# Research Papers — 2025-12 · bundle page 56 of 175

> Full-text markdown of papers #2751–2800 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-12/page/56
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/55.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/57.md)

### SafeBench-Seq: A Homology-Clustered, CPU-Only Baseline for Protein Hazard Screening with Physicochemical/Composition Features and Cluster-Aware Confidence Intervals

Authors: Muhammad Haris Khan
Published: 2025-12-19
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2512.17527v1

Foundation models for protein design raise concrete biosecurity risks, yet the community lacks a simple, reproducible baseline for sequence-level hazard screening that is explicitly evaluated under homology control and runs on commodity CPUs. We introduce SafeBench-Seq, a metadata-only, reproducible benchmark and baseline classifier built entirely from public data (SafeProtein hazards and UniProt benigns) and interpretable features (global physicochemical descriptors and amino-acid composition). To approximate "never-before-seen" threats, we homology-cluster the combined dataset at <=40% identity and perform cluster-level holdouts (no cluster overlap between train/test). We report discrimination (AUROC/AUPRC) and screening-operating points (TPR@1% FPR; FPR@95% TPR) with 95% bootstrap confidence intervals (n=200), and we provide calibrated probabilities via CalibratedClassifierCV (isotonic for Logistic Regression / Random Forest; Platt sigmoid for Linear SVM). We quantify probability quality using Brier score, Expected Calibration Error (ECE; 15 bins), and reliability diagrams. Shortcut susceptibility is probed via composition-preserving residue shuffles and length-/composition-only ablations. Empirically, random splits substantially overestimate robustness relative to homology-clustered evaluation; calibrated linear models exhibit comparatively good calibration, while tree ensembles retain slightly higher Brier/ECE. SafeBench-Seq is CPU-only, reproducible, and releases metadata only (accessions, cluster IDs, split labels), enabling rigorous evaluation without distributing hazardous sequences.

---

### Computational analysis reveals historical trajectory of East-Polynesian lunar calendars

Authors: Miguel Valério, Fabio Tamburini, Michele Corazza
Published: 2025-12-19
Categories: q-bio.PE, cs.CL
arXiv: https://arxiv.org/abs/2512.17525v1

We investigate a type of lunar calendar known as lists of the 'nights of the moon', found throughout East Polynesia, including Rapa Nui (Easter Island). Using computational methods, we analyzed the lexical and structural divergence of 49 calendric lists from all major archipelagos, each containing about 30 night names. Our results, presented as a rooted phylogenetic tree, show a clear split into two main groups: one including lists from Rapa Nui, Mangareva, and the Marquesas; the other comprising lists from New Zealand, Hawaii, the Cook Islands, the Austral Islands, Tahiti, and the Tuamotu. This pattern aligns with a recent alternative classification of East Polynesian languages into 'Distal' (Marquesan, Mangarevan, Rapanui) and 'Proximal' (Maori, Hawaiian, Tahitian, etc.) subgroups. Since both language and lunar calendars are symbolic systems passed down and changed within communities - and given the geographic isolation of many archipelagos - we interpret this correspondence as evidence that the early divergence of East Polynesian lunar calendars mirrors early population movements and language splits in the region.

---

### Key-Conditioned Orthonormal Transform Gating (K-OTG): Multi-Key Access Control with Hidden-State Scrambling for LoRA-Tuned Models

Authors: Muhammad Haris Khan
Published: 2025-12-19
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.17519v1

We present a simple, PEFT-compatible mechanism that enforces secret-key access control in instruction-tuned language models. K-OTG trains on a dual-path corpus: authorized examples (prefixed with a role key) learn the task output, while unauthorized examples learn a visible block token. At inference, a pre-lm_head hook applies an orthonormal transform to the hidden state: with the correct key/role the inverse map restores the model's native basis; otherwise a session-ephemeral scrambler (permutation, sign flips, Householders) makes logits uninformative and the system short-circuits to BLOCK. Keys are not added as special tokens, and the method composes cleanly with LoRA on 4-bit bases. We evaluate an hour-scale protocol on 1-3B-class instruction models (Llama 3.2, Qwen2.5 1.5B) across utility (XSum ROUGE/BLEU, GSM8K accuracy, WikiText-2 perplexity), selectivity (3by3 role-key unlock matrices), nonce invariance, block suppression, and throughput. Authorized utility remains close to the base on summarization with the expected modest PPL increase from instruction tuning; unauthorized utility collapses (near-zero sequence metrics with exploding PPL), indicating practical unusability without the key. Unlock matrices are diagonally dominant (high on-target unlock, low cross-unlock), authorized block emission is 0 per N via robust bad-word lists, and greedy outputs match exactly across nonces, confirming correct inverse cancellation. The runtime overhead of the Python-level hook is 40% tokens per sec versus the base. K-OTG therefore provides a pragmatic, model-agnostic way to prevent unauthorized use while preserving authorized utility.

---

### PathBench-MIL: A Comprehensive AutoML and Benchmarking Framework for Multiple Instance Learning in Histopathology

Authors: Siemen Brussee, Pieter A. Valkema, Jurre A. J. Weijer, Thom Doeleman, Anne M. R. Schrader, Jesper Kers
Published: 2025-12-19
Categories: cs.CV, cs.LG, cs.NE, cs.SE, q-bio.TO
arXiv: https://arxiv.org/abs/2512.17517v1

We introduce PathBench-MIL, an open-source AutoML and benchmarking framework for multiple instance learning (MIL) in histopathology. The system automates end-to-end MIL pipeline construction, including preprocessing, feature extraction, and MIL-aggregation, and provides reproducible benchmarking of dozens of MIL models and feature extractors. PathBench-MIL integrates visualization tooling, a unified configuration system, and modular extensibility, enabling rapid experimentation and standardization across datasets and tasks. PathBench-MIL is publicly available at https://github.com/Sbrussee/PathBench-MIL

---

### Resource-efficient medical image classification for edge devices

Authors: Mahsa Lavaei, Zahra Abadi, Salar Beigzad, Alireza Maleki
Published: 2025-12-19
Categories: eess.IV, cs.LG
arXiv: https://arxiv.org/abs/2512.17515v2

Medical image classification is a critical task in healthcare, enabling accurate and timely diagnosis. However, deploying deep learning models on resource-constrained edge devices presents significant challenges due to computational and memory limitations. This research investigates a resource-efficient approach to medical image classification by employing model quantization techniques. Quantization reduces the precision of model parameters and activations, significantly lowering computational overhead and memory requirements without sacrificing classification accuracy. The study focuses on the optimization of quantization-aware training (QAT) and post-training quantization (PTQ) methods tailored for edge devices, analyzing their impact on model performance across medical imaging datasets. Experimental results demonstrate that quantized models achieve substantial reductions in model size and inference latency, enabling real-time processing on edge hardware while maintaining clinically acceptable diagnostic accuracy. This work provides a practical pathway for deploying AI-driven medical diagnostics in remote and resource-limited settings, enhancing the accessibility and scalability of healthcare technologies.

---

### Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection

Authors: Sairam VCR, Rishabh Lalla, Aveen Dayal, Tejal Kulkarni, Anuj Lalla, Vineeth N Balasubramanian, Muhammad Haris Khan
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17514v3

Current state-of-the-art approaches in Source-Free Object Detection (SFOD) typically rely on Mean-Teacher self-labeling. However, domain shift often reduces the detector's ability to maintain strong object-focused representations, causing high-confidence activations over background clutter. This weak object focus results in unreliable pseudo-labels from the detection head. While prior works mainly refine these pseudo-labels, they overlook the underlying need to strengthen the feature space itself. We propose FALCON-SFOD (Foundation-Aligned Learning with Clutter suppression and Noise robustness), a framework designed to enhance object-focused adaptation under domain shift. It consists of two complementary components. SPAR (Spatial Prior-Aware Regularization) leverages the generalization strength of vision foundation models to regularize the detector's feature space. Using class-agnostic binary masks derived from OV-SAM, SPAR promotes structured and foreground-focused activations by guiding the network toward object regions. IRPL (Imbalance-aware Noise Robust Pseudo-Labeling) complements SPAR by promoting balanced and noise-tolerant learning under severe foreground-background imbalance. Guided by a theoretical analysis that connects these designs to tighter localization and classification error bounds, FALCON-SFOD achieves competitive performance across SFOD benchmarks.

