# Research Papers — 2025-12 · bundle page 143 of 175

> Full-text markdown of papers #7101–7150 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/143
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/142.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/144.md)

### TS-HINT: Enhancing Semiconductor Time Series Regression Using Attention Hints From Large Language Model Reasoning

Authors: Jonathan Adam Rico, Nagarajan Raghavan, Senthilnath Jayavelu
Published: 2025-12-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.05419v1

Existing data-driven methods rely on the extraction of static features from time series to approximate the material removal rate (MRR) of semiconductor manufacturing processes such as chemical mechanical polishing (CMP). However, this leads to a loss of temporal dynamics. Moreover, these methods require a large amount of data for effective training. In this paper, we propose TS-Hint, a Time Series Foundation Model (TSFM) framework, integrated with chain-of-thought reasoning which provides attention hints during training based on attention mechanism data and saliency data. Experimental results demonstrate the effectiveness of our model in limited data settings via few-shot learning and can learn directly from multivariate time series features.

---

### Performance Evaluation of Deep Learning for Tree Branch Segmentation in Autonomous Forestry Systems

Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green
Published: 2025-12-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.05418v1

UAV-based autonomous forestry operations require rapid and precise tree branch segmentation for safe navigation and automated pruning across varying pixel resolutions and operational conditions. We evaluate different deep learning methods at three resolutions (256x256, 512x512, 1024x1024) using the Urban Street Tree Dataset, employing standard metrics (IoU, Dice) and specialized measures including Thin Structure IoU (TS-IoU) and Connectivity Preservation Rate (CPR). Among 22 configurations tested, U-Net with MiT-B4 backbone achieves strong performance at 256x256. At 512x512, MiT-B4 leads in IoU, Dice, TS-IoU, and Boundary-F1. At 1024x1024, U-Net+MiT-B3 shows the best validation performance for IoU/Dice and precision, while U-Net++ excels in boundary quality. PSPNet provides the most efficient option (2.36/9.43/37.74 GFLOPs) with 25.7/19.6/11.8 percentage point IoU reductions compared to top performers at respective resolutions. These results establish multi-resolution benchmarks for accuracy-efficiency trade-offs in embedded forestry systems. Implementation is available at https://github.com/BennyLinntu/PerformanceTreeBranchSegmentation.

---

### Sepsis Prediction Using Graph Convolutional Networks over Patient-Feature-Value Triplets

Authors: Bozhi Dan, Di Wu, Ji Xu, Xiang Liu, Yiziting Zhu, Xin Shu, Yujie Li, Bin Yi
Published: 2025-12-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.05416v1

In the intensive care setting, sepsis continues to be a major contributor to patient illness and death; however, its timely detection is hindered by the complex, sparse, and heterogeneous nature of electronic health record (EHR) data. We propose Triplet-GCN, a single-branch graph convolutional model that represents each encounter as patient-feature-value triplets, constructs a bipartite EHR graph, and learns patient embeddings via a Graph Convolutional Network (GCN) followed by a lightweight multilayer perceptron (MLP). The pipeline applies type-specific preprocessing -- median imputation and standardization for numeric variables, effect coding for binary features, and mode imputation with low-dimensional embeddings for rare categorical attributes -- and initializes patient nodes with summary statistics, while retaining measurement values on edges to preserve "who measured what and by how much". In a retrospective, multi-center Chinese cohort (N = 648; 70/30 train-test split) drawn from three tertiary hospitals, Triplet-GCN consistently outperforms strong tabular baselines (KNN, SVM, XGBoost, Random Forest) across discrimination and balanced error metrics, yielding a more favorable sensitivity-specificity trade-off and improved overall utility for early warning. These findings indicate that encoding EHR as triplets and propagating information over a patient-feature graph produce more informative patient representations than feature-independent models, offering a simple, end-to-end blueprint for deployable sepsis risk stratification.

---

### Moving object detection from multi-depth images with an attention-enhanced CNN

Authors: Masato Shibukawa, Fumi Yoshida, Toshifumi Yanagisawa, Takashi Ito, Hirohisa Kurosaki, Makoto Yoshikawa, Kohki Kamiya, Ji-an Jiang, Wesley Fraser, JJ Kavelaars, Susan Benecchi, Anne Verbiscer et al.
Published: 2025-12-05
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.05415v1

One of the greatest challenges for detecting moving objects in the solar system from wide-field survey data is determining whether a signal indicates a true object or is due to some other source, like noise. Object verification has relied heavily on human eyes, which usually results in significant labor costs. In order to address this limitation and reduce the reliance on manual intervention, we propose a multi-input convolutional neural network integrated with a convolutional block attention module. This method is specifically tailored to enhance the moving object detection system that we have developed and used previously. The current method introduces two innovations. This first one is a multi-input architecture that processes multiple stacked images simultaneously. The second is the incorporation of the convolutional block attention module which enables the model to focus on essential features in both spatial and channel dimensions. These advancements facilitate efficient learning from multiple inputs, leading to more robust detection of moving objects. The performance of the model is evaluated on a dataset consisting of approximately 2,000 observational images. We achieved an accuracy of nearly 99% with AUC (an Area Under the Curve) of >0.99. These metrics indicate that the proposed model achieves excellent classification performance. By adjusting the threshold for object detection, the new model reduces the human workload by more than 99% compared to manual verification.

---

### LMSpell: Spell Correction with Pre-Trained Language Models

Authors: Akesh Gunathilake, Nadil Karunarathna, Tharusha Bandaranayake, Nisansa de Silva, Surangika Ranathunga, Nevidu Jayatilleke
Published: 2025-12-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.05414v4

Spell correction is still a challenging problem for many languages, especially low-resource languages (LRLs). While pre-trained language models (PLMs) have been employed for spell correction, there has been no proper comparison across PLMs. We present the first empirical study on the effectiveness of the three types of PLMs for spell correction across multiple languages, including low-resource languages. We show that even relatively small PLMs such as the 270M-parameter Gemma 3 and mBART50, when fine-tuned on a dataset of only 5k sentences, can outperform rule-based spell correctors, highlighting a practical pathway for building effective spell correction systems with limited data. We also present a case study with Sinhala to shed light on the plight of spell correction for LRLs.

---

### YOLO and SGBM Integration for Autonomous Tree Branch Detection and Depth Estimation in Radiata Pine Pruning Applications

Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green
Published: 2025-12-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.05412v1

Manual pruning of radiata pine trees poses significant safety risks due to extreme working heights and challenging terrain. This paper presents a computer vision framework that integrates YOLO object detection with Semi-Global Block Matching (SGBM) stereo vision for autonomous drone-based pruning operations. Our system achieves precise branch detection and depth estimation using only stereo camera input, eliminating the need for expensive LiDAR sensors. Experimental evaluation demonstrates YOLO's superior performance over Mask R-CNN, achieving 82.0% mAPmask50-95 for branch segmentation. The integrated system accurately localizes branches within a 2 m operational range, with processing times under one second per frame. These results establish the feasibility of cost-effective autonomous pruning systems that enhance worker safety and operational efficiency in commercial forestry.

---

### A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems

Authors: Pranav Pushkar Mishra, Kranti Prakash Yeole, Ramyashree Keshavamurthy, Mokshit Bharat Surana, Fatemeh Sarayloo
Published: 2025-12-05
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2512.05411v2

In enterprise settings, efficiently retrieving relevant information from large and complex knowledge bases is essential for operational productivity and informed decision-making. This research presents a systematic empirical framework for metadata enrichment using large language models (LLMs) to enhance document retrieval in Retrieval-Augmented Generation (RAG) systems. Our approach employs a structured pipeline that dynamically generates meaningful metadata for document segments, substantially improving their semantic representations and retrieval accuracy. Through a controlled 3 X 3 experimental matrix, we compare three chunking strategies -- semantic, recursive, and naive -- and evaluate their interactions with three embedding techniques -- content-only, TF-IDF weighted, and prefix-fusion -- isolating the contribution of each component through ablation analysis. The results demonstrate that metadata-enriched approaches consistently outperform content-only baselines, with recursive chunking paired with TF-IDF weighted embeddings yielding 82.5% precision and naive chunking with prefix-fusion achieving the strongest ranking quality (NDCG 0.813). Our evaluation employs cross-encoder reranking for silver-standard ground truth generation, with statistical significance confirmed via Bonferroni-corrected paired t-tests. These findings confirm that metadata enrichment improves vector space organization and retrieval effectiveness while maintaining sub-30 ms P95 latency, providing a quantitative decision framework for deploying high-performance, scalable RAG systems in enterprise settings.

