solvability for every seed or possible Qiskit assessment. The tested personalized, execution-oriented take-home designs therefore did not prevent successful completion under a minimally engaged-student workflow. Correct artifacts should be complemented by direct assessment through supervised modification, oral defense, prediction, and transfer tasks.
Read the full abstract

Hardware Architecture

Automated Estimation of MBIST Area and Test Time in Heterogeneous Memory IPs via Stacked Ensemble Framework

Embedded memories occupy a large portion of modern System-on-Chip (SoC) designs, especially in high-performance applications such as artificial intelligence and edge computing. Memory Built-In Self-Test (MBIST) is commonly used to ensure memory reliability, but it introduces additional area and test time overhead. Accurate early estimation of these overheads is important during design planning, yet conventional methods rely on full Register Transfer Level (RTL) synthesis and test pattern generation, which are slow and resource-intensive. This study proposes a supervised learning framework that predicts MBIST area and test time directly from RTL-level design parameters without synthesis. A dataset of 4,470 samples for area and 624 for test time was generated using Synopsys Design Compiler and MINT, an Intel-enhanced MBIST tool. Input features include memory count, word width, address depth, port configuration, and clock domains. For area prediction, the features are processed through polynomial expansion, log transformation, and scaling, followed by a stacked ensemble model using XGBoost, LightGBM, and a Neural Network with Gradient Boosting as the meta-learner. For test time, XGBoost and LightGBM are combined using Ridge Regression, with hyperparameters tuned through a 100-trial Optuna search. The models achieved 90.68% accuracy for area and 96.80% for test time within a +/-10% margin, improving over baseline methods by 8.53% and 48.80% respectively. The results show that this approach enables faster estimation of MBIST costs and supports more efficient design decisions in memory IP development.
Read the full abstract

All authors Chee Jin Teoh, Ab Al-Hadi Ab Rahman, Johnny Kee Hui Wong, Premkumar A/L Kesavan Prabagaran, Muhammad Nadzir Marsono, Nuzhat Khan

Software Engineering

Loreley: Repository-Scale Program Evolution with Quality-Diversity Search

Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the root. Loreley instead retains complete repository states in a Quality-Diversity (QD) archive and samples them as parents or supplies them as context for later edits. Candidates are Git commits produced in isolated worktrees and judged by a project-supplied evaluator. We compare configured Loreley QD, sequential champion editing, and independent root proposals in a matched Zstandard experiment: seven paired blocks and 48 physical candidate jobs per policy and block (1,008 total), with root-only initialization and each policy's native concurrency. Validation selected a winner at each budget checkpoint; an agent-hidden holdout measured the fixed candidate. At 48 jobs, QD was 0.135% below Sequential Champion (95% BCa interval for the paired effect: -0.556% to +0.161%) and 0.320% above Independent Root (-0.082% to +0.686%). Neither contrast established a QD advantage; Sequential had the highest observed 48-job mean and median. Archive retention and later sampling did occur. Four of seven final QD winners had a non-incumbent state in their primary-parent ancestry under a retrospective one-incumbent rule applied only to the observed QD stream. Including inspiration edges raised the count to six, without showing that supplied context caused an edit. Three earlier capability campaigns produced generation-4, multi-file improvements in two Python libraries and a separate Zstandard revision. Loreley engaged the intended stepping-stone mechanism, but the controlled experiment did not show an endpoint benefit at 48 jobs.
Read the full abstract

Numerical Analysis

Exact hierarchical algorithms for accelerating particle–mesh coupling in sparse-grid particle-in-cell methods