---

### Adaptive Covariance and Quaternion-Focused Hybrid Error-State EKF/UKF for Visual-Inertial Odometry

Authors: Ufuk Asil, Efendi Nasibov
Published: 2025-12-19
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2512.17505v1

This study presents an innovative hybrid Visual-Inertial Odometry (VIO) method for Unmanned Aerial Vehicles (UAVs) that is resilient to environmental challenges and capable of dynamically assessing sensor reliability. Built upon a loosely coupled sensor fusion architecture, the system utilizes a novel hybrid Quaternion-focused Error-State EKF/UKF (Qf-ES-EKF/UKF) architecture to process inertial measurement unit (IMU) data. This architecture first propagates the entire state using an Error-State Extended Kalman Filter (ESKF) and then applies a targeted Scaled Unscented Kalman Filter (SUKF) step to refine only the orientation. This sequential process blends the accuracy of SUKF in quaternion estimation with the overall computational efficiency of ESKF. The reliability of visual measurements is assessed via a dynamic sensor confidence score based on metrics, such as image entropy, intensity variation, motion blur, and inference quality, adapting the measurement noise covariance to ensure stable pose estimation even under challenging conditions. Comprehensive experimental analyses on the EuRoC MAV dataset demonstrate key advantages: an average improvement of 49% in position accuracy in challenging scenarios, an average of 57% in rotation accuracy over ESKF-based methods, and SUKF-comparable accuracy achieved with approximately 48% lower computational cost than a full SUKF implementation. These findings demonstrate that the presented approach strikes an effective balance between computational efficiency and estimation accuracy, and significantly enhances UAV pose estimation performance in complex environments with varying sensor reliability.

---

### InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion

Authors: Hoiyeong Jin, Hyojin Jang, Junha Hyung, Jeongho Kim, Kinam Kim, Dongjin Kim, Huijin Choi, Hyeonji Kim, Jaegul Choo
Published: 2025-12-19
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.17504v2

Recent advances in diffusion models have enabled impressive video editing capabilities, yet production-grade Video Object Insertion (VOI) remains challenging due to inadequate 4D scene understanding and a lack of proper optical interactions, such as shadows and reflections. To address these limitations, we present InsertAnywhere, a comprehensive VOI framework that achieves geometrically grounded object placement and optics-aware video synthesis. Our approach first leverages a 4D-aware mask generation module that allows users to anchor an object's 3D pose in a single frame. The framework automatically propagates this placement across the video, accurately handling local scene dynamics and occlusions. To synthesize realistic physical lighting interactions, we introduce Optics-Aware Representation Alignment, a novel strategy that utilizes an extended mask to guide feature extraction, enabling optical effects to seamlessly extend beyond the inserted object's boundary. Finally, to overcome the lack of training data for such phenomena, we construct and open-source ROSE++, a specialized quadruplet dataset tailored for the supervised learning of optical effects. Extensive experiments demonstrate that InsertAnywhere produces geometrically plausible and photometrically realistic insertions in complex real-world scenarios, significantly outperforming existing research and commercial generative tools.

---

### Validation of Diagnostic Artificial Intelligence Models for Prostate Pathology in a Middle Eastern Cohort

Authors: Peshawa J. Muhammad Ali, Navin Vincent, Saman S. Abdulla, Han N. Mohammed Fadhl, Anders Blilie, Kelvin Szolnoky, Julia Anna Mielcarz, Xiaoyi Ji, Nita Mulliqi, Abdulbasit K. Al-Talabani, Kimmo Kartasalo
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17499v1

Background: Artificial intelligence (AI) is improving the efficiency and accuracy of cancer diagnostics. The performance of pathology AI systems has been almost exclusively evaluated on European and US cohorts from large centers. For global AI adoption in pathology, validation studies on currently under-represented populations - where the potential gains from AI support may also be greatest - are needed. We present the first study with an external validation cohort from the Middle East, focusing on AI-based diagnosis and Gleason grading of prostate cancer. Methods: We collected and digitised 339 prostate biopsy specimens from the Kurdistan region, Iraq, representing a consecutive series of 185 patients spanning the period 2013-2024. We evaluated a task-specific end-to-end AI model and two foundation models in terms of their concordance with pathologists and consistency across samples digitised on three scanner models (Hamamatsu, Leica, and Grundium). Findings: Grading concordance between AI and pathologists was similar to pathologist-pathologist concordance with Cohen's quadratically weighted kappa 0.801 vs. 0.799 (p=0.9824). Cross-scanner concordance was high (quadratically weighted kappa > 0.90) for all AI models and scanner pairs, including low-cost compact scanner. Interpretation: AI models demonstrated pathologist-level performance in prostate histopathology assessment. Compact scanners can provide a route for validation studies in non-digitalised settings and enable cost-effective adoption of AI in laboratories with limited sample volumes. This first openly available digital pathology dataset from the Middle East supports further research into globally equitable AI pathology. Funding: SciLifeLab and Wallenberg Data Driven Life Science Program, Instrumentarium Science Foundation, Karolinska Institutet Research Foundation.

---

### GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation

Authors: Rang Li, Lei Li, Shuhuai Ren, Hao Tian, Shuhao Gu, Shicheng Li, Zihao Yue, Yudong Wang, Wenhan Ma, Zhe Yang, Jingyuan Ma, Zhifang Sui et al.
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17495v2

Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language models (MLLMs) achieve impressive scores on existing benchmarks, a fundamental question remains: can MLLMs truly visually ground with human-like sophistication, or are they merely pattern-matching on simplified datasets? Current benchmarks fail to capture real-world complexity where humans effortlessly navigate intricate references and recognize when grounding is impossible. To rigorously assess MLLMs' true capabilities, we introduce GroundingME, a benchmark that systematically challenges models across four critical dimensions: (1) Discriminative: distinguishing highly similar objects, (2) Spatial: understanding complex relational descriptions, (3) Limited: handling occlusions or tiny objects, and (4) Rejection: recognizing ungroundable queries. Through careful curation combining automated generation with human verification, we create 1,005 challenging examples mirroring real-world complexity. Evaluating 25 state-of-the-art MLLMs reveals a profound capability gap: the best model achieves only 45.1% accuracy, while most score 0% on rejection tasks. We explore two strategies for improvements: (1) test-time scaling selects optimal response by thinking trajectory to improve overall performance by up to 4.5%, and (2) data-mixture training boosts rejection accuracy from 0% to 27.9%. GroundingME thus serves as both a diagnostic tool revealing current limitations in MLLMs and a roadmap toward human-level visual grounding. Project page: https://groundingme.github.io

---

### MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding

Authors: Oskar Kristoffersen, Alba Reinders Sánchez, Morten Rieger Hannemose, Anders Bjorholm Dahl, Dim P. Papadopoulos
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17492v2

Geo-spatial analysis of our world benefits from a multimodal approach, as every single geographic location can be described in numerous ways (images from various viewpoints, textual descriptions, geographic coordinates, etc.). Current benchmarks have limited coverage across modalities, leading to specialized models that perform well in their respective domains, but do not fully take advantage of other geo-spatial modalities. We introduce the Multi-Modal Landmark dataset (MMLandmarks), a benchmark composed of four modalities: 197k high-resolution aerial images, 329k ground-view images, textual information, and geographic coordinates for 18.557 distinct landmarks in the United States. The MMLandmarks dataset has a one-to-one landmark level correspondence across every modality, which enables training and benchmarking models for various geo-spatial tasks, including cross-view Ground-to-Satellite retrieval, ground and satellite geolocalization, Text-to-Image, and Text-to-GPS retrieval. We show that current specialized and off-the-shelf foundation models cannot be trivially used to solve this variety of geo-spatial tasks, illustrating a gap where multimodal datasets lead to broader geo-spatial understanding. We employ a simple CLIP-inspired baseline that reflects versatility and broad generalization when trained with MMLandmarks.

