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 12 August

Machine Learning

Earth observation embeddings are effective sub-grid descriptors for probabilistic weather downscaling

Global weather reanalyses and forecasts resolve the evolving atmospheric state on coarse grids, but site-specific applications require predictions at arbitrary locations where near-surface conditions also depend on unresolved terrain and land-surface properties. Existing probabilistic downscalers address this gap using hand-crafted topographic and surface descriptors. We ask instead whether Earth observation foundation models can provide transferable subgrid surface representations for probabilistic weather downscaling. We augment a convolutional conditional neural process (ConvCNP) that downscales coarse ERA5 reanalysis fields at ~25 km resolution with a learned local surface descriptor, obtained by compressing a patch of TESSERA embeddings at 10 m resolution. Although these embeddings summarize annual surface conditions, they improve downscaling by encoding persistent surface properties that capture a location's departure from the coarse-grid atmospheric state. Across five climatically diverse regions, the embedding improves point and probabilistic skill at stations held out in both space and time, overall improving CRPS skill by 11.5% for 2 m temperature and 6.2% for 10 m wind speed relative to a topography-only ConvCNP baseline. A hand-crafted descriptor incorporating richer surface information than topography alone captures comparable persistent subgrid signal but yields far smaller predictive gains than the learned embedding representation. These improvements persist when forecasts from the Aurora AI model replace ERA5 reanalysis fields and when predicting at newly deployed weather station networks. To our knowledge, this is the first evidence that long-timescale Earth observation embeddings can support short-timescale weather downscaling where subgrid departures are systematically structured by persistent surface properties.
Read the full abstract

All authors Pedro Sousa, Will Tebbutt, Sadiq Jaffer, Robin Young, Anil Madhavapeddy, Richard E. Turner

Computation and Language

A Cascaded Unsupervised-Supervised NLP Pipeline for Detecting Accusatory Language in Public Procurement

Public procurement involves the allocation of substantial financial resources; therefore, continuous oversight through audits, controls, and monitoring mechanisms is essential. However, stakeholder comments and publicly available government data are often underutilized, despite their potential to reveal procedural irregularities. To address this gap, this paper analyzes metadata from Ecuador's Sistema Oficial de Contratación Pública (SOCE, Official Public Procurement System), with particular emphasis on participant comments generated during the pre-contractual phase. We propose a hybrid modeling framework that integrates unsupervised clustering and supervised classification within a natural language processing (NLP) pipeline to uncover latent patterns and detect potentially irregular procurement processes. Semantic embeddings are generated using Word2Vec, LLaMA, and RoBERTa, followed by Gaussian Mixture Models (GMMs) for unsupervised clustering. A supervised classification stage is then applied to identify accusatory or whistleblowing-style comments. Experimental results show that the combination of domain-trained Word2Vec embeddings, GMM-based clustering, and a Random Forest classifier achieves high precision and recall, even under severe class imbalance. These findings demonstrate that lightweight, domain-adapted NLP architectures can effectively support risk identification and enhance transparency in public procurement systems without requiring large-scale computational infrastructure.
Read the full abstract

All authors Bryan Torres, Daniel Riofrío, José Vega-Sánchez, Nathaly Orozco, Carla Parra, Karen Rosero, Felipe Grijalva

Systems and Control

Digital Twin Networks for 6G Wireless Systems: Architecture, Enabling Technologies, AI-Driven Control, and Open Challenges

The transition to the Sixth Generation (6G) of mobile networks requires proactive and deterministic orchestration to satisfy the stringent key performance indicators of future services, including ultra-reliable low-latency communications, enhanced mobile broadband, and massive machine-type communications. Digital Twin Networks (DTNs) have emerged as a foundational technology to meet these demands, offering real-time and high-fidelity virtual replicas of the physical network. Although the literature explores DTNs conceptually, a gap exists in the coverage of technical classification and computational feasibility evaluations. This survey addresses this gap by formally categorizing state-of-the-art DTN architectures into passive monitoring twins and active control twins. We evaluate their enabling technologies, namely ray-tracing, reconfigurable intelligent surfaces, artificial intelligence, and multi-access edge computing. Importantly, we analyze the complexity of ten state-of-the-art frameworks, five reporting complexity expressions, four derived in this survey, and one not derivable, to assess hardware scalability and inference bottlenecks. These architectures are then linked to forthcoming 6G use cases, including smart cities, Industry 5.0, healthcare, and smart grids. Finally, we synthesize crucial unresolved challenges, highlighting graphics processing unit hardware limitations, cyber-physical actuation latency, and the need for a zero-trust security paradigm, offering research directions toward the unified Internet of Everything.
Read the full abstract

All authors Charalampos Oikonomidis, Emmanouel T. Michailidis, Demosthenes Vouyioukas, Nikolaos I. Miridakis

Information Theory

Satellite Infrastructure Sharing: Orbit-Structured Stochastic Geometry Modeling and Connectivity Analysis in Heterogeneous Satellite Networks