In this paper, we propose two hierarchical algorithms for charge deposition and electric-field interpolation that apply to both the sparse-grid combination technique (SGCT-PIC) and hierarchical sparse-grid (HSG-PIC) particle-in-cell methods. The two algorithms are inspired by the fast multipole method (FMM) and exploit clusters of particles associated with a directed acyclic graph (DAG) of particle-populated boxes to reduce the number of particle–mesh interactions. The particle–mesh interactions are governed by piecewise-polynomial kernels, so that the associated multipole expansions are exact, requiring neither truncation nor approximation, and are valid in both near- and far-field regions, thereby eliminating the need for multipole-to-local translations. The arithmetic complexity of the charge deposition and field interpolation steps is reduced from $\O(p^d n^{d-1}N)$ to $\O(p^d(N+M))$, where $M=2^{dn}$ denotes the number of full-grid mesh nodes and is typically no larger than the particle population in the considered regime, $M\lesssim N$. Numerical experiments in two-dimensional configurations demonstrate charge-deposition speedups of $8.2\times$–$66.9\times$ for SGCT-PIC and $3.1\times$–$18.8\times$ for HSG-PIC, and field-interpolation speedups of $4.1\times$–$62.6\times$ and $4.2\times$–$13.7\times$, respectively, depending on the particle-per-cell ratio, while preserving the exact particle–mesh interactions. The speedups increase with the particle-per-cell ratio, reflecting the reduced dependence of the hierarchical algorithms on the number of particles and their increasing advantage for large particle populations.
Read the full abstract

Artificial Intelligence

Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration

Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence and combine them through voting or weighting. However, this independence assumption often fails in multi-agent settings: memories written by different agents may inherit the same upstream source or shared bias, causing correlated evidence to be repeatedly counted and creating a false majority. We term this failure mode Memory Correlation Bias. To address the issue, we propose the Correlation-Aware Memory Arbitration (CAMA) framework that jointly decouples retrieved memories and recovers missing independent evidence. We model the retrieved memories as query-conditioned evidence groups and combine neural dependency inference with provenance-based symbolic priors to estimate the effective number of independent evidence sources, thereby preventing correlated memories from forming a false majority. Since critical independent evidence may be absent from the initial retrieval set, CAMA further learns a sequential recovery policy that actively retrieves alternative evidence or traces upstream sources before making the final decision, aiming to recover sufficient independent evidence for reliable arbitration while minimizing retrieval cost. Experiments on multiple benchmarks demonstrate the superiority of our method over the state-of-the-art baseline methods, suppressing false majorities induced by correlated memories.
Read the full abstract

All authors Chenchen Lin, Wenhao Yuan, Xuehe Wang, Edith Cheuk Han Ngai

Multiagent Systems

An Evidence-Grounded Multi-Agent System for High-Level Bio-Robot Design

In this paper, a bio-robot is an engineered living or biohybrid system in which living cells perform one or more core functions, such as sensing, information processing, actuation or output. We focus on systems whose cell-based functions are programmed by genetic circuits; physical movement is optional. Designing such a system requires translating application requirements into sensing, logic or memory, output, assembly, host and containment modules, while grounding each choice in traceable parts and evidence. We present micro_biorobot_agent, an offline multi-agent system built on Qwen3.5-27B. The system combines requirement analysis, module-specific retrieval, candidate assembly, conflict checking, local repair, independent review and validation over an integrated library of 23,762 records covering biological parts, measured combinations, literature-supported relationships and actuation evidence. Deterministic output checks align the final report with the retrieved part set and correct false gaps, unsupported part mentions and source-tracking errors. On two author-developed evaluation sets of 50 queries each, the system obtains mean overall scores of 7.35 and 8.04, the highest among the seven evaluated systems; on Scenario Design it exceeds the runner-up by 2.23 points. A 50-query paired ablation shows that the source-tracking check reduces false-gap incidents from 15 to 3, an 80% reduction, and increases source accuracy by 0.75 points. This paper reports the Qwen3.5-based v1 system and evaluates high-level design reports rather than experimentally validated circuits.
Read the full abstract

