# Research Papers — 2025-12 · bundle page 130 of 175

> Full-text markdown of papers #6451–6500 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/130
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/129.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/131.md)

### Evaluating Anomaly Detectors for Simulated Highly Imbalanced Industrial Classification Problems

Authors: Lesley Wheat, Martin v. Mohrenschildt, Saeid Habibi
Published: 2025-12-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.00005v2

Machine learning offers potential solutions to current issues in industrial systems in areas such as quality control and predictive maintenance, but also faces unique barriers in industrial applications. An ongoing challenge is extreme class imbalance, primarily due to the limited availability of faulty data during training. This paper presents a comprehensive evaluation of anomaly detection algorithms using a problem-agnostic simulated dataset that reflects real-world engineering constraints. Using a synthetic dataset with a hyper-spherical based anomaly distribution in 2D and 10D, we benchmark 14 detectors across training datasets with anomaly rates between 0.05% and 20% and training sizes between 1 000 and 10 000 (with a testing dataset size of 40 000) to assess performance and generalization error. Our findings reveal that the best detector is highly dependant on the total number of faulty examples in the training dataset, with additional healthy examples offering insignificant benefits in most cases. With less than 20 faulty examples, unsupervised methods (kNN/LOF) dominate; but around 30-50 faulty examples, semi-supervised (XGBOD) and supervised (SVM/CatBoost) detectors, we see large performance increases. While semi-supervised methods do not show significant benefits with only two features, the improvements are evident at ten features. The study highlights the performance drop on generalization of anomaly detection methods on smaller datasets, and provides practical insights for deploying anomaly detection in industrial environments.

---

### BIONIX: A Wireless, Low-Cost Prosthetic Arm with Dual-Signal EEG and EMG Control

Authors: Pranesh Sathish Kumar
Published: 2025-12-07
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2512.16929v1

Affordable upper-limb prostheses often lack intuitive control systems, limiting functionality and accessibility for amputees in low-resource settings. This project presents a low-cost, dual-mode neuro-muscular control system integrating electroencephalography (EEG) and electromyography (EMG) to enable real-time, multi-degree-of-freedom control of a prosthetic arm. EEG signals are acquired using the NeuroSky MindWave Mobile 2 and transmitted via ThinkGear Bluetooth packets to an ESP32 microcontroller running a lightweight classification model. The model was trained on 1500 seconds of recorded EEG data using a 6-frame sliding window with low-pass filtering, excluding poor-signal samples and using a 70/20/10 training--validation--test split. The classifier detects strong blink events, which toggle the hand between open and closed states. EMG signals are acquired using a MyoWare 2.0 sensor and SparkFun wireless shield and transmitted to a second ESP32, which performs threshold-based detection. Three activation bands (rest: 0--T1; extension: T1--T2; contraction: greater than T2) enable intuitive elbow control, with movement triggered only after eight consecutive frames in a movement class to improve stability. The EEG-controlled ESP32 actuates four finger servos, while the EMG-controlled ESP32 drives two elbow servos. A functional prototype was constructed using low-cost materials (total cost approximately 240 dollars), with most expense attributed to the commercial EEG headset. Future work includes transitioning to a 3D-printed chassis, integrating auto-regressive models to reduce EMG latency, and upgrading servo torque for improved load capacity and grip strength. This system demonstrates a feasible pathway to low-cost, biologically intuitive prosthetic control suitable for underserved and global health applications.

---

### The Principle of Proportional Duty: A Knowledge-Duty Framework for Ethical Equilibrium in Human and Artificial Systems

Authors: Timothy Prescher
Published: 2025-12-07
Categories: cs.AI, math.OC
arXiv: https://arxiv.org/abs/2512.15740v1

Traditional ethical frameworks often struggle to model decision-making under uncertainty, treating it as a simple constraint on action. This paper introduces the Principle of Proportional Duty (PPD), a novel framework that models how ethical responsibility scales with an agent's epistemic state. The framework reveals that moral duty is not lost to uncertainty but transforms: as uncertainty increases, Action Duty (the duty to act decisively) is proportionally converted into Repair Duty (the active duty to verify, inquire, and resolve uncertainty). This dynamic is expressed by the equation D_total = K((1-HI) + HI * g(C_signal)), where Total Duty is a function of Knowledge (K), Humility/Uncertainty (HI), and Contextual Signal Strength (C_signal). Monte Carlo simulations demonstrate that systems maintaining a baseline humility coefficient (lambda > 0) produce more stable duty allocations and reduce the risk of overconfident decision-making. By formalizing humility as a system parameter, the PPD offers a mathematically tractable approach to moral responsibility that could inform the development of auditable AI decision systems. This paper applies the framework across four domains, clinical ethics, recipient-rights law, economic governance, and artificial intelligence, to demonstrate its cross-disciplinary validity. The findings suggest that proportional duty serves as a stabilizing principle within complex systems, preventing both overreach and omission by dynamically balancing epistemic confidence against contextual risk.

---

### LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts

Authors: Krunal Jesani, Dmitry Ignatov, Radu Timofte
Published: 2025-12-07
Categories: cs.LG, cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2512.14706v1

Neural architecture search (NAS) traditionally requires significant human expertise or automated trial-and-error to design deep learning models. We present NN-Caption, an LLM-guided neural architecture search pipeline that generates runnable image-captioning models by composing CNN encoders from LEMUR's classification backbones with sequence decoders (LSTM/GRU/Transformer) under a strict Net API. Using DeepSeek-R1-0528-Qwen3-8B as the primary generator, we present the prompt template and examples of generated architectures. We evaluate on MS COCO with BLEU-4. The LLM generated dozens of captioning models, with over half successfully trained and producing meaningful captions. We analyse the outcomes of using different numbers of input model snippets (5 vs. 10) in the prompt, finding a slight drop in success rate when providing more candidate components. We also report training dynamics (caption accuracy vs. epochs) and the highest BLEU-4 attained. Our results highlight the promise of LLM-guided NAS: the LLM not only proposes architectures but also suggests hyperparameters and training practices. We identify the challenges encountered (e.g., code hallucinations or API compliance issues) and detail how prompt rules and iterative code fixes addressed them. This work presents a pipeline that integrates prompt-based code generation with automatic evaluation, and adds dozens of novel captioning models to the open LEMUR dataset to facilitate reproducible benchmarking and downstream AutoML research.

---

### LoopBench: Discovering Emergent Symmetry Breaking Strategies with LLM Swarms

Authors: Ali Parsaee, Yashar Talebirad, Csongor Szepesvári, Vishwajeet Ohal, Eden Redman
Published: 2025-12-07
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2512.13713v1

Large Language Models (LLMs) are increasingly being utilized as autonomous agents, yet their ability to coordinate in distributed systems remains poorly understood. We introduce \textbf{LoopBench}, a benchmark to evaluate LLM reasoning in distributed symmetry breaking and meta-cognitive thinking. The benchmark focuses on coloring odd cycle graphs ($C_3, C_5, C_{11}$) with limited colors, where deterministic, non-communicating agents fail in infinite loops. A strategy passing mechanism is implemented as a form of consistent memory. We show that while standard LLMs and classical heuristics struggle, advanced reasoning models (e.g., O3) devise strategies to escape deadlocks. LoopBench allows the study of emergent distributed algorithms based on language-based reasoning, offering a testbed for collective intelligence.

---

### It's About Time: The Temporal and Modal Dynamics of Copilot Usage

Authors: Beatriz Costa-Gomes, Sophia Chen, Connie Hsueh, Deborah Morgan, Philipp Schoenegger, Yash Shah, Sam Way, Yuki Zhu, Timothé Adeline, Michael Bhaskar, Mustafa Suleyman, Seth Spielman
Published: 2025-12-07
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2512.11879v1

We analyze 37.5 million deidentified conversations with Microsoft's Copilot between January and September 2025. Unlike prior analyses of AI usage, we focus not just on what people do with AI, but on how and when they do it. We find that how people use AI depends fundamentally on context and device type. On mobile, health is the dominant topic, which is consistent across every hour and every month we observed - with users seeking not just information but also advice. On desktop, the pattern is strikingly different: work and technology dominate during business hours, with "Work and Career" overtaking "Technology" as the top topic precisely between 8 a.m. and 5 p.m. These differences extend to temporal rhythms: programming queries spike on weekdays while gaming rises on weekends, philosophical questions climb during late-night hours, and relationship conversations surge on Valentine's Day. These patterns suggest that users have rapidly integrated AI into the full texture of their lives, as a work aid at their desks and a companion on their phones.