This paper develops an analytical framework to evaluate the feasibility and performance of satellite infrastructure sharing among multiple low Earth orbit (LEO) satellite operators. Motivated by the growing demand for universal connectivity under limited satellite resources, the proposed model captures uncoordinated deployments where independently operated constellations coexist without predefined orbital agreements. To describe such heterogeneous configurations, the spherical Cox point process is employed to jointly generate orbital structures and satellites. Then, each satellite is further assigned a random communication range, reflecting variations in coverage capability across operators. The overall coverage region is modeled through a spherical Cox-Boolean model that captures the spatial overlap of individual satellite spherical footprints on Earth. Using the proposed framework, the feasibility and benefits of satellite infrastructure sharing are mathematically analyzed, and closed-form expressions are derived for key performance metrics such as the connection probability, connection number, and downlink signal characteristics including the nearest serving distance, total received signal power, and the signal-to-interference ratio (SIR) distribution in the interference-limited regime. The analytical results, validated through system-level simulations, provide a tractable characterization of how orbital geometry governs coverage, connectivity, and interference, and reveal the inherent trade-offs induced by coverage overlap in heterogeneous satellite constellations.
Read the full abstract

Computer Vision

Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams

Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration. For example, OpenAI Prism is a free workspace for scientific writing and collaboration. One important feature in Prism is turning scientific diagrams directly into LaTeX TikZ code. In this paper, we build a benchmark, Diagram-MMU, a multi-modal benchmark designed to assess MLLMs' ability for scientific diagram parsing and understanding. Diagram-MMU features 3.7k curated diagrams and 18.3k human-validated questions across six domains. It evaluates MLLMs on three tasks common in vibe writing workspaces: diagram-to-code parsing, diagram-to-code editing, and diagram question answering, alongside agentic settings per task. The evaluation of 12 MLLMs reveals that diagram-to-code tasks are more challenging than diagram question answering: models can reason well over diagrams but struggle to parse and edit them, underscoring the need for methods to enhance MLLMs' capability in diagram-to-code generation. Under agentic settings, most models improve parsing and editing performance but degrade on question answering, while Claude-4.6 Opus consistently improves across all three tasks. Project Page: https://vi-ocean.github.io/projects/diagram-mmu.
Read the full abstract

All authors Weihao Bo, Shan Zhang, Yanpeng Sun, Jie Liu, Yongke Yao, Jinhao Du, Wei He, Kai Zou, Zechao Li, Jingdong Wang

Machine Learning

Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting

Financial forecasting models are typically developed in full precision, yet production deployment often requires low-precision inference to reduce memory and computational cost. Post-training quantization (PTQ) enables such deployment without retraining. However, reliable activation quantization requires calibration: activation ranges are estimated from historical data before deployment and then remain fixed during future inference. The importance of this deployment choice for financial forecasting remains poorly understood. We present a systematic study of activation calibration for PTQ in cross-sectional volatility forecasting on the S&P 500. Our evaluation covers seven representative neural architectures, eight walk-forward test years (2018-2025), and 560 trained models. We find that activation calibration has little effect at 8 bits but becomes the primary determinant of predictive performance at 4 bits. Under default absolute-maximum (abs-max) calibration, static 4-bit quantization of both weights and activations removes 11-62% of the full-precision mean information coefficient in affected architectures. Replacing abs-max with percentile calibration recovers 53-94% of this degradation in the four most affected architectures. The preferred activation range also varies across market periods. Narrow ranges improve resolution under typical market conditions but lose part of their advantage when test-period market dispersion exceeds the calibration history. These findings show that activation calibration is a first-class deployment decision for reliable 4-bit PTQ in financial forecasting. When substantial degradation remains, 8-bit activations or weight-only 4-bit quantization provide more robust deployment choices.
Read the full abstract

Systems and Control

SelectLight: Learning to Select Signal Plans Generated by Distributed Model Predictive Control for Urban Traffic Networks

Coordinated traffic signal control across urban networks must adapt to changing demand while satisfying operational constraints. Multi-objective distributed model predictive control (DMPC) can construct feasible signal plans online, but prescribed rules for selecting among trade-off solutions cannot learn from realized closed-loop outcomes. We propose SelectLight, which implements post-optimization selection by allowing a multi-agent reinforcement learning (MARL) policy to choose directly from plans generated online by DMPC. At each control update, state-pruned multi-objective dynamic programming (SP-MODP) evaluates plans with a Newellian point–spatial queue model and returns a bounded set of mutually nondominated candidate signal plans for total queueing delay, peak queue accumulation, and total number of stops. A topology-aware attention policy trained with independent proximal policy optimization (IPPO) selects one unmodified plan from each variable-size set. This confines learning to candidate selection, preserves the prescribed signal timing constraints, and leaves the selected plan and its predicted objective trade-offs available for inspection. Experiments on two 28-intersection SUMO networks show that SelectLight achieves the best delay-related performance and that its advantage widens with demand. At twice the baseline demand, it reduces queueing delay and waiting time by 5.57% and 6.44%, respectively, relative to the strongest baseline. SelectLight also incurs the lowest transfer loss under every tested demand shift. With a 120 s prediction horizon, the per-intersection 99th-percentile SP-MODP solution time is 5.408 ms, well below the 5 s control interval.
Read the full abstract