---

### Genetic Algorithms For Parameter Optimization for Disparity Map Generation of Radiata Pine Branch Images

Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green
Published: 2025-12-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.05410v1

Traditional stereo matching algorithms like Semi-Global Block Matching (SGBM) with Weighted Least Squares (WLS) filtering offer speed advantages over neural networks for UAV applications, generating disparity maps in approximately 0.5 seconds per frame. However, these algorithms require meticulous parameter tuning. We propose a Genetic Algorithm (GA) based parameter optimization framework that systematically searches for optimal parameter configurations for SGBM and WLS, enabling UAVs to measure distances to tree branches with enhanced precision while maintaining processing efficiency. Our contributions include: (1) a novel GA-based parameter optimization framework that eliminates manual tuning; (2) a comprehensive evaluation methodology using multiple image quality metrics; and (3) a practical solution for resource-constrained UAV systems. Experimental results demonstrate that our GA-optimized approach reduces Mean Squared Error by 42.86% while increasing Peak Signal-to-Noise Ratio and Structural Similarity by 8.47% and 28.52%, respectively, compared with baseline configurations. Furthermore, our approach demonstrates superior generalization performance across varied imaging conditions, which is critcal for real-world forestry applications.

---

### SQ-format: A Unified Sparse-Quantized Hardware-friendly Data Format for LLMs

Authors: Ruixuan Huang, Hao Zeng, Hantao Huang, Jinyuan Shi, Minghui Yu, Ian En-Hsu Yen, Shuai Wang
Published: 2025-12-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.05409v1

Post-training quantization (PTQ) plays a crucial role in the democratization of large language models (LLMs). However, existing low-bit quantization and sparsification techniques are difficult to balance accuracy and efficiency due to the limited hardware support. For example, W4A8 can only achieve the same peak TOPS as W8A8 whereas the GPU-supported sparse data format (2:4 semi-structure sparse) is seldomly adopted due to the loss of accuracy. To bridge this gap, in this paper, we propose the Sparse-Quantized Format (SQ-format), which is a unified data format for quantization and sparsification potentially easily supported by new hardware and existing GPUs. SQ-format makes use of the fact that sparse matrix can be accelerated in high-precision, and low-precision matrix multiplication can also be accelerated accordingly. As such, SQ-format is proposed to achieve Pareto improvement between performance and throughput. This format is particularly suitable for activations with outlier inequality status and makes their static compression possible. We show the state-of-the-art PTQ performance with SQ-format, propose the hardware required to support it, and further offer the design exploration and insights for the next-generation AI accelerators.

---

### RevoNAD: Reflective Evolutionary Exploration for Neural Architecture Design

Authors: Gyusam Chang, Jeongyoon Yoon, Shin han yi, JaeHyeok Lee, Sujin Jang, Sangpil Kim
Published: 2025-12-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.05403v1

Recent progress in leveraging large language models (LLMs) has enabled Neural Architecture Design (NAD) systems to generate new architecture not limited from manually predefined search space. Nevertheless, LLM-driven generation remains challenging: the token-level design loop is discrete and non-differentiable, preventing feedback from smoothly guiding architectural improvement. These methods, in turn, commonly suffer from mode collapse into redundant structures or drift toward infeasible designs when constructive reasoning is not well grounded. We introduce RevoNAD, a reflective evolutionary orchestrator that effectively bridges LLM-based reasoning with feedback-aligned architectural search. First, RevoNAD presents a Multi-round Multi-expert Consensus to transfer isolated design rules into meaningful architectural clues. Then, Adaptive Reflective Exploration adjusts the degree of exploration leveraging reward variance; it explores when feedback is uncertain and refines when stability is reached. Finally, Pareto-guided Evolutionary Selection effectively promotes architectures that jointly optimize accuracy, efficiency, latency, confidence, and structural diversity. Across CIFAR10, CIFAR100, ImageNet16-120, COCO-5K, and Cityscape, RevoNAD achieves state-of-the-art performance. Ablation and transfer studies further validate the effectiveness of RevoNAD in allowing practically reliable, and deployable neural architecture design.

---

### Smart Timing for Mining: A Deep Learning Framework for Bitcoin Hardware ROI Prediction

Authors: Sithumi Wickramasinghe, Bikramjit Das, Dorien Herremans
Published: 2025-12-05
Categories: cs.LG, cs.AI, cs.CE, cs.NE
arXiv: https://arxiv.org/abs/2512.05402v2

Bitcoin mining hardware acquisition requires strategic timing due to volatile markets, rapid technological obsolescence, and protocol-driven revenue cycles. Despite mining's evolution into a capital-intensive industry, there is little guidance on when to purchase new Application-Specific Integrated Circuit (ASIC) hardware, and no prior computational frameworks address this decision problem. We address this gap by formulating hardware acquisition as a time series classification task, predicting whether purchasing ASIC machines yields profitable (Return on Investment (ROI) >= 1), marginal (0 < ROI < 1), or unprofitable (ROI <= 0) returns within one year. We propose MineROI-Net, an open-source Transformer-based architecture designed to capture multi-scale temporal patterns in mining profitability. Evaluated on data from 20 ASIC miners released between 2015 and 2024 across diverse market regimes, MineROI-Net outperforms recurrent, convolutional, and attention-based baselines, achieving 83.2% accuracy and 83.5% macro F1-score. The model demonstrates strong economic relevance, achieving 97.8% precision in detecting unprofitable periods and 81.5% precision in detecting profitable ones, while avoiding misclassifying profitable scenarios as unprofitable and vice versa. These results indicate that MineROI-Net offers a practical, data-driven tool for timing mining hardware acquisitions, potentially reducing financial risk in capital-intensive mining operations.

---

### The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos

Authors: Zhuoyuan Wu, Xurui Yang, Jiahui Huang, Yue Wang, Jun Gao
Published: 2025-12-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.05398v1

Estimating accurate camera poses, 3D scene geometry, and object motion from in-the-wild videos is a long-standing challenge for classical structure from motion pipelines due to the presence of dynamic objects. Recent learning-based methods attempt to overcome this challenge by training motion estimators to filter dynamic objects and focus on the static background. However, their performance is largely limited by the availability of large-scale motion segmentation datasets, resulting in inaccurate segmentation and, therefore, inferior structural 3D understanding. In this work, we introduce the Dynamic Prior (\ourmodel) to robustly identify dynamic objects without task-specific training, leveraging the powerful reasoning capabilities of Vision-Language Models (VLMs) and the fine-grained spatial segmentation capacity of SAM2. \ourmodel can be seamlessly integrated into state-of-the-art pipelines for camera pose optimization, depth reconstruction, and 4D trajectory estimation. Extensive experiments on both synthetic and real-world videos demonstrate that \ourmodel not only achieves state-of-the-art performance on motion segmentation, but also significantly improves accuracy and robustness for structural 3D understanding.