---

### The Art of Storytelling in Authoritarian Regimes: Crafting State Narratives on Chinese Social Media

Authors: Ting Luo, Yan Wang
Published: 2025-12-07
Categories: cs.CY, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2512.11875v1

This article examines how authoritarian regimes construct state narratives about politically consequential events. Building on the narrative policy framework and existing research on authoritarian propaganda, we propose two dimensions that shape narrative construction: legitimacy implications -- whether events enhance or threaten regime legitimacy, and citizen verification capacity -- the extent to which citizens can evaluate official narratives through alternative sources. Using quantitative narrative analysis of Chinese social media posts by government, state media, and celebrity accounts, we extract subject-verb-object (SVO) triplets to map dominant narrative structures across four major events. Our findings show that legitimacy implications of the event shape regime's efforts in storytelling and the beliefs highlighted in the narratives, while citizen's verification capacity could balance the strategic choice between a top-down manipulation and bottom-up responsiveness of state narratives. Together, the results reveal propaganda as a complex process of narrative construction adaptive to specific contexts, offering new insights into how dynamic storytelling sustains authoritarian resilience.

---

### Pseudo-Label Refinement for Robust Wheat Head Segmentation via Two-Stage Hybrid Training

Authors: Jiahao Jiang, Zhangrui Yang, Xuanhan Wang, Jingkuan Song
Published: 2025-12-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.11874v1

This extended abstract details our solution for the Global Wheat Full Semantic Segmentation Competition. We developed a systematic self-training framework. This framework combines a two-stage hybrid training strategy with extensive data augmentation. Our core model is SegFormer with a Mix Transformer (MiT-B4) backbone. We employ an iterative teacher-student loop. This loop progressively refines model accuracy. It also maximizes data utilization. Our method achieved competitive performance. This was evident on both the Development and Testing Phase datasets.

---

### Mathematics of natural intelligence

Authors: Evgenii Vityaev
Published: 2025-12-07
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2512.10988v1

In the process of evolution, the brain has achieved such perfection that artificial intelligence systems do not have and which needs its own mathematics. The concept of cognitome, introduced by the academician K.V. Anokhin, as the cognitive structure of the mind -- a high-order structure of the brain and a neural hypernetwork, is considered as the basis for modeling. Consciousness then is a special form of dynamics in this hypernetwork -- a large-scale integration of its cognitive elements. The cognitome, in turn, consists of interconnected COGs (cognitive groups of neurons) of two types -- functional systems and cellular ensembles. K.V. Anokhin sees the task of the fundamental theory of the brain and mind in describing these structures, their origin, functions and processes in them. The paper presents mathematical models of these structures based on new mathematical results, as well as models of different cognitive processes in terms of these models. In addition, it is shown that these models can be derived based on a fairly general principle of the brain works: \textit{the brain discovers all possible causal relationships in the external world and draws all possible conclusions from them}. Based on these results, the paper presents models of: ``natural" classification; theory of functional brain systems by P.K. Anokhin; prototypical theory of categorization by E. Roche; theory of causal models by Bob Rehter; theory of consciousness as integrated information by G. Tononi.

---

### ELANA: A Simple Energy and Latency Analyzer for LLMs

Authors: Hung-Yueh Chiang, Bokun Wang, Diana Marculescu
Published: 2025-12-07
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2512.09946v1

The latency and power consumption of large language models (LLMs) are major constraints when serving them across a wide spectrum of hardware platforms, from mobile edge devices to cloud GPU clusters. Benchmarking is crucial for optimizing efficiency in both model deployment and next-generation model development. To address this need, we open-source a simple profiling tool, \textbf{ELANA}, for evaluating LLMs. ELANA is designed as a lightweight, academic-friendly profiler for analyzing model size, key-value (KV) cache size, prefilling latency (Time-to-first-token, TTFT), generation latency (Time-per-output-token, TPOT), and end-to-end latency (Time-to-last-token, TTLT) of LLMs on both multi-GPU and edge GPU platforms. It supports all publicly available models on Hugging Face and offers a simple command-line interface, along with optional energy consumption logging. Moreover, ELANA is fully compatible with popular Hugging Face APIs and can be easily customized or adapted to compressed or low bit-width models, making it ideal for research on efficient LLMs or for small-scale proof-of-concept studies. We release the ELANA profiling tool at: https://github.com/enyac-group/Elana.

---

### DAUNet: A Lightweight UNet Variant with Deformable Convolutions and Parameter-Free Attention for Medical Image Segmentation

Authors: Adnan Munir, Muhammad Shahid Jabbar, Shujaat Khan
Published: 2025-12-07
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.07051v2

Medical image segmentation plays a pivotal role in automated diagnostic and treatment planning systems. In this work, we present DAUNet, a novel lightweight UNet variant that integrates Deformable V2 Convolutions and Parameter-Free Attention (SimAM) to improve spatial adaptability and context-aware feature fusion without increasing model complexity. DAUNet's bottleneck employs dynamic deformable kernels to handle geometric variations, while the decoder and skip pathways are enhanced using SimAM attention modules for saliency-aware refinement. Extensive evaluations on two challenging datasets, FH-PS-AoP (fetal head and pubic symphysis ultrasound) and FUMPE (CT-based pulmonary embolism detection), demonstrate that DAUNet outperforms state-of-the-art models in Dice score, HD95, and ASD, while maintaining superior parameter efficiency. Ablation studies highlight the individual contributions of deformable convolutions and SimAM attention. DAUNet's robustness to missing context and low-contrast regions establishes its suitability for deployment in real-time and resource-constrained clinical environments.

---

### Transformation of Biological Networks into Images via Semantic Cartography for Visual Interpretation and Scalable Deep Analysis

Authors: Sakib Mostafa, Lei Xing, Md. Tauhidul Islam
Published: 2025-12-07
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2512.07040v1

Complex biological networks are fundamental to biomedical science, capturing interactions among molecules, cells, genes, and tissues. Deciphering these networks is critical for understanding health and disease, yet their scale and complexity represent a daunting challenge for current computational methods. Traditional biological network analysis methods, including deep learning approaches, while powerful, face inherent challenges such as limited scalability, oversmoothing long-range dependencies, difficulty in multimodal integration, expressivity bounds, and poor interpretability. We present Graph2Image, a framework that transforms large biological networks into sets of two-dimensional images by spatially arranging representative network nodes on a 2D grid. This transformation decouples the nodes as images, enabling the use of convolutional neural networks (CNNs) with global receptive fields and multi-scale pyramids, thus overcoming limitations of existing biological network analysis methods in scalability, memory efficiency, and long-range context capture. Graph2Image also facilitates seamless integration with other imaging and omics modalities and enhances interpretability through direct visualization of node-associated images. When applied to several large-scale biological network datasets, Graph2Image improved classification accuracy by up to 67.2% over existing methods and provided interpretable visualizations that revealed biologically coherent patterns. It also allows analysis of very large biological networks (nodes > 1 billion) on a personal computer. Graph2Image thus provides a scalable, interpretable, and multimodal-ready approach for biological network analysis, offering new opportunities for disease diagnosis and the study of complex biological systems.