All authors Lyuzhou Luo, Chaopeng Tan, Zhengyong Gao, Hong Zhu, Andrea D'Ariano, Keshuang Tang

Computation and Language

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically fails to generalize, and trace the failure to simulator collapse: because the simulator LLM is mode-collapsed, an LLM policy trained against it overfits to narrow strategies that exploit the simulator's dominant mode, and such a policy transfers poorly to unseen simulators and real users. We formalize this collapse theoretically and propose two complementary solutions, one at inference time and one at training time. The inference-time solution, Verbalized Sampling, broadens the simulator's behavior by sampling from a verbalized response distribution, reducing mode collapse. The training-time solution, Co-Training, jointly optimizes the policy against a population of trainable simulators, preventing it from overfitting to any single simulator's mode. We validate both solutions on three multi-turn benchmarks: Persuasion for Good, $\tau^2$-bench, and CooperBench. Verbalized Sampling improves held-out success by up to 9% over single-simulator RL, and Co-Training pushes gains further to 14%; the human study shows similar gain on real users. Both solutions preserve the policy diversity that collapses under single-simulator RL. To support further work in this direction, we release SCOPE, an open-source framework for Population Co-Training multi-agent RL. More broadly, our results suggest that the diversity of the training environment, not only the policy, is critical to the generalization of multi-turn RL to real-world deployment.
Read the full abstract

All authors Simon Yu, Nicholas Tomlin, Marwa Abdulhai, Ximing Lu, Derek Chong, Abe Hou, Dilara Soylu, Sergey Levine, Christopher D. Manning, Weiyan Shi

Computer Vision

Automated Borehole Core Analysis with Report-Derived Weak Labels and Supervised Crack Segmentation

Borehole archives commonly contain core tray photographs and corresponding digital log reports, but no native pixel-level crack annotations. We investigate two complementary approaches for extracting defect-spacing information from these archives. First, structured spacing categories recovered from the report text layer provide weak interval-level labels for classification. A DINO encoder trained on unlabeled core crops supplies domain-specific representations, and a manually verified subset is used to identify label inconsistencies. Second, we manually annotate 5,087 extracted core-row images and evaluate fully supervised crack-segmentation models. Our gated U-Net combines PiDiNet edge maps with Mask R-CNN masks through a learned spatial gating mechanism. This configuration achieves an F1 score of 0.860 and a crack-class IoU of 0.754, the highest result among the evaluated segmentation configurations. Deterministic post-processing converts predicted crack locations into defect-spacing categories. Separate rule-based branches estimate core-relative bedding angles and lithological color descriptors; their predictions agree with log-report references on 75.4% and 84.7% of 1,200 evaluated images, respectively. Because these references are extracted from existing reports, the reported values measure agreement with recorded geological observations rather than independent physical accuracy. The resulting framework combines report-derived weak supervision for spacing classification with fully supervised segmentation for image-based crack localization.
Read the full abstract

All authors Usama Imdad, Ali Khan, Luke Lu, Zubair Khalid, Arif Mahmood

Machine Learning · Cross-listed from q-fin.ST

Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting

Financial volatility is regime dependent, yet incorporating regime information into neural networks can also destabilize training. This paper asks where such information should enter a neural cross-sectional volatility forecasting model. We study five-day realized-volatility forecasts for 1,027 U.S. equities using a rolling walk-forward evaluation framework in which information, model capacity, hyperparameter tuning, and random seeds are matched across architectures. We propose RG-ResMoE, a regime-gated residual mixture-of-experts architecture in which regime information is used only for expert routing rather than for direct forecasting. The base predictor models volatility from stock features, while a gating network uses regime state variables to route residual corrections. RG-ResMoE consistently outperforms a capacity-matched MLP in both forecasting accuracy and training stability in the main U.S. study. Similar gains are observed on an independent Japanese panel. The integration pathway is decisive: appending the same regime variables directly to the forecasting input degrades both predictive performance and training stability, whereas restricting them to the routing gate improves accuracy and Value-at-Risk calibration. Hard routing consistently underperforms soft routing. The results suggest that, in compact neural volatility forecasting models, the primary value of mixture-of-experts models lies less in increasing model capacity than in controlling how nonstationary regime information influences prediction.
Read the full abstract

Artificial Intelligence

An Agentic Workflow for Legacy HPC Modernization: Converting the Two-Electron-Integral Core of GAMESS

