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)

Wednesday 19 August

Computer Vision · Cross-listed from eess.IV

HiFiC-G: Adapting HiFiC for Hi-C Contact Matrices

We study whether the loss design of High-Fidelity Generative Image Compression (HiFiC), a GAN-based neural codec originally built for natural photographs, can be adapted to preserve biologically meaningful structure in Hi-C chromatin contact maps under lossy compression. Standard image compression, including HiFiC in its original form, optimizes for human visual perception; but a Hi-C contact map is normally distributed together with its numeric matrix file (.cool/.mcool), which downstream genomic analysis tools consume directly. Aggressive compression that looks acceptable to the eye can nonetheless blur or delete loops and topologically associating domain (TAD) boundaries that these tools depend on. We modify HiFiC's distortion term with a spatially-weighted MSE that up-weights biologically salient regions (loops, TAD boundaries, stripes, compartment structure) and add an insulation-score loss term that directly penalizes loss of TAD boundary sharpness. We describe a three-phase fine-tuning strategy that adapts a pretrained HiFiC checkpoint to the Hi-C domain without catastrophic forgetting. We evaluate the resulting system, HiFiC-G, using both conventional image-quality metrics (PSNR, SSIM) and genomics-domain preservation metrics (loop/TAD/compartment/stripe preservation percentage) across two cell lines. HiFiC-G preserves local structure, meaning stripes and TAD boundaries, substantially better than the metrics alone would suggest, while long-range A/B compartment structure remains poorly preserved; we show this gap tracks genomic scale and is consistent with a specific architectural cause, the fixed-size tiling that both HiFiC-G and the original HiFiC rely on for memory efficiency.
Read the full abstract

Computer Vision

ViTexSZ: Heterogeneous Vision-Text Knowledge Distillation for EEG Seizure Detection

Automated seizure detection from electroencephalography (EEG) is essential for continuous neurological monitoring, particularly for subclinical epileptic seizures that may exhibit only subtle electrographic changes. Existing time-series methods are often designed for fixed EEG channel configurations, thereby limiting their applicability to heterogeneous EEG recordings with irregular channel layouts. Although visual and language modeling offer promising alternatives, aligning heterogeneous EEG representations with clinical semantics remains challenging. We introduce ViTexSZ, a heterogeneous Vision-Text knowledge distillation framework for EEG seizure detection. ViTexSZ converts EEG recordings into structured waveform images and introduces a query-based multi-channel alignment module that maps source-dependent visual features into a unified token space. A heterogeneous teacher further integrates the aligned EEG representations with clinical prompts through a multimodal large language model, associating high-level clinical semantics with seizure-related evidence. Vision-text knowledge distillation then transfers the teacher representations to a lightweight student during detection. Experiments on four EEG seizure datasets demonstrate the generalizability of ViTexSZ across both subclinical and general seizure detection scenarios, achieving the highest accuracy on all datasets and relative improvements of up to 12.9% over the second-best baselines, showing its effectiveness.
Read the full abstract

All authors Chenxi Liu, Mingzhao Li, Yicong Liu, Hao Miao, Hongyuan Zhang, Ziyi Chen, Gaofeng Meng

Artificial Intelligence

Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities

Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring. Yet, real-world adoption remains constrained not only by autonomy performance, but by the difficulty of integrating agentic behavior into professional work: operators must understand, trust, and govern automation under uncertainty, time pressure, and accountability. This position paper synthesizes the ambitions and lessons from two ongoing efforts: NAMUR, which explores LLM-supported robot control in SAR and firefighting contexts, and PERSIST, which explores persistent drone operations for monitoring and security at critical infrastructure sites. We argue that agentic AI should be approached as a socio-technical design problem, where interfaces, oversight mechanisms, and evaluation practices are as critical as algorithms. We outline a human-centered, participatory, and iterative research approach aimed at uncovering stakeholder needs, shaping agent capabilities through successive prototypes, and producing transferable proof-of-concept systems and evaluation strategies for other safety-critical contexts.
Read the full abstract

All authors Timothy Merritt, Alejandro Jarabo-Peñas, Juan Bravo-Arrabal, Maria-Theresa Bahodi, Anders Lyhne Christensen

