# Research Papers — 2025-12 · bundle page 68 of 175 > Full-text markdown of papers #3351–3400 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/68 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/67.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/69.md) ### Explainable AI in Big Data Fraud Detection Authors: Ayush Jain, Rahul Kulkarni, Siyi Lin Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.16037v1 Big Data has become central to modern applications in finance, insurance, and cybersecurity, enabling machine learning systems to perform large-scale risk assessments and fraud detection. However, the increasing dependence on automated analytics introduces important concerns about transparency, regulatory compliance, and trust. This paper examines how explainable artificial intelligence (XAI) can be integrated into Big Data analytics pipelines for fraud detection and risk management. We review key Big Data characteristics and survey major analytical tools, including distributed storage systems, streaming platforms, and advanced fraud detection models such as anomaly detectors, graph-based approaches, and ensemble classifiers. We also present a structured review of widely used XAI methods, including LIME, SHAP, counterfactual explanations, and attention mechanisms, and analyze their strengths and limitations when deployed at scale. Based on these findings, we identify key research gaps related to scalability, real-time processing, and explainability for graph and temporal models. To address these challenges, we outline a conceptual framework that integrates scalable Big Data infrastructure with context-aware explanation mechanisms and human feedback. The paper concludes with open research directions in scalable XAI, privacy-aware explanations, and standardized evaluation methods for explainable fraud detection systems. --- ### Topic Discovery and Classification for Responsible Generative AI Adaptation in Higher Education Authors: Diane Myung-kyung Woodbridge, Allyson Seba, Freddie Seba, Aydin Schwartz Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.16036v1 As generative artificial intelligence (GenAI) becomes increasingly capable of delivering personalized learning experiences and real-time feedback, a growing number of students are incorporating these tools into their academic workflows. They use GenAI to clarify concepts, solve complex problems, and, in some cases, complete assignments by copying and pasting model-generated contents. While GenAI has the potential to enhance learning experience, it also raises concerns around misinformation, hallucinated outputs, and its potential to undermine critical thinking and problem-solving skills. In response, many universities, colleges, departments, and instructors have begun to develop and adopt policies to guide responsible integration of GenAI into learning environments. However, these policies vary widely across institutions and contexts, and their evolving nature often leaves students uncertain about expectations and best practices. To address this challenge, the authors designed and implemented an automated system for discovering and categorizing AI-related policies found in course syllabi and institutional policy websites. The system combines unsupervised topic modeling techniques to identify key policy themes with large language models (LLMs) to classify the level of GenAI allowance and other requirements in policy texts. The developed application achieved a coherence score of 0.73 for topic discovery. In addition, GPT-4.0-based classification of policy categories achieved precision between 0.92 and 0.97, and recall between 0.85 and 0.97 across eight identified topics. By providing structured and interpretable policy information, this tool promotes the safe, equitable, and pedagogically aligned use of GenAI technologies in education. Furthermore, the system can be integrated into educational technology platforms to help students understand and comply with relevant guidelines. --- ### Examining the Utility of Self-disclosure Types for Modeling Annotators of Social Norms Authors: Kieran Henderson, Kian Omoomi, Vasudha Varadarajan, Allison Lahnala, Charles Welch Published: 2025-12-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.16034v2 Recent work has explored the use of personal information in the form of persona sentences or self-disclosures to improve modeling of individual characteristics and prediction of annotator labels for subjective tasks. The volume of personal information has historically been restricted and thus little exploration has gone into understanding what kind of information is most informative for predicting annotator labels. In this work, we categorize self-disclosures and use them to build annotator models for predicting judgments of social norms. We perform several ablations and analyses to examine the impact of the type