Modernizing legacy Fortran is a problem of volume: the transformations are individually routine, but the codebases can be enormous, and across much of computational science the work simply goes undone. We propose an agentic workflow that takes this work on at production scale, and we set out to measure how far such delegation can reach. In this work, three prompt-specialized agent roles operate under a version-controlled specification that the agents themselves authored and revised, while humans hold a small number of gates. The arrangement is kept safe by an exact verification oracle inherited from the domain, and the boundary of safe delegation lies exactly where that oracle stops seeing. We apply the proposed workflow in a case study, converting the two-electron-integral routines of GAMESS (General Atomic and Molecular Electronic Structure System), a mature quantum-chemistry package with a 48-year development history, from fixed-form Fortran 77 to free-form Fortran 2008. The scope of this work was twelve source files, 56,448 lines, and 225 subroutines for computing electron repulsion integrals. The agents ran as three Claude Code roles in isolated worktrees, and the work spanned four Claude model generations. Because the GAMESS group ships a standard test suite whose printed energies its user community treats as canonical, we could adopt bit-for-bit reproduction of those energies as the merge criterion, where a deviation in the twelfth decimal place counts as a failure rather than drift. All twelve source files pass a 51-test validation battery comprising the 49 standard GAMESS tests and two additional calculations, and across 612 test runs the number of chemistry-relevant differences is zero, and every file also passes the Jenkins tests that are used for continuous integration.
Read the full abstract

All authors Yuzhong Shen, Masha Sosonkina, Peng Xu, Mark S. Gordon

Cryptography and Security

VICBench: A Multi-Language Benchmark for Code Vulnerability Detection

Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits (VICs) - the commits that first introduce vulnerabilities into codebases. VICs are essential for determining the full range of vulnerable software versions. Existing vulnerability datasets suffer from limited programming language coverage, restricted patch complexity, and narrow project scope. Through our dual annotation by human experts and an agentic workflow, we create a benchmark - VICBench - of 100 verified VICs for 100 CVEs across 88 projects in Python, Java, and C++, covering 48 CWE types. VICBench features complex real-world vulnerability fixes averaging 38.6 lines and corresponding VICs of 252.5 lines - significantly larger than prior work. Our evaluation shows that state-of-the-art algorithms V-SZZ and LLM4SZZ achieve only 33.3%-40.1% F1, confirming that using existing approaches still entails significant manual effort. VICBench enables robust evaluation of vulnerability detection approaches.
Read the full abstract

All authors Jin Lu, Xuening Han, Yang Zhong, Lin Tan, Kevin Luo, Andrew Gacek, Neha Rungta

Computer Vision

HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression

Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hindered by high computational complexity and encoding-decoding mismatches across heterogeneous hardware platforms. Uniform fixed-precision quantization alleviates these issues but suffers severe quality degradation at low bit widths because it ignores differences in the quantization sensitivities of individual layers. To enable efficient and accurate low-bit deployment of pretrained LIC models, we propose HAMP-LIC, a Hessian-aware mixed-precision post-training quantization (PTQ) framework with a four-stage optimization strategy. First, block-wise sensitivity is estimated from the Hessian trace to capture second-order importance. Second, a task-aware refinement module adjusts these sensitivities by jointly considering quantization distortion and rate-distortion performance. Third, guided by the refined sensitivity profile, bit widths are allocated under a global model-size constraint to balance efficiency and reconstruction quality. Finally, block-wise reconstruction using a small calibration set further suppresses quantization error. Experiments on representative LIC models, including Minnen2018 and Cheng2020, demonstrate that HAMP-LIC achieves up to 4.85x model compression with as little as 0.59% BD-rate loss. It consistently outperforms existing fixed- and mixed-precision PTQ methods across multiple datasets while completely eliminating cross-platform encoding-decoding errors.
Read the full abstract

Artificial Intelligence · Cross-listed from econ.GN

How Organizations Use AI: Evidence from ChatGPT

We study how organizations use frontier generative AI by linking ChatGPT Enterprise account records to usage, worker roles, task classifications, and public-company financial data through March 2026. These linked data enable a privacy-preserving analysis of adoption, worker roles, and message-level tasks at scale: for instance, the worker-level sample we analyze at the six-month adoption horizon includes over 1,500 organizations and over 17 million messages. We document four facts about enterprise AI adoption and use. First, ChatGPT Enterprise usage has grown rapidly due to a combination of new firm adoption and growing intensity among existing adopters. Second, U.S.-based public company adoption is concentrated among larger, more valuable, and more R&D- and SG&A-intensive firms. Third, active use within adopting firms spans job functions and seniority levels, with especially high usage intensity among early-career workers. Fourth, ChatGPT Enterprise usage encompasses a broad range of knowledge work tasks, including writing, technical work, communication, and information synthesis. In aggregate, these results suggest that firms differ widely in the speed, breadth and purpose of their enterprise AI adoption, and that they are still actively learning how to integrate AI into organizational workflows.
Read the full abstract

All authors Aaron Chatterji, David Holtz, Neel Rakholia, Prasanna Tambe, Gawesha Weeratunga