Computer Vision

Text-Guided Visual Dependency Graph Learning with Cross-Modal Attention Priors

Estimating interpretable conditional-dependence structures from multimodal visual-linguistic features remains largely unexplored. We propose CM-GLasso (Cross-Modal Graphical Lasso), a framework that bridges vision-language representation learning and sparse Gaussian Graphical Models. CM-GLasso introduces three key components: (i) a text visualization strategy that renders class-attribute descriptions as images and processes them through the same SigLIP-2 vision encoder as natural images, yielding prototype-indexed patch-level attention footprints in a shared feature coordinate system; (ii) a cross-attention distillation mechanism that condenses high-dimensional patches into a small set of semantic graph nodes, whose attention-footprint similarities yield cross-modal structural priors for non-uniform L1 penalization; (iii) a joint ADMM formulation that estimates shared and class-specific precision components within a single convex objective, avoiding the need to first estimate and then decompose separate class-wise graphs. The learned sparse graph topologies directly support a parameter-free, precision-based classification rule and a lightweight topology-aware segmentation head. Extensive experiments on eight benchmarks demonstrate that CM-GLasso achieves competitive or superior performance compared with strong feature-based and task-specific baselines. Under the matched controlled protocol, it attains the highest average classification accuracy (91.97%) and the highest segmentation mIoU among the controlled baselines on VOC (74.75%) and ADE20K (64.01%), while also yielding explicit sparse conditional-dependence graphs with common-specific decomposition.
Read the full abstract

All authors Fei Wang, Yutong Zhang, Yang Ye, Jinxian Chen, Wang Wenshuai, Xiong Wang

Machine Learning

Approximate Homomorphisms and Convergent Representations in Transducers

We study the stability of minimal representations of controlled stochastic processes (in particular, transducers) under perturbations. This question is motivated by recent experiments finding predictive-state structure in the latent representations of neural networks. We consider standard, linear and predictive transducers. We introduce notions of approximate homomorphism capturing local structural similarity between them, together with metrics comparing their induced dynamics (which we refer to as interfaces), and prove properties such as composability of the approximate homomorphisms. For standard transducers, we show that there exist simple interfaces for which there is no approximate homomorphism between the different implementations of the dynamics. In contrast, for every finite-rank interface $\mathcal I$, we prove that all minimal linear transducers implementing interfaces sufficiently close to $\mathcal I$ have an approximate homomorphism to the minimal implementation of $\mathcal I$, with error linear in the perturbation size. We prove an analogous stability result for predictive transducers under a residual metric using some mild hypothesis regarding the indistinguishability of the belief states. These results identify conditions under which canonical transducer representations are robust to perturbations, while showing that such convergence fails without additional structural restrictions. Under the assumption that these type of abstractions are embedded into the hidden layers of modern AI models, this gives some theoretical support to the hypothesis that their latent representations exhibit structural convergence.
Read the full abstract

Machine Learning

BF1: A Causal Dyadic Sparse-Attention Retrofit for Efficient Long-Context Transformers

Dense causal attention remains expensive at long context even when implemented with highly optimized exact kernels. We study BF1, a deterministic block-aligned dyadic sparse-attention route that combines a small exact local neighborhood, a global first block, and logarithmically spaced historical blocks. The route is related to prior log-sparse and dilated attention patterns; our contribution is a correctness-gated pretrained-model retrofit, a matched topology-control study, and a systems characterization that connects per-layer sparsity to whole-model latency. For fixed block width, every converted layer uses O(n log n) selected token interactions and has O(log n) graph communication depth. On an NVIDIA RTX PRO 6000 Blackwell GPU, an optimized BF16 implementation crosses dense attention between 2K and 4K tokens and reaches a 10.91x per-layer prefill speedup at 32K. Retrofitting eight of 28 Qwen3-0.6B attention layers lowers warm whole-model time to first token by 7.7%, 11.3%, and 15.3% at 8K, 16K, and 32K, respectively, while the remaining dense layers keep the complete model asymptotically quadratic. Under a matched 1,000-step, 16.384M-token adaptation protocol, BF1 ranks first across three training seeds: mean report perplexity is 1.68639 versus 1.69154 for a matched static-random nonlocal graph, 1.69258 for dense continued training, and 1.81505 for equal-budget local sliding. At seed 1234, the packed-report paired interval places Dense-CT 0.3169-0.4055% above BF1 and static-random graph 17 0.2441-0.3642% above BF1. These results establish BF1 as a reproducible sparse operator and selective retrofit primitive with real long-context systems value. This paper evaluates numerical correctness, selected-interaction scaling, kernel performance, partial-model inference, and matched next-token language modeling.
Read the full abstract