All authors Yujun Chen, Tianle Li, Jiayu Chen, Zhen Yin

Computer Vision

RIPE++: Reinforced Keypoint Learning from Positive Pairs Only

Sparse keypoint extraction and matching underpin core tasks in geometric computer vision, including structure-from-motion, visual SLAM, augmented reality, and medical image registration. Learning robust local feature representations, however, typically requires accurate camera poses or depth supervision, which are often unavailable in real-world settings. Reinforcement learning (RL) has recently emerged as a promising alternative, requiring only the information if two images show the same scene or not. However, existing RL formulations such as RIPE rely on coarse binary rewards and carefully constructed negative training pairs, limiting training stability and descriptor discriminability. In this paper, we revisit RL-based keypoint learning and propose a reward that fully exploits the geometric consistency signal, deriving both reward and penalty from a single positive pair without contrasting against negatives. This richer signal provides sufficient supervisory contrast to learn discriminative detectors and descriptors from positive image pairs alone, enabling representation learning under extremely limited supervision. Furthermore, we show that the same RL objective can be extended to the matching stage by adapting LightGlue, raising AUC@5 on MegaDepth1500 from 56.58 to 59.65 and enabling weakly-supervised training of the full sparse matching pipeline from image pairs with partial visual overlap. We validate our approach on established benchmarks, demonstrating competitive results compared to fully-supervised methods. We further show that the method can be even trained on low texture medical video sequences, where camera poses are usually unavailable and standard SfM pipelines often fail. Code and data are available at https://github.com/fraunhoferhhi/RIPEpp .
Read the full abstract

Artificial Intelligence

Rethinking the Evaluation and Optimization of LLM-Based Social Simulation

LLM-based social simulation is a promising complement to traditional methods such as surveys and behavioral experiments. A core question is how to evaluate the fidelity of LLM-simulated human behavior and optimize LLMs toward it. Prevailing practice evaluates by accuracy, checking whether the model selects the single response observed from a human, and trains the LLM to reproduce this hard label. However, human behavior is inherently subjective: the same person in the same situation may reasonably act differently, so an observed response is only one draw from an underlying response distribution, rendering accuracy-based evaluation unreliable and hard-label training misleading. To address these problems, we first introduce the subjectivity coefficient, an entropy-based quantity distinguishing objective tasks such as coding from subjective ones such as social simulation, and use it to systematically analyze how accuracy-based evaluation and hard-label training fail as subjectivity grows. Based on the subjectivity coefficient, we propose Subjectivity-Adaptive soft-Label Training (SALT): it pools observed outputs from semantically nearby inputs into soft distributional labels, with an aggregation radius adapted to the estimated subjectivity of each input; in the near-objective limit the neighborhood shrinks, so SALT naturally falls back to standard single-label training. Moreover, since existing datasets record only single observed responses and cannot support distributional evaluation, we construct SUBJSIM, a benchmark of 19,300 contexts covering 193 annotators and 100 subjective questions. Since real-world data typically provide only a single observation per input, our experiments train models from single observed outputs while evaluating them against the full response distributions, verifying feasibility in realistic settings. Results on SUBJSIM demonstrate the advantages of our method.
Read the full abstract

Numerical Analysis

Learning Deterministic and Stochastic Forced Hamiltonian Systems

We develop a geometric framework for learning deterministic and stochastic forced Hamiltonian systems with neural networks. Motivated by the Lagrange-d'Alembert principle and the theory of variational integrators, we introduce the notion of a Lagrange-d'Alembert map and establish a $C^r$ convergence theorem for first-order one-step methods. Building on these results, we propose Generalized Forced Hamiltonian Neural Networks (GFHNNs), a class of structure-preserving neural networks obtained by concatenating Lagrange-d'Alembert-Euler maps, and prove a universal approximation theorem for this architecture. We further extend the framework to parameter-dependent systems, leading to Parametric Generalized Forced Hamiltonian Neural Networks (PGFHNNs). By interpreting the multiple Stratonovich integrals appearing in the Stratonovich-Taylor expansion as parameters, the same framework can be applied to stochastic forced Hamiltonian systems whenever information about the underlying Wiener process is available. Our numerical experiments demonstrate that the proposed geometric architectures provide significantly improved long-time stability and accuracy compared to non-geometric residual neural networks, while requiring substantially less training data to achieve a comparable level of performance.
Read the full abstract

Artificial Intelligence

Learning Hierarchical Skill Policies with Offline Quality-Diversity Reinforcement Learning