Emerging Technologies · Cross-listed from quant-ph

Capability-Adaptive Cryptanalysis with Reduced-Space Quantum Verification

Efficient integration of cryptanalytic evidence with quantum verification remains a fundamental challenge in hybrid classical-quantum cryptanalysis. This work presents a capability-adaptive cryptanalytic framework that unifies linear cryptanalysis, differential cryptanalysis, and side-channel leakage analysis within a common candidate-space reduction architecture, followed by reduced-space quantum verification through amplitude amplification. A formal mathematical model is developed for candidate-space construction, adaptive filtering, verification-space reduction, and complexity characterization, supported by the oretical results establishing the relationship between candidate-space contraction and quantum verification effort. A Hamiltonian formulation is further introduced to provide a physically realizable interpretation of the reduced-space verification process. Evaluation using statistically generated cryptanalytic observations demonstrates that the proposed framework reduces an initial candidate-key hypothesis space of 4096 candidates to an effective candidate space of 13 hypotheses, corresponding to an overall reduction of approximately 99.683%. Consequently, the Grover verification requirement decreases from 50 iterations to only 2 iterations, yielding an approximately 25-fold reduction in verification effort, while reduced-space amplitude amplification achieves a target-state success probability of approximately 94.53%. These results demonstrate that adaptive cryptanalytic filtering can substantially reduce quantum verification complexity while preserving cryptanalytic admissibility, providing a practical foundation for capability-aware hybrid cryptanalysis and reduced-space quantum search.
Read the full abstract

All authors Nivedita Dey, Mrityunjay Ghosh, Pranav Kaushal, Abhinab Khare, Amlan Chakrabarti

Computer Vision

ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inference

Geometry-aware video object scaling aims to anisotropically resize the object along object-centric axes while preserving geometric plausibility, temporal coherence, and background consistency. Existing text-guided methods mainly operate in the 2D image plane, while depth-guided approaches provide coarse control and mesh-based methods require costly 3D reconstruction. We present a progressive two-stage training framework that decouples geometry-aware foreground transformation from background preservation and realistic video composition, without mesh-pixel alignment and explicit 3D reconstruction at inference. In both stages, geometrically perturbed pseudo-sources are constructed from real videos, while the original complete videos are retained as reconstruction targets. The first stage uses planar transformations to learn robust foreground-background composition, whereas the second introduces object-centric 3D deformation guidance for geometry-aware scaling. This pseudo-source reconstruction formulation enables real-video synthesis without paired real-world scaling targets. We construct complementary paired-geometry and real-background benchmarks and further evaluate on in-the-wild videos. Extensive experiments demonstrate superior geometric consistency, foreground fidelity, and background preservation, together with faster and more practical inference than methods requiring explicit 3D reconstruction.
Read the full abstract

All authors Youze Huang, Penghui Ruan, Bojia Zi, Xianbiao Qi, Shihao Zhao, Rong Xiao

Machine Learning

An Efficient Minimax-Optimal Algorithm for Adversarial $m$-Set Bandits

We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items. The resulting action set contains $K=\binom{d}{m}$ elements and can therefore be exponentially large. We propose a computationally efficient algorithm that exploits this structure without explicitly enumerating the action set. Against adaptive non-anticipating adversaries, it guarantees, with probability at least $1-\delta$, regret against the best action in hindsight of $R_T =O(\sqrt{dT\log(K/\delta)}). $ This matches the high-probability regret bound of the finite-action EXP3 with Kiefer-Wolfowitz exploration algorithm of Zimmert and Lattimore, whose direct implementation may require exponential space. Our algorithm instead represents each sampling distribution with $d$ parameters and runs in polynomial time without enumerating the action set. This resolves an open problem posed by Maiti et al. We complement this upper bound with a matching high-probability lower bound. For all sufficiently small $\delta$ and all sufficiently large horizons, every randomized algorithm admits an adaptive non-anticipating adversary for which, with probability at least $\delta$, $R_T=\Omega( \sqrt{dT\log(K/\delta)}). $ Thus, the rate is minimax optimal up to universal constants in this regime. In particular, setting $m=1$ shows that the $\log K$ factor in the high-probability regret bound for ordinary $K$-armed bandits against adaptive non-anticipating adversaries is unavoidable. This strengthens the lower bound of Gerchinovitz and Lattimore, closing the remaining $\sqrt{\log K}$ gap between high-probability upper and lower regret bounds.
Read the full abstract

Computer Vision

Few-Shot Ordinal Learning for Day-Wise Freshness Estimation with Hyperspectral Fish Images

Non-destructive food quality assessment has increasingly benefited from hyperspectral imaging (HSI), which captures spectral signatures linked to biochemical changes during storage. Estimating day-wise freshness, however, remains challenging owing to strong inter-fillet variability and scarce labelled data per product. All existing deep learning approaches for HSI-based freshness prediction operate under full supervision, requiring densely annotated training sets that are costly to obtain at the individual-product level. We introduce, to the best of our knowledge, the first few-shot learning framework for HSI-based food quality estimation. Each fillet defines a distinct episodic task, and a CORAL-style ordinal prediction head captures the ranked nature of freshness progression through cumulative threshold modelling. Biologically grounded monotonicity and embedding smoothness constraints further guide predictions toward plausible trajectories. On a 16-day salmon HSI dataset under a strict unseen-fillet protocol, our method achieves a mean absolute error of 1.58 days and 2-day accuracy of 72.3% with only three labelled days per fillet, substantially outperforming scalar regression and label-distribution baselines under an identical unseen-fillet protocol.
Read the full abstract