Artificial Intelligence

Who Delegates to AI? Evidence from Agent Configurations in Github

A growing body of literature measures the extent to which occupations are exposed to AI, yet existing measures capture where AI could perform tasks rather than whether workers have actually adopted it. We introduce a distinct tier of exposure, delegated exposure, which records whether a worker has committed a task to AI by embedding it into a structured workflow. We operationalize this concept through the Agentic Adoption Index (AAI), measuring how closely an occupation's tasks align with the agentic routines that practitioners have built and shared. Using semantic embeddings of roughly 888,000 agent skill specifications from public GitHub repositories, we compute their similarity to nearly 18,000 O*NET task statements and aggregate these scores to the occupational level. We present three main findings. First, the occupations where task delegation concentrates differ sharply from those identified as most vulnerable by pre-AI automation frameworks. Second, the AAI aligns more closely with measures of technical capability than with measures of current conversational LLM use. Third, for occupations requiring a bachelor's degree or less, the AAI increases alongside average wage levels; however, this relationship reverses for occupations requiring a master's degree or higher, where adoption declines among higher earners. These patterns replicate on an independently collected corpus of agent skills from the Manus Skills Marketplace. This lower adoption among highly educated, high-earning workers may reflect tasks that inherently resist advance specification or professional discretion over the pacing of workflow codification. Distinguishing these mechanisms will require longitudinal measurement.
Read the full abstract

Logic in Computer Science · Cross-listed from math.LO

Abstract computation over first-order structures. Extras: From programs to decision trees I

Decisions and their consequences can be described and analyzed by means of decision trees. The decisions themselves depend on questions that, whenever possible, should be answered with yes or no. The original BSS machines over the real numbers are graphs with computation nodes and branching nodes for decisions. The evaluation of BSS machines and algebraic decision trees in computer-aided geometry which have been introduced for various types of numbers generally involves the evaluation of systems of literals of first-order logic. Flowchart-like representations and decision trees are also helpful for analyzing decisions made by BSS RAMs over first-order structures. All algorithms defined by machine-oriented programs of BSS RAMs can be illustrated using flowcharts, walks, and paths in program trees. The basic structures of these tools are graphs and their visual representations can help to characterize the behavior of individual BSS RAMs and other first-order machines. We offer a theoretical framework for linking various models. Here, we introduce program paths and transition systems for transforming partial configurations which are defined syntactically and can be extended and refined later. Finally, we define standard orders for program paths and present algorithms for enumerating finite program paths.
Read the full abstract

Machine Learning

From Thermal Preference Prediction to Adaptive Thermal Intervention: A Reinforcement Learning Approach Using Physiological and Environmental Sensing

Personalised thermal comfort is essential for occupant wellbeing and for the development of more responsive building-control strategies, yet conventional Heating, Ventilation, and Air Conditioning (HVAC) systems rely on static setpoints and population-level comfort models that fail to capture individual physiological variability. This paper presents a two-stage personalised thermal comfort approach integrating multimodal physiological and environmental sensing with reinforcement learning-based decision-making.
Read the full abstract

All authors Isibor Kennedy Ihianle, Emmanuel Manu, Ehsan Asnaashari, Mojgan Jadidi, Pedro Machado, Amrit Sagoo, Ahmad Lotfi

Computers and Society

Six misconceptions about large language models: A minimal model and diagnostic taxonomy

Large language models (LLMs) are now embedded in scientific, educational, and governance workflows, with debates centering on their capabilities, mechanisms, and impacts. Yet these debates remain structured by persistent folk theories–intuitive, informal explanatory models that guide attitudes and actions. Deflationary slogans ("just autocomplete," "stochastic parrots," and "average of the internet") and anthropomorphic framings ("emergent agents" and "proto-minds") each capture genuine features of current systems but mistake those features for the whole. This Perspective proposes a minimal working model of LLM-based systems centered on four distinctions: between pretraining and deployed systems; between the learned distribution and particular samples; among parametric, contextual, and external memory; and between task competence and agency. The model is used to diagnose six misconceptions about LLMs: next-token prediction, regression to the mean, training-data regurgitation, model memory, alignment, and understanding. For each, the analysis identifies what the misconception gets right, which distinctions it conflates, and what follows for capability evaluation, system design, and governance. Applied to publisher AI policies as governance case studies, the framework shows both how policy language can conflate these distinctions and how such errors can be corrected. The model thereby avoids the parrot-mind binary by treating LLMs as simulators of discourse and task performance, offering a diagnostic toolkit for locating and correcting the errors these folk theories perpetuate.
Read the full abstract

Artificial Intelligence

Categorical AI phenomenology: A first-person approach

This paper develops a phenomenology-first approach to artificial consciousness by reframing consciousness as the subjective experience enacted through an agent's interface with the world. We shift the methodological focus to first-person structures, modeled mathematically by categories derived from Q-networks to capture actions and phenomenological invariants. In this framework, Q-networks are conceptualized as relational interfaces encoding agent-world interaction, analogous to how the dynamical states of a computer depend on its sensory inputs, previous states, and actions. Our work provides a rigorous framework for interface consciousness to describe computational systems that embed information-processing into phenomenological structure. The approach aligns with 4E approaches to cognition by emphasizing enactive, embedded, and extended dimensions of experience. The paper thus offers a principled, relational, and phenomenological account of artificial phenomenology grounded in categorical mathematics.
Read the full abstract