---

### Simulating Life Paths with Digital Twins: AI-Generated Future Selves Influence Decision-Making and Expand Human Choice

Authors: Rachel Poonsiriwong, Chayapatr Archiwaranguprok, Constanze Albrecht, Peggy Yin, Nattavudh Powdthavee, Hal Hershfield, Monchai Lertsutthiwong, Kavin Winson, Pat Pataranutaporn
Published: 2025-12-05
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2512.05397v2

Major life transitions demand high-stakes decisions, yet people often struggle to imagine how their future selves will live with the consequences. To support this limited capacity for mental time travel, we introduce AI-enabled digital twins that have ``lived through'' simulated life scenarios. Rather than predicting optimal outcomes, these simulations extend prospective cognition by making alternative futures vivid enough to support deliberation without assuming which path is best. We evaluate this idea in a randomized controlled study (N=192) using multimodal synthesis - facial age progression, voice cloning, and large language model dialogue - to create personalized avatars representing participants 30 years forward. Young adults 18 to 28 years old described pending binary decisions and were assigned to guided imagination or one of four avatar conditions: single-option, balanced dual-option, or expanded three-option with a system-generated novel alternative. Results showed asymmetric effects: single-sided avatars increased shifts toward the presented option, while balanced presentation produced movement toward both. Introducing a system-generated third option increased adoption of this new alternative compared to control, suggesting that AI-generated future selves can expand choice by surfacing paths that might otherwise go unnoticed. Participants rated evaluative reasoning and eudaimonic meaning-making as more important than emotional or visual vividness. Perceived persuasiveness and baseline agency predicted decision change. These findings advance understanding of AI-mediated episodic prospection and raise questions about autonomy in AI-augmented decisions.

---

### Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability

Authors: Shizhan Liu, Xinran Deng, Zhuoyi Yang, Jiayan Teng, Xiaotao Gu, Jie Tang
Published: 2025-12-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.05394v3

Latent diffusion models pair VAEs with diffusion backbones, and the structure of VAE latents strongly influences the difficulty of diffusion training. However, existing video VAEs typically focus on reconstruction fidelity, overlooking latent structure. We present a statistical analysis of video VAE latent spaces and identify two spectral properties essential for diffusion training: a spatio-temporal frequency spectrum biased toward low frequencies, and a channel-wise eigenspectrum dominated by a few modes. To induce these properties, we propose two lightweight, backbone-agnostic regularizers: Local Correlation Regularization and Latent Masked Reconstruction. Experiments show that our Spectral-Structured VAE (SSVAE) achieves a $3\times$ speedup in text-to-video generation convergence and a 10\% gain in video reward, outperforming strong open-source VAEs. The code is available at https://github.com/zai-org/SSVAE.

---

### LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models

Authors: Qingqiao Hu, Weimin Lyu, Meilong Xu, Kehan Qi, Xiaoling Hu, Saumya Gupta, Jiawei Zhou, Chao Chen
Published: 2025-12-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.05391v3

Whole Slide Image (WSI) MLLMs are difficult to build and deploy because gigapixel slides induce thousands of visual tokens, while only a small fraction of regions is diagnostically relevant. Existing slide-level pathology MLLMs typically combine heavy slide-level encoders with long visual prefixes, making end-to-end slide-level development and deployment expensive under limited computational resources. We revisit this regime and show that WSI tile features are highly redundant at both global and local scales, while task-relevant evidence is sparse and query-dependent. We therefore introduce LoC-Path, a resource-efficient slide-level MLLM that compresses before fusion. LoC-Path uses a Sparse Token Merger (STM) and an MAE-pretrained resampler to replace expensive slide-level encoding with a compact latent interface, then uses a Token Importance Scorer (TIS) to select the most relevant latents and a Cross-Attention Routing Adapter (CARA) to fuse them into a few LLM decoder layers. This design lowers both multimodal tuning cost and inference-time latency/memory by avoiding heavy slide-level encoding and long visual prefixes. Extensive experiments show that LoC-Path remains competitive with prior slide-level MLLMs while making end-to-end development and deployment more practical under limited computational resources.

---

### Learning from Self Critique and Refinement for Faithful LLM Summarization

Authors: Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari, Cem Koc, Oncel Tuzel, Raviteja Vemulapalli
Published: 2025-12-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.05387v2

Large Language Models (LLMs) often suffer from hallucinations: output content that is not grounded in the input context, when performing long-form text generation tasks such as summarization. Prior works have shown that hallucinations can be reduced by iteratively critiquing and refining previously generated outputs using either the same model or a more powerful teacher model as the critique. However, these approaches either require additional test-time compute or assume access to more powerful teacher models, making them costly and less practical. In this work, we propose Self Critique and Refinement-based Preference Optimization (SCRPO), which is a self-supervised training framework that first constructs a preference dataset by leveraging the LLM's own critique and refinement capabilities, and then applies preference learning to improve the same LLM for faithful summarization. Experiments on three summarization benchmarks (XSUM CNNDM and SAMSum), demonstrate that our approach outperforms state-of-the-art self-supervised learning methods in terms of faithfulness metrics while either maintaining or improving other metrics that measure the overall quality of the summary. Moreover, compared to test-time refinement, our approach not only improves efficiency but also results in more faithful summaries.

---

### Generalization Beyond Benchmarks: Evaluating Learnable Protein-Ligand Scoring Functions on Unseen Targets

Authors: Jakub Kopko, David Graber, Saltuk Mustafa Eyrilmez, Stanislav Mazurenko, David Bednar, Jiri Sedlar, Josef Sivic
Published: 2025-12-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.05386v1

As machine learning becomes increasingly central to molecular design, it is vital to ensure the reliability of learnable protein-ligand scoring functions on novel protein targets. While many scoring functions perform well on standard benchmarks, their ability to generalize beyond training data remains a significant challenge. In this work, we evaluate the generalization capability of state-of-the-art scoring functions on dataset splits that simulate evaluation on targets with a limited number of known structures and experimental affinity measurements. Our analysis reveals that the commonly used benchmarks do not reflect the true challenge of generalizing to novel targets. We also investigate whether large-scale self-supervised pretraining can bridge this generalization gap and we provide preliminary evidence of its potential. Furthermore, we probe the efficacy of simple methods that leverage limited test-target data to improve scoring function performance. Our findings underscore the need for more rigorous evaluation protocols and offer practical guidance for designing scoring functions with predictive power extending to novel protein targets.

---

### ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models

Authors: Yingjie Xia, Tao Liu, Jinglei Shi, Qingsong Xie, Heng Guo, Jian Yang, Xi Wang
Published: 2025-12-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.05385v2

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes severe performance degradation under high compression ratios, limiting its practical benefits. In this work, we uncover an overlooked failure mode in shallow-layer attention pruning: attention scores in early decoder layers can become unreliable indicators of token utility, resulting in unstable token selection under aggressive compression. We show that this effect arises from the joint influence of insufficient token interaction, content-agnostic positional bias, and redundancy among high-attention tokens, which together distort attention-based importance estimation before informative representations fully emerge. Motivated by this insight, we propose ShaRP, a unified pruning framework that restores reliable attention-based token selection by jointly improving local information aggregation, calibrating positional bias, and reducing redundancy. Extensive evaluations show that ShaRP preserves about 97.2% of the original performance while reducing TFLOPs by 86% and achieving a 5.1x speedup in the prefilling stage, providing a scalable solution for efficient training-free VLLM inference.