of information on our ability to predict annotation patterns. Contrary to previous work, only a small number of comments related to the original post are needed. Lastly, a more diverse sample of annotator self-disclosures did not lead to the best performance. Sampling from a larger pool of comments without filtering still yields the best performance, suggesting that there is still much to uncover in terms of what information about an annotator is most useful for verdict prediction. --- ### Techno-economic optimization of a heat-pipe microreactor, part I: theory and cost optimization Authors: Paul Seurin, Dean Price, Luis Nunez Published: 2025-12-17 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2512.16032v1 Microreactors, particularly heat-pipe microreactors (HPMRs), are compact, transportable, self-regulated power systems well-suited for access-challenged remote areas where costly fossil fuels dominate. However, they suffer from diseconomies of scale, and their financial viability remains unconvincing. One step in addressing this shortcoming is to design these reactors with comprehensive economic and physics analyses informing early-stage design iteration. In this work, we present a novel unifying geometric design optimization approach that accounts for techno-economic considerations. We start by generating random samples to train surrogate models, including Gaussian processes (GPs) and multi-layer perceptrons (MLPs). We then deploy these surrogates within a reinforcement learning (RL)-based optimization framework to optimize the levelized cost of electricity (LCOE), all the while imposing constraints on the fuel lifetime, shutdown margin (SDM), peak heat flux, and rod-integrated peaking factor. We study two cases: one in which the axial reflector cost is very high, and one in which it is inexpensive. We found that the operation and maintenance and capital costs are the primary contributors to the overall LCOE particularly the cost of the axial reflectors (for the first case) and the control drum materials. The optimizer cleverly changes the design parameters so as to minimize one of them while still satisfying the constraints, ultimately reducing the LCOE by more than 57% in both instances. A comprehensive integration of fuel and HP performance with multi-objective optimization is currently being pursued to fully understand the interaction between constraints and cost performance. --- ### Do Large Language Models Know What They Don't Know? Kalshibench: A New Benchmark for Evaluating Epistemic Calibration via Prediction Markets Authors: Lukas Nel Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.16030v1 A well-calibrated model should express confidence that matches its actual accuracy -- when it claims 80\% confidence, it should be correct 80\% of the time. While large language models (LLMs) have achieved remarkable performance across diverse tasks, their epistemic calibration remains poorly understood. We introduce \textbf{KalshiBench}, a benchmark of 300 prediction market questions from Kalshi, a CFTC-regulated exchange, with verifiable real-world outcomes occurring after model training cutoffs. Unlike traditional benchmarks measuring accuracy on static knowledge, KalshiBench evaluates whether models can appropriately quantify uncertainty about genuinely unknown future events. We evaluate five frontier models -- Claude Opus 4.5, GPT-5.2, DeepSeek-V3.2, Qwen3-235B, and Kimi-K2 -- and find \textbf{systematic overconfidence across all models}. Even the best-calibrated model (Claude Opus 4.5, ECE=0.120) shows substantial calibration errors, while reasoning-enhanced models like GPT-5.2-XHigh exhibit \emph{worse} calibration (ECE=0.395) despite comparable accuracy. Critically, only one model achieves a positive Brier Skill Score, indicating most models perform worse than simply predicting base rates. Our findings suggest that scaling and enhanced reasoning do not automatically confer calibration benefits, highlighting epistemic calibration as a distinct capability requiring targeted development. --- ### Cross-Language Bias Examination in Large Language Models Authors: Yuxuan Liang, Marwa Mahmoud Published: 2025-12-17 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.16029v1 This study introduces an innovative multilingual bias evaluation framework for assessing bias in Large Language Models, combining explicit bias assessment through the BBQ benchmark with implicit bias measurement using a prompt-based Implicit Association Test. By translating the prompts and word list into five target languages, English, Chinese, Arabic, French, and Spanish, we directly compare different types of bias across languages. The results reveal substantial gaps in bias across languages used in LLMs. For example, Arabic and Spanish consistently show higher levels of stereotype bias, while Chinese and English exhibit lower levels of