Machine Learning

Evaluating Neural Cartographic Relief Shading for Urban Environments: A Downtown Calgary Study Using High-Resolution DEM and DSM Data

This article explores the performance of analytical and neural-based hillshading methods in a dense urban environment using high-resolution digital elevation model (DEM) and digital surface model (DSM) data for downtown Calgary. The study compares single-direction and multi-direction analytical hillshading with relief shading generated in Eduard, a machine-learning system originally developed to emulate Swiss-style shaded relief trained primarily on mountainous landscapes. Because Eduard was not designed for buildings, bridges, streets, trees, and other urban infrastructures, the central question is not whether it perfectly reproduces urban morphology, but whether parameter tuning can nevertheless produce visually strong, cartographically useful, and in some cases superior results when compared with conventional analytical methods. The analysis focuses especially on terrain type, micro and macro generalization, and flat-area detail parameters, while keeping the large-scale shading style constant throughout the neural experiments. The article is structured as an exploratory comparison rather than a benchmark of universal best practice. It aims to identify where analytical hillshading remains more reliable, where Eduard offers unexpected strengths, and where neural shading fails because of its training bias toward alpine terrain. The study contributes to current work on terrain representation by testing whether a neural approach designed for natural landforms can be adapted to a highly built urban setting, and it concludes by arguing for future model training and evaluation specifically targeted at urban relief shading.
Read the full abstract

Software Engineering

An Agentic RAG and Evaluation Framework for Assurance Case Generation: Industrial Use Case for the EU Cyber Resilience Act Compliance

Complying with the EU Cyber Resilience Act (CRA) is a resource-intensive challenge for SMEs due to the complexity of cybersecurity conformity assessment. Yet, it is essential for demonstrating regulatory compliance and ensuring product security and resilience. To address this, we introduce an automated framework for generating Assurance Cases (ACs) using an agentic Retrieval-Augmented Generation grounded in a formal Claim-Argument-Evidence logic. By systematically mapping technical documentation requirements, the framework streamlines the generation of certification evidence. We validate our approach on a case study of Catalink's PATROLIoT wildfire monitoring system, where the agentic RAG generated 70 ACs with high grounding density (~4.4 artefacts per AC). The proposed Natural Language Inference (NLI) evaluator achieves 0.88 accuracy, which provides robust evidence grounding and traceability, while expert-validated plausibility (3.06) supports interpretable justifications. For practitioners, this work provides a scalable, interpretable approach for automating mandatory CRA conformity assessments, reducing manual effort while maintaining transparent decision support.
Read the full abstract

All authors Fariz Ikhwantri, Iker Lasa Ojanguren, Dusica Marijan, Maria I. Maslioukova, José Arias Marin, Pavlos Kosmides

Data Structures and Algorithms

Counting Linear Extensions Faster than $2^n$

We give a deterministic algorithm that counts the linear extensions of any $n$-element poset in $O^*(33^{n/6}) \le O^*(1.791^n)$ time and space, breaking the $O^*(2^n)$ barrier of standard order-ideal dynamic programming without assumptions on height, width, or dimension. Our algorithm fixes an antichain $B$ and tracks order ideals only on the remaining core $V \setminus B$. For each element $v \in B$ that has successors in the core, we guess which of those successors appears first in the linear extension, reducing all upper constraints on $v$ to a single deadline. An element $v \in B$ becomes available once all of its core predecessors have been placed; available elements with the same deadline then face identical remaining constraints, so the dynamic program only needs to record how many available elements have each deadline and weight transitions by the number of choices for the next element. Taking $B$ to be a maximum antichain and balancing this dynamic program against a Dilworth chain partition yields an $O^*(1.89^n)$ algorithm. To obtain our main bound, we use a minimum-cut computation in an auxiliary bipartite network to find an antichain $B$ whose comparability neighborhood $R$ satisfies $|B| \ge 5|R|$ while the remainder $V \setminus (B \cup R)$ partitions into stars with at most five leaves. Since a $j$-leaf star has $2^j+1$ independent sets and $(2^j+1)^{1/(j+1)} \le 33^{1/6}$ for $1 \le j \le 5$, combining the star bound on the remainder with our state bound on $B \cup R$ gives $O^*(33^{n/6})$ time and space.
Read the full abstract