---

### Ideal Attribution and Faithful Watermarks for Language Models

Authors: Min Jae Song, Kameron Shahabi
Published: 2025-12-07
Categories: cs.CR, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.07038v1

We introduce ideal attribution mechanisms, a formal abstraction for reasoning about attribution decisions over strings. At the core of this abstraction lies the ledger, an append-only log of the prompt-response interaction history between a model and its user. Each mechanism produces deterministic decisions based on the ledger and an explicit selection criterion, making it well-suited to serve as a ground truth for attribution. We frame the design goal of watermarking schemes as faithful representation of ideal attribution mechanisms. This novel perspective brings conceptual clarity, replacing piecemeal probabilistic statements with a unified language for stating the guarantees of each scheme. It also enables precise reasoning about desiderata for future watermarking schemes, even when no current construction achieves them, since the ideal functionalities are specified first. In this way, the framework provides a roadmap that clarifies which guarantees are attainable in an idealized setting and worth pursuing in practice.

---

### Evaluating and Preserving High-level Fidelity in Super-Resolution

Authors: Josep M. Rocafort, Shaolin Su, Alexandra Gomez-Villa, Javier Vazquez-Corral
Published: 2025-12-07
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.07037v2

Recent image Super-Resolution (SR) models are achieving impressive effects in reconstructing details and delivering visually pleasant outputs. However, the overpowering generative ability can sometimes hallucinate and thus change the image content despite gaining high visual quality. This type of high-level change can be easily identified by humans yet not well-studied in existing low-level image quality metrics. In this paper, we establish the importance of measuring high-level fidelity for SR models as a complementary criterion to reveal the reliability of generative SR models. We construct the first annotated dataset with fidelity scores from different SR models, and evaluate how state-of-the-art (SOTA) SR models actually perform in preserving high-level fidelity. Based on the dataset, we then analyze how existing image quality metrics correlate with fidelity measurement, and further show that this high-level task can be better addressed by foundation models. Finally, by fine-tuning SR models based on our fidelity feedback, we show that both semantic fidelity and perceptual quality can be improved, demonstrating the potential value of our proposed criteria, both in model evaluation and optimization. We will release the dataset, code, and models upon acceptance.

---

### Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues

Authors: Tuan-Anh Vu, Hai Nguyen-Truong, Ziqiang Zheng, Binh-Son Hua, Qing Guo, Ivor Tsang, Sai-Kit Yeung
Published: 2025-12-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.07034v1

Glass is a prevalent material among solid objects in everyday life, yet segmentation methods struggle to distinguish it from opaque materials due to its transparency and reflection. While it is known that human perception relies on boundary and reflective-object features to distinguish glass objects, the existing literature has not yet sufficiently captured both properties when handling transparent objects. Hence, we propose incorporating both of these powerful visual cues via the Boundary Feature Enhancement and Reflection Feature Enhancement modules in a mutually beneficial way. Our proposed framework, TransCues, is a pyramidal transformer encoder-decoder architecture to segment transparent objects. We empirically show that these two modules can be used together effectively, improving overall performance across various benchmark datasets, including glass object semantic segmentation, mirror object semantic segmentation, and generic segmentation datasets. Our method outperforms the state-of-the-art by a large margin, achieving +4.2% mIoU on Trans10K-v2, +5.6% mIoU on MSD, +10.1% mIoU on RGBD-Mirror, +13.1% mIoU on TROSD, and +8.3% mIoU on Stanford2D3D, showing the effectiveness of our method against glass objects.

---

### A Comprehensive Study of Supervised Machine Learning Models for Zero-Day Attack Detection: Analyzing Performance on Imbalanced Data

Authors: Zahra Lotfi, Mostafa Lotfi
Published: 2025-12-07
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.07030v1

Among the various types of cyberattacks, identifying zero-day attacks is problematic because they are unknown to security systems as their pattern and characteristics do not match known blacklisted attacks. There are many Machine Learning (ML) models designed to analyze and detect network attacks, especially using supervised models. However, these models are designed to classify samples (normal and attacks) based on the patterns they learn during the training phase, so they perform inefficiently on unseen attacks. This research addresses this issue by evaluating five different supervised models to assess their performance and execution time in predicting zero-day attacks and find out which model performs accurately and quickly. The goal is to improve the performance of these supervised models by not only proposing a framework that applies grid search, dimensionality reduction and oversampling methods to overcome the imbalance problem, but also comparing the effectiveness of oversampling on ml model metrics, in particular the accuracy. To emulate attack detection in real life, this research applies a highly imbalanced data set and only exposes the classifiers to zero-day attacks during the testing phase, so the models are not trained to flag the zero-day attacks. Our results show that Random Forest (RF) performs best under both oversampling and non-oversampling conditions, this increased effectiveness comes at the cost of longer processing times. Therefore, we selected XG Boost (XGB) as the top model due to its fast and highly accurate performance in detecting zero-day attacks.

---

### Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localization

Authors: Genevieve Caumartin, Glaucia Melo
Published: 2025-12-07
Categories: cs.SE, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2512.07022v1

Bug localization remains a critical yet time-consuming challenge in large-scale software repositories. Traditional information retrieval-based bug localization (IRBL) methods rely on unchanged bug descriptions, which often contain noisy information, leading to poor retrieval accuracy. Recent advances in large language models (LLMs) have improved bug localization through query reformulation, yet the effect on agent performance remains unexplored. In this study, we investigate how an LLM-powered agent can improve file-level bug localization via lightweight query reformulation and summarization. We first employ an open-source, non-fine-tuned LLM to extract key information from bug reports, such as identifiers and code snippets, and reformulate queries pre-retrieval. Our agent then orchestrates BM25 retrieval using these preprocessed queries, automating localization workflow at scale. Using the best-performing query reformulation technique, our agent achieves 35% better ranking in first-file retrieval than our BM25 baseline and up to +22% file retrieval performance over SWE-agent.

---

### Transferring Clinical Knowledge into ECGs Representation

Authors: Jose Geraldo Fernandes, Luiz Facury de Souza, Pedro Robles Dutenhefner, Gisele L. Pappa, Wagner Meira
Published: 2025-12-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.07021v1

Deep learning models have shown high accuracy in classifying electrocardiograms (ECGs), but their black box nature hinders clinical adoption due to a lack of trust and interpretability. To address this, we propose a novel three-stage training paradigm that transfers knowledge from multimodal clinical data (laboratory exams, vitals, biometrics) into a powerful, yet unimodal, ECG encoder. We employ a self-supervised, joint-embedding pre-training stage to create an ECG representation that is enriched with contextual clinical information, while only requiring the ECG signal at inference time. Furthermore, as an indirect way to explain the model's output we train it to also predict associated laboratory abnormalities directly from the ECG embedding. Evaluated on the MIMIC-IV-ECG dataset, our model outperforms a standard signal-only baseline in multi-label diagnosis classification and successfully bridges a substantial portion of the performance gap to a fully multimodal model that requires all data at inference. Our work demonstrates a practical and effective method for creating more accurate and trustworthy ECG classification models. By converting abstract predictions into physiologically grounded \emph{explanations}, our approach offers a promising path toward the safer integration of AI into clinical workflows.

---

### Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought Length

Authors: Zhiyu Xu, Jia Liu, Yixin Wang, Yuqi Gu
Published: 2025-12-07
Categories: stat.ME, cs.AI, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2512.07019v4

The proliferation of Large Language Models (LLMs) necessitates valid evaluation methods to provide guidance for both downstream applications and actionable future improvements. The Item Response Theory (IRT) model with Computerized Adaptive Testing has recently emerged as a promising framework for evaluating LLMs via their response accuracy. Beyond simple response accuracy, LLMs' chain of thought (CoT) lengths serve as a vital indicator of their reasoning ability. To leverage the CoT length information to assist LLM evaluation, we propose the \textbf{La}tency-\textbf{R}esponse \textbf{T}heory (LaRT) model, which jointly models both the response accuracy and CoT length by introducing a key correlation parameter between the latent ability and the latent speed. We derive an efficient stochastic approximation Expectation-Maximization algorithm for parameter estimation. We establish rigorous identifiability results for the latent ability and latent speed parameters to ensure the statistical validity of their estimation. Through both theoretical asymptotic analyses and simulation studies, we demonstrate LaRT's advantages over IRT in terms of superior estimation accuracy and shorter confidence intervals for latent trait estimation. To evaluate LaRT in real data, we collect responses from diverse LLMs on popular benchmark datasets. We find that LaRT yields different LLM rankings than IRT and outperforms IRT across multiple key evaluation metrics including predictive power, item efficiency, ranking validity, and LLM evaluation efficiency. Code and data are available at https://github.com/Toby-X/Latency-Response-Theory-Model