bias. We also identify contrasting patterns across bias types. Age shows the lowest explicit bias but the highest implicit bias, emphasizing the importance of detecting implicit biases that are undetectable with standard benchmarks. These findings indicate that LLMs vary significantly across languages and bias dimensions. This study fills a key research gap by providing a comprehensive methodology for cross-lingual bias analysis. Ultimately, our work establishes a foundation for the development of equitable multilingual LLMs, ensuring fairness and effectiveness across diverse languages and cultures. --- ### CoVAR: Co-generation of Video and Action for Robotic Manipulation via Multi-Modal Diffusion Authors: Liudi Yang, Yang Bai, George Eskandar, Fengyi Shen, Mohammad Altillawi, Dong Chen, Ziyuan Liu, Abhinav Valada Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.16023v1 We present a method to generate video-action pairs that follow text instructions, starting from an initial image observation and the robot's joint states. Our approach automatically provides action labels for video diffusion models, overcoming the common lack of action annotations and enabling their full use for robotic policy learning. Existing methods either adopt two-stage pipelines, which limit tightly coupled cross-modal information sharing, or rely on adapting a single-modal diffusion model for a joint distribution that cannot fully leverage pretrained video knowledge. To overcome these limitations, we (1) extend a pretrained video diffusion model with a parallel, dedicated action diffusion model that preserves pretrained knowledge, (2) introduce a Bridge Attention mechanism to enable effective cross-modal interaction, and (3) design an action refinement module to convert coarse actions into precise controls for low-resolution datasets. Extensive evaluations on multiple public benchmarks and real-world datasets demonstrate that our method generates higher-quality videos, more accurate actions, and significantly outperforms existing baselines, offering a scalable framework for leveraging large-scale video data for robotic learning. --- ### Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting Authors: Defu Cao, Michael Gee, Jinbo Liu, Hengxuan Wang, Wei Yang, Rui Wang, Yan Liu Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.16022v1 The proliferation of time series foundation models has created a landscape where no single method achieves consistent superiority, framing the central challenge not as finding the best model, but as orchestrating an optimal ensemble with interpretability. While Large Language Models (LLMs) offer powerful reasoning capabilities, their direct application to time series forecasting has proven ineffective. We address this gap by repositioning the LLM as an intelligent judge that evaluates, explains, and strategically coordinates an ensemble of foundation models. To overcome the LLM's inherent lack of domain-specific knowledge on time series, we introduce an R1-style finetuning process, guided by SHAP-based faithfulness scores, which teaches the model to interpret ensemble weights as meaningful causal statements about temporal dynamics. The trained agent then engages in iterative, multi-turn conversations to perform forward-looking assessments, provide causally-grounded explanations for its weighting decisions, and adaptively refine the optimization strategy. Validated on the GIFT-Eval benchmark on 23 datasets across 97 settings, our approach significantly outperforms leading time series foundation models on both CRPS and MASE metrics, establishing new state-of-the-art results. --- ### Few-Shot Inference of Human Perceptions of Robot Performance in Social Navigation Scenarios Authors: Qiping Zhang, Nathan Tsoi, Mofeed Nagib, Hao-Tien Lewis Chiang, Marynel Vázquez Published: 2025-12-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.16019v1 Understanding how humans evaluate robot behavior during human-robot interactions is crucial for developing socially aware robots that behave according to human expectations. While the traditional approach to capturing these evaluations is to conduct a user study, recent work has proposed utilizing machine learning instead. However, existing data-driven methods require large amounts of labeled data, which limits their use in practice. To address this gap, we propose leveraging the few-shot learning capabilities of Large Language Models (LLMs) to improve how well a robot can predict a user's perception of its performance, and study this idea experimentally in social navigation tasks. To this end, we extend the SEAN TOGETHER dataset with additional real-world human-robot navigation episodes and participant feedback. Using this augmented dataset, we evaluate the ability of several LLMs to predict human perceptions of robot performance from a small number of in-context examples, based