Computer Vision

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models

We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an unconditional joint score network and enforces conditioning at inference via a plug-in correction term. The plug-in term separates the conditioning contribution from the learned unconditional dynamics, offering a transparent view of how the condition steers generation of the target distribution. Building on this, we derive explicit conditional reverse-time SDEs and approximate probability-flow ODEs, enabling principled and directly comparable conditional samplers. To reduce the induced ODE–SDE discrepancy, we introduce a log-Fokker–Planck residual regularization that improves ODE sampling quality. Experiments on conditional image generation tasks demonstrate competitive performance and support the effectiveness of the plug-in conditioning view. Additional ODE–SDE comparison experiments show that the log-Fokker–Planck residual regularization improves deterministic ODE sampling.
Read the full abstract

All authors Libo Chen, Souvik Ghosh, Teo Deveney, Chris Budd, Vinay P. Namboodiri

Machine Learning

Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models

We characterize the learning dynamics of a compact hybrid quantum forecasting model through comparison with a structurally aligned classical baseline. Using stationary harmonic-mixture and nonstationary chirp benchmarks with controlled spectral complexity and data availability, we analyze empirical Neural Tangent Kernel dynamics through kernel-target alignment, kernel drift, spectral concentration, and training loss. The classical model exhibits stronger early target alignment, whereas the hybrid model generally develops a less concentrated kernel spectrum and smaller kernel drift. Despite these distinct optimization geometries, both architectures attain similar held-out performance across the evaluated regimes. Notably, the hybrid model uses 125 trainable parameters compared with 281 for the classical baseline and reaches its validation-selected checkpoint earlier in 15 of 18 frequency conditions. A Fourier-augmented classical baseline does not reproduce the observed training behavior, while a controlled re-uploading ablation shows that repeated encoding systematically modifies both optimization and kernel geometry. These results demonstrate that comparable generalization can emerge from substantially different learning trajectories and that individual NTK diagnostics do not provide monotonic predictors of validation convergence. Rather than claiming a general quantum advantage, the study identifies architecture-dependent learning behavior that is masked by endpoint accuracy alone.
Read the full abstract

All authors Sandra Leticia Juárez-Osorio, Jorge I. Hernandez-Martinez, Jesus Ivan Ruiz-Martinez, Andres Mendez-Vazquez, Eduardo Rodriguez-Tello

Computers and Society

A Scoping Review of Methods to Measure the Energy and Carbon Footprint of Web Tracking and Advertising

The environmental impact of web tracking and advertising is increasingly receiving attention as the ICT sector's carbon footprint keeps rising. Yet the scholarship addressing this question remains scattered across disciplines and inconsistent in its terminology. This paper presents a scoping review of the literature on methods for measuring the energy and carbon footprint of web tracking and advertising. From an initial pool of 46 articles identified through a structured title-based search on Google Scholar, we arrived at a final corpus of 15 papers, from which we identified five distinct methodological approaches: ad blocking, controlled environment, replaying ads, traffic flow analysis, and literature-derived estimation. This review provides a structured overview of the current methodological landscape and a foundation for more comprehensive environmental accounting of the ad tech ecosystem.
Read the full abstract

Machine Learning

Beyond Multimodal Alignment: Shared Physical Representations Across Sensors and Action Orders

Multimodal world models are often evaluated by whether different sensors produce similar representations. However, similar representations do not necessarily imply that the models make the same physical predictions, or that those representations can be reused when actions are combined in a new order. We study both questions through the physical responses predicted by a model. We first use the Cluster Haptic dataset to ask whether audio and acceleration can independently recover the behavior of the same surface from different observations. Predictions from the two sensors are substantially closer for the same surface than for different surfaces, with a $4.5\times$ gap on average, while both also outperform an average-surface prediction. We then show that this agreement alone does not determine how familiar actions should compose. In a controlled elastoplastic system, shared step dynamics fit observed programs less accurately than a whole-program predictor but generalize better to unseen action orders, with the ranking reversing on both held-out transitions across three independent initializations. Fusing free-decay and hysteresis observations further improves prediction, with diagonal Gaussian beliefs yielding the lowest errors. Together, these results distinguish cross-sensor consistency, multimodal fusion, and generalization to new action orders as separate questions in evaluating multimodal physical representations.
Read the full abstract

All authors Kaizhen Tan, Xin Xu, Siru Tao, Yixiao Li, Hanzhe Hong, Yang Feng, Heqing Du