---

### FVA-RAG: Falsification-Verification Alignment for Mitigating Sycophantic Hallucinations

Authors: Mayank Ravishankara
Published: 2025-12-07
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2512.07015v2

Retrieval-Augmented Generation (RAG) reduces hallucinations by grounding answers in retrieved evidence, yet standard retrievers often exhibit retrieval sycophancy: they preferentially surface evidence that supports a user's premise, even when the premise is false. We propose FVA-RAG (Falsification-Verification Alignment RAG), a pipeline that inverts the standard RAG workflow by treating the initial response as a draft hypothesis and explicitly retrieving anti-context to stress-test it. We evaluate on the full TruthfulQA-Generation benchmark (N=817) under a fully frozen protocol with 0 live web calls and identical retrieval budgets across methods. Using gpt-4o for generation and deterministic judging, FVA-RAG achieves 79.80-80.05% accuracy across two independently built frozen corpora , significantly outperforming prompted variants of Self-RAG (71.11-72.22%) and CRAG (71.36-73.93%) with p < 10^-6 according to McNemar's test. FVA-RAG triggers falsification on 24.5-29.3% of queries, demonstrating that targeted counter-evidence retrieval is decisive for mitigating premise-confirming hallucinations.

---

### Block Sparse Flash Attention

Authors: Daniel Ohayon, Itay Lamprecht, Itay Hubara, Israel Cohen, Daniel Soudry, Noam Elata
Published: 2025-12-07
Categories: cs.LG, cs.CL, cs.PF
arXiv: https://arxiv.org/abs/2512.07011v2

Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity creates a severe computational bottleneck. We present Block Sparse Flash Attention (BSFA), a drop-in replacement that accelerates long-context inference while preserving model quality. Unlike methods that predict importance before computing scores, BSFA computes exact query-key similarities to select the top-k most important value blocks for each query. By comparing per-block maximum scores against calibrated thresholds, we skip approximately 50% of the computation and memory transfers for pruned blocks. Our training-free approach requires only a one-time threshold calibration on a small dataset to learn the per-layer and per-head attention score distributions. We provide a CUDA kernel implementation that can be used as a drop-in replacement for FlashAttention. On Llama-3.1-8B, BSFA achieves up to 1.13x end-to-end speedup on LongBench with only a 1.1% accuracy drop, and up to 1.24x on Needle-in-a-Haystack retrieval at a 1% accuracy drop. The attention kernel itself accelerates by up to 1.38x. We compare BSFA against five recent sparse attention baselines (SpargeAttention, MInference, FlexPrefill, XAttention, and BLASST), and verify the method on Qwen2.5-7B and on A6000 and H100 GPUs. The implementation is available at https://github.com/Danielohayon/Block-Sparse-Flash-Attention.

---

### Always Keep Your Promises: A Model-Agnostic Attribution Algorithm for Neural Networks

Authors: Kevin Lee, Duncan Smith-Halverson, Pablo Millan Arias
Published: 2025-12-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.07010v4

Layer-wise Relevance Propagation (LRP) provides principled attribution for neural networks through conservation properties and foundations in Deep Taylor Decomposition. However, existing implementations operate at the module level, requiring architecture-specific propagation rules and model modifications. These limit the generality of target model and sustainability of implementations as architectures evolve. We introduce DynamicLRP, a model-agnostic LRP framework operating at the tensor operation level. By decomposing attribution to individual operations within computation graphs and introducing a novel mechanism for deferred activation resolution, named the Promise System, our approach achieves true architecture agnosticity while maintaining LRP's theoretical guarantees. This design operates independently of backpropagation machinery, requiring no model modification, enabling side-by-side execution with gradient backpropagation. Being based on computation graphs, this method is theoretically extensible to other deep learning libraries that support auto-differentiation. We demonstrate faithfulness matching or exceeding specialized implementations (1.77 vs 1.69 ABPC on VGG, equivalent performance on ViT, 93.70% and 95.06% top-1 attribution accuracy for explaining RoBERTa-large and Flan-T5-large answers on SQuADv2, respectively) while maintaining practical efficiency on models with 100M-1B parameters. We achieved 99.92% node coverage across 31,465 computation graph nodes from 15 diverse architectures, including state-space models (Mamba), audio transformers (Whisper), and multimodal systems (DePlot) without any model-specific code with rules for 47 fundamental operations implemented. Our operation-level decomposition and Promise System establish a sustainable, extensible foundation for LRP across evolving architectures. All code is available at https://github.com/keeinlev/dynamicLRP .

---

### Optimizing video analytics inference pipelines: a case study

Authors: Saeid Ghafouri, Yuming Ding, Katerine Diaz Chito, Jesús Martinez del Rincón, Niamh O'Connell, Hans Vandierendonck
Published: 2025-12-07
Categories: cs.DC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.07009v1

Cost-effective and scalable video analytics are essential for precision livestock monitoring, where high-resolution footage and near-real-time monitoring needs from commercial farms generates substantial computational workloads. This paper presents a comprehensive case study on optimizing a poultry welfare monitoring system through system-level improvements across detection, tracking, clustering, and behavioral analysis modules. We introduce a set of optimizations, including multi-level parallelization, Optimizing code with substituting CPU code with GPU-accelerated code, vectorized clustering, and memory-efficient post-processing. Evaluated on real-world farm video footage, these changes deliver up to a 2x speedup across pipelines without compromising model accuracy. Our findings highlight practical strategies for building high-throughput, low-latency video inference systems that reduce infrastructure demands in agricultural and smart sensing deployments as well as other large-scale video analytics applications.

---

### Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition

Authors: Zihao Wang, Ruibin Yuan, Ziqi Geng, Hengjia Li, Xingwei Qu, Xinyi Li, Songye Chen, Haoying Fu, Roger B. Dannenberg, Kejun Zhang
Published: 2025-12-07
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2512.07005v1

Singing accent research is underexplored compared to speech accent studies, primarily due to the scarcity of suitable datasets. Existing singing datasets often suffer from detail loss, frequently resulting from the vocal-instrumental separation process. Additionally, they often lack regional accent annotations. To address this, we introduce the Multi-Accent Mandarin Dry-Vocal Singing Dataset (MADVSD). MADVSD comprises over 670 hours of dry vocal recordings from 4,206 native Mandarin speakers across nine distinct Chinese regions. In addition to each participant recording audio of three popular songs in their native accent, they also recorded phonetic exercises covering all Mandarin vowels and a full octave range. We validated MADVSD through benchmark experiments in singing accent recognition, demonstrating its utility for evaluating state-of-the-art speech models in singing contexts. Furthermore, we explored dialectal influences on singing accent and analyzed the role of vowels in accentual variations, leveraging MADVSD's unique phonetic exercises.

---

### Benchmarking Deep Neural Networks for Modern Recommendation Systems

Authors: Abderaouf Bahi, Inoussa Mouiche, Ibtissem Gasmi
Published: 2025-12-07
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2512.07000v2

This paper presents a requirement-oriented benchmark of seven deep neural architectures, CNN, RNN, GNN, Autoencoder, Transformer, Neural Collaborative Filtering, and Siamese Networks, across three real-world datasets: Retail E-commerce, Amazon Products, and Netflix Prize. To ensure a fair and comprehensive comparison aligned with the evolving demands of modern recommendation systems, we adopt a Requirement-Oriented Benchmarking (ROB) framework that structures evaluation around predictive accuracy, recommendation diversity, relational awareness, temporal dynamics, and computational efficiency. Under a unified evaluation protocol, models are assessed using standard accuracy-oriented metrics alongside diversity and efficiency indicators. Experimental results show that different architectures exhibit complementary strengths across requirements, motivating the use of hybrid and ensemble designs. The findings provide practical guidance for selecting and combining neural architectures to better satisfy multi-objective recommendation system requirements.