Recent studies investigate how to leverage pre-collected datasets to improve the policy performance and sample efficiency of RL. One promising approach to achieve this goal is to employ a two-stage strategy: In the first stage, diverse skills are extracted as a low-level policy from a given dataset, and a high-level policy is trained to solve a specific task in the second stage. Typically, extraction of the low-level policy is performed based on unsupervised learning such as trajectory VAE. However, a limitation of this approach is that the quality of the low-level policy highly depends on the quality of the dataset. To address this issue, we introduce QDOS (Quality-Diversity Offline Skill learning), a unified pipeline for robust offline-to-online learning. Our approach incorporates an Advantage-Weighted Quality-Diversity pretraining objective, which weights the skill extraction and diversity objectives by the estimated advantage of each trajectory segment. This approach allows the model to extract diverse and high-value skills. By providing robust and task-relevant skill representations, QDOS significantly improves the quality of the embedded skill space used by the low-level policy. We further integrate this with a dual dataset reuse strategy, where offline data is used both for skill pretraining and for populating the online replay buffer via pseudo-labeling. Experiments demonstrate that QDOS significantly outperforms strong baselines in structured manipulation tasks and unstructured locomotion tasks, confirming its ability to accelerate exploration and improve final returns in challenging sparse-reward domains.
Read the full abstract

Logic in Computer Science

Lexicographic Combination of Reduction Pairs (Extended Version)

We present a simple criterion for combining reduction pairs lexicographically. The criterion is applicable to arbitrary classes of reduction pairs, such as the polynomial interpretation, the matrix interpretation, and the Knuth-Bendix order. In addition, we investigate a variant of the matrix interpretation where the lexicographic order is employed instead of the usual component-wise order. Effectiveness is demonstrated by experiments and examples, including Touzet's Hydra Battle.
Read the full abstract

Performance

Accelerating Performance Inference over Closed Systems by Asymptotic Methods

Recent years have seen a rapid growth of interest in exploiting monitoring data collected from enterprise applications for automated management and performance analysis. In spite of this trend, even simple performance inference problems involving queueing theoretic formulas often incur computational bottlenecks, for example upon computing likelihoods in models of batch systems. Motivated by this issue, we revisit the solution of multiclass closed queueing networks, which are popular models used to describe batch and distributed applications with parallelism constraints. We first prove that the normalizing constant of the equilibrium state probabilities of a closed model can be reformulated exactly as a multidimensional integral over the unit simplex. This gives as a by-product novel explicit expressions for the multiclass normalizing constant. We then derive a method based on cubature rules to efficiently evaluate the proposed integral form in small and medium-sized models. For large models, we propose novel asymptotic expansions and Monte Carlo sampling methods to efficiently and accurately approximate normalizing constants and likelihoods. We illustrate the resulting accuracy gains in problems involving optimization-based inference.
Read the full abstract

Artificial Intelligence

Frequency-Aware Continual Learning for Smart Contract Vulnerability Detection with Large Language Models

Smart contract vulnerability detection with Large Language Models (LLMs) faces three causally linked challenges. First, new vulnerability categories demand parameter-efficient adaptation, since full retraining is prohibitive for sequentially arriving tasks. Second, training per-task adapters on a shared backbone causes catastrophic forgetting of previously learned vulnerabilities. Third, the resulting multiplicity of adapters must be consolidated into a single model, since task identity is unknown at inference time. Each challenge arises directly from the solution to its predecessor, making an integrated framework essential. We propose a three-stage pipeline in which each stage addresses one challenge and feeds into the next. The adaptation stage uses Frequency-Aware Low-Rank Adaptation (FA-LoRA), which performs adaptation in the Fourier domain with per-frequency importance gates, requiring only 0.4% trainable parameters while outperforming standard LoRA and QLoRA. The continual learning stage applies Forget-Aware Replay (FAR), which uses these frequency gates to estimate per-sample forgetting risk via loss dynamics and prioritizes vulnerable knowledge for rehearsal, achieving an average Micro-F1 of 0.8022 across sequential tasks. The deployment stage employs Anchor-Protected Progressive Merging (APPM), which exploits the asymmetric generalization produced by FAR training to identify the strongest-generalizing adapter as an anchor and consolidates all adapters into a single model via anchor-protected weighted merging with frequency-domain gate competition. APPM achieves a Micro-F1 of 0.8085, within 2.7% of the independent per-task upper bound, at a merge cost of 156 ms and no additional runtime memory. Experiments on DIVE confirm the framework effectively addresses all three challenges for evolving blockchain ecosystems.
Read the full abstract