---

### LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models

Authors: Muhammad Atif Butt, Kai Wang, Javier Vazquez-Corral, Joost Van De Weijer
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17489v2

Text-to-image (T2I) models have demonstrated remarkable progress in creative image generation, yet they still lack precise control over scene illuminants which is a crucial factor for content designers to manipulate visual aesthetics of generated images. In this paper, we present an illuminant personalization method named LumiCtrl that learns illuminant prompt given single image of the object. LumiCtrl consists of three components: given an image of the object, our method apply (a) physics-based illuminant augmentation along with Planckian locus to create fine-tuning variants under standard illuminants; (b) Edge-Guided Prompt Disentanglement using frozen ControlNet to ensure prompts focus on illumination, not the structure; and (c) a Masked Reconstruction Loss that focuses learning on foreground object while allowing background to adapt contextually which enables what we call Contextual Light Adaptation. We qualitatively and quantitatively compare LumiCtrl against other T2I customization methods. The results show that LumiCtrl achieves significantly better illuminant fidelity, aesthetic quality, and scene coherence compared to existing baselines. A human preference study further confirms the strong user preference for LumiCtrl generations.

---

### TwinSegNet: A Digital Twin-Enabled Federated Learning Framework for Brain Tumor Analysis

Authors: Almustapha A. Wakili, Adamu Hussaini, Abubakar A. Musa, Woosub Jung, Wei Yu
Published: 2025-12-19
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.17488v1

Brain tumor segmentation is critical in diagnosis and treatment planning for the disease. Yet, current deep learning methods rely on centralized data collection, which raises privacy concerns and limits generalization across diverse institutions. In this paper, we propose TwinSegNet, which is a privacy-preserving federated learning framework that integrates a hybrid ViT-UNet model with personalized digital twins for accurate and real-time brain tumor segmentation. Our architecture combines convolutional encoders with Vision Transformer bottlenecks to capture local and global context. Each institution fine-tunes the global model of private data to form its digital twin. Evaluated on nine heterogeneous MRI datasets, including BraTS 2019-2021 and custom tumor collections, TwinSegNet achieves high Dice scores (up to 0.90%) and sensitivity/specificity exceeding 90%, demonstrating robustness across non-independent and identically distributed (IID) client distributions. Comparative results against centralized models such as TumorVisNet highlight TwinSegNet's effectiveness in preserving privacy without sacrificing performance. Our approach enables scalable, personalized segmentation for multi-institutional clinical settings while adhering to strict data confidentiality requirements.

---

### Deep Learning-Based Surrogate Creep Modelling in Inconel 625: A High-Temperature Alloy Study

Authors: Shubham Das, Kaushal Singhania, Amit Sadhu, Suprabhat Das, Arghya Nandi
Published: 2025-12-19
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2512.17477v1

Time-dependent deformation, particularly creep, in high-temperature alloys such as Inconel 625 is a key factor in the long-term reliability of components used in aerospace and energy systems. Although Inconel 625 shows excellent creep resistance, finite-element creep simulations in tools such as ANSYS remain computationally expensive, often requiring tens of minutes for a single 10,000-hour run. This work proposes deep learning based surrogate models to provide fast and accurate replacements for such simulations. Creep strain data was generated in ANSYS using the Norton law under uniaxial stresses of 50 to 150 MPa and temperatures of 700 to 1000 $^\circ$C, and this temporal dataset was used to train two architectures: a BiLSTM Variational Autoencoder for uncertainty-aware and generative predictions, and a BiLSTM Transformer hybrid that employs self-attention to capture long-range temporal behavior. Both models act as surrogate predictors, with the BiLSTM-VAE offering probabilistic output and the BiLSTM-Transformer delivering high deterministic accuracy. Performance is evaluated using RMSE, MAE, and $R^2$. Results show that the BiLSTM-VAE provides stable and reliable creep strain forecasts, while the BiLSTM-Transformer achieves strong accuracy across the full time range. Latency tests indicate substantial speedup: while each ANSYS simulation requires 30 to 40 minutes for a given stress-temperature condition, the surrogate models produce predictions within seconds. The proposed framework enables rapid creep assessment for design optimization and structural health monitoring, and provides a scalable solution for high-temperature alloy applications.

---

### Alternating Direction Method of Multipliers for Nonlinear Matrix Decompositions

Authors: Atharva Awari, Nicolas Gillis, Arnaud Vandaele
Published: 2025-12-19
Categories: eess.SP, cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2512.17473v3

We present an algorithm based on the alternating direction method of multipliers (ADMM) for solving nonlinear matrix decompositions (NMD). Given an input matrix $X \in \mathbb{R}^{m \times n}$ and a factorization rank $r \ll \min(m, n)$, NMD seeks matrices $W \in \mathbb{R}^{m \times r}$ and $H \in \mathbb{R}^{r \times n}$ such that $X \approx f(WH)$, where $f$ is an element-wise nonlinear function. We evaluate our method on several representative nonlinear models: the rectified linear unit activation $f(x) = \max(0, x)$, suitable for nonnegative sparse data approximation, the component-wise square $f(x) = x^2$, applicable to probabilistic circuit representation, and the MinMax transform $f(x) = \min(b, \max(a, x))$, relevant for recommender systems. The proposed framework flexibly supports diverse loss functions, including least squares, $\ell_1$ norm, and the Kullback-Leibler divergence, and can be readily extended to other nonlinearities and metrics. We illustrate the applicability, efficiency, and adaptability of the approach on real-world datasets, highlighting its potential for a broad range of applications.

---

### Translating the Rashomon Effect to Sequential Decision-Making Tasks

Authors: Dennis Gross, Jørn Eirik Betten, Helge Spieker
Published: 2025-12-19
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.17470v1

The Rashomon effect describes the phenomenon where multiple models trained on the same data produce identical predictions while differing in which features they rely on internally. This effect has been studied extensively in classification tasks, but not in sequential decision-making, where an agent learns a policy to achieve an objective by taking actions in an environment. In this paper, we translate the Rashomon effect to sequential decision-making. We define it as multiple policies that exhibit identical behavior, visiting the same states and selecting the same actions, while differing in their internal structure, such as feature attributions. Verifying identical behavior in sequential decision-making differs from classification. In classification, predictions can be directly compared to ground-truth labels. In sequential decision-making with stochastic transitions, the same policy may succeed or fail on any single trajectory due to randomness. We address this using formal verification methods that construct and compare the complete probabilistic behavior of each policy in the environment. Our experiments demonstrate that the Rashomon effect exists in sequential decision-making. We further show that ensembles constructed from the Rashomon set exhibit greater robustness to distribution shifts than individual policies. Additionally, permissive policies derived from the Rashomon set reduce computational requirements for verification while maintaining optimal performance.

---

### Linear Attention for Joint Power Optimization and User-Centric Clustering in Cell-Free Networks

Authors: Irched Chafaa, Giacomo Bacci, Luca Sanguinetti
Published: 2025-12-19
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2512.17466v3

Optimal AP clustering and power allocation are critical in user-centric cell-free massive MIMO systems. Existing deep learning models lack flexibility to handle dynamic network configurations. Furthermore, many approaches overlook pilot contamination and suffer from high computational complexity. In this paper, we propose a lightweight transformer model that overcomes these limitations by jointly predicting AP clusters and powers solely from spatial coordinates of user devices and AP. Our model is architecture-agnostic to users load, handles both clustering and power allocation without channel estimation overhead, and eliminates pilot contamination by assigning users to AP within a pilot reuse constraint. We also incorporate a customized linear attention mechanism to capture user-AP interactions efficiently and enable linear scalability with respect to the number of users. Numerical results confirm the model's effectiveness in maximizing the minimum spectral efficiency and providing near-optimal performance while ensuring adaptability and scalability in dynamic scenarios.

---

### Behavioural Effects of Agentic Messaging: A Case Study on a Financial Service Application

Authors: Olivier Jeunen, Schaun Wheeler
Published: 2025-12-19
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.17462v1

Marketing and product personalisation provide a prominent and visible use-case for the application of Information Retrieval methods across several business domains. Recently, agentic approaches to these problems have been gaining traction. This work evaluates the behavioural and retention effects of agentic personalisation on a financial service application's customer communication system during a 2025 national tax filing period. Through a two month-long randomised controlled trial, we compare an agentic messaging approach against a business-as-usual (BAU) rule-based campaign system, focusing on two primary outcomes: unsubscribe behaviour and conversion timing. Empirical results show that agent-led messaging reduced unsubscribe events by 21\% ($\pm 0.01$) relative to BAU and increased early filing behaviour in the weeks preceding the national deadline. These findings demonstrate how adaptive, user-level decision-making systems can modulate engagement intensity whilst improving long-term retention indicators.