---

### Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model

Authors: Zihao Wang, Ruibin Yuan, Ziqi Geng, Hengjia Li, Xingwei Qu, Xinyi Li, Songye Chen, Haoying Fu, Roger B. Dannenberg, Kejun Zhang
Published: 2025-12-07
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2512.06999v1

Automated singing assessment is crucial for education and entertainment. However, existing systems face two fundamental limitations: reliance on reference tracks, which stifles creative expression, and the simplification of complex performances into non-diagnostic scores based solely on pitch and rhythm. We advocate for a shift from discriminative to descriptive evaluation, creating a complete ecosystem for reference-free, multi-dimensional assessment. First, we introduce Sing-MD, a large-scale dataset annotated by experts across four dimensions: breath control, timbre quality, emotional expression, and vocal technique. Our analysis reveals significant annotation inconsistencies among experts, challenging the validity of traditional accuracy-based metrics. Second, addressing the memory limitations of Multimodal Large Language Models (MLLMs) in analyzing full-length songs, we propose VocalVerse. This efficient hybrid architecture leverages a lightweight acoustic encoder to model global performance features and long-term dependencies. Third, to address automated metric shortcomings, we establish the H-TPR (Human-in-the-loop Tiered Perceptual Ranking) benchmark, which evaluates a model's ability to generate perceptually valid rankings rather than predicting noisy ground-truth scores.

---

### Toward Reliable Machine Unlearning: Theory, Algorithms, and Evaluation

Authors: Ali Ebrahimpour-Boroojeny
Published: 2025-12-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.06993v1

We propose new methodologies for both unlearning random set of samples and class unlearning and show that they outperform existing methods. The main driver of our unlearning methods is the similarity of predictions to a retrained model on both the forget and remain samples. We introduce Adversarial Machine UNlearning (AMUN), which surpasses prior state-of-the-art methods for image classification based on SOTA MIA scores. AMUN lowers the model's confidence on forget samples by fine-tuning on their corresponding adversarial examples. Through theoretical analysis, we identify factors governing AMUN's performance, including smoothness. To facilitate training of smooth models with a controlled Lipschitz constant, we propose FastClip, a scalable method that performs layer-wise spectral-norm clipping of affine layers. In a separate study, we show that increased smoothness naturally improves adversarial example transfer, thereby supporting the second factor above. Following the same principles for class unlearning, we show that existing methods fail in replicating a retrained model's behavior by introducing a nearest-neighbor membership inference attack (MIA-NN) that uses the probabilities assigned to neighboring classes to detect unlearned samples and demonstrate the vulnerability of such methods. We then propose a fine-tuning objective that mitigates this leakage by approximating, for forget-class inputs, the distribution over remaining classes that a model retrained from scratch would produce. To construct this approximation, we estimate inter-class similarity and tilt the target model's distribution accordingly. The resulting Tilted ReWeighting(TRW) distribution serves as the desired target during fine-tuning. Across multiple benchmarks, TRW matches or surpasses existing unlearning methods on prior metrics.

---

### Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models

Authors: Jing Jie Tan, Ban-Hoe Kwan, Danny Wee-Kiat Ng, Yan-Chai Hum, Anissa Mokraoui, Shih-Yu Lo
Published: 2025-12-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.06991v1

Large Language Models (LLMs) have demonstrated remarkable capabilities across various natural language processing tasks. This research introduces a novel "Prompting-in-a-Series" algorithm, termed PICEPR (Psychology-Informed Contents Embeddings for Personality Recognition), featuring two pipelines: (a) Contents and (b) Embeddings. The approach demonstrates how a modularised decoder-only LLM can summarize or generate content, which can aid in classifying or enhancing personality recognition functions as a personality feature extractor and a generator for personality-rich content. We conducted various experiments to provide evidence to justify the rationale behind the PICEPR algorithm. Meanwhile, we also explored closed-source models such as \textit{gpt4o} from OpenAI and \textit{gemini} from Google, along with open-source models like \textit{mistral} from Mistral AI, to compare the quality of the generated content. The PICEPR algorithm has achieved a new state-of-the-art performance for personality recognition by 5-15\% improvement. The work repository and models' weight can be found at https://research.jingjietan.com/?q=PICEPR.

---

### Utilizing Multi-Agent Reinforcement Learning with Encoder-Decoder Architecture Agents to Identify Optimal Resection Location in Glioblastoma Multiforme Patients

Authors: Krishna Arun, Moinak Bhattachrya, Paras Goel
Published: 2025-12-07
Categories: cs.AI, cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2512.06990v1

Currently, there is a noticeable lack of AI in the medical field to support doctors in treating heterogenous brain tumors such as Glioblastoma Multiforme (GBM), the deadliest human cancer in the world with a five-year survival rate of just 5.1%. This project develops an AI system offering the only end-to-end solution by aiding doctors with both diagnosis and treatment planning. In the diagnosis phase, a sequential decision-making framework consisting of 4 classification models (Convolutional Neural Networks and Support Vector Machine) are used. Each model progressively classifies the patient's brain into increasingly specific categories, with the final step being named diagnosis. For treatment planning, an RL system consisting of 3 generative models is used. First, the resection model (diffusion model) analyzes the diagnosed GBM MRI and predicts a possible resection outcome. Second, the radiotherapy model (Spatio-Temporal Vision Transformer) generates an MRI of the brain's progression after a user-defined number of weeks. Third, the chemotherapy model (Diffusion Model) produces the post-treatment MRI. A survival rate calculator (Convolutional Neural Network) then checks if the generated post treatment MRI has a survival rate within 15% of the user defined target. If not, a feedback loop using proximal policy optimization iterates over this system until an optimal resection location is identified. When compared to existing solutions, this project found 3 key findings: (1) Using a sequential decision-making framework consisting of 4 small diagnostic models reduced computing costs by 22.28x, (2) Transformers regression capabilities decreased tumor progression inference time by 113 hours, and (3) Applying Augmentations resembling Real-life situations improved overall DICE scores by 2.9%. These results project to increase survival rates by 0.9%, potentially saving approximately 2,250 lives.

---

### Flash Multi-Head Feed-Forward Network

Authors: Minshen Zhang, Xiang Hu, Jianguo Li, Wei Wu, Kewei Tu
Published: 2025-12-07
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.06989v1

We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively applying them to FFNs faces two challenges: memory consumption scaling with the head count, and an imbalanced ratio between the growing intermediate size and the fixed head dimension as models scale, which degrades scalability and expressive power. To address these challenges, we propose Flash Multi-Head FFN (FlashMHF), with two key innovations: an I/O-aware fused kernel computing outputs online in SRAM akin to FlashAttention, and a design using dynamically weighted parallel sub-networks to maintain a balanced ratio between intermediate and head dimensions. Validated on models from 128M to 1.3B parameters, FlashMHF consistently improves perplexity and downstream task accuracy over SwiGLU FFNs, while reducing peak memory usage by 3-5x and accelerating inference by up to 1.08x. Our work establishes the multi-head design as a superior architectural principle for FFNs, presenting FlashMHF as a powerful, efficient, and scalable alternative to FFNs in Transformers.