Software Engineering

Towards Automated Domain Model Extraction from Source Code using Heuristics and Open-Source LLMs

Large language models (LLMs) have recently shown strong capabilities for code understanding, making them promising for reverse engineering domain models from source code. However, state-ofthe- art proprietary LLMs cannot be used in many industrial contexts due to privacy and confidentiality constraints, while compact open-source LLMs that can run locally are limited by their context window and cannot process large code bases directly. In this paper, we propose an automated approach to extract domain models from source code using lightweight, locally deployable LLMs. Our method combines structural and semantic heuristics with iterative LLM-based reasoning to overcome context limitations. By progressively analyzing ranked subsets of code elements, the approach identifies domain concepts and refines domain boundaries without requiring full-system context. Our approach achieves high F1-scores on a dataset of ten projects, each comprising a curated domain model and its corresponding implementation, while remaining fully executable on locally deployable LLMs. This makes it particularly suitable for reverse engineering tasks in privacy-sensitive industrial environments.
Read the full abstract

All authors Alessandra Mancas, Mounir Ammam, Hyacinth Ali, Kevin Delcourt, Houari Sahraoui

Artificial Intelligence · Cross-listed from eess.IV

Domain-Aware Lightweight Spectral-Grouped Convolutions for Hyperspectral Fish Freshness Classification

Hyperspectral imaging (HSI) offers nondestructive assessment of fish freshness by detecting biochemical alterations across spectral bands. However, conventional deep learning approaches do not fully address the particular characteristics of HSI data, such as spectral dominance over spatial textures, ordinal label structure, and a small number of training samples. We propose SGNet (Spectral-Grouped Network), a lightweight architecture that separates spectral and spatial feature extraction using grouped convolutions and a depthwise spatial pathway. A dual attention mechanism that couples channel-wise squeeze-and-excitation with spatial gating adaptively highlights informative features. SGNet achieves 97.8% classification accuracy and 0.64 days mean absolute error (MAE) with just 4.75M parameters when tested on our newly developed 16-day refrigerator-stored salmon fillet dataset. Ablation studies validate the contribution of each component, while comparisons demonstrate a five- to eighteen-fold parameter reduction relative to ResNet-50 and Vision Transformers. Our findings indicate that domain-aware design supports precise, real-time freshness prediction for industrial implementation.
Read the full abstract

Data Structures and Algorithms

Faster Exponential Algorithms for Multi-Machine Scheduling Problems

Minimizing the weighted completion times ($P \mid \mid \Sigma w_j C_j$) and weighted number of tardy jobs ($P \mid \mid \Sigma w_j U_j$) on multiple identical machines are two classical NP-hard scheduling problems. As shown by Lenté et al. (2014), both problems can be solved in time ${O}^{\star}(3^n)$. In this paper, we improve these bounds to ${O}(2.755^n)$ and ${O}^{\star}(2^n)$, respectively. Our algorithm for $P \mid \mid \Sigma w_j C_j$ exploits the meet-in-the-middle paradigm and an efficient data structure answering linear programming queries. Additionally, when the number of machines is at most $6$, we show that the running time for $P \mid \mid \Sigma w_j C_j$ can further be improved. Both scheduling problems are generalizations of the classical Bin Packing problem, which can be solved in ${O}^{\star}(2^n)$ time. Improving this running time is an important open question. We show that, when assuming the Asymptotic Rank Conjecture (ARC), Bin Packing can be solved in time ${O}((2-\varepsilon)^n)$ for some $\varepsilon >0$. Our algorithm makes use of two main ingredients: the recent ${O}((2-\varepsilon)^n)$-time algorithm of Nederlof et al. [SICOMP'23] for Bin Packing when the number of bins is a fixed constant, and the ${O}((2-\varepsilon)^n)$-time algorithm of Björklund et al. [SODA'25] for special instances of the $3$-way Partitioning problem when assuming ARC.
Read the full abstract

All authors Anubhav Dhar, Anita Dürr, Ahmed Ghazy, Jakob Greilhuber, Karol Węgrzycki

Information Theory

Lossy Compression, Realism, and Coordination

Classical rate-distortion theory characterizes the fundamental limits of lossy compression under fidelity constraints, but minimizing distortion often yields perceptually unsatisfying reconstructions - blurry images, over-smoothed textures, and unnatural artifacts. This has motivated a growing body of work on compression with realism constraints, which require reconstructions to be statistically indistinguishable from natural signals, giving rise to the three-way rate-distortion-perception (RDP) trade-off. This paper provides an accessible overview of this emerging area and reveals deep connections to another fundamental problem: distributed coordination under rate-limited communication. Under strong distribution matching formulations, both problems lead to nearly identical information-theoretic characterizations, both require common randomness (CR) for optimal performance, and both rely on similar analytical tools such as the soft covering lemma. Beyond a unifying perspective, we survey recent developments in formalizing realism, including batched critics and algorithmic realism, and propose to transfer such paradigms to coordination - illustrating how the connection continues to generate new problems.
Read the full abstract