on observed spatio-temporal cues of the robot and surrounding human motion. Our results demonstrate that LLMs can match or exceed the performance of traditional supervised learning models while requiring an order of magnitude fewer labeled instances. We further show that prediction performance can improve with more in-context examples, confirming the scalability of our approach. Additionally, we investigate what kind of sensor-based information an LLM relies on to make these inferences by conducting an ablation study on the input features considered for performance prediction. Finally, we explore the novel application of personalized examples for in-context learning, i.e., drawn from the same user being evaluated, finding that they further enhance prediction accuracy. This work paves the path to improving robot behavior in a scalable manner through user-centered feedback. --- ### Towards Fine-Tuning-Based Site Calibration for Knowledge-Guided Machine Learning: A Summary of Results Authors: Ruolei Zeng, Arun Sharma, Shuai An, Mingzhou Yang, Shengya Zhang, Licheng Liu, David Mulla, Shashi Shekhar Published: 2025-12-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.16013v1 Accurate and cost-effective quantification of the agroecosystem carbon cycle at decision-relevant scales is essential for climate mitigation and sustainable agriculture. However, both transfer learning and the exploitation of spatial variability in this field are challenging, as they involve heterogeneous data and complex cross-scale dependencies. Conventional approaches often rely on location-independent parameterizations and independent training, underutilizing transfer learning and spatial heterogeneity in the inputs, and limiting their applicability in regions with substantial variability. We propose FTBSC-KGML (Fine-Tuning-Based Site Calibration-Knowledge-Guided Machine Learning), a pretraining- and fine-tuning-based, spatial-variability-aware, and knowledge-guided machine learning framework that augments KGML-ag with a pretraining-fine-tuning process and site-specific parameters. Using a pretraining-fine-tuning process with remote-sensing GPP, climate, and soil covariates collected across multiple midwestern sites, FTBSC-KGML estimates land emissions while leveraging transfer learning and spatial heterogeneity. A key component is a spatial-heterogeneity-aware transfer-learning scheme, which is a globally pretrained model that is fine-tuned at each state or site to learn place-aware representations, thereby improving local accuracy under limited data without sacrificing interpretability. Empirically, FTBSC-KGML achieves lower validation error and greater consistency in explanatory power than a purely global model, thereby better capturing spatial variability across states. This work extends the prior SDSA-KGML framework. --- ### Concurrence: A dependence criterion for time series, applied to biological data Authors: Evangelos Sariyanidi, John D. Herrington, Lisa Yankowitz, Pratik Chaudhari, Theodore D. Satterthwaite, Casey J. Zampella, Jeffrey S. Morris, Edward Gunning, Robert T. Schultz, Russell T. Shinohara, Birkan Tunc Published: 2025-12-17 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2512.16001v2 Measuring the statistical dependence between observed signals is a primary tool for scientific discovery. However, biological systems often exhibit complex non-linear interactions that currently cannot be captured without a priori knowledge or large datasets. We introduce a criterion for dependence, whereby two time series are deemed dependent if one can construct a classifier that distinguishes between temporally aligned vs. misaligned segments extracted from them. We show that this criterion, concurrence, is theoretically linked with dependence, and can become a standard approach for scientific analyses across disciplines, as it can expose relationships across a wide spectrum of signals (fMRI, physiological and behavioral data) without ad-hoc parameter tuning or large amounts of data. --- ### Information theory and discriminative sampling for model discovery Authors: Yuxuan Bao, J. Nathan Kutz Published: 2025-12-17 Categories: cs.IT, cs.LG, math.AP, math.DS arXiv: https://arxiv.org/abs/2512.16000v1 Fisher information and Shannon entropy are fundamental tools for understanding and analyzing dynamical systems from complementary perspectives. They can characterize unknown parameters by quantifying the information contained in variables, or measure how different initial trajectories or temporal segments of a trajectory contribute to learning or inferring system dynamics. In this work, we leverage the Fisher Information Matrix (FIM) within the data-driven framework of {\em sparse identification of nonlinear dynamics} (SINDy). We visualize information patterns in chaotic and non-chaotic systems for both single trajectories and multiple initial