---

### Fuzzing the brain: Automated stress testing for the safety of ML-driven neurostimulation

Authors: Mara Downing, Matthew Peng, Jacob Granley, Michael Beyeler, Tevfik Bultan
Published: 2025-12-05
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2512.05383v1

Objective: Machine learning (ML) models are increasingly used to generate electrical stimulation patterns in neuroprosthetic devices such as visual prostheses. While these models promise precise and personalized control, they also introduce new safety risks when model outputs are delivered directly to neural tissue. We propose a systematic, quantitative approach to detect and characterize unsafe stimulation patterns in ML-driven neurostimulation systems. Approach: We adapt an automated software testing technique known as coverage-guided fuzzing to the domain of neural stimulation. Here, fuzzing performs stress testing by perturbing model inputs and tracking whether resulting stimulation violates biophysical limits on charge density, instantaneous current, or electrode co-activation. The framework treats encoders as black boxes and steers exploration with coverage metrics that quantify how broadly test cases span the space of possible outputs and violation types. Main results: Applied to deep stimulus encoders for the retina and cortex, the method systematically reveals diverse stimulation regimes that exceed established safety limits. Two violation-output coverage metrics identify the highest number and diversity of unsafe outputs, enabling interpretable comparisons across architectures and training strategies. Significance: Violation-focused fuzzing reframes safety assessment as an empirical, reproducible process. By transforming safety from a training heuristic into a measurable property of the deployed model, it establishes a foundation for evidence-based benchmarking, regulatory readiness, and ethical assurance in next-generation neural interfaces.

---

### Mitigating Self-Preference by Authorship Obfuscation

Authors: Taslim Mahbub, Shi Feng
Published: 2025-12-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.05379v1

Language models (LMs) judges are widely used to evaluate the quality of LM outputs. Despite many advantages, LM judges display concerning biases that can impair their integrity in evaluations. One such bias is self-preference: LM judges preferring their own answers over those produced by other LMs or humans. The bias is hard to eliminate as frontier LM judges can distinguish their own outputs from those of others, even when the evaluation candidates are not labeled with their sources. In this paper, we investigate strategies to mitigate self-preference by reducing the LM judges' ability to recognize their own outputs. We apply black-box perturbations to evaluation candidates in pairwise comparison to obfuscate the authorship and reduce self-recognition. We find that perturbations as simple as synonym replacement for a few words predictably reduce self-preference. However, we also uncover fundamental challenges to eliminating the bias: when we extrapolate our perturbations to a more complete neutralization of stylistic differences between the evaluation candidates, self-preference recovers. Our findings suggest that self-recognition and self-preference can happen on many semantic levels, and complete mitigation remains challenging despite promising initial results.

---

### China Regional 3km Downscaling Based on Residual Corrective Diffusion Model

Authors: Honglu Sun, Hao Jing, Zhixiang Dai, Sa Xiao, Wei Xue, Jian Sun, Qifeng Lu
Published: 2025-12-05
Categories: cs.LG, cs.AI, physics.ao-ph
arXiv: https://arxiv.org/abs/2512.05377v4

A fundamental challenge in numerical weather prediction is to efficiently produce high-resolution forecasts. A common solution is applying downscaling methods, which include dynamical downscaling and statistical downscaling, to the outputs of global models. This work focuses on statistical downscaling, which establishes statistical relationships between low-resolution and high-resolution historical data using statistical models. Deep learning has emerged as a powerful tool for this task, giving rise to various high-performance super-resolution models, which can be directly applied for downscaling, such as diffusion models and Generative Adversarial Networks. This work relies on a diffusion-based downscaling framework named CorrDiff. In contrast to the original work of CorrDiff, the region considered in this work is nearly 40 times larger, and we not only consider surface variables as in the original work, but also encounter high-level variables (six pressure levels) as target downscaling variables. In addition, a global residual connection is added to improve accuracy. In order to generate the 3km forecasts for the China region, we apply our trained models to the 25km global grid forecasts of CMA-GFS, an operational global model of the China Meteorological Administration (CMA), and SFF, a data-driven deep learning-based weather model developed from Spherical Fourier Neural Operators (SFNO). CMA-MESO, a high-resolution regional model, is chosen as the baseline model. The experimental results demonstrate that the forecasts downscaled by our method generally outperform the direct forecasts of CMA-MESO in terms of MAE for the target variables. Our forecasts of radar composite reflectivity show that CorrDiff, as a generative model, can generate fine-scale details that lead to more realistic predictions compared to the corresponding deterministic regression models.

---

### Please Don't Kill My Vibe: Empowering Agents with Data Flow Control

Authors: Charlie Summers, Haneen Mohammed, Eugene Wu
Published: 2025-12-05
Categories: cs.CR, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2512.05374v1

The promise of Large Language Model (LLM) agents is to perform complex, stateful tasks. This promise is stunted by significant risks - policy violations, process corruption, and security flaws - that stem from the lack of visibility and mechanisms to manage undesirable data flows produced by agent actions. Today, agent workflows are responsible for enforcing these policies in ad hoc ways. Just as data validation and access controls shifted from the application to the DBMS, freeing application developers from these concerns, we argue that systems should support Data Flow Controls (DFCs) and enforce DFC policies natively. This paper describes early work developing a portable instance of DFC for DBMSes and outlines a broader research agenda toward DFC for agent ecosystems.

---

### Text Rationalization for Robust Causal Effect Estimation

Authors: Lijinghua Zhang, Hengrui Cai
Published: 2025-12-05
Categories: cs.LG, cs.AI, cs.CL, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2512.05373v1

Recent advances in natural language processing have enabled the increasing use of text data in causal inference, particularly for adjusting confounding factors in treatment effect estimation. Although high-dimensional text can encode rich contextual information, it also poses unique challenges for causal identification and estimation. In particular, the positivity assumption, which requires sufficient treatment overlap across confounder values, is often violated at the observational level, when massive text is represented in feature spaces. Redundant or spurious textual features inflate dimensionality, producing extreme propensity scores, unstable weights, and inflated variance in effect estimates. We address these challenges with Confounding-Aware Token Rationalization (CATR), a framework that selects a sparse necessary subset of tokens using a residual-independence diagnostic designed to preserve confounding information sufficient for unconfoundedness. By discarding irrelevant texts while retaining key signals, CATR mitigates observational-level positivity violations and stabilizes downstream causal effect estimators. Experiments on synthetic data and a real-world study using the MIMIC-III database demonstrate that CATR yields more accurate, stable, and interpretable causal effect estimates than existing baselines.

---

### ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications

Authors: Changwen Xing, SamZaak Wong, Xinlai Wan, Yanfeng Lu, Mengli Zhang, Zebin Ma, Lei Qi, Zhengxiong Li, Nan Guan, Zhe Jiang, Xi Wang, Jun Yang
Published: 2025-12-05
Categories: cs.AI, cs.AR
arXiv: https://arxiv.org/abs/2512.05371v1

While Large Language Models (LLMs) demonstrate immense potential for automating integrated circuit (IC) development, their practical deployment is fundamentally limited by restricted context windows. Existing context-extension methods struggle to achieve effective semantic modeling and thorough multi-hop reasoning over extensive, intricate circuit specifications. To address this, we introduce ChipMind, a novel knowledge graph-augmented reasoning framework specifically designed for lengthy IC specifications. ChipMind first transforms circuit specifications into a domain-specific knowledge graph ChipKG through the Circuit Semantic-Aware Knowledge Graph Construction methodology. It then leverages the ChipKG-Augmented Reasoning mechanism, combining information-theoretic adaptive retrieval to dynamically trace logical dependencies with intent-aware semantic filtering to prune irrelevant noise, effectively balancing retrieval completeness and precision. Evaluated on an industrial-scale specification reasoning benchmark, ChipMind significantly outperforms state-of-the-art baselines, achieving an average improvement of 34.59% (up to 72.73%). Our framework bridges a critical gap between academic research and practical industrial deployment of LLM-aided Hardware Design (LAD).