---

### OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction

Authors: Emily Jin, Andrei Cristian Nica, Mikhail Galkin, Jarrid Rector-Brooks, Kin Long Kelvin Lee, Santiago Miret, Frances H. Arnold, Michael Bronstein, Avishek Joey Bose, Alexander Tong, Cheng-Hao Liu
Published: 2025-12-07
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2512.06987v3

Accurately predicting experimentally realizable 3D molecular crystal structures from their 2D chemical graphs is a long-standing open challenge in computational chemistry called crystal structure prediction (CSP). Efficiently solving this problem has implications ranging from pharmaceuticals to organic semiconductors, as crystal packing directly governs the physical and chemical properties of organic solids. In this paper, we introduce OXtal, a large-scale 100M parameter all-atom diffusion model that directly learns the conditional joint distribution over intramolecular conformations and periodic packing. To efficiently scale OXtal, we abandon explicit equivariant architectures imposing inductive bias arising from crystal symmetries in favor of data augmentation strategies. We further propose a novel crystallization-inspired lattice-free training scheme, Stoichiometric Stochastic Shell Sampling ($S^4$), that efficiently captures long-range interactions while sidestepping explicit lattice parametrization -- thus enabling more scalable architectural choices at all-atom resolution. By leveraging a large dataset of 600K experimentally validated crystal structures (including rigid and flexible molecules, co-crystals, and solvates), OXtal achieves orders-of-magnitude improvements over prior ab initio machine learning CSP methods, while remaining orders of magnitude cheaper than traditional quantum-chemical approaches. Specifically, OXtal recovers experimental structures with conformer $\text{RMSD}_1<0.5$ Å and attains over 80\% packing similarity rate, demonstrating its ability to model both thermodynamic and kinetic regularities of molecular crystallization.

---

### On Memory: A comparison of memory mechanisms in world models

Authors: Eli J. Laird, Corey Clark
Published: 2025-12-07
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.06983v2

World models enable agents to plan within imagined environments by predicting future states conditioned on past observations and actions. However, their ability to plan over long horizons is limited by the effective memory span of the backbone architecture. This limitation leads to perceptual drift in long rollouts, degrading the model's capacity to recall recently observed scenes. In this work, we investigate the effective memory span of transformer-based world models through an analysis of memory augmentation mechanisms. We introduce a taxonomy that distinguishes between memory \emph{encoding} and memory \emph{injection} mechanisms, motivating their roles in extending the world model's memory through the lens of residual stream dynamics. We evaluate twenty combinations of four encoding methods and five injection methods in the MemoryMaze environment. Using a state recall evaluation task across multiple imagination horizons, we measure the memory recall capacity of each mechanism and analyze their respective trade-offs in reconstruction quality, latent prediction error, and computational cost. We further ablate the effect of injection depth and compare the best memory-augmented vision transformer against a pure state-space model backbone. Our central finding is that the mLSTM memory encoder outperforms all alternatives in both reconstruction and latent fidelity metrics. Paired with additive injection, it exhibits the strongest recall capabilities at a moderate computational cost while matching or slightly exceeding a pure Mamba backbone. This evaluation is limited to a single environment and does not explore the effect of each mechanism on downstream task performance. We believe these research directions merit an in-depth study of their own to clearly isolate the effects, and therefore are left for future work.

---

### LLM-Driven Composite Neural Architecture Search for Multi-Source RL State Encoding

Authors: Yu Yu, Qian Xie, Nairen Cao, Li Jin
Published: 2025-12-07
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.06982v2

Designing state encoders for reinforcement learning (RL) with multiple information sources -- such as sensor measurements, time-series signals, image observations, and textual instructions -- remains underexplored and often requires manual design. We formalize this challenge as a problem of composite neural architecture search (NAS), where multiple source-specific modules and a fusion module are jointly optimized. Existing NAS methods overlook useful side information from the intermediate outputs of these modules -- such as their representation quality -- limiting sample efficiency in multi-source RL settings. To address this, we propose an LLM-driven NAS pipeline in which the LLM serves as a neural architecture design agent, leveraging language-model priors and intermediate-output signals to guide sample-efficient search for high-performing composite state encoders. On a mixed-autonomy traffic control task, our approach discovers higher-performing architectures with fewer candidate evaluations than traditional NAS baselines and the LLM-based GENIUS framework.

---

### Selective Masking based Self-Supervised Learning for Image Semantic Segmentation

Authors: Yuemin Wang, Ian Stavness
Published: 2025-12-07
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.06981v1

This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation used in most masked image modelling pretraining methods. The proposed selective masking method selectively masks image patches with the highest reconstruction loss by breaking the image reconstruction pretraining into iterative steps to leverage the trained model's knowledge. We show on two general datasets (Pascal VOC and Cityscapes) and two weed segmentation datasets (Nassar 2020 and Sugarbeets 2016) that our proposed selective masking method outperforms the traditional random masking method and supervised ImageNet pretraining on downstream segmentation accuracy by 2.9% for general datasets and 2.5% for weed segmentation datasets. Furthermore, we found that our selective masking method significantly improves accuracy for the lowest-performing classes. Lastly, we show that using the same pretraining and downstream dataset yields the best result for low-budget self-supervised pretraining. Our proposed Selective Masking Image Reconstruction method provides an effective and practical solution to improve end-to-end semantic segmentation workflows, especially for scenarios that require limited model capacity to meet inference speed and computational resource requirements.

---

### Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging

Authors: Laurentius Valdy, Richard D. Paul, Alessio Quercia, Zhuo Cao, Xuan Zhao, Hanno Scharr, Arya Bangun
Published: 2025-12-07
Categories: eess.IV, cs.LG
arXiv: https://arxiv.org/abs/2512.06977v1

Accurate multi-slice reconstruction from limited measurement data is crucial to speed up the acquisition process in medical and scientific imaging. However, it remains challenging due to the ill-posed nature of the problem and the high computational and memory demands. We propose a framework that addresses these challenges by integrating partitioned diffusion priors with physics-based constraints. By doing so, we substantially reduce memory usage per GPU while preserving high reconstruction quality, outperforming both physics-only and full multi-slice reconstruction baselines for different modalities, namely Magnetic Resonance Imaging (MRI) and four-dimensional Scanning Transmission Electron Microscopy (4D-STEM). Additionally, we show that the proposed method improves in-distribution accuracy as well as strong generalization to out-of-distribution datasets.

---

### Feasibility-aware Learning of Robust Temporal Logic Controllers using BarrierNet

Authors: Wenliang Liu, Shuo Liu, Wei Xiao, Calin A. Belta
Published: 2025-12-07
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2512.06973v3

Control Barrier Functions (CBFs) have been used to enforce safety and task specifications expressed in Signal Temporal Logic (STL). However, existing CBF-STL approaches typically rely on fixed hyperparameters and per-step optimization, which can lead to overly conservative behavior, infeasibility near tight input limits, and difficulty satisfying long-horizon STL tasks. To address these limitations, we propose a feasibility-aware learning framework that constructs trainable, time-varying High Order Control Barrier Function (HOCBF) constraints and hyperparameters that guarantee satisfaction of a given STL specification. We introduce a unified robustness measure that jointly captures STL satisfaction, constraint feasibility, and control-bound compliance, and propose a neural network architecture to generate control inputs that maximize this robustness. The resulting controller guarantees STL satisfaction with strictly feasible HOCBF constraints and requires no manual tuning. Simulation results demonstrate that the proposed framework maintains high STL robustness under tight input bounds and significantly outperforms fixed-parameter and non-adaptive baselines in complex environments.

---

### Prediction with Expert Advice under Local Differential Privacy

Authors: Ben Jacobsen, Kassem Fawaz
Published: 2025-12-07
Categories: cs.LG, cs.CR, cs.DS, stat.ML
arXiv: https://arxiv.org/abs/2512.06971v1

We study the classic problem of prediction with expert advice under the constraint of local differential privacy (LDP). In this context, we first show that a classical algorithm naturally satisfies LDP and then design two new algorithms that improve it: RW-AdaBatch and RW-Meta. For RW-AdaBatch, we exploit the limited-switching behavior induced by LDP to provide a novel form of privacy amplification that grows stronger on easier data, analogous to the shuffle model in offline learning. Drawing on the theory of random walks, we prove that this improvement carries essentially no utility cost. For RW-Meta, we develop a general method for privately selecting between experts that are themselves non-trivial learning algorithms, and we show that in the context of LDP this carries no extra privacy cost. In contrast, prior work has only considered data-independent experts. We also derive formal regret bounds that scale inversely with the degree of independence between experts. Our analysis is supplemented by evaluation on real-world data reported by hospitals during the COVID-19 pandemic; RW-Meta outperforms both the classical baseline and a state-of-the-art \textit{central} DP algorithm by 1.5-3$\times$ on the task of predicting which hospital will report the highest density of COVID patients each week.