conditions, demonstrating how information-based analysis can improve sampling efficiency and enhance model performance by prioritizing more informative data. The benefits of statistical bagging are further elucidated through spectral analysis of the FIM. We also illustrate how Fisher information and entropy metrics can promote data efficiency in three scenarios: when only a single trajectory is available, when a tunable control parameter exists, and when multiple trajectories can be freely initialized. As data-driven model discovery continues to gain prominence, principled sampling strategies guided by quantifiable information metrics offer a powerful approach for improving learning efficiency and reducing data requirements. --- ### Surrogate Neural Architecture Codesign Package (SNAC-Pack) Authors: Jason Weitz, Dmitri Demler, Benjamin Hawks, Nhan Tran, Javier Duarte Published: 2025-12-17 Categories: cs.LG, cs.AI, hep-ex arXiv: https://arxiv.org/abs/2512.15998v1 Neural Architecture Search is a powerful approach for automating model design, but existing methods struggle to accurately optimize for real hardware performance, often relying on proxy metrics such as bit operations. We present Surrogate Neural Architecture Codesign Package (SNAC-Pack), an integrated framework that automates the discovery and optimization of neural networks focusing on FPGA deployment. SNAC-Pack combines Neural Architecture Codesign's multi-stage search capabilities with the Resource Utilization and Latency Estimator, enabling multi-objective optimization across accuracy, FPGA resource utilization, and latency without requiring time-intensive synthesis for each candidate model. We demonstrate SNAC-Pack on a high energy physics jet classification task, achieving 63.84% accuracy with resource estimation. When synthesized on a Xilinx Virtex UltraScale+ VU13P FPGA, the SNAC-Pack model matches baseline accuracy while maintaining comparable resource utilization to models optimized using traditional BOPs metrics. This work demonstrates the potential of hardware-aware neural architecture search for resource-constrained deployments and provides an open-source framework for automating the design of efficient FPGA-accelerated models. --- ### Higher-Order LaSDI: Reduced Order Modeling with Multiple Time Derivatives Authors: Robert Stephany, William Michael Anderson, Youngsoo Choi Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15997v1 Solving complex partial differential equations is vital in the physical sciences, but often requires computationally expensive numerical methods. Reduced-order models (ROMs) address this by exploiting dimensionality reduction to create fast approximations. While modern ROMs can solve parameterized families of PDEs, their predictive power degrades over long time horizons. We address this by (1) introducing a flexible, high-order, yet inexpensive finite-difference scheme and (2) proposing a Rollout loss that trains ROMs to make accurate predictions over arbitrary time horizons. We demonstrate our approach on the 2D Burgers equation. --- ### Eyes on the Grass: Biodiversity-Increasing Robotic Mowing Using Deep Visual Embeddings Authors: Lars Beckers, Arno Waes, Aaron Van Campenhout, Toon Goedemé Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.15993v1 This paper presents a robotic mowing framework that actively enhances garden biodiversity through visual perception and adaptive decision-making. Unlike passive rewilding approaches, the proposed system uses deep feature-space analysis to identify and preserve visually diverse vegetation patches in camera images by selectively deactivating the mower blades. A ResNet50 network pretrained on PlantNet300K provides ecologically meaningful embeddings, from which a global deviation metric estimates biodiversity without species-level supervision. These estimates drive a selective mowing algorithm that dynamically alternates between mowing and conservation behavior. The system was implemented on a modified commercial robotic mower and validated both in a controlled mock-up lawn and on real garden datasets. Results demonstrate a strong correlation between embedding-space dispersion and expert biodiversity assessment, confirming the feasibility of deep visual diversity as a proxy for ecological richness and the effectiveness of the proposed mowing decision approach. Widespread adoption of such systems will turn ecologically worthless, monocultural lawns into vibrant, valuable biotopes that boost urban biodiversity. --- ### Time-Frequency Analysis for Neural Networks Authors: Ahmed Abdeljawad, Elena Cordero Published: 2025-12-17 Categories: math.NA, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2512.15992v2 We develop a quantitative approximation theory for shallow neural networks using tools from time-frequency analysis. Working in weighted modulation spaces $M^{p,q}_m(\mathbf{R}^{d})$, we