---

### Enhancing Dimensionality Prediction in Hybrid Metal Halides via Feature Engineering and Class-Imbalance Mitigation

Authors: Mariia Karabin, Isaac Armstrong, Leo Beck, Paulina Apanel, Markus Eisenbach, David B. Mitzi, Hanna Terletska, Hendrik Heinz
Published: 2025-12-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.05367v1

We present a machine learning framework for predicting the structural dimensionality of hybrid metal halides (HMHs), including organic-inorganic perovskites, using a combination of chemically-informed feature engineering and advanced class-imbalance handling techniques. The dataset, consisting of 494 HMH structures, is highly imbalanced across dimensionality classes (0D, 1D, 2D, 3D), posing significant challenges to predictive modeling. This dataset was later augmented to 1336 via the Synthetic Minority Oversampling Technique (SMOTE) to mitigate the effects of the class imbalance. We developed interaction-based descriptors and integrated them into a multi-stage workflow that combines feature selection, model stacking, and performance optimization to improve dimensionality prediction accuracy. Our approach significantly improves F1-scores for underrepresented classes, achieving robust cross-validation performance across all dimensionalities.

---

### MCP-AI: Protocol-Driven Intelligence Framework for Autonomous Reasoning in Healthcare

Authors: Zag ElSayed, Craig Erickson, Ernest Pedapati
Published: 2025-12-05
Categories: cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2512.05365v1

Healthcare AI systems have historically faced challenges in merging contextual reasoning, long-term state management, and human-verifiable workflows into a cohesive framework. This paper introduces a completely innovative architecture and concept: combining the Model Context Protocol (MCP) with a specific clinical application, known as MCP-AI. This integration allows intelligent agents to reason over extended periods, collaborate securely, and adhere to authentic clinical logic, representing a significant shift away from traditional Clinical Decision Support Systems (CDSS) and prompt-based Large Language Models (LLMs). As healthcare systems become more complex, the need for autonomous, context-aware clinical reasoning frameworks has become urgent. We present MCP-AI, a novel architecture for explainable medical decision-making built upon the Model Context Protocol (MCP) a modular, executable specification for orchestrating generative and descriptive AI agents in real-time workflows. Each MCP file captures clinical objectives, patient context, reasoning state, and task logic, forming a reusable and auditable memory object. Unlike conventional CDSS or stateless prompt-based AI systems, MCP-AI supports adaptive, longitudinal, and collaborative reasoning across care settings. MCP-AI is validated through two use cases: (1) diagnostic modeling of Fragile X Syndrome with comorbid depression, and (2) remote coordination for Type 2 Diabetes and hypertension. In either scenario, the protocol facilitates physician-in-the-loop validation, streamlines clinical processes, and guarantees secure transitions of AI responsibilities between healthcare providers. The system connects with HL7/FHIR interfaces and adheres to regulatory standards, such as HIPAA and FDA SaMD guidelines. MCP-AI provides a scalable basis for interpretable, composable, and safety-oriented AI within upcoming clinical environments.

---

### Transformer-Enabled Diachronic Analysis of Vedic Sanskrit: Neural Methods for Quantifying Types of Language Change

Authors: Ananth Hariharan, David Mortensen
Published: 2025-12-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.05364v1

This study demonstrates how hybrid neural-symbolic methods can yield significant new insights into the evolution of a morphologically rich, low-resource language. We challenge the naive assumption that linguistic change is simplification by quantitatively analyzing over 2,000 years of Sanskrit, demonstrating how weakly-supervised hybrid methods can yield new insights into the evolution of morphologically rich, low-resource languages. Our approach addresses data scarcity through weak supervision, using 100+ high-precision regex patterns to generate pseudo-labels for fine-tuning a multilingual BERT. We then fuse symbolic and neural outputs via a novel confidence-weighted ensemble, creating a system that is both scalable and interpretable. Applying this framework to a 1.47-million-word diachronic corpus, our ensemble achieves a 52.4% overall feature detection rate. Our findings reveal that Sanskrit's overall morphological complexity does not decrease but is instead dynamically redistributed: while earlier verbal features show cyclical patterns of decline, complexity shifts to other domains, evidenced by a dramatic expansion in compounding and the emergence of new philosophical terminology. Critically, our system produces well-calibrated uncertainty estimates, with confidence strongly correlating with accuracy (Pearson r = 0.92) and low overall calibration error (ECE = 0.043), bolstering the reliability of these findings for computational philology.

---

### PoolNet: Deep Learning for 2D to 3D Video Process Validation

Authors: Sanchit Kaul, Joseph Luna, Shray Arora
Published: 2025-12-05
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.05362v1

Lifting Structure-from-Motion (SfM) information from sequential and non-sequential image data is a time-consuming and computationally expensive task. In addition to this, the majority of publicly available data is unfit for processing due to inadequate camera pose variation, obscuring scene elements, and noisy data. To solve this problem, we introduce PoolNet, a versatile deep learning framework for frame-level and scene-level validation of in-the-wild data. We demonstrate that our model successfully differentiates SfM ready scenes from those unfit for processing while significantly undercutting the amount of time state of the art algorithms take to obtain structure-from-motion data.

---

### FieldSeer I: Physics-Guided World Models for Long-Horizon Electromagnetic Dynamics under Partial Observability

Authors: Ziheng Guo, Fang Wu, Maoxiong Zhao, Chaoqun Fang, Yang Bu
Published: 2025-12-05
Categories: physics.optics, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2512.05361v1

We introduce FieldSeer I, a geometry-aware world model that forecasts electromagnetic field dynamics from partial observations in 2-D TE waveguides. The model assimilates a short prefix of observed fields, conditions on a scalar source action and structure/material map, and generates closed-loop rollouts in the physical domain. Training in a symmetric-log domain ensures numerical stability. Evaluated on a reproducible FDTD benchmark (200 unique simulations, structure-wise split), FieldSeer I achieves higher suffix fidelity than GRU and deterministic baselines across three practical settings: (i) software-in-the-loop filtering (64x64, P=80->Q=80), (ii) offline single-file rollouts (80x140, P=240->Q=40), and (iii) offline multi-structure rollouts (80x140, P=180->Q=100). Crucially, it enables edit-after-prefix geometry modifications without re-assimilation. Results demonstrate that geometry-conditioned world models provide a practical path toward interactive digital twins for photonic design.

---

### Group Orthogonal Low-Rank Adaptation for RGB-T Tracking

Authors: Zekai Shao, Yufan Hu, Jingyuan Liu, Bin Fan, Hongmin Liu
Published: 2025-12-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.05359v2

Parameter-efficient fine-tuning has emerged as a promising paradigm in RGB-T tracking, enabling downstream task adaptation by freezing pretrained parameters and fine-tuning only a small set of parameters. This set forms a rank space made up of multiple individual ranks, whose expressiveness directly shapes the model's adaptability. However, quantitative analysis reveals low-rank adaptation exhibits significant redundancy in the rank space, with many ranks contributing almost no practical information. This hinders the model's ability to learn more diverse knowledge to address the various challenges in RGB-T tracking. To address this issue, we propose the Group Orthogonal Low-Rank Adaptation (GOLA) framework for RGB-T tracking, which effectively leverages the rank space through structured parameter learning. Specifically, we adopt a rank decomposition partitioning strategy utilizing singular value decomposition to quantify rank importance, freeze crucial ranks to preserve the pretrained priors, and cluster the redundant ranks into groups to prepare for subsequent orthogonal constraints. We further design an inter-group orthogonal constraint strategy. This constraint enforces orthogonality between rank groups, compelling them to learn complementary features that target diverse challenges, thereby alleviating information redundancy. Experimental results demonstrate that GOLA effectively reduces parameter redundancy and enhances feature representation capabilities, significantly outperforming state-of-the-art methods across four benchmark datasets and validating its effectiveness in RGB-T tracking tasks.

---

### AI & Human Co-Improvement for Safer Co-Superintelligence

Authors: Jason Weston, Jakob Foerster
Published: 2025-12-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.05356v2

Self-improvement is a goal currently exciting the field of AI, but is fraught with danger, and may take time to fully achieve. We advocate that a more achievable and better goal for humanity is to maximize co-improvement: collaboration between human researchers and AIs to achieve co-superintelligence. That is, specifically targeting improving AI systems' ability to work with human researchers to conduct AI research together, from ideation to experimentation, in order to both accelerate AI research and to generally endow both AIs and humans with safer superintelligence through their symbiosis. Focusing on including human research improvement in the loop will both get us there faster, and more safely.