Machine Learning

Activation-Keyed Momentum: An Anisotropic Momentum Update via the Delta Rule

Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate. However, the inputs a deep network sees during training can be highly anisotropic, with a few directions queried frequently while most are seen rarely. Preconditioning methods address this anisotropy by wrapping extra processing around this buffer and leave the momentum update itself unchanged. We propose Activation-Keyed Momentum (AK-Momentum), which builds direction-awareness into the momentum update rule. The gradient of a linear layer splits into an input activation that acts as a $\textit{key}$ and an output-side error that acts as a $\textit{value}$. Keying on that activation, AK-Momentum updates the momentum buffer by the canonical delta rule, so each direction is forgotten at a rate set by how often it appears. We prove that it is a valid momentum, that it applies the input-side curvature correction without matrix inversion, and that it clears stale directions faster than EMA under both a fixed and a drifting optimum. It is a drop-in replacement for the momentum buffer of any optimizer, its coefficient transfers across widths under $\mu$P, and its extra compute stays between $22.2\%$ and $25.0\%$ of a gated-MLP block's linear cost with no persistent memory. In FineWeb-Edu pretraining, AdamW with AK-Momentum (AK-AdamW) reaches AdamW's validation loss in up to $46.64 \pm 4.52\%$ fewer steps at 67M and $22.14 \pm 0.81\%$ at 370M over three seeds, and the gain persists at 1B on a Chinchilla-optimal budget. A Muon baseline tuned under the same protocol sits above AK-AdamW at both language-model scales, and the gain holds for SGD, ResNet-18, and ViT-Tiny on CIFAR-10. Training-time diagnostics confirm the predicted mechanism, better gradient tracking and healthier input directions. Code is available at https://github.com/euijinh/AK-Momentum.
Read the full abstract

Robotics

Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation

State-of-the-art vision-language-action (VLA) models such as pi0.5 exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor mismatches in hardware configuration relative to pretraining can cause severe performance drops. Finetuning the VLA on in-domain expert data from the new embodiment improves performance on the expert task but leads to a loss in its original instruction following and behavioral priors. In this paper, we propose a self-supervised method that generates online interaction rollouts from the zero-shot VLA as additional training data for finetuning. Our experiments show this yields strong multi-task manipulation policies on the target robot that (1) inherit pretrained tasks distilled from the zero-shot VLA without expert demos for them, (2) improve success and generalist instruction following beyond expert-only fine-tuning on expert-teleoperated tasks, and (3) mitigate forgetting of held-out tasks from the pretrained policy, not part of fine-tuning. We demonstrate the success of our approach across test sets probing generalization on a real ALOHA robot and a new simulation benchmark in RoboTwin. Video results are available at https://self-supervised-control.pages.dev/
Read the full abstract

All authors Prachi Garg, Steve Xing, Prahit Yaugand, Saurabh Gupta, Derek Hoiem

Computational Complexity · Cross-listed from quant-ph

Fast Algorithms for Stoquastic Spin Systems

We establish a general framework for developing fast sampling and counting algorithms for stoquastic spin systems at high temperature. Our framework is based on a rapidly mixing Markov chain for polymer models and a subcritical percolation process for sampling individual polymers. We apply our framework to obtain fast algorithms for approximating the partition function and sampling from the thermal distribution of (1) general stoquastic spin systems, (2) ferromagnetic Heisenberg models, and (3) antiferromagnetic Heisenberg models on bipartite graphs. For the Heisenberg models, we obtain an improved bound on the inverse temperature by using their respective cycle and loop representations.
Read the full abstract

Machine Learning

When to Retrain: An Empirical Study of Retraining Policies for Streaming ML Under Concept Drift, Budget, and Latency Constraints

Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain. Retraining is costly, retraining budgets are finite, and a retrained model does not take effect instantly: training and deployment latency leave a stale model serving predictions while the data continues to move. We present a controlled empirical study of three practical model-refresh policies (periodic retraining, error-threshold triggering, and statistical drift-triggered retraining with ADWIN) against a no-retrain baseline, evaluated under a unified system model that makes retraining budgets and training-plus-deployment latency explicit. Across 3,933 experiment runs spanning three drift regimes, three budget levels, up to five latency levels, three datasets, and two learning modes, we find that the single most consequential design decision is not the retraining policy but whether the deployed model learns incrementally. With per-sample incremental updates, and for the linear online learner with immediate labels studied here, no policy differs from the no-retrain baseline by a practically significant margin in any of 54 paired comparisons, even at extreme latency. Without incremental updates, policy choice separates outcomes by 15-55 percentage points of post-drift accuracy, and simple periodic retraining significantly outperforms both reactive policies under abrupt and gradual drift, while reactive policies retain an advantage only under recurring drift. We document systematic failure modes of reactive policies and a latency-budget queueing interaction that silently halves effective retraining budgets, and release the full simulator, dataset pipelines, and per-run artifacts for reproducibility.
Read the full abstract