prove dimension-independent approximation rates in Sobolev norms $W^{n,r}(Ω)$ for networks whose units combine standard activations with localized time-frequency windows. Our main result shows that for $f \in M^{p,q}_m(\mathbf{R}^{d})$ one can achieve \( \|f - f_N\|_{W^{n,r}(Ω)} \lesssim N^{-1/2}\,\|f\|_{M^{p,q}_m(\mathbf{R}^{d})}, \) on bounded domains, with explicit control of all constants. We further obtain global approximation theorems on $\mathbf{R}^{d}$ using weighted modulation dictionaries, and derive consequences for Feichtinger's algebra, Fourier-Lebesgue spaces, and Barron spaces. Numerical experiments in one and two dimensions confirm that modulation-based networks achieve substantially better Sobolev approximation than standard ReLU networks, consistent with the theoretical estimates. --- ### Provably Extracting the Features from a General Superposition Authors: Allen Liu Published: 2025-12-17 Categories: cs.LG, cs.AI, cs.DS, stat.ML arXiv: https://arxiv.org/abs/2512.15987v2 It is widely believed that complex machine learning models generally encode features through linear representations. This is the foundational hypothesis behind a vast body of work on interpretability. A key challenge toward extracting interpretable features, however, is that they exist in superposition. In this work, we study the question of extracting features in superposition from a learning theoretic perspective. We start with the following fundamental setting: we are given query access to a function \( f(x)=\sum_{i=1}^n σ_i(v_i^\top x), \) where each unit vector $v_i$ encodes a feature direction and $σ_i:\R\to\R$ is an arbitrary response function and our goal is to recover the $v_i$ and the function $f$. In learning-theoretic terms, superposition refers to the \emph{overcomplete regime}, when the number of features is larger than the underlying dimension (i.e. $n > d$), which has proven especially challenging for typical algorithmic approaches. Our main result is an efficient query algorithm that, from noisy oracle access to $f$, identifies all feature directions whose responses are non-degenerate and reconstructs the function $f$. Crucially, our algorithm works in a significantly more general setting than all related prior results. We allow for essentially arbitrary superpositions, only requiring that $v_i, v_j$ are not nearly identical for $i \neq j$, and allowing for general response functions $σ_i$. At a high level, our algorithm introduces an approach for searching in Fourier space by iteratively refining the search space to locate the hidden directions $v_i$. --- ### Hierarchical Neural Surfaces for 3D Mesh Compression Authors: Sai Karthikey Pentapati, Gregoire Phillips, Alan Bovik Published: 2025-12-17 Categories: cs.CG, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2512.15985v1 Implicit Neural Representations (INRs) have been demonstrated to achieve state-of-the-art compression of a broad range of modalities such as images, videos, 3D surfaces, and audio. Most studies have focused on building neural counterparts of traditional implicit representations of 3D geometries, such as signed distance functions. However, the triangle mesh-based representation of geometry remains the most widely used representation in the industry, while building INRs capable of generating them has been sparsely studied. In this paper, we present a method for building compact INRs of zero-genus 3D manifolds. Our method relies on creating a spherical parameterization of a given 3D mesh - mapping the surface of a mesh to that of a unit sphere - then constructing an INR that encodes the displacement vector field defined continuously on its surface that regenerates the original shape. The compactness of our representation can be attributed to its hierarchical structure, wherein it first recovers the coarse structure of the encoded surface before adding high-frequency details to it. Once the INR is computed, 3D meshes of arbitrary resolution/connectivity can be decoded from it. The decoding can be performed in real time while achieving a state-of-the-art trade-off between reconstruction quality and the size of the compressed representations. --- ### Lifting Biomolecular Data Acquisition Authors: Eli N. Weinstein, Andrei Slabodkin, Mattia G. Gollub, Kerry Dobbs, Xiao-Bing Cui, Fang Zhang, Kristina Gurung, Elizabeth B. Wood Published: 2025-12-17 Categories: q-bio.BM, stat.ML arXiv: https://arxiv.org/abs/2512.15984v1 One strategy to scale up ML-driven science is to increase wet lab experiments' information density. We present a method based on a neural extension of compressed sensing to function space. We measure the activity of multiple different molecules simultaneously, rather than individually. Then, we deconvolute the molecule-activity map during model training. Co-design of wet lab experiments and learning algorithms provably leads to