---

### Comparing BFGS and OGR for Second-Order Optimization

Authors: Adrian Przybysz, Mikołaj Kołek, Franciszek Sobota, Jarek Duda
Published: 2025-12-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.06969v1

Estimating the Hessian matrix, especially for neural network training, is a challenging problem due to high dimensionality and cost. In this work, we compare the classical Sherman-Morrison update used in the popular BFGS method (Broy-den-Fletcher-Goldfarb-Shanno), which maintains a positive definite Hessian approximation under a convexity assumption, with a novel approach called Online Gradient Regression (OGR). OGR performs regression of gradients against positions using an exponential moving average to estimate second derivatives online, without requiring Hessian inversion. Unlike BFGS, OGR allows estimation of a general (not necessarily positive definite) Hessian and can thus handle non-convex structures. We evaluate both methods across standard test functions and demonstrate that OGR achieves faster convergence and improved loss, particularly in non-convex settings.

---

### Neuro-Vesicles: Neuromodulation Should Be a Dynamical System, Not a Tensor Decoration

Authors: Zilin Li, Weiwei Xu, Vicki Kane
Published: 2025-12-07
Categories: cs.NE
arXiv: https://arxiv.org/abs/2512.06966v1

We introduce Neuro-Vesicles, a framework that augments conventional neural networks with a missing computational layer: a dynamical population of mobile, discrete vesicles that live alongside the network rather than inside its tensors. Each vesicle is a self contained object v = (c, kappa, l, tau, s) carrying a vector payload, type label, location on the graph G = (V, E), remaining lifetime, and optional internal state. Vesicles are emitted in response to activity, errors, or meta signals; migrate along learned transition kernels; probabilistically dock at nodes; locally modify activations, parameters, learning rules, or external memory through content dependent release operators; and finally decay or are absorbed. This event based interaction layer reshapes neuromodulation. Instead of applying the same conditioning tensors on every forward pass, modulation emerges from the stochastic evolution of a vesicle population that can accumulate, disperse, trigger cascades, carve transient pathways, and write structured traces into topological memory. Dense, short lived vesicles approximate familiar tensor mechanisms such as FiLM, hypernetworks, or attention. Sparse, long lived vesicles resemble a small set of mobile agents that intervene only at rare but decisive moments. We give a complete mathematical specification of the framework, including emission, migration, docking, release, decay, and their coupling to learning; a continuous density relaxation that yields differentiable reaction diffusion dynamics on the graph; and a reinforcement learning view where vesicle control is treated as a policy optimized for downstream performance. We also outline how the same formalism extends to spiking networks and neuromorphic hardware such as the Darwin3 chip, enabling programmable neuromodulation on large scale brain inspired computers.

---

### VideoVLA: Video Generators Can Be Generalizable Robot Manipulators

Authors: Yichao Shen, Fangyun Wei, Zhiying Du, Yaobo Liang, Yan Lu, Jiaolong Yang, Nanning Zheng, Baining Guo
Published: 2025-12-07
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2512.06963v1

Generalization in robot manipulation is essential for deploying robots in open-world environments and advancing toward artificial general intelligence. While recent Vision-Language-Action (VLA) models leverage large pre-trained understanding models for perception and instruction following, their ability to generalize to novel tasks, objects, and settings remains limited. In this work, we present VideoVLA, a simple approach that explores the potential of transforming large video generation models into robotic VLA manipulators. Given a language instruction and an image, VideoVLA predicts an action sequence as well as the future visual outcomes. Built on a multi-modal Diffusion Transformer, VideoVLA jointly models video, language, and action modalities, using pre-trained video generative models for joint visual and action forecasting. Our experiments show that high-quality imagined futures correlate with reliable action predictions and task success, highlighting the importance of visual imagination in manipulation. VideoVLA demonstrates strong generalization, including imitating other embodiments' skills and handling novel objects. This dual-prediction strategy - forecasting both actions and their visual consequences - explores a paradigm shift in robot learning and unlocks generalization capabilities in manipulation systems.

---

### Learning Conditional Independence Differential Graphs From Time-Dependent Data

Authors: Jitendra K Tugnait
Published: 2025-12-07
Categories: stat.ML, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2512.06960v1

Estimation of differences in conditional independence graphs (CIGs) of two time series Gaussian graphical models (TSGGMs) is investigated where the two TSGGMs are known to have similar structure. The TSGGM structure is encoded in the inverse power spectral density (IPSD) of the time series. In several existing works, one is interested in estimating the difference in two precision matrices to characterize underlying changes in conditional dependencies of two sets of data consisting of independent and identically distributed (i.i.d.) observations. In this paper we consider estimation of the difference in two IPSDs to characterize the underlying changes in conditional dependencies of two sets of time-dependent data. Our approach accounts for data time dependencies unlike past work. We analyze a penalized D-trace loss function approach in the frequency domain for differential graph learning, using Wirtinger calculus. We consider both convex (group lasso) and non-convex (log-sum and SCAD group penalties) penalty/regularization functions. An alternating direction method of multipliers (ADMM) algorithm is presented to optimize the objective function. We establish sufficient conditions in a high-dimensional setting for consistency (convergence of the inverse power spectral density to true value in the Frobenius norm) and graph recovery. Both synthetic and real data examples are presented in support of the proposed approaches. In synthetic data examples, our log-sum-penalized differential time-series graph estimator significantly outperformed our lasso based differential time-series graph estimator which, in turn, significantly outperformed an existing lasso-penalized i.i.d. modeling approach, with $F_1$ score as the performance metric.

---

### Statistical analysis of Inverse Entropy-regularized Reinforcement Learning

Authors: Denis Belomestny, Alexey Naumov, Artemy Rubtsov, Sergey Samsonov
Published: 2025-12-07
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2512.06956v2

Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of the recovered reward: many reward functions can induce the same optimal policy, rendering the inverse problem ill-posed. In this paper, we develop a statistical framework for Inverse Entropy-regularized Reinforcement Learning that resolves this ambiguity by combining entropy regularization with a least-squares reconstruction of the reward from the soft Bellman residual. This combination yields a unique and well-defined so-called least-squares reward consistent with the expert policy. We model the expert demonstrations as a Markov chain with the invariant distribution defined by an unknown expert policy $π^\star$ and estimate the policy by a penalized maximum-likelihood procedure over a class of conditional distributions on the action space. We establish high-probability bounds for the excess Kullback--Leibler divergence between the estimated policy and the expert policy, accounting for statistical complexity through covering numbers of the policy class. These results lead to non-asymptotic minimax optimal convergence rates for the least-squares reward function, revealing the interplay between smoothing (entropy regularization), model complexity, and sample size. Our analysis bridges the gap between behavior cloning, inverse reinforcement learning, and modern statistical learning theory.

---

### Statistical analysis of Inverse Entropy-regularized Reinforcement Learning

Authors: Denis Belomestny, Alexey Naumov, Sergey Samsonov
Published: 2025-12-07
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2512.06956v1

Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of the recovered reward: many reward functions can induce the same optimal policy, rendering the inverse problem ill-posed. In this paper, we develop a statistical framework for Inverse Entropy-regularized Reinforcement Learning that resolves this ambiguity by combining entropy regularization with a least-squares reconstruction of the reward from the soft Bellman residual. This combination yields a unique and well-defined so-called least-squares reward consistent with the expert policy. We model the expert demonstrations as a Markov chain with the invariant distribution defined by an unknown expert policy $π^\star$ and estimate the policy by a penalized maximum-likelihood procedure over a class of conditional distributions on the action space. We establish high-probability bounds for the excess Kullback--Leibler divergence between the estimated policy and the expert policy, accounting for statistical complexity through covering numbers of the policy class. These results lead to non-asymptotic minimax optimal convergence rates for the least-squares reward function, revealing the interplay between smoothing (entropy regularization), model complexity, and sample size. Our analysis bridges the gap between behavior cloning, inverse reinforcement learning, and modern statistical learning theory.