All authors Tenghui Huang, Jiawen Kang, Dongning Liu, Changyan Yi, Chengjun Cai, Anjia Yang, Li Li, Dong In Kim

Systems and Control

Reachability-based Time-domain Distance Protection

Distance relays detect faults on transmission lines from local voltage and current measurements. In this paper, we characterize the set of time-domain measurements a distance relay can observe during a fault as a reachable set. We define corresponding fault tests in terms of set-based state estimation. This allows us to model the full network as an RLC circuit with voltage and current sources. In general, computing reachable sets and set-based state estimates is intractable. For each fault type, we construct a reduced-order, two-dimensional model in terms of the apparent voltage and current seen by the relay. This makes all computations efficient, aligns with standard quantities in distance protection, and allows us to define instantaneous fault tests in terms of unsolved differential equations.
Read the full abstract

Distributed Computing

CacheRoute: Planned Prefix-Affinity Routing for Large-Scale LLM Serving

Prefix caching avoids prefill only when a repeated request returns to a server that still holds the prefix KV. Cache-blind balancing disperses that reuse; fixed affinity preserves it but can overload a server. CacheRoute resolves this tradeoff with a periodic routing plan. It admits high-rate keys to a stable warm set and places their assignments by expected load. Hot keys may use more than one destination, although every key in our primary semi-synthetic aggregate uses exactly one. On Llama-3.3-70B in fp8 across 60 H100 GPUs, CacheRoute sustains 176+/-11 QPS at a 3.5-s p99 SLO, 2.3x the strongest of five baselines. Served KV-cache hit rate rises from 64.1+/-1.3% under cache-blind balancing to 93.2+/-0.5%. A second semi-synthetic aggregate and controlled 8B and burst experiments separate the effects of affinity and placement. Two 32B workloads provide the counterexamples: when affinity recovers too little KV work, its residual load skew reduces or erases the improvement. We therefore recommend gating any deployment with a shadow replay rather than enabling affinity from workload statistics alone.
Read the full abstract

Programming Languages

Escaping the Quicksand: A Call to Arms

Computing has been an astonishing success - but the accumulated technical debt exposes us all to huge costs in business and societal risk. For 75 years, we've built systems to prose specifications with test-and-debug development. That works well enough for industry to thrive, but it's an expensive and ineffective feedback loop, and leaves everyone relying on shaky foundations. Now, AI-enabled engineering is amplifying the success by reducing coding costs, but also amplifies the risks, by rapidly increasing technical debt, and by automating detection of the vulnerabilities therein. How can we do better? Research has long pursued mathematical proof of correctness, which, unlike testing, can cover all cases. This too has advanced massively, but it remains hard to apply, both technically and because of a deep-seated cultural disconnect. Instead, we argue for a pragmatic approach to flexible combinations of testing, *specification*, and proof, that provides more effective feedback loops for both AI and human development. Most simply, one can incrementally co-develop executable-as-test-oracle partial specifications alongside conventional prose descriptions, code, and tests. This clarifies design and makes testing much more discriminating. Developers can and should do it today. Or, even better, one can use specifications that support the full gamut of testing, property-based testing, symbolic execution, and proof. This enables a range of intertwined feedback loops, again both for AI and humans, from cheap testing to more expensive proof. However, making it really practical needs *semantics infrastructure*: specifications and tooling for the main programming languages and other abstractions, which we now more-or-less know how to build, but which is not yet in place. We call the community to arms to create and deploy it - to enable a future built on firmer ground.
Read the full abstract

Human-Computer Interaction

Grounding Mindfulness in Embodied Tangibles: A Scoping Review & Theoretical Framework for HCI Design