---

### SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training

Authors: Yang Zheng, Hao Tan, Kai Zhang, Peng Wang, Leonidas Guibas, Gordon Wetzstein, Wang Yifan
Published: 2025-12-05
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2512.05354v2

The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches based on diffusion or optimization are ill-suited for this task, as they are often prohibitively slow, destructive to the original asset's identity, or lack the precision for fine-grained control. To address this, we introduce SplatPainter, a state-aware feedforward model that enables continuous editing of 3D Gaussian assets from user-provided 2D view(s). Our method directly predicts updates to the attributes of a compact, feature-rich Gaussian representation and leverages Test-Time Training to create a state-aware, iterative workflow. The versatility of our approach allows a single architecture to perform diverse tasks, including high-fidelity local detail refinement, local paint-over, and consistent global recoloring, all at interactive speeds, paving the way for fluid and intuitive 3D content authoring.

---

### Invisible Load: Uncovering the Challenges of Neurodivergent Women in Software Engineering

Authors: Munazza Zaib, Wei Wang, Dulaji Hidellaarachchi, Isma Farah Siddiqui
Published: 2025-12-05
Categories: cs.SE, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2512.05350v1

Neurodivergent women in Software Engineering (SE) encounter distinctive challenges at the intersection of gender bias and neurological differences. To the best of our knowledge, no prior work in SE research has systematically examined this group, despite increasing recognition of neurodiversity in the workplace. Underdiagnosis, masking, and male-centric workplace cultures continue to exacerbate barriers that contribute to stress, burnout, and attrition. In response, we propose a hybrid methodological approach that integrates InclusiveMag's inclusivity framework with the GenderMag walkthrough process, tailored to the context of neurodivergent women in SE. The overarching design unfolds across three stages, scoping through literature review, deriving personas and analytic processes, and applying the method in collaborative workshops. We present a targeted literature review that synthesize challenges into cognitive, social, organizational, structural and career progression challenges neurodivergent women face in SE, including how under/late diagnosis and masking intensify exclusion. These findings lay the groundwork for subsequent stages that will develop and apply inclusive analytic methods to support actionable change.

---

### SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling

Authors: Elisabetta Fedele, Francis Engelmann, Ian Huang, Or Litany, Marc Pollefeys, Leonidas Guibas
Published: 2025-12-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.05343v2

Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing approaches predominantly rely on text or image prompts, which often fall short in geometric specificity: language can be ambiguous, and images are difficult to manipulate. In this work, we introduce SpaceControl, a training-free test-time method for explicit spatial control of 3D asset generation. Our approach accepts a wide range of geometric inputs, from coarse primitives to detailed meshes, and integrates seamlessly with modern generative models without requiring any additional training. A control parameter lets users trade off between geometric fidelity and output realism. Extensive quantitative evaluation and user studies demonstrate that SpaceControl outperforms both training-based and optimization-based baselines in geometric faithfulness while preserving high visual quality. Finally, we present an interactive interface for real-time superquadric editing and direct 3D asset generation, enabling seamless use in creative workflows. Project page: https://spacecontrol3d.github.io/.

---

### First Demonstration of Second-order Training of Deep Neural Networks with In-memory Analog Matrix Computing

Authors: Saitao Zhang, Yubiao Luo, Shiqing Wang, Pushen Zuo, Yongxiang Li, Lunshuai Pan, Zheng Miao, Zhong Sun
Published: 2025-12-05
Categories: cs.ET, cs.AR, cs.NE
arXiv: https://arxiv.org/abs/2512.05342v1

Second-order optimization methods, which leverage curvature information, offer faster and more stable convergence than first-order methods such as stochastic gradient descent (SGD) and Adam. However, their practical adoption is hindered by the prohibitively high cost of inverting the second-order information matrix, particularly in large-scale neural network training. Here, we present the first demonstration of a second-order optimizer powered by in-memory analog matrix computing (AMC) using resistive random-access memory (RRAM), which performs matrix inversion (INV) in a single step. We validate the optimizer by training a two-layer convolutional neural network (CNN) for handwritten letter classification, achieving 26% and 61% fewer training epochs than SGD with momentum and Adam, respectively. On a larger task using the same second-order method, our system delivers a 5.88x improvement in throughput and a 6.9x gain in energy efficiency compared to state-of-the-art digital processors. These results demonstrate the feasibility and effectiveness of AMC circuits for second-order neural network training, opening a new path toward energy-efficient AI acceleration.

---

### When Forgetting Builds Reliability: LLM Unlearning for Reliable Hardware Code Generation

Authors: Yiwen Liang, Qiufeng Li, Shikai Wang, Weidong Cao
Published: 2025-12-05
Categories: cs.LG, cs.AR
arXiv: https://arxiv.org/abs/2512.05341v1

Large Language Models (LLMs) have shown strong potential in accelerating digital hardware design through automated code generation. Yet, ensuring their reliability remains a critical challenge, as existing LLMs trained on massive heterogeneous datasets often exhibit problematic memorization of proprietary intellectual property (IP), contaminated benchmarks, and unsafe coding patterns. To mitigate these risks, we propose a novel unlearning framework tailored for LLM-based hardware code generation. Our method combines (i) a syntax-preserving unlearning strategy that safeguards the structural integrity of hardware code during forgetting, and (ii) a fine-grained floor-aware selective loss that enables precise and efficient removal of problematic knowledge. This integration achieves effective unlearning without degrading LLM code generation capabilities. Extensive experiments show that our framework supports forget sets up to 3x larger, typically requiring only a single training epoch, while preserving both syntactic correctness and functional integrity of register-transfer level (RTL) codes. Our work paves an avenue towards reliable LLM-assisted hardware design.

---

### Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models

Authors: Mahesh Kumar Nandwana, Youngwan Lim, Joseph Liu, Alex Yang, Varun Notibala, Nishchaie Khanna
Published: 2025-12-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.05339v1

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust safeguards that operate across both model inputs and outputs. In this work, we introduce Roblox Guard 1.0, a state-of-the-art instruction fine-tuned LLM designed to enhance the safety of LLM systems through comprehensive input-output moderation, using a pipeline of LLMs to enhance moderation capability. Built on the Llama-3.1-8B-Instruct backbone, our model is instruction fine-tuned to generalize across previously unseen safety taxonomies and demonstrates strong performance on out-of-domain safety benchmarks. The instruction fine-tuning process uses a mix of synthetic and open-source safety datasets, augmented with chain-of-thought (CoT) rationales and input inversion to enhance contextual understanding and decision making. To support systematic evaluation, we also release RobloxGuard-Eval, a new benchmark featuring an extensible safety taxonomy to assess the effectiveness of LLM guardrails and moderation frameworks.

---

### Interaction Tensor SHAP

Authors: Hiroki Hasegawa, Yukihiko Okada
Published: 2025-12-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.05338v2

This study proposes Interaction Tensor SHAP (IT-SHAP), a tensor algebraic formulation of the Shapley Taylor Interaction Index (STII) that makes its computational structure explicit. STII extends the Shapley value to higher order interactions, but its exponential combinatorial definition makes direct computation intractable at scale. We reformulate STII as a linear transformation acting on a value function and derive an explicit algebraic representation of its weight tensor. This weight tensor is shown to possess a multilinear structure induced by discrete finite difference operators. When the value function admits a Tensor Train representation, higher order interaction indices can be computed in the parallel complexity class NC squared. In contrast, under general tensor network representations without structural assumptions, the same computation is proven to be P sharp hard. The main contributions are threefold. First, we establish an exact Tensor Train representation of the STII weight tensor. Second, we develop a parallelizable evaluation algorithm with explicit complexity bounds under the Tensor Train assumption. Third, we prove that computational intractability is unavoidable in the absence of such structure. These results demonstrate that the computational difficulty of higher order interaction analysis is determined by the underlying algebraic representation rather than by the interaction index itself, providing a theoretical foundation for scalable interpretation of high dimensional models.