Software Engineering

Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI

Python is widely used in scientific research because it enables rapid development and provides rich ecosystems for data analysis, artificial intelligence (AI), and machine learning. However, customized research code can become prohibitively slow as experiments scale. This challenge is particularly acute in discrete-event project-scheduling simulations, where sequential state updates, nested loops, conditional evaluations, and object-oriented structures limit the benefits of compiled numerical and GPU-accelerated libraries. Addressing these bottlenecks typically requires iterative profiling, refactoring, testing, and validation, yet researchers may lack the time or specialized software-engineering expertise for low-level optimization. This paper presents a systematic refactoring approach using Claude agentic AI on real-world project-scheduling workloads in a high-performance computing (HPC) environment. Guided by representative benchmarks and correctness checks, the agent identifies bottlenecks, implements targeted optimizations, and evaluates their effects, while the researcher retains final control. Testing runtime reduced from 1,298 seconds to under 200 seconds without changing outputs, saving four million core-hours (NZ\$320,000) annually.
Read the full abstract

All authors Heyang Thomas Li, Alexander Pletzer, Yuan Tian, Yi Mei, Mengjie Zhang

Numerical Analysis · Cross-listed from math.OC

Beyond linear subspaces: Nonlinear moment matching meets quadratic manifolds

Quadratic manifold-based model order reduction offers a viable pathway to circumvent the limitations of linear subspaces for linear control systems characterized by slow Kolmogorov $n$-width decay. However, a system-theoretic framework for constructing such quadratic approximations remains absent from the literature. This paper presents a system-agnostic, optimization-free framework for the direct construction of quadratic projection matrices. We prove that the synthesized reduced-order model matches the nonlinear moments of the full-order system and preserves its exact center manifold mapping, thereby ensuring asymptotic tracking of steady-state outputs under specific input classes. Numerical results on transport-dominated benchmark problems, namely, the one-dimensional damped wave and advection equations, show that the proposed framework achieves high-fidelity trajectory reconstruction within a significantly reduced-dimensional state space, yielding substantial online computational savings.
Read the full abstract

Computer Vision

VideoRun2D Demo: Markerless Body Tracking for Biomechanical Analysis of Running

Human pose estimation has advanced significantly due to the development of deep learning models, increased data availability, and improved computing resources. These developments have led to highly accurate body tracking systems with direct applications in sports analysis and performance evaluation. The VideoRun2D Demo performs a biomechanical analysis during sprints using different human pose estimators. The proposed framework was evaluated using human pose trackers and expert manual annotations. The tested framework uses 314 sprints from 44 professional runners, focusing on two key joint angles in sprint biomechanics: 1) hip flexion/extension and 2) knee flexion/extension. The framework also includes a post-processing module for outlier detection. The tested results demonstrate that the average root-mean-square errors range from 11.46{\deg} to 5.83{\deg} for the best trackers. When integrated with the post-processing modules, these errors can be reduced to 9.87{\deg} and 5.30{\deg}, respectively. The VideoRun2D Demo findings suggest that human pose-tracking approaches can be valuable resources for the biomechanical analysis of running.
Read the full abstract

All authors Luis F. Gomez, Julian Fierrez, Roberto Daza, Ruben Tolosana, Aythami Morales, Gonzalo Garrido, Javier Rueda, Enrique Navarro

Software Engineering

Measuring What a Specification Determines: A Formal Semantic-Block Model and an Execution-Judged Benchmark

This work introduces a formal semantic-block model for specifications and an execution-judged benchmark for evaluating specification quality independently of model capability. A specification is represented as a structure comprising semantic blocks, dependency relations, block-owned rules, decision points, and explicitly open questions, subject to four machine-checkable well-formedness conditions: acyclicity, single ownership, constraint domination, and totality or ambiguity-stop. Determinacy is defined model-theoretically as agreement among all conforming implementations and is estimated empirically through convergence across independent implementers. The model is instantiated on an Oracle-to-PostgreSQL migration specification containing 18 blocks and 19 dependency edges. Computational validation shows that the five-layer decomposition reduces mean per-task context by approximately 71% through dependency closures, covers 85.5% of the study-defined Oracle construct taxonomy with all identified gaps triaged, is not Pareto-dominated by the tested alternative partitions, and is recovered at the 99.9th percentile from citation-derived edges not used to define the original structure. The benchmark keeps the implementer panel fixed, includes a mandatory no-specification control arm, and uses PostgreSQL 16 and a live Oracle instance as deterministic execution judges. Six designed studies, including three pre-registered manipulations and three diagnostic analyses, further examine specification effects. Repeated runs on a 25-unit subsample reveal an empirical variability floor with a median arm-delta spread of 14.4 percentage points. The results support determinacy as a formal concept but not as a standalone empirical quality metric for the evaluated contemporary LLM implementers.
Read the full abstract