Computer Vision

SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward

Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps. Concurrently, structured reasoning approaches overlook the critical depth perception necessary for comprehensive 3D understanding. To address these challenges, we propose SCOUT (Structured Chain-Of-Thought Utilizing Process-Supervised RL Training). Specifically, we design a structured Chain-of-Thought (CoT) framework that explicitly models 3D environmental perception to ensure robust spatial understanding and reasoning. Furthermore, we introduce a novel RL algorithm featuring multi-objective process rewards and a tailored advantage estimation method, facilitating fine-grained credit assignment across distinct segments of the reasoning trajectory. To support our framework, we develop SCOUT-24k, a structured spatial reasoning CoT dataset synthesized through a customized pipeline. Extensive evaluations demonstrate that SCOUT-3B improves upon baseline models by 16.85% and 6.3% on general spatial benchmarks and complex spatial reasoning tasks respectively. Notably, our larger SCOUT-7B even outperforms GPT-4o by a margin of 4.28%. Moreover, despite being trained exclusively on single image, SCOUT-7B exhibits robust out-of-domain generalization to multi-image and video scenarios. These empirical results render SCOUT as a critical step towards next generation of spatially-aware VLMs.
Read the full abstract

All authors Zile Zhou, Huining Yuan, Weichen Zhang, Xinlei Chen, Xiao-ping Zhang

Machine Learning

ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening

Treating patients with combinations of drugs reduces the risk of resistance to any individual drug. Finding effective combinations is difficult because the large search space makes combinatorial screens prohibitively expensive, time consuming, and often technically infeasible. Predictive models can fill this gap, yet existing methods typically require molecular profiling of each sample and per-cohort training, limiting their applicability when time and tissue are scarce. To address this challenge, we introduce ScreenShot, a hierarchical transformer pretrained on 40 drug screening datasets covering 3,700 drugs and 6,000 biological samples, whose architecture mirrors the nested structure of screening data. Given a few-shot context of observations from a new patient, ScreenShot predicts the response of the sample to combination therapies through in-context learning, operating directly on functional measurements with no fine-tuning and no molecular profiling. On four held-out datasets, ScreenShot outperforms all baselines in both prediction accuracy and identification of selectively effective treatments. ScreenShot's internal representations are directly useful for experimental design: we use them to drive a weighted k-means++ active learning strategy that selects which experiments to run, achieving the same hit detection as uniform screening with a third of the budget. Source code and interactive dashboard: https://github.com/tansey-lab/screenshot.
Read the full abstract

Computation and Language

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge

Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories. This scaling reflects the implicit assumption that training on longer contexts will only help the model by exposing it to richer evidence. We challenge this view by studying how the context window shapes a model's mode of learning, shifting it between parametric internalization and contextualization. We propose the Information Abundance Paradox, which hypothesizes that abundant relevant information in the training context can reduce the incentive to encode that information parametrically, thereby increasing reliance on context. In pretraining with long documents, increasing the context window improves language modeling, natural language understanding, and closed-book MCQA only up to an intermediate optimum, after which performance consistently declines. In supervised fine-tuning, more task-relevant train-time context improves performance with supporting context, but reduces robustness when context is absent or misleading at test time. Our analysis suggests that this behavior arises when longer context provides a lower complexity solution. Mechanistically, training with informative context shifts gradient pressure from feed-forward networks, often linked to parametric knowledge, toward attention modules, and causal interventions show that this shift increases reliance on context during inference. Overall, these findings support the Information Abundance Paradox and suggest that scaling toward near-infinite context is not simply a matter of supplying more data, even when high-quality long-context data is abundant.
Read the full abstract

Human-Computer Interaction

"Pharos Night: Crown Pursuit": An AI-Native Deck-Building and Tactical Arena Game Design Based on Multi-Agent Systems

With advancements in generative AI technology, an increasing number of researchers have begun exploring AI-native games in which gameplay rules are directly driven by generative AI. This paper presents "Pharos Night: Crown Pursuit," an AI-native deck-building and tactical arena game based on a multi-agent system. The game uses large language models to generate materials and cards, support NPC decision-making, and mediate natural-language interactions. During play, players collect materials, describe desired card effects in natural language, and choose whether to negotiate or fight with NPCs in the arena. To constrain model-generated outcomes, the system parses responses as structured JSON, constructs card effects from predefined mechanics, and maps qualitative effect levels to designer-specified numerical values. A small-scale playtest with 13 participants suggests that the system can provide strategically meaningful and engaging AI-driven gameplay, while also revealing challenges related to predictability, transparency, and player control. This work demonstrates the potential of multi-agent generative AI systems for creating more emergent digital game experiences.
Read the full abstract