Embodied and tangible devices are increasingly used to support mindfulness practices across meditation, yoga, and everyday routines. However, existing HCI research lacks a coherent theoretical foundation for explaining how such systems support distinct mindfulness processes and outcomes. First, we report findings from a scoping review of tangible devices (n=65) for mindfulness in HCI based on the mechanisms of action of mindfulness. The review found that most systems primarily target attentional regulation and body awareness, while emotion regulation and change in perspective on the self remain comparatively underexplored. Also, the evaluation methods used to assess the effectiveness of tangible systems for mindfulness-related outcomes were found to be fragmented and weakly grounded in theory. Building on these findings, a theoretical framework grounded in the Self-Awareness, Self-Regulation, and Self-Transcendence (S-ART) framework is proposed to explain how tangible systems support different forms of mindfulness practice. Within the framework, we present two complementary models: (1) Embodied Sensory Expansion (ESE) for focused-attention meditation (FAM) and (2) Embodied Sensory Anchoring (ESA) for open-monitoring meditation (OMM). Together, we show how this framework can provide a principled basis for explaining designs, generating hypotheses, and evaluating tangible mindfulness technologies in HCI, while highlighting key gaps for future research.
Read the full abstract

All authors Tharaka Sachintha Ratnayake, Samangi Wadinambiarachchi, Sarah Schömbs, Jonathan Eden, Denny Oetomo, Wafa Johal

Machine Learning

SAGE-XGBoost: Spatially Augmented Graph Embeddings–Machine Learning Framework for Natural Hazards Susceptibility Mapping under Data Scarcity

Natural hazard susceptibility mapping is often constrained by limited labeled data, reducing the generalizability of conventional machine learning and limiting the applicability of complex deep learning models. This study proposes SAGE (Spatially Augmented Graph Embeddings), a structurally informed feature-engineering framework that combines controlled noise-based data augmentation with neighborhood-based graph embeddings to improve prediction under data-scarce conditions. A K-nearest neighbor graph is constructed to derive local spatial statistics, which are reduced using principal component analysis and integrated with environmental covariates and spatial coordinates. The resulting features are used with XGBoost to develop the SAGE-XGBoost model. The framework was evaluated for landslide and wildfire susceptibility mapping. SAGE-XGBoost consistently outperformed conventional and spatially explicit machine learning models. Compared with Spatial XGBoost, it achieved an absolute improvement of above 33 percentage points across the two case studies. The model reached AUC values of approximately 0.97 for landslide susceptibility and 0.95 for wildfire susceptibility. Feature importance analysis confirmed the contribution of graph embeddings to prediction, while their integration improved spatial coherence and reduced local noise amplification. Overall, SAGE-XGBoost provides an efficient and transferable alternative to deep representation learning for environmental hazard assessment and other geospatial prediction tasks under limited supervision.
Read the full abstract

Robotics

SAGE: Ergodic Control for Autonomous and Adaptive Inspection of Subsea Infrastructure

Subsea Christmas Trees (XTs) are underwater structures that use valves for directing oil flow, needing constant inspection. But not every valve carries the same risk at the same time: a valve with a suspected leak needs to be revisited far more often than one with a clean history, and that risk picture changes during the mission as new leaks are found. To handle this, we present SAGE (Semantic and Adaptive Generative Ergodicity), an ergodic-control architecture that allocates vehicle time in proportion to a live, sensor-derived risk distribution rather than a scripted route. We study a two-XT scenario, with five valves in total, and compare a fixed-loop A* tour against SAGE. Both methods can be tuned to spend similar total time near a high-risk valve, but only ergodic control also checks it more often: in simulation, a dominant-risk valve was revisited every 5.8 s under ergodic control against a fixed 8.1 s for every valve under A*, regardless of risk, so a leak can go unnoticed for barely two-thirds as long. Because the tracked distribution is recomputed rather than planned once, a newly detected leak shifts vehicle behavior on the next control cycle with no explicit re-planning step and no operator in the loop, which a fixed tour cannot do without a discrete re-route. We derive the ergodic control law behind this behavior and report simulation results on the five-valve scenario.
Read the full abstract