---

### Fair Voting Methods as a Catalyst for Democratic Resilience: A Trilogy on Legitimacy, Impact and AI Safeguarding

Authors: Evangelos Pournaras
Published: 2025-12-19
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2512.17461v1

This article shows how fair voting methods can be a catalyst for change in the way we make collective decisions, and how such change can promote long-awaited upgrades of democracy. Based on real-world evidence from democratic innovations in participatory budgeting, in Switzerland and beyond, I highlight a trilogy of key research results: Fair voting methods achieve to be (i) legitimacy incubator, (ii) novel impact accelerator and (iii) safeguard for risks of artificial intelligence (AI). Compared to majoritarian voting methods, combining expressive ballot formats (e.g. cumulative voting) with ballot aggregation methods that promote proportional representation (e.g. equal shares) results in more winners and higher (geographical) representation of citizens. Such fair voting methods are preferred and found fairer even by voters who do not win, while promoting stronger democratic values for citizens such as altruism and compromise. They also result in new resourceful ideas to put for voting, which are cost-effective and win, especially in areas of welfare, education and culture. Strikingly, fair voting methods are also more resilient to biases and inconsistencies of generative AI in emerging scenarios of AI voting assistance or AI representation of voters who would be likely to abstain. I also review the relevance of such upgrades for democracies in crisis, such as the one of Greece featured in the recent study of `Unmute Democracy'. Greek democracy can build stronger resilience via higher representation of citizens in democratic processes as well as democratic innovations in participation. Fair voting methods can be a catalyst for both endeavors.

---

### When Data Quality Issues Collide: A Large-Scale Empirical Study of Co-Occurring Data Quality Issues in Software Defect Prediction

Authors: Emmanuel Charleson Dapaah, Jens Grabowski
Published: 2025-12-19
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2512.17460v1

Software Defect Prediction (SDP) models are central to proactive software quality assurance, yet their effectiveness is often constrained by the quality of available datasets. Prior research has typically examined single issues such as class imbalance or feature irrelevance in isolation, overlooking that real-world data problems frequently co-occur and interact. This study presents, to our knowledge, the first large-scale empirical analysis in SDP that simultaneously examines five co-occurring data quality issues (class imbalance, class overlap, irrelevant features, attribute noise, and outliers) across 374 datasets and five classifiers. We employ Explainable Boosting Machines together with stratified interaction analysis to quantify both direct and conditional effects under default hyperparameter settings, reflecting practical baseline usage. Our results show that co-occurrence is nearly universal: even the least frequent issue (attribute noise) appears alongside others in more than 93% of datasets. Irrelevant features and imbalance are nearly ubiquitous, while class overlap is the most consistently harmful issue. We identify stable tipping points around 0.20 for class overlap, 0.65-0.70 for imbalance, and 0.94 for irrelevance, beyond which most models begin to degrade. We also uncover counterintuitive patterns, such as outliers improving performance when irrelevant features are low, underscoring the importance of context-aware evaluation. Finally, we expose a performance-robustness trade-off: no single learner dominates under all conditions. By jointly analyzing prevalence, co-occurrence, thresholds, and conditional effects, our study directly addresses a persistent gap in SDP research. Hence, moving beyond isolated analyses to provide a holistic, data-aware understanding of how quality issues shape model performance in real-world settings.

---

### 3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework

Authors: Tobias Sautter, Jan-Niklas Dihlmann, Hendrik P. A. Lensch
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17459v1

Recent advances in 3D scene generation produce visually appealing output, but current representations hinder artists' workflows that require modifiable 3D textured mesh scenes for visual effects and game development. Despite significant advances, current textured mesh scene reconstruction methods are far from artist ready, suffering from incorrect object decomposition, inaccurate spatial relationships, and missing backgrounds. We present 3D-RE-GEN, a compositional framework that reconstructs a single image into textured 3D objects and a background. We show that combining state of the art models from specific domains achieves state of the art scene reconstruction performance, addressing artists' requirements. Our reconstruction pipeline integrates models for asset detection, reconstruction, and placement, pushing certain models beyond their originally intended domains. Obtaining occluded objects is treated as an image editing task with generative models to infer and reconstruct with scene level reasoning under consistent lighting and geometry. Unlike current methods, 3D-RE-GEN generates a comprehensive background that spatially constrains objects during optimization and provides a foundation for realistic lighting and simulation tasks in visual effects and games. To obtain physically realistic layouts, we employ a novel 4-DoF differentiable optimization that aligns reconstructed objects with the estimated ground plane. 3D-RE-GEN~achieves state of the art performance in single image 3D scene reconstruction, producing coherent, modifiable scenes through compositional generation guided by precise camera recovery and spatial optimization.

---

### A lightweight Spatial-Temporal Graph Neural Network for Long-term Time Series Forecasting

Authors: Henok Tenaw Moges, Deshendran Moodley
Published: 2025-12-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.17453v1

We propose Lite-STGNN, a lightweight spatial-temporal graph neural network for long-term multivariate forecasting that integrates decomposition-based temporal modeling with learnable sparse graph structure. The temporal module applies trend-seasonal decomposition, while the spatial module performs message passing with low-rank Top-$K$ adjacency learning and conservative horizon-wise gating, enabling spatial corrections that enhance a strong linear baseline. Lite-STGNN achieves state-of-the-art accuracy on four benchmark datasets for horizons up to 720 steps, while being parameter-efficient and substantially faster to train than transformer-based methods. Ablation studies show that the spatial module yields 4.6% improvement over the temporal baseline, Top-$K$ enhances locality by 3.3%, and learned adjacency matrices reveal domain-specific interaction dynamics. Lite-STGNN thus offers a compact, interpretable, and efficient framework for long-term multivariate time series forecasting.

---

### KV Admission: Learning What to Write for Efficient Long-Context LLM Inference

Authors: Yen-Chieh Huang, Pi-Cheng Hsiu, Rui Fang, Ming-Syan Chen
Published: 2025-12-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.17452v4

Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear Key-Value (KV) cache growth. Prior approaches mitigate this via post-hoc selection or eviction but overlook the root inefficiency: indiscriminate token admission. In this paper, we formalize KV management as a causal system of three primitives: KV Admission, Selection, and Eviction. We instantiate KV Admission via Write-Gated KV (WG-KV), a lightweight mechanism that learns to predict token utility before cache entry. By filtering out redundant states early to maintain a compact global cache alongside a sliding local cache, WG-KV significantly reduces memory usage and accelerates both prefill and decode phases. Our results demonstrate that learning what to write is a principled and practical recipe for efficient long-context inference. Code is available at https://github.com/EMCLab-Sinica/WG-KV.

---

### MULTIAQUA: A multimodal maritime dataset and robust training strategies for multimodal semantic segmentation

Authors: Jon Muhovič, Janez Perš
Published: 2025-12-19
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.17450v1

Unmanned surface vehicles can encounter a number of varied visual circumstances during operation, some of which can be very difficult to interpret. While most cases can be solved only using color camera images, some weather and lighting conditions require additional information. To expand the available maritime data, we present a novel multimodal maritime dataset MULTIAQUA (Multimodal Aquatic Dataset). Our dataset contains synchronized, calibrated and annotated data captured by sensors of different modalities, such as RGB, thermal, IR, LIDAR, etc. The dataset is aimed at developing supervised methods that can extract useful information from these modalities in order to provide a high quality of scene interpretation regardless of potentially poor visibility conditions. To illustrate the benefits of the proposed dataset, we evaluate several multimodal methods on our difficult nighttime test set. We present training approaches that enable multimodal methods to be trained in a more robust way, thus enabling them to retain reliable performance even in near-complete darkness. Our approach allows for training a robust deep neural network only using daytime images, thus significantly simplifying data acquisition, annotation, and the training process.

---

### LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents

Authors: Yun He, Francesco Pittaluga, Ziyu Jiang, Matthias Zwicker, Manmohan Chandraker, Zaid Tasneem
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17445v3

LangDriveCTRL is a natural-language-controllable framework for editing real-world driving videos to synthesize diverse traffic scenarios. It represents each video as an explicit 3D scene graph, decomposing the scene into a static background and dynamic object nodes. To enable fine-grained editing and realism, it introduces a feedback-driven agentic pipeline. An Orchestrator converts user instructions into executable graphs that coordinate specialized multi-modal agents and tools. An Object Grounding Agent aligns free-form text with target object nodes in the scene graph; a Behavior Editing Agent generates multi-object trajectories from language instructions; and a Behavior Reviewer Agent iteratively reviews and refines the generated trajectories. The edited scene graph is rendered and harmonized using a video diffusion tool, and then further refined by a Video Reviewer Agent to ensure photorealism and appearance alignment. LangDriveCTRL supports both object node editing (removal, insertion, and replacement) and multi-object behavior editing from natural-language instructions. Quantitatively, it achieves nearly $2\times$ higher instruction alignment than the previous SoTA, with superior photorealism, structural preservation, and traffic realism. Project page is available at: https://yunhe24.github.io/langdrivectrl/.