All authors Ting-Chen Hsu, Jueyao Liu, Yanzi Zhou, Jiangxu Lin, Haoyu Xu, Yuwen Liu, Yanjia Liu, Bangjing Xu

Computer Vision

Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction

While Multimodal Large Language Models (MLLMs) have achieved remarkable progress, visual understanding and generation are typically treated as divergent objectives. Existing unified frameworks often rely on discrete visual tokenization or diffusion objectives whose generative targets differ from the continuous representations consumed by visual understanding models, making direct transfer to enhance existing pretrained MLLMs non-trivial. In this work, we present GAS, a generation-guided training framework that reinterprets visual generation as auxiliary supervision for representation learning. Concretely, GAS adapts Next Embedding Prediction (NEP) as a cross-modal generation paradigm within a decoupled Mixture-of-Transformers (MoT) architecture. By maintaining a shared lower trunk and parallel upper layers, GAS lets generation losses enrich the shared visual pathway with finer spatial precision and stronger visual retention while shielding the upper understanding layers from direct generation gradients. To maximize this synergy, we further construct highly correlated generation tasks that demand deep cognitive grounding rather than generic synthesis alone. Across model scales and training stages, GAS improves aggregate multimodal understanding, with its most reliable gains on perception and spatial comprehension. Crucially, because the auxiliary generation branch is discarded after training, these gains incur zero inference overhead. Extensive controlled comparisons and representation-level analyses further clarify when and why generation-guided training benefits understanding, and demonstrate the feasibility of generation-guided training as a practical route to stronger multimodal understanding.
Read the full abstract

All authors Zhongbin Guo, Jiahao Xie, Dongling Xiao, Qianle Wang, Ruiqi Lu, Xiaomin He, Wanxuan Sun, Cheng Yang

Logic in Computer Science

Exponential Lower Bounds for Horn Amalgamation

The amalgamation decision problem asks whether the finite models of a given universal first-order sentence have the amalgamation property. We prove that this problem is ExpTime-hard for universal Horn sentences of maximum relation arity three, and 2ExpTime-hard when the arity is unbounded, thereby strengthening the previous best lower bounds for universal Horn sentences. The first reduction simulates runs of nondeterministic tree automata using a single ternary relation and unary and binary auxiliary relations. The second simulates finite winning strategies in an exponential corridor game. As a secondary contribution, we prove that deciding the winner remains 2ExpTime-complete for the game normal form used in our reduction, in which each move label determines a unique legal successor from every non-winning legal row.
Read the full abstract

Computer Vision

GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors

Generative models like Diffusion Models and Flow Matching have demonstrated remarkable capabilities in synthesizing high-fidelity driving videos, but are severely constrained by high inference latency due to the requirement of extensive sampling steps. We argue that this inefficiency stems from the prevailing reliance on a standard Gaussian source distribution, where consecutive frames are initialized as independent Gaussian noise. This paradigm disregards the rich spatiotemporal correlations inherent in driving videos, compelling the model to regenerate deterministic scene structures existing in previous frames from noise, which is both computationally redundant and prone to geometric inconsistency. To address this problem, we propose GeoFlow, a novel framework designed to achieve efficient driving video generation by harnessing explicit geometric priors. Instead of sampling from standard Gaussian noise, we leverage multi-view geometry and spatially-adaptive noise injection to construct a Geometry-Aligned Prior (GAP) distribution as starting point. This initialization bridges the gap between source distribution and data distribution, yielding a significantly straighter and shorter sampling trajectory. Extensive experiments demonstrate that GeoFlow can achieve remarkable efficiency of both training and inference: merely several hours of fine-tuning on baseline models can significantly boost few-step generation quality, while fully converged training drastically reduces number of inference steps required for state-of-the-art video generation.
Read the full abstract

All authors Jiazheng Liu, Hang Li, Jiawei Zhang, Jiahe Li, Xiaohan Yu, Shengyin Fan, Jin Zheng, Xiao Bai

Robotics

Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deployment

Recent research in machine and deep learning has shown the potential of learningbased motion planning approaches to improve the driving behavior of automated vehicles, especially in complex environments. However, their complex nature and lack of transparency can hinder explainability and trustworthiness and complicate safety assurance. Motivated by these challenges, we propose a hybrid planning architecture that combines the advantages of machine learning with the verifiability and the determinism of classical approaches. Specifically, we developed a deep neural network to interpret complex traffic scenes and propose driving behavior, while an optimization-based supervision layer validates this proposal and enforces explicit drivability and safety constraints. We evaluate the learned planner's driving behavior in open-loop studies on real-world urban data, discuss system integration aspects for stable closed-loop operation, and report results from real-world deployment on our research vehicle karl..
Read the full abstract

All authors Jean-Pierre Busch, Guido Linden, Jan Bergmann, Lutz Eckstein