---

### Symmetric Linear Dynamical Systems are Learnable from Few Observations

Authors: Minh Vu, Andrey Y. Lokhov, Marc Vuffray
Published: 2025-12-05
Categories: stat.ML, cs.LG, eess.SY, math.OC
arXiv: https://arxiv.org/abs/2512.05337v2

We consider the problem of learning the parameters of a $N$-dimensional stochastic linear dynamics under both full and partial observations from a single trajectory of time $T$. We introduce and analyze a new estimator that achieves a small maximum element-wise error on the recovery of symmetric dynamic matrices using only $T=\mathcal{O}(\log N)$ observations, irrespective of whether the matrix is sparse or dense. This estimator is based on the method of moments and does not rely on problem-specific regularization. This is especially important for applications such as structure discovery.

---

### PathFinder: MCTS and LLM Feedback-based Path Selection for Multi-Hop Question Answering

Authors: Durga Prasad Maram, Kalpa Gunaratna, Vijay Srinivasan, Haris Jeelani, Srinivas Chappidi
Published: 2025-12-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.05336v1

Multi-hop question answering is a challenging task in which language models must reason over multiple steps to reach the correct answer. With the help of Large Language Models and their reasoning capabilities, existing systems are able to think and decompose an input question over multiple steps to analyze, retrieve, and reason. However, training-based approaches for this problem still suffer from LLM hallucinations and incorrect reasoning paths that hinder performance. Hence, we propose PATHFINDER, an approach that: (i) uses Monte Carlo Tree Search to generate training path traces, (ii) improves training data quality by filtering erroneous and lengthy traces using sub-answer recall and LLM-as-a-judge verification, and (iii) reformulates sub-queries to handle failed retrieval cases. By following these steps, we demonstrate that PATHFINDER improves the performance of multi-hop QA over public benchmark datasets.

---

### The Effect of Document Summarization on LLM-Based Relevance Judgments

Authors: Samaneh Mohtadi, Kevin Roitero, Stefano Mizzaro, Gianluca Demartini
Published: 2025-12-05
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.05334v1

Relevance judgments are central to the evaluation of Information Retrieval (IR) systems, but obtaining them from human annotators is costly and time-consuming. Large Language Models (LLMs) have recently been proposed as automated assessors, showing promising alignment with human annotations. Most prior studies have treated documents as fixed units, feeding their full content directly to LLM assessors. We investigate how text summarization affects the reliability of LLM-based judgments and their downstream impact on IR evaluation. Using state-of-the-art LLMs across multiple TREC collections, we compare judgments made from full documents with those based on LLM-generated summaries of different lengths. We examine their agreement with human labels, their effect on retrieval effectiveness evaluation, and their influence on IR systems' ranking stability. Our findings show that summary-based judgments achieve comparable stability in systems' ranking to full-document judgments, while introducing systematic shifts in label distributions and biases that vary by model and dataset. These results highlight summarization as both an opportunity for more efficient large-scale IR evaluation and a methodological choice with important implications for the reliability of automatic judgments.

---

### Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats

Authors: Sadat Shahriar, Navid Ayoobi, Arjun Mukherjee, Mostafa Musharrat, Sai Vishnu Vamsi
Published: 2025-12-05
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.05331v1

The local news landscape, a vital source of reliable information for 28 million Americans, faces a growing threat from Pink Slime Journalism, a low-quality, auto-generated articles that mimic legitimate local reporting. Detecting these deceptive articles requires a fine-grained analysis of their linguistic, stylistic, and lexical characteristics. In this work, we conduct a comprehensive study to uncover the distinguishing patterns of Pink Slime content and propose detection strategies based on these insights. Beyond traditional generation methods, we highlight a new adversarial vector: modifications through large language models (LLMs). Our findings reveal that even consumer-accessible LLMs can significantly undermine existing detection systems, reducing their performance by up to 40% in F1-score. To counter this threat, we introduce a robust learning framework specifically designed to resist LLM-based adversarial attacks and adapt to the evolving landscape of automated pink slime journalism, and showed and improvement by up to 27%.

---

### Non-Convex Federated Optimization under Cost-Aware Client Selection

Authors: Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
Published: 2025-12-05
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2512.05327v1

Different federated optimization algorithms typically employ distinct client-selection strategies: some methods communicate only with a randomly sampled subset of clients at each round, while others need to periodically communicate with all clients or use a hybrid scheme that combines both strategies. However, existing metrics for comparing optimization methods typically do not distinguish between these strategies, which often incur different communication costs in practice. To address this disparity, we introduce a simple and natural model of federated optimization that quantifies communication and local computation complexities. This new model allows for several commonly used client-selection strategies and explicitly associates each with a distinct cost. Within this setting, we propose a new algorithm that achieves the best-known communication and local complexities among existing federated optimization methods for non-convex optimization. This algorithm is based on the inexact composite gradient method with a carefully constructed gradient estimator and a special procedure for solving the auxiliary subproblem at each iteration. The gradient estimator is based on SAGA, a popular variance-reduced gradient estimator. We first derive a new variance bound for it, showing that SAGA can exploit functional similarity. We then introduce the Recursive-Gradient technique as a general way to potentially improve the error bound of a given conditionally unbiased gradient estimator, including both SAGA and SVRG. By applying this technique to SAGA, we obtain a new estimator, RG-SAGA, which has an improved error bound compared to the original one.

---

### LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning

Authors: Ömer Faruk Akgül, Yusuf Hakan Kalaycı, Rajgopal Kannan, Willie Neiswanger, Viktor Prasanna
Published: 2025-12-05
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.05325v1

Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have enough information to answer correctly. This wastes inference-time compute and can hurt accuracy. Existing attempts to stop early either manipulate decoding with extra sampling and heuristics, rely on auxiliary verifier models, or operate only as post-hoc analysis pipelines without formal guarantees. We introduce LYNX, an online early-exit mechanism that turns a model's own hidden-state awareness into confidence-controlled stopping decisions. LYNX attaches exit decisions to naturally occurring reasoning cues (e.g., "hmm", "wait") during generation, trains a lightweight probe on hidden states at those cue tokens using supervision from forced exits, and wraps the resulting scores in split conformal prediction to obtain distribution-free control over premature exits. Crucially, we train and calibrate this probe once on a generic mathematical corpus and reuse it unchanged across benchmarks, decoding temperatures, and even non-mathematical tasks. Across three model families spanning 1.5B to 32B parameters, a single mathematically trained probe per base model yields strong accuracy--efficiency tradeoffs. On GSM8K, LYNX matches or improves baseline accuracy while reducing tokens by 40--65\%; on MATH-500 it improves accuracy by up to 12 points with roughly 35--60\% fewer tokens; on AIME 2024 it recovers baseline accuracy with more than 50\% token savings; and on CommonsenseQA, a non-math benchmark, it transfers zero-shot with modest accuracy gains and up to 70\% fewer tokens. Compared to state-of-the-art early-exit methods, LYNX offers competitive or superior Pareto frontiers while remaining fully online, requiring no proxy models at inference, and providing explicit, user-tunable confidence guarantees.