---

### Assessing Long-Term Electricity Market Design for Ambitious Decarbonization Targets using Multi-Agent Reinforcement Learning

Authors: Javier Gonzalez-Ruiz, Carlos Rodriguez-Pardo, Iacopo Savelli, Alice Di Bella, Massimo Tavoni
Published: 2025-12-19
Categories: cs.LG, cs.AI, cs.NE, econ.GN
arXiv: https://arxiv.org/abs/2512.17444v1

Electricity systems are key to transforming today's society into a carbon-free economy. Long-term electricity market mechanisms, including auctions, support schemes, and other policy instruments, are critical in shaping the electricity generation mix. In light of the need for more advanced tools to support policymakers and other stakeholders in designing, testing, and evaluating long-term markets, this work presents a multi-agent reinforcement learning model capable of capturing the key features of decarbonizing energy systems. Profit-maximizing generation companies make investment decisions in the wholesale electricity market, responding to system needs, competitive dynamics, and policy signals. The model employs independent proximal policy optimization, which was selected for suitability to the decentralized and competitive environment. Nevertheless, given the inherent challenges of independent learning in multi-agent settings, an extensive hyperparameter search ensures that decentralized training yields market outcomes consistent with competitive behavior. The model is applied to a stylized version of the Italian electricity system and tested under varying levels of competition, market designs, and policy scenarios. Results highlight the critical role of market design for decarbonizing the electricity sector and avoiding price volatility. The proposed framework allows assessing long-term electricity markets in which multiple policy and market mechanisms interact simultaneously, with market participants responding and adapting to decarbonization pathways.

---

### A Systematic Reproducibility Study of BSARec for Sequential Recommendation

Authors: Jan Hutter, Hua Chang Bakker, Stan Fris, Madelon Bernardy, Yuanna Liu
Published: 2025-12-19
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2512.17442v1

In sequential recommendation (SR), the self-attention mechanism of Transformer-based models acts as a low-pass filter, limiting their ability to capture high-frequency signals that reflect short-term user interests. To overcome this, BSARec augments the Transformer encoder with a frequency layer that rescales high-frequency components using the Fourier transform. However, the overall effectiveness of BSARec and the roles of its individual components have yet to be systematically validated. We reproduce BSARec and show that it outperforms other SR methods on some datasets. To empirically assess whether BSARec improves performance on high-frequency signals, we propose a metric to quantify user history frequency and evaluate SR methods across different user groups. We compare digital signal processing (DSP) techniques and find that the discrete wavelet transform (DWT) offer only slight improvements over Fourier transforms, and DSP methods provide no clear advantage over simple residual connections. Finally, we explore padding strategies and find that non-constant padding significantly improves recommendation performance, whereas constant padding hinders the frequency rescaler's ability to capture high-frequency signals.

---

### Xiaomi MiMo-VL-Miloco Technical Report

Authors: Jiaze Li, Jingyang Chen, Yuxun Qu, Shijie Xu, Zhenru Lin, Junyou Zhu, Boshen Xu, Wenhui Tan, Pei Fu, Jianzhong Ju, Zhenbo Luo, Jian Luan
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17436v2

We open-source MiMo-VL-Miloco-7B and its quantized variant MiMo-VL-Miloco-7B-GGUF, a pair of home-centric vision-language models that achieve strong performance on both home-scenario understanding and general multimodal reasoning. Built on the MiMo-VL-7B backbone, MiMo-VL-Miloco-7B is specialized for smart-home environments, attaining leading F1 scores on gesture recognition and common home-scenario understanding, while also delivering consistent gains across video benchmarks such as Video-MME, Video-MMMU, and Charades-STA, as well as language understanding benchmarks including MMMU-Pro and MMLU-Pro. In our experiments, MiMo-VL-Miloco-7B outperforms strong closed-source and open-source baselines on home-scenario understanding and several multimodal reasoning benchmarks. To balance specialization and generality, we design a two-stage training pipeline that combines supervised fine-tuning with reinforcement learning based on Group Relative Policy Optimization, leveraging efficient multi-domain data. We further incorporate chain-of-thought supervision and token-budget-aware reasoning, enabling the model to learn knowledge in a data-efficient manner while also performing reasoning efficiently. Our analysis shows that targeted home-scenario training not only enhances activity and gesture understanding, but also improves text-only reasoning with only modest trade-offs on document-centric tasks. Model checkpoints, quantized GGUF weights, and our home-scenario evaluation toolkit are publicly available at https://github.com/XiaoMi/xiaomi-mimo-vl-miloco to support research and deployment in real-world smart-home applications.

---

### AIFloodSense: A Global Aerial Imagery Dataset for Semantic Segmentation and Understanding of Flooded Environments

Authors: Georgios Simantiris, Konstantinos Bacharidis, Apostolos Papanikolaou, Petros Giannakakis, Costas Panagiotakis
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17432v1

Accurate flood detection from visual data is a critical step toward improving disaster response and risk assessment, yet datasets for flood segmentation remain scarce due to the challenges of collecting and annotating large-scale imagery. Existing resources are often limited in geographic scope and annotation detail, hindering the development of robust, generalized computer vision methods. To bridge this gap, we introduce AIFloodSense, a comprehensive, publicly available aerial imagery dataset comprising 470 high-resolution images from 230 distinct flood events across 64 countries and six continents. Unlike prior benchmarks, AIFloodSense ensures global diversity and temporal relevance (2022-2024), supporting three complementary tasks: (i) Image Classification with novel sub-tasks for environment type, camera angle, and continent recognition; (ii) Semantic Segmentation providing precise pixel-level masks for flood, sky, and buildings; and (iii) Visual Question Answering (VQA) to enable natural language reasoning for disaster assessment. We establish baseline benchmarks for all tasks using state-of-the-art architectures, demonstrating the dataset's complexity and its value in advancing domain-generalized AI tools for climate resilience.

---

### Perfect reconstruction of sparse signals using nonconvexity control and one-step RSB message passing

Authors: Xiaosi Gu, Ayaka Sakata, Tomoyuki Obuchi
Published: 2025-12-19
Categories: stat.ML, cond-mat.dis-nn, cs.LG
arXiv: https://arxiv.org/abs/2512.17426v2

We consider sparse signal reconstruction via minimization of the smoothly clipped absolute deviation (SCAD) penalty, and develop one-step replica-symmetry-breaking (1RSB) extensions of approximate message passing (AMP), termed 1RSB-AMP. Starting from the 1RSB formulation of belief propagation, we derive explicit update rules of 1RSB-AMP together with the corresponding state evolution (1RSB-SE) equations. A detailed comparison shows that 1RSB-AMP and 1RSB-SE agree remarkably well at the macroscopic level, even in parameter regions where replica-symmetric (RS) AMP, termed RS-AMP, diverges and where the 1RSB description itself is not expected to be thermodynamically exact. Fixed-point analysis of 1RSB-SE reveals a phase diagram consisting of success, failure, and diverging phases, as in the RS case. However, the diverging-region boundary now depends on the Parisi parameter due to the 1RSB ansatz, and we propose a new criterion---minimizing the size of the diverging region---rather than the conventional zero-complexity condition, to determine its value. Combining this criterion with the nonconvexity-control (NCC) protocol proposed in a previous RS study improves the algorithmic limit of perfect reconstruction compared with RS-AMP. Numerical solutions of 1RSB-SE and experiments with 1RSB-AMP confirm that this improved limit is achieved in practice, though the gain is modest and remains slightly inferior to the Bayes-optimal threshold. We also report the behavior of thermodynamic quantities---overlaps, free entropy, complexity, and the non-self-averaging susceptibility---that characterize the 1RSB phase in this problem.