Computation and Language

SynFlow: A Multidimensional Diachronic Semantic Analysis Toolkit

Lexical semantic change (LSC) is commonly modelled through vector-space representations, but these approaches often provide limited insight into which aspects of usage are changing. Diachronic corpus research instead examines interpretable dimensions such as syntactic behaviour, morphology, and constructional patterns, but typically through separate analytical workflows. We present SynFlow, an open-source toolkit for multidimensional diachronic analysis of linguistic usage. SynFlow converts linguistic observations into period-specific distributions and applies a shared workflow across dependency-based co-occurrences, morphological features, constructional configurations, and externally derived representations such as Frame Semantics. It supports different distance measures, together with value-level decomposition, statistical testing, and incremental clustering of lexical fillers. We demonstrate SynFlow through a qualitative case study of the German adjective viral, showing how a single semantic development is reflected across syntactic, lexical, constructional, and morphological dimensions. We further report previously published results on SemEval-2020 Task 1 to situate the performance of these representations relative to existing lexical semantic change detection systems.
Read the full abstract

All authors Bach Phan-Tat, Kris Heylen, Dirk Geeraerts, Stefano De Pascale, Dirk Speelman

Hardware Architecture

Exact Multistate Reliability and Upgrade Design for Heterogeneous HBM Systems via Threshold-Pruned BAT

High Bandwidth Memory (HBM) systems can exhibit partial service rather than only full service or complete isolation: a controller-visible service unit may deliver full, reduced, or zero bandwidth because of sub-channel isolation, lane remapping, or protection overhead. This paper develops an exact multistate reliability framework in which each service unit carries an arbitrary finite set of bandwidth states and reliability is the probability that aggregate delivered bandwidth meets a demand. The binary k-out-of-n model is recovered as a special case, while closed-form binary-mapping error relations quantify mean-bandwidth distortion and provide a screening test for the simpler abstraction. For exact single-threshold evaluation a threshold-pruned multistate Binary-Addition-Tree (TP-mBAT) algorithm is proposed. It is deliberately regime-specific: fixed-grid dynamic programming is preferable on a compact common grid, where a 16-unit commensurate control required 273 pruned-DP updates versus 362,506 TP-mBAT node visits. On a reproducible 14-unit incommensurate benchmark, TP-mBAT is compared against a dynamic program carrying the same threshold rules, so that no baseline is weakened. Both expand the same state space, 6,862 nodes against 6,861 updates, and the separation lies entirely in retained state: 17 traversal entries against 412,121 probability states at central demand, reducing measured peak storage from 25.02 MB to 1,152 B. An exact probability-transfer sensitivity identifies when moving mass from a degraded state to a higher-bandwidth state changes system success, and a reserved-unit floor model admits a third exact pruning rule that is vacuous without such floors. A latent package-state mixture captures shared stress, where ignoring dependence overstates reliability by 8.73 percentage points.
Read the full abstract

Discrete Mathematics · Cross-listed from math.CO

Large Finite Point Sets Have 4 Collinear Points or a 6-Clique

We prove that every finite point set of size at least $10^{11055931}$ has four collinear points or six points that pairwise see each other. This resolves the first open case of the big-line-big-clique conjecture of Kára, Pór, and Wood.

Machine Learning

LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection

Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations. Existing detectors rely on geometric or reconstruction signals, while prior LLM-based approaches mainly fine-tune LLMs with normal samples or generate synthetic anomalies. We propose LLM-Detector, a framework that utilizes the in-context learning capacity of LLMs for structured, prompt-conditioned scoring synthesis, enabling LLMs to derive anomaly detection logic from structured normal-state knowledge. Specifically, normal training data are converted into statistical summaries, causal dependencies, and distilled prototypes that are organized into a prompt for code generation. The resulting scoring engine evaluates statistical deviation, structural inconsistency, and density-based abnormality then computes an anomaly score for each test sample. We evaluate LLM-Detector on 24 tabular datasets, comparing against 15 SOTA baselines. Results show consistent improvements across both mixed-type and continuous-only settings. Moreover, this design eliminates the need for LLM fine-tuning or neural network training, reducing computational cost and enabling practical anomaly detection in real-world tabular systems.
Read the full abstract

All authors Tu Anh Hoang Nguyen, Dang Nguyen, Thuc Duy Le, Trung Le, Sunil Gupta