---

### DABench-LLM: Standardized and In-Depth Benchmarking of Post-Moore Dataflow AI Accelerators for LLMs

Authors: Ziyu Hu, Zhiqing Zhong, Weijian Zheng, Zhijing Ye, Xuwei Tan, Xueru Zhang, Zheng Xie, Rajkumar Kettimuthu, Xiaodong Yu
Published: 2025-12-04
Categories: cs.AR, cs.AI, cs.CL, cs.DC, cs.PF
arXiv: https://arxiv.org/abs/2601.19904v1

The exponential growth of large language models has outpaced the capabilities of traditional CPU and GPU architectures due to the slowdown of Moore's Law. Dataflow AI accelerators present a promising alternative; however, there remains a lack of in-depth performance analysis and standardized benchmarking methodologies for LLM training. We introduce DABench-LLM, the first benchmarking framework designed for evaluating LLM workloads on dataflow-based accelerators. By combining intra-chip performance profiling and inter-chip scalability analysis, DABench-LLM enables comprehensive evaluation across key metrics such as resource allocation, load balance, and resource efficiency. The framework helps researchers rapidly gain insights into underlying hardware and system behaviors, and provides guidance for performance optimizations. We validate DABench-LLM on three commodity dataflow accelerators, Cerebras WSE-2, SambaNova RDU, and Graphcore IPU. Our framework reveals performance bottlenecks and provides specific optimization strategies, demonstrating its generality and effectiveness across a diverse range of dataflow-based AI hardware platforms.

---

### Decision-Focused Bias Correction for Fluid Approximation

Authors: Can Er, Mo Liu
Published: 2025-12-04
Categories: math.OC, math.PR, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2512.15726v2

We revisit the multi-period newsvendor network problem, in which demands from multiple customers are correlated and jointly time-varying. Due to the curse of dimensionality associated with estimating the full joint demand distribution, we consider fluid approximation, a widely used approach for solving two-stage stochastic optimization problems such as large-scale service-system design. However, replacing the underlying random distribution (e.g., the demand distribution) with its mean (e.g., the time-varying average arrival rate) introduces bias in performance estimation and can lead to suboptimal decisions. In this paper, we investigate how to identify an alternative point statistic, not necessarily the mean, such that substituting this statistic into the two-stage newsvendor network problem yields an optimal decision. We refer to this statistic as the decision-corrected point estimate (a time-varying arrival rate). Although the critical fractile is well known to be the decision-corrected point forecast for the single-item newsvendor problem, counterexamples show that such a point statistic may not exist for newsvendor networks. We establish necessary and sufficient conditions for the existence of such a corrected point estimate and propose an algorithm for computing it. Numerical experiments on real data demonstrate that using the proposed decision-corrected point forecast in fluid approximation achieves substantially lower cost than traditional fluid approximation and sample average approximation benchmarks.

---

### Value Lens: Using Large Language Models to Understand Human Values

Authors: Eduardo de la Cruz Fernández, Marcelo Karanik, Sascha Ossowski
Published: 2025-12-04
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.15722v1

The autonomous decision-making process, which is increasingly applied to computer systems, requires that the choices made by these systems align with human values. In this context, systems must assess how well their decisions reflect human values. To achieve this, it is essential to identify whether each available action promotes or undermines these values. This article presents Value Lens, a text-based model designed to detect human values using generative artificial intelligence, specifically Large Language Models (LLMs). The proposed model operates in two stages: the first aims to formulate a formal theory of values, while the second focuses on identifying these values within a given text. In the first stage, an LLM generates a description based on the established theory of values, which experts then verify. In the second stage, a pair of LLMs is employed: one LLM detects the presence of values, and the second acts as a critic and reviewer of the detection process. The results indicate that Value Lens performs comparably to, and even exceeds, the effectiveness of other models that apply different methods for similar tasks.

---

### Enhancing Transparency and Traceability in Healthcare AI: The AI Product Passport

Authors: A. Anil Sinaci, Senan Postaci, Dogukan Cavdaroglu, Machteld J. Boonstra, Okan Mercan, Kerem Yilmaz, Gokce B. Laleci Erturkmen, Folkert W. Asselbergs, Karim Lekadir
Published: 2025-12-04
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2512.13702v1

Objective: To develop the AI Product Passport, a standards-based framework improving transparency, traceability, and compliance in healthcare AI via lifecycle-based documentation. Materials and Methods: The AI Product Passport was developed within the AI4HF project, focusing on heart failure AI tools. We analyzed regulatory frameworks (EU AI Act, FDA guidelines) and existing standards to design a relational data model capturing metadata across AI lifecycle phases: study definition, dataset preparation, model generation/evaluation, deployment/monitoring, and passport generation. MLOps/ModelOps concepts were integrated for operational relevance. Co-creation involved feedback from AI4HF consortium and a Lisbon workshop with 21 diverse stakeholders, evaluated via Mentimeter polls. The open-source platform was implemented with Python libraries for automated provenance tracking. Results: The AI Product Passport was designed based on existing standards and methods with well-defined lifecycle management and role-based access. Its implementation is a web-based platform with a relational data model supporting auditable documentation. It generates machine- and human-readable reports, customizable for stakeholders. It aligns with FUTURE-AI principles (Fairness, Universality, Traceability, Usability, Robustness, Explainability), ensuring fairness, traceability, and usability. Exported passports detail model purpose, data provenance, performance, and deployment context. GitHub-hosted backend/frontend codebases enhance accessibility. Discussion and Conclusion: The AI Product Passport addresses transparency gaps in healthcare AI, meeting regulatory and ethical demands. Its open-source nature and alignment with standards foster trust and adaptability. Future enhancements include FAIR data principles and FHIR integration for improved interoperability, promoting responsible AI deployment.

---

### Blind Radio Mapping via Spatially Regularized Bayesian Trajectory Inference

Authors: Zheng Xing, Junting Chen
Published: 2025-12-04
Categories: cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2512.13701v1

Radio maps enable intelligent wireless applications by capturing the spatial distribution of channel characteristics. However, conventional construction methods demand extensive location-labeled data, which are costly and impractical in many real-world scenarios. This paper presents a blind radio map construction framework that infers user trajectories from indoor multiple-input multiple-output (MIMO)-Orthogonal Frequency-Division Multiplexing (OFDM) channel measurements without relying on location labels. It first proves that channel state information (CSI) under non-line-of-sight (NLOS) exhibits spatial continuity under a quasi-specular environmental model, allowing the derivation of a CSI-distance metric that is proportional to the corresponding physical distance. For rectilinear trajectories in Poisson-distributed access point (AP) deployments, it is shown that the Cramer-Rao Lower Bound (CRLB) of localization error vanishes asymptotically, even under poor angular resolution. Building on these theoretical results, a spatially regularized Bayesian inference framework is developed that jointly estimates channel features, distinguishes line-of-sight (LOS)/NLOS conditions and recovers user trajectories. Experiments on a ray-tracing dataset demonstrate an average localization error of 0.68 m and a beam map reconstruction error of 3.3%, validating the effectiveness of the proposed blind mapping method.

---

### Explainable AI for Smart Greenhouse Control: Interpretability of Temporal Fusion Transformer in the Internet of Robotic Things

Authors: Muhammad Jawad Bashir, Shagufta Henna, Eoghan Furey
Published: 2025-12-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.11852v1

The integration of the Internet of Robotic Things (IoRT) in smart greenhouses has revolutionised precision agriculture by enabling efficient and autonomous environmental control. However, existing time series forecasting models in such setups often operate as black boxes, lacking mechanisms for explainable decision-making, which is a critical limitation when trust, transparency, and regulatory compliance are paramount in smart farming practices. This study leverages the Temporal Fusion Transformer (TFT) model to automate actuator settings for optimal greenhouse management. To enhance interpretability and trust in the model decision-making process, both local and global explanation techniques were employed using model-inherent interpretation, local interpretable model-agnostic explanations (LIME), and SHapley additive explanations (SHAP). These explainability methods provide information on how different sensor readings, such as temperature, humidity, CO2 levels, light, and outer climate, contribute to actuator control decisions in an automated greenhouse. The trained TFT model achieved a test accuracy of 95% on a class-imbalanced dataset for actuator control settings in an automated greenhouse environment. The results demonstrate the varying influence of each sensor on real-time greenhouse adjustments, ensuring transparency and enabling adaptive fine-tuning for improved crop yield and resource efficiency.

---