---

### SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories

Authors: Lilin Wang, Lucas Ramalho, Alan Celestino, Phuc Anthony Pham, Yu Liu, Umang Kumar Sinha, Andres Portillo, Onassis Osunwa, Gabriel Maduekwe
Published: 2025-12-19
Categories: cs.SE, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.17419v1

Benchmarks like SWE-bench have standardized the evaluation of Large Language Models (LLMs) on repository-level software engineering tasks. However, these efforts remain limited by manual curation, static datasets, and a focus on Python-based bug fixes. We introduce SWE-Bench++, an automated framework that generates repository-level coding tasks from open-source GitHub projects. Unlike synthetic approaches, our pipeline harvests live pull requests to cover both bug fixes and feature requests across 11 languages. SWE-Bench++ turns GitHub pull requests (PRs) into reproducible, execution-based tasks via four stages: programmatic sourcing, environment synthesis, test oracle extraction, and quality assurance. A final hint-guided trajectory synthesis step converts instances that strong models fail on into training trajectories. Our initial benchmark consists of 11,133 instances from 3,971 repositories across 11 languages. On a subset of 1,782 instances of this benchmark, today's strongest models perform as follows: claude-sonnet-4.5 achieves 36.20% pass@10, gpt-5-2025-08-07 34.57%, gemini/gemini-2.5-pro 24.92%, and gpt-4o 16.89%. We further demonstrate the utility of our dataset by showing that fine-tuning on SWE-Bench++ instances yields measurable improvements on the SWE-bench Multilingual benchmark. SWE-Bench++ provides a scalable, multilingual benchmark for evaluating and improving repository-level code generation.

---

### Beyond Occlusion: In Search for Near Real-Time Explainability of CNN-Based Prostate Cancer Classification

Authors: Martin Krebs, Jan Obdržálek, Vít Musil, Tomáš Brázdil
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17416v1

Deep neural networks are starting to show their worth in critical applications such as assisted cancer diagnosis. However, for their outputs to get accepted in practice, the results they provide should be explainable in a way easily understood by pathologists. A well-known and widely used explanation technique is occlusion, which, however, can take a long time to compute, thus slowing the development and interaction with pathologists. In this work, we set out to find a faster replacement for occlusion in a successful system for detecting prostate cancer. Since there is no established framework for comparing the performance of various explanation methods, we first identified suitable comparison criteria and selected corresponding metrics. Based on the results, we were able to choose a different explanation method, which cut the previously required explanation time at least by a factor of 10, without any negative impact on the quality of outputs. This speedup enables rapid iteration in model development and debugging and brings us closer to adopting AI-assisted prostate cancer detection in clinical settings. We propose that our approach to finding the replacement for occlusion can be used to evaluate candidate methods in other related applications.

---

### Optimisation of Aircraft Maintenance Schedules

Authors: Neil Urquhart, Amir Rahimi, Efstathios-Al. Tingas
Published: 2025-12-19
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2512.17412v1

We present an aircraft maintenance scheduling problem, which requires suitably qualified staff to be assigned to maintenance tasks on each aircraft. The tasks on each aircraft must be completed within a given turn around window so that the aircraft may resume revenue earning service. This paper presents an initial study based on the application of an Evolutionary Algorithm to the problem. Evolutionary Algorithms evolve a solution to a problem by evaluating many possible solutions, focusing the search on those solutions that are of a higher quality, as defined by a fitness function. In this paper, we benchmark the algorithm on 60 generated problem instances to demonstrate the underlying representation and associated genetic operators.

---

### Detection and Analysis of Sensitive and Illegal Content on the Ethereum Blockchain Using Machine Learning Techniques

Authors: Xingyu Feng
Published: 2025-12-19
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.17411v1

Blockchain technology, lauded for its transparent and immutable nature, introduces a novel trust model. However, its decentralized structure raises concerns about potential inclusion of malicious or illegal content. This study focuses on Ethereum, presenting a data identification and restoration algorithm. Successfully recovering 175 common files, 296 images, and 91,206 texts, we employed the FastText algorithm for sentiment analysis, achieving a 0.9 accuracy after parameter tuning. Classification revealed 70,189 neutral, 5,208 positive, and 15,810 negative texts, aiding in identifying sensitive or illicit information. Leveraging the NSFWJS library, we detected seven indecent images with 100% accuracy. Our findings expose the coexistence of benign and harmful content on the Ethereum blockchain, including personal data, explicit images, divisive language, and racial discrimination. Notably, sensitive information targeted Chinese government officials. Proposing preventative measures, our study offers valuable insights for public comprehension of blockchain technology and regulatory agency guidance. The algorithms employed present innovative solutions to address blockchain data privacy and security concerns.

---

### meval: A Statistical Toolbox for Fine-Grained Model Performance Analysis

Authors: Dishantkumar Sutariya, Eike Petersen
Published: 2025-12-19
Categories: cs.LG, stat.AP, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2512.17409v1

Analyzing machine learning model performance stratified by patient and recording properties is becoming the accepted norm and often yields crucial insights about important model failure modes. Performing such analyses in a statistically rigorous manner is non-trivial, however. Appropriate performance metrics must be selected that allow for valid comparisons between groups of different sample sizes and base rates; metric uncertainty must be determined and multiple comparisons be corrected for, in order to assess whether any observed differences may be purely due to chance; and in the case of intersectional analyses, mechanisms must be implemented to find the most `interesting' subgroups within combinatorially many subgroup combinations. We here present a statistical toolbox that addresses these challenges and enables practitioners to easily yet rigorously assess their models for potential subgroup performance disparities. While broadly applicable, the toolbox is specifically designed for medical imaging applications. The analyses provided by the toolbox are illustrated in two case studies, one in skin lesion malignancy classification on the ISIC2020 dataset and one in chest X-ray-based disease classification on the MIMIC-CXR dataset.

---

### DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inference

Authors: Yonathan Bornfeld, Shai Avidan
Published: 2025-12-19
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2512.17398v1

Private Inference (PI) uses cryptographic primitives to perform privacy preserving machine learning. In this setting, the owner of the network runs inference on the data of the client without learning anything about the data and without revealing any information about the model. It has been observed that a major computational bottleneck of PI is the calculation of the gate (i.e., ReLU), so a considerable amount of effort have been devoted to reducing the number of ReLUs in a given network. We focus on the DReLU, which is the non-linear step function of the ReLU and show that one DReLU can serve many ReLU operations. We suggest a new activation module where the DReLU operation is only performed on a subset of the channels (Prototype channels), while the rest of the channels (replicate channels) replicates the DReLU of each of their neurons from the corresponding neurons in one of the prototype channels. We then extend this idea to work across different layers. We show that this formulation can drastically reduce the number of DReLU operations in resnet type network. Furthermore, our theoretical analysis shows that this new formulation can solve an extended version of the XOR problem, using just one non-linearity and two neurons, something that traditional formulations and some PI specific methods cannot achieve. We achieve new SOTA results on several classification setups, and achieve SOTA results on image segmentation.

---

### RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answering

Authors: Léo Butsanets, Charles Corbière, Julien Khlaut, Pierre Manceron, Corentin Dancette
Published: 2025-12-19
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.17396v2

In this work, we introduce RadImageNet-VQA, a large-scale dataset designed to advance radiologic visual question answering (VQA) on CT and MRI exams. Existing medical VQA datasets are limited in scale, dominated by X-ray imaging or biomedical illustrations, and often prone to text-based shortcuts. RadImageNet-VQA is built from expert-curated annotations and provides 750K images paired with 7.5M question-answer samples. It covers three key tasks - abnormality detection, anatomy recognition, and pathology identification - spanning eight anatomical regions and 97 pathology categories, and supports open-ended, closed-ended, and multiple-choice questions. Extensive experiments show that state-of-the-art vision-language models still struggle with fine-grained pathology identification, particularly in open-ended settings and even after fine-tuning. Text-only analysis further reveals that model performance collapses to near-random without image inputs, confirming that RadImageNet-VQA is free from linguistic shortcuts. The full dataset and benchmark are publicly available at https://huggingface.co/datasets/raidium/RadImageNet-VQA.