---

### Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge

Authors: Ilia Larchenko, Gleb Zarin, Akash Karnatak
Published: 2025-12-07
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.06951v2

We present a vision-action policy that won 1st place in the 2025 BEHAVIOR Challenge - a large-scale benchmark featuring 50 diverse long-horizon household tasks in photo-realistic simulation, requiring bimanual manipulation, navigation, and context-aware decision making. Building on the Pi0.5 architecture, we introduce several innovations. Our primary contribution is correlated noise for flow matching, which improves training efficiency and enables correlation-aware inpainting for smooth action sequences. We also apply learnable mixed-layer attention and System 2 stage tracking for ambiguity resolution. Training employs multi-sample flow matching to reduce variance, while inference uses action compression and challenge-specific correction rules. Our approach achieves 26% q-score across all 50 tasks on both public and private leaderboards.

---

### Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge

Authors: Ilia Larchenko, Gleb Zarin, Akash Karnatak
Published: 2025-12-07
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.06951v1

We present a vision-action policy that won 1st place in the 2025 BEHAVIOR Challenge - a large-scale benchmark featuring 50 diverse long-horizon household tasks in photo-realistic simulation, requiring bimanual manipulation, navigation, and context-aware decision making. Building on the Pi0.5 architecture, we introduce several innovations. Our primary contribution is correlated noise for flow matching, which improves training efficiency and enables correlation-aware inpainting for smooth action sequences. We also apply learnable mixed-layer attention and System 2 stage tracking for ambiguity resolution. Training employs multi-sample flow matching to reduce variance, while inference uses action compression and challenge-specific correction rules. Our approach achieves 26% q-score across all 50 tasks on both public and private leaderboards.

---

### PARIS: Pruning Algorithm via the Representer theorem for Imbalanced Scenarios

Authors: Enrico Camporeale
Published: 2025-12-07
Categories: stat.ML, cs.LG, physics.space-ph
arXiv: https://arxiv.org/abs/2512.06950v1

The challenge of \textbf{imbalanced regression} arises when standard Empirical Risk Minimization (ERM) biases models toward high-frequency regions of the data distribution, causing severe degradation on rare but high-impact ``tail'' events. Existing strategies uch as loss re-weighting or synthetic over-sampling often introduce noise, distort the underlying distribution, or add substantial algorithmic complexity. We introduce \textbf{PARIS} (Pruning Algorithm via the Representer theorem for Imbalanced Scenarios), a principled framework that mitigates imbalance by \emph{optimizing the training set itself}. PARIS leverages the representer theorem for neural networks to compute a \textbf{closed-form representer deletion residual}, which quantifies the exact change in validation loss caused by removing a single training point \emph{without retraining}. Combined with an efficient Cholesky rank-one downdating scheme, PARIS performs fast, iterative pruning that eliminates uninformative or performance-degrading samples. We use a real-world space weather example, where PARIS reduces the training set by up to 75\% while preserving or improving overall RMSE, outperforming re-weighting, synthetic oversampling, and boosting baselines. Our results demonstrate that representer-guided dataset pruning is a powerful, interpretable, and computationally efficient approach to rare-event regression.

---

### Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology

Authors: Shravan Venkatraman, Muthu Subash Kavitha, Joe Dhanith P R, V Manikandarajan, Jia Wu
Published: 2025-12-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06949v3

Histopathology image segmentation is essential for delineating tissue structures in skin cancer diagnostics, but modeling spatial context and inter-tissue relationships remains a challenge, especially in regions with overlapping or morphologically similar tissues. Current convolutional neural network (CNN)-based approaches operate primarily on visual texture, often treating tissues as independent regions and failing to encode biological context. To this end, we introduce Neural Tissue Relation Modeling (NTRM), a novel segmentation framework that augments CNNs with a tissue-level graph neural network to model spatial and functional relationships across tissue types. NTRM constructs a graph over predicted regions, propagates contextual information via message passing, and refines segmentation through spatial projection. Unlike prior methods, NTRM explicitly encodes inter-tissue dependencies, enabling structurally coherent predictions in boundary-dense zones. On the benchmark Histopathology Non-Melanoma Skin Cancer Segmentation Dataset, NTRM outperforms state-of-the-art methods, achieving a robust Dice similarity coefficient that is 4.9\% to 31.25\% higher than the best-performing models among the evaluated approaches. Our experiments indicate that relational modeling offers a principled path toward more context-aware and interpretable histological segmentation, compared to local receptive-field architectures that lack tissue-level structural awareness. Our code is available at https://github.com/shravan-18/NTRM.

---

### Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology

Authors: Shravan Venkatraman, Muthu Subash Kavitha, Joe Dhanith P R, V Manikandarajan, Jia Wu
Published: 2025-12-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06949v1

Histopathology image segmentation is essential for delineating tissue structures in skin cancer diagnostics, but modeling spatial context and inter-tissue relationships remains a challenge, especially in regions with overlapping or morphologically similar tissues. Current convolutional neural network (CNN)-based approaches operate primarily on visual texture, often treating tissues as independent regions and failing to encode biological context. To this end, we introduce Neural Tissue Relation Modeling (NTRM), a novel segmentation framework that augments CNNs with a tissue-level graph neural network to model spatial and functional relationships across tissue types. NTRM constructs a graph over predicted regions, propagates contextual information via message passing, and refines segmentation through spatial projection. Unlike prior methods, NTRM explicitly encodes inter-tissue dependencies, enabling structurally coherent predictions in boundary-dense zones. On the benchmark Histopathology Non-Melanoma Skin Cancer Segmentation Dataset, NTRM outperforms state-of-the-art methods, achieving a robust Dice similarity coefficient that is 4.9\% to 31.25\% higher than the best-performing models among the evaluated approaches. Our experiments indicate that relational modeling offers a principled path toward more context-aware and interpretable histological segmentation, compared to local receptive-field architectures that lack tissue-level structural awareness. Our code is available at https://github.com/shravan-18/NTRM.

---

### Symmetric Aggregation of Conformity Scores for Efficient Uncertainty Sets

Authors: Nabil Alami, Jad Zakharia, Souhaib Ben Taieb
Published: 2025-12-07
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.06945v2

Access to multiple predictive models trained for the same task, whether in regression or classification, is increasingly common in many applications. Aggregating their predictive uncertainties to produce reliable and efficient uncertainty quantification is therefore a critical but still underexplored challenge, especially within the framework of conformal prediction (CP). While CP methods can generate individual prediction sets from each model, combining them into a single, more informative set remains a challenging problem. To address this, we propose SACP (Symmetric Aggregated Conformal Prediction), a novel method that aggregates nonconformity scores from multiple predictors. SACP transforms these scores into e-values and combines them using any symmetric aggregation function. This flexible design enables a robust, data-driven framework for selecting aggregation strategies that yield sharper prediction sets. We also provide theoretical insights that help justify the validity and performance of the SACP approach. Extensive experiments on diverse datasets show that SACP consistently improves efficiency and often outperforms state-of-the-art model aggregation baselines.

---

### Symmetric Aggregation of Conformity Scores for Efficient Uncertainty Sets

Authors: Nabil Alami, Jad Zakharia, Souhaib Ben Taieb
Published: 2025-12-07
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.06945v1

Access to multiple predictive models trained for the same task, whether in regression or classification, is increasingly common in many applications. Aggregating their predictive uncertainties to produce reliable and efficient uncertainty quantification is therefore a critical but still underexplored challenge, especially within the framework of conformal prediction (CP). While CP methods can generate individual prediction sets from each model, combining them into a single, more informative set remains a challenging problem. To address this, we propose SACP (Symmetric Aggregated Conformal Prediction), a novel method that aggregates nonconformity scores from multiple predictors. SACP transforms these scores into e-values and combines them using any symmetric aggregation function. This flexible design enables a robust, data-driven framework for selecting aggregation strategies that yield sharper prediction sets. We also provide theoretical insights that help justify the validity and performance of the SACP approach. Extensive experiments on diverse datasets show that SACP consistently improves efficiency and often outperforms state-of-the-art model aggregation baselines.

---