---

### Are Vision Language Models Cross-Cultural Theory of Mind Reasoners?

Authors: Zabir Al Nazi, GM Shahariar, Md. Abrar Hossain, Wei Peng
Published: 2025-12-19
Categories: cs.CL, cs.CV, cs.CY
arXiv: https://arxiv.org/abs/2512.17394v2

Theory of Mind (ToM) - the ability to attribute beliefs and intents to others - is fundamental for social intelligence, yet Vision-Language Model (VLM) evaluations remain largely Western-centric. In this work, we introduce CulturalToM-VQA, a benchmark of 5,095 visually situated ToM probes across diverse cultural contexts, rituals, and social norms. Constructed through a frontier proprietary MLLM, human-verified pipeline, the dataset spans a taxonomy of six ToM tasks and four complexity levels. We benchmark 10 VLMs (2023-2025) and observe a significant performance leap: while earlier models struggle, frontier models achieve high accuracy (>93%). However, significant limitations persist: models struggle with false belief reasoning (19-83% accuracy) and show high regional variance (20-30% gaps). Crucially, we find that SOTA models exhibit social desirability bias - systematically favoring semantically positive answer choices over negative ones. Ablation experiments reveal that some frontier models rely heavily on parametric social priors, frequently defaulting to safety-aligned predictions. Furthermore, while Chain-of-Thought prompting aids older models, it yields minimal gains for newer ones. Overall, our work provides a testbed for cross-cultural social reasoning, underscoring that despite architectural gains, achieving robust, visually grounded understanding remains an open challenge.

---

### CIFE: Code Instruction-Following Evaluation

Authors: Sravani Gunnu, Shanmukha Guttula, Hima Patel
Published: 2025-12-19
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2512.17387v1

Large Language Models (LLMs) are increasingly applied to real-world code generation, where functional correctness alone is insufficient for reliable deployment, developers also expect adherence to explicit requirements for robustness, formatting, and security. Existing benchmarks primarily assess correctness through test-case execution, offering limited insight into how reliably models follow such constraints. We introduce a benchmark of 1,000 Python tasks, each paired with an average of 7 developer-specified constraints spanning 13 categories. Constraints are curated through a four-stage human-LLM pipeline to ensure they are atomic, relevant, and objective. We evaluate 14 open- and closed-source models using complementary adherence metrics and propose the C2A Score, a composite measure that jointly captures correctness and constraint compliance. Results reveal a substantial gap between partial and strict satisfaction, while strong models achieve over 90% partial adherence, strict adherence remains between 39-66%. These findings highlight that trustworthy code generation requires not only correctness but also consistent adherence to developer intent.

---

### UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models

Authors: Jiajun Wu, Jian Yang, Wei Zhang, Lin Jing, Yuqing Ma, Ensheng Shi, Yuchi Ma, Zhoujun Li, Xianglong Liu
Published: 2025-12-19
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.17385v1

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, their effectiveness heavily relies on supervised training with extensive labeled (e.g., question-answering pairs) or unlabeled datasets (e.g., code snippets), which are often expensive and difficult to obtain at scale. To address this limitation, this paper introduces a method IPC, an unsupervised framework that leverages Internal Probing of LLMs for Code generation without any external corpus, even unlabeled code snippets. We introduce the problem space probing, test understanding probing, solution space probing, and knowledge consolidation and reinforcement to probe the internal knowledge and confidence patterns existing in LLMs. Further, IPC identifies reliable code candidates through self-consistency mechanisms and representation-based quality estimation to train UCoder (coder with unsupervised learning). We validate the proposed approach across multiple code benchmarks, demonstrating that unsupervised methods can achieve competitive performance compared to supervised approaches while significantly reducing the dependency on labeled data and computational resources. Analytic experiments reveal that internal model states contain rich signals about code quality and correctness, and that properly harnessing these signals enables effective unsupervised learning for code generation tasks, opening new directions for training code LLMs in resource-constrained scenarios.

---

### Timely Information Updating for Mobile Devices Without and With ML Advice

Authors: Yu-Pin Hsu, Yi-Hsuan Tseng
Published: 2025-12-19
Categories: cs.NI, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2512.17381v2

This paper investigates an information update system in which a mobile device monitors a physical process and sends status updates to an access point (AP). A fundamental trade-off arises between the timeliness of the information maintained at the AP and the update cost incurred at the device. To address this trade-off, we propose an online algorithm that determines when to transmit updates using only available observations. The proposed algorithm asymptotically achieves the optimal competitive ratio against an adversary that can simultaneously manipulate multiple sources of uncertainty, including the operation duration, information staleness, update cost, and update opportunities. Furthermore, by incorporating machine learning (ML) advice of unknown reliability into the design, we develop an ML-augmented algorithm that asymptotically attains the optimal consistency-robustness trade-off, even when the adversary can additionally corrupt the ML advice. The optimal competitive ratio scales linearly with the range of update costs, but is unaffected by other sources of uncertainty. Moreover, an optimal competitive online algorithm exhibits a threshold-like response to the ML advice: it either fully trusts or completely ignores the ML advice, as partially trusting the advice cannot improve the consistency without severely degrading the robustness. Extensive simulations in stochastic settings further validate the theoretical findings in the adversarial environment.

---

### Towards Deeper Emotional Reflection: Crafting Affective Image Filters with Generative Priors

Authors: Peixuan Zhang, Shuchen Weng, Jiajun Tang, Si Li, Boxin Shi
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17376v1

Social media platforms enable users to express emotions by posting text with accompanying images. In this paper, we propose the Affective Image Filter (AIF) task, which aims to reflect visually-abstract emotions from text into visually-concrete images, thereby creating emotionally compelling results. We first introduce the AIF dataset and the formulation of the AIF models. Then, we present AIF-B as an initial attempt based on a multi-modal transformer architecture. After that, we propose AIF-D as an extension of AIF-B towards deeper emotional reflection, effectively leveraging generative priors from pre-trained large-scale diffusion models. Quantitative and qualitative experiments demonstrate that AIF models achieve superior performance for both content consistency and emotional fidelity compared to state-of-the-art methods. Extensive user study experiments demonstrate that AIF models are significantly more effective at evoking specific emotions. Based on the presented results, we comprehensively discuss the value and potential of AIF models.

---

### AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens

Authors: Tung-Ling Li, Yuhao Wu, Hongliang Liu
Published: 2025-12-19
Categories: cs.LG, cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2512.17375v3

LLM-as-a-Judge systems supply the reward signal in modern RLHF and RLVR pipelines, but their binary verdict reduces to a single linear readout F_gap on one hidden state. We show this readout is shallow enough that short, low-perplexity tokens flip the verdict from "No" to "Yes". These tokens are sampled from the judge's own next-token distribution at the response position, with no manual seed set and no gradient-based optimization. Our procedure, AdvJudge-Zero, reaches $>$90% ensemble false-positive rate on 22 of 24 (model, dataset) cells across six Qwen, Llama, and Gemma judges, versus 54-72% for the prior curated 10-token benchmark, and the discovered surface transfers cross-format to a 70B scalar reward model. The same discovered pool enables a defense: a LoRA fine-tune stratified by a 9-class mechanism taxonomy hardens cross-family generalization where naive sampling on the same pool fails, with mechanism breadth rather than pool size carrying the gain. Under GRPO training, the hardened judge eliminates the reward-collapse failures (false-positive spikes and length collapse) we observe in the unhardened baseline on both MATH and GSM8K at ten seeds per condition. The discovered pool, the mechanism taxonomy, and per-prompt flip records will be released under responsible disclosure.

---

### Generative modeling of conditional probability distributions on the level-sets of collective variables

Authors: Fatima-Zahrae Akhyar, Wei Zhang, Gabriel Stoltz, Christof Schütte
Published: 2025-12-19
Categories: stat.ML, math.OC
arXiv: https://arxiv.org/abs/2512.17374v3

Given a probability distribution $μ$ in $\mathbb{R}^d$ represented by data, we study in this paper the generative modeling of the corresponding conditional probability distributions on the level-sets of a collective variable $ξ:\mathbb{R}^d \rightarrow \mathbb{R}^k$, where $1 \le k<d$. We propose a general and efficient learning approach that can learn generative models on different level-sets of $ξ$ simultaneously. To improve the learning quality on level-sets in low-probability regions, we also propose a data enrichment strategy by utilizing data from enhanced sampling techniques. We demonstrate the effectiveness of our proposed learning approach through concrete numerical examples. The proposed approach is potentially useful for the generative modeling of molecular systems in biophysics.

---

### Dialectics for Artificial Intelligence

Authors: Zhengmian Hu
Published: 2025-12-19
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.17373v2

Can artificial intelligence discover, from raw experience and without human supervision, concepts that humans have discovered? One challenge is that human concepts themselves are fluid: conceptual boundaries can shift, split, and merge as inquiry progresses (e.g., Pluto is no longer considered a planet). To make progress, we need a definition of "concept" that is not merely a dictionary label, but a structure that can be revised, compared, and aligned across agents. We propose an algorithmic-information viewpoint that treats a concept as an information object defined only through its structural relation to an agent's total experience. The core constraint is determination: a set of parts forms a reversible consistency relation if any missing part is recoverable from the others (up to the standard logarithmic slack in Kolmogorov-style identities). This reversibility prevents "concepts" from floating free of experience and turns concept existence into a checkable structural claim. To judge whether a decomposition is natural, we define excess information, measuring the redundancy overhead introduced by splitting experience into multiple separately described parts. On top of these definitions, we formulate dialectics as an optimization dynamics: as new patches of information appear (or become contested), competing concepts bid to explain them via shorter conditional descriptions, driving systematic expansion, contraction, splitting, and merging. Finally, we formalize low-cost concept transmission and multi-agent alignment using small grounds/seeds that allow another agent to reconstruct the same concept under a shared protocol, making communication a concrete compute-bits trade-off.

---

### TakeAD: Preference-based Post-optimization for End-to-end Autonomous Driving with Expert Takeover Data

Authors: Deqing Liu, Yinfeng Gao, Deheng Qian, Qichao Zhang, Xiaoqing Ye, Junyu Han, Yupeng Zheng, Xueyi Liu, Zhongpu Xia, Dawei Ding, Yifeng Pan, Dongbin Zhao
Published: 2025-12-19
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.17370v2

Existing end-to-end autonomous driving methods typically rely on imitation learning (IL) but face a key challenge: the misalignment between open-loop training and closed-loop deployment. This misalignment often triggers driver-initiated takeovers and system disengagements during closed-loop execution. How to leverage those expert takeover data from disengagement scenarios and effectively expand the IL policy's capability presents a valuable yet unexplored challenge. In this paper, we propose TakeAD, a novel preference-based post-optimization framework that fine-tunes the pre-trained IL policy with this disengagement data to enhance the closed-loop driving performance. First, we design an efficient expert takeover data collection pipeline inspired by human takeover mechanisms in real-world autonomous driving systems. Then, this post optimization framework integrates iterative Dataset Aggregation (DAgger) for imitation learning with Direct Preference Optimization (DPO) for preference alignment. The DAgger stage equips the policy with fundamental capabilities to handle disengagement states through direct imitation of expert interventions. Subsequently, the DPO stage refines the policy's behavior to better align with expert preferences in disengagement scenarios. Through multiple iterations, the policy progressively learns recovery strategies for disengagement states, thereby mitigating the open-loop gap. Experiments on the closed-loop Bench2Drive benchmark demonstrate our method's effectiveness compared with pure IL methods, with comprehensive ablations confirming the contribution of each component.

---

### Adversarially Robust Detection of Harmful Online Content: A Computational Design Science Approach

Authors: Yidong Chai, Yi Liu, Mohammadreza Ebrahimi, Weifeng Li, Balaji Padmanabhan
Published: 2025-12-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.17367v3

Social media platforms are plagued by harmful content such as hate speech, misinformation, and extremist rhetoric. Machine learning (ML) models are widely adopted to detect such content; however, they remain highly vulnerable to adversarial attacks, wherein malicious users subtly modify text to evade detection. Enhancing adversarial robustness is therefore essential, requiring detectors that can defend against diverse attacks (generalizability) while maintaining high overall accuracy. However, simultaneously achieving both optimal generalizability and accuracy is challenging. Following the computational design science paradigm, this study takes a sequential approach that first proposes a novel framework (Large Language Model-based Sample Generation and Aggregation, LLM-SGA) by identifying the key invariances of textual adversarial attacks and leveraging them to ensure that a detector instantiated within the framework has strong generalizability. Second, we instantiate our detector (Adversarially Robust Harmful Online Content Detector, ARHOCD) with three novel design components to improve detection accuracy: (1) an ensemble of multiple base detectors that exploits their complementary strengths; (2) a novel weight assignment method that dynamically adjusts weights based on each sample's predictability and each base detector's capability, with weights initialized using domain knowledge and updated via Bayesian inference; and (3) a novel adversarial training strategy that iteratively optimizes both the base detectors and the weight assignor. We addressed several limitations of existing adversarial robustness enhancement research and empirically evaluated ARHOCD across three datasets spanning hate speech, rumor, and extremist content. Results show that ARHOCD offers strong generalizability and improves detection accuracy under adversarial conditions.

---

### Adaptive Graph Pruning with Sudden-Events Evaluation for Traffic Prediction using Online Semi-Decentralized ST-GNNs

Authors: Ivan Kralj, Lodovico Giaretta, Gordan Ježić, Ivana Podnar Žarko, Šarūnas Girdzijauskas
Published: 2025-12-19
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2512.17352v1

Spatio-Temporal Graph Neural Networks (ST-GNNs) are well-suited for processing high-frequency data streams from geographically distributed sensors in smart mobility systems. However, their deployment at the edge across distributed compute nodes (cloudlets) createssubstantial communication overhead due to repeated transmission of overlapping node features between neighbouring cloudlets. To address this, we propose an adaptive pruning algorithm that dynamically filters redundant neighbour features while preserving the most informative spatial context for prediction. The algorithm adjusts pruning rates based on recent model performance, allowing each cloudlet to focus on regions experiencing traffic changes without compromising accuracy. Additionally, we introduce the Sudden Event Prediction Accuracy (SEPA), a novel event-focused metric designed to measure responsiveness to traffic slowdowns and recoveries, which are often missed by standard error metrics. We evaluate our approach in an online semi-decentralized setting with traditional FL, server-free FL, and Gossip Learning on two large-scale traffic datasets, PeMS-BAY and PeMSD7-M, across short-, mid-, and long-term prediction horizons. Experiments show that, in contrast to standard metrics, SEPA exposes the true value of spatial connectivity in predicting dynamic and irregular traffic. Our adaptive pruning algorithm maintains prediction accuracy while significantly lowering communication cost in all online semi-decentralized settings, demonstrating that communication can be reduced without compromising responsiveness to critical traffic events.

---

### Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers

Authors: Zeyuan Allen-Zhu
Published: 2025-12-19
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.17351v2

Understanding architectural differences in language models is challenging, especially at academic-scale pretraining (e.g., 1.3B parameters, 100B tokens), where results are often dominated by noise and randomness. To overcome this, we introduce controlled synthetic pretraining tasks that isolate and evaluate core model capabilities. Within this framework, we discover CANON LAYERS: lightweight architectural components -- named after the musical term "canon" -- that promote horizontal information flow across neighboring tokens. Canon layers compute weighted sums of nearby token representations and integrate seamlessly into Transformers, linear attention, state-space models, or any sequence architecture. We present 12 key results. This includes how Canon layers enhance reasoning depth (e.g., by $2\times$), reasoning breadth, knowledge manipulation, etc. They lift weak architectures like NoPE to match RoPE, and linear attention to rival SOTA linear models like Mamba2/GDN -- validated both through synthetic tasks and real-world academic-scale pretraining. This synthetic playground offers an economical, principled path to isolate core model capabilities often obscured at academic scales. Equipped with infinite high-quality data, it may even PREDICT how future architectures will behave as training pipelines improve -- e.g., through better data curation or RL-based post-training -- unlocking deeper reasoning and hierarchical inference.

---

### Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection

Authors: Chenming Zhou, Jiaan Wang, Yu Li, Lei Li, Juan Cao, Sheng Tang
Published: 2025-12-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.17350v1

The rapid evolution of generative technologies necessitates reliable methods for detecting AI-generated images. A critical limitation of current detectors is their failure to generalize to images from unseen generative models, as they often overfit to source-specific semantic cues rather than learning universal generative artifacts. To overcome this, we introduce a simple yet remarkably effective pixel-level mapping pre-processing step to disrupt the pixel value distribution of images and break the fragile, non-essential semantic patterns that detectors commonly exploit as shortcuts. This forces the detector to focus on more fundamental and generalizable high-frequency traces inherent to the image generation process. Through comprehensive experiments on GAN and diffusion-based generators, we show that our approach significantly boosts the cross-generator performance of state-of-the-art detectors. Extensive analysis further verifies our hypothesis that the disruption of semantic cues is the key to generalization.

---