orders-of-magnitude gains in information density. We demonstrate on antibodies and cell therapies. --- ### Embedding Software Intent: Lightweight Java Module Recovery Authors: Yirui He, Yuqi Huai, Xingyu Chen, Joshua Garcia Published: 2025-12-17 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.15980v1 As an increasing number of software systems reach unprecedented scale, relying solely on code-level abstractions is becoming impractical. While architectural abstractions offer a means to manage these systems, maintaining their consistency with the actual code has been problematic. The Java Platform Module System (JPMS), introduced in Java 9, addresses this limitation by enabling explicit module specification at the language level. JPMS enhances architectural implementation through improved encapsulation and direct specification of ground-truth architectures within Java projects. Although many projects are written in Java, modularizing existing monolithic projects to JPMS modules is an open challenge due to ineffective module recovery by existing architecture recovery techniques. To address this challenge, this paper presents ClassLAR (Class-and Language model-based Architectural Recovery), a novel, lightweight, and efficient approach that recovers Java modules from monolithic Java systems using fully-qualified class names. ClassLAR leverages language models to extract semantic information from package and class names, capturing both structural and functional intent. In evaluations across 20 popular Java projects, ClassLAR outperformed all state-of-the-art techniques in architectural-level similarity metrics while achieving execution times that were 3.99 to 10.50 times faster. --- ### OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering Authors: Mia Mohammad Imran, Tarannum Shaila Zaman Published: 2025-12-17 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.15979v2 Large Language Models (LLMs) are increasingly used in empirical software engineering (ESE) to automate or assist annotation tasks such as labeling commits, issues, and qualitative artifacts. Yet the reliability and reproducibility of such annotations remain underexplored. Existing studies often lack standardized measures for reliability, calibration, and drift, and frequently omit essential configuration details. We argue that LLM-based annotation should be treated as a measurement process rather than a purely automated activity. In this position paper, we outline the \textbf{Operationalization for LLM-based Annotation Framework (OLAF)}, a conceptual framework that organizes key constructs: \textit{reliability, calibration, drift, consensus, aggregation}, and \textit{transparency}. The paper aims to motivate methodological discussion and future empirical work toward more transparent and reproducible LLM-based annotation in software engineering research. --- ### Are vision-language models ready to zero-shot replace supervised classification models in agriculture? Authors: Earl Ranario, Mason J. Earles Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.15977v3 Vision-language models (VLMs) are increasingly proposed as general-purpose solutions for visual recognition tasks, yet their reliability for agricultural decision support remains poorly understood. We benchmark a diverse set of open-source and closed-source VLMs on 27 agricultural image classification datasets from the AgML collection (https://github.com/Project-AgML), spanning 162 classes and 248,000 images across plant disease, pest and damage, and plant and weed species identification. Across all tasks, zero-shot VLMs substantially underperform a supervised task-specific baseline (YOLO11), which consistently achieves markedly higher accuracy than any foundation model. Under multiple-choice prompting, the best-performing VLM (Gemini-3 Pro) reaches approximately 62% average accuracy, while open-ended prompting yields much lower performance, with raw accuracies typically below 25%. Applying LLM-based semantic judging increases open-ended accuracy (e.g., from ~21% to ~30% for top models) and alters model rankings, demonstrating that evaluation methodology meaningfully affects reported conclusions. Among open-source models, Qwen-VL-72B performs best, approaching closed-source performance under constrained prompting but still trailing top proprietary systems. Task-level analysis shows that plant and weed species classification is consistently easier than pest and damage identification, which remains the most challenging category across models. Overall, these results indicate that current off-the-shelf VLMs are not yet suitable as standalone agricultural diagnostic systems, but can function as assistive components when paired with constrained interfaces, explicit label ontologies, and domain-aware evaluation strategies. --- ### Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models Authors: Caner Erden Published: 2025-12-17 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.15973v2 Dynamic Rank Reinforcement Learning (DR-RL) approximations rely on static rank assumptions, limiting their flexibility across diverse linguistic contexts. Our method dynamically modulates ranks based on real-time sequence dynamics, layer-specific sensitivities, and hardware constraints. The core innovation is a deep reinforcement learning agent that formulates rank selection as a sequential policy optimization problem, strictly balancing attention fidelity against computational latency. To ensure stability during inference, we derive and employ online matrix perturbation bounds, enabling incremental rank updates without the prohibitive cost of full decomposition. Furthermore, the integration of a lightweight Transformer-based policy network and batched Singular Value Decomposition (SVD) operations ensures scalable deployment on modern architectures. Extensive experiments demonstrate that DR-RL significantly reduces Floating Point Operations (FLOPs) by over 40% in long-sequence regimes (L > 4096) while maintaining downstream accuracy statistically equivalent to full-rank attention. Beyond standard language modeling benchmarks, we validate the real-world applicability of DR-RL on the GLUE benchmark. Specifically, our method achieves 92.78% accuracy on the SST-2 sentiment analysis task, matching the performance of full-rank baselines and outperforming static low-rank methods, such as Performer and Nyströmformer, by a significant margin. --- ### From Words to Wavelengths: VLMs for Few-Shot Multispectral Object Detection Authors: Manuel Nkegoum, Minh-Tan Pham, Élisa Fromont, Bruno Avignon, Sébastien Lefèvre Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.15971v2 Multispectral object detection is critical for safety-sensitive applications such as autonomous driving and surveillance, where robust perception under diverse illumination conditions is essential. However, the limited availability of annotated multispectral data severely restricts the training of deep detectors. In such data-scarce scenarios, textual class information can serve as a valuable source of semantic supervision. Motivated by the recent success of Vision-Language Models (VLMs) in computer vision, we explore their potential for few-shot multispectral object detection. Specifically, we adapt two representative VLM-based detectors, Grounding DINO and YOLO-World, to handle multispectral inputs and propose an effective mechanism to integrate text, visual and thermal modalities. Through extensive experiments on two popular multispectral image benchmarks, FLIR and M3FD, we demonstrate that VLM-based detectors not only excel in few-shot regimes, significantly outperforming specialized multispectral models trained with comparable data, but also achieve competitive or superior results under fully supervised settings. Our findings reveal that the semantic priors learned by large-scale VLMs effectively transfer to unseen spectral modalities, ofFering a powerful pathway toward data-efficient multispectral perception. --- ### xtdml: Double Machine Learning Estimation to Static Panel Data Models with Fixed Effects in R Authors: Annalivia Polselli Published: 2025-12-17 Categories: econ.EM, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.15965v1 The double machine learning (DML) method combines the predictive power of machine learning with statistical estimation to conduct inference about the structural parameter of interest. This paper presents the R package `xtdml`, which implements DML methods for partially linear panel regression models with low-dimensional fixed effects, high-dimensional confounding variables, proposed by Clarke and Polselli (2025). The package provides functionalities to: (a) learn nuisance functions with machine learning algorithms from the `mlr3` ecosystem, (b) handle unobserved individual heterogeneity choosing among first-difference transformation, within-group transformation, and correlated random effects, (c) transform the covariates with min-max normalization and polynomial expansion to improve learning performance. We showcase the use of `xtdml` with both simulated and real longitudinal data. --- ### BRAID: Bounded Reasoning for Autonomous Inference and Decisions Authors: Armağan Amcalar, Eyup Cinar Published: 2025-12-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.15959v1 Large Language Models (LLMs) exhibit nonlinear relationships between performance, cost, and token usage. This paper presents a quantitative study on structured prompting using BRAID (Bounded Reasoning for Au tonomous Inference and Decisions) across multiple GPT model tiers, eval uated on the AdvancedIF, GSM-Hard, and the SCALE MultiChallenge benchmark datasets. BRAID introduces a bounded reasoning framework using Mermaid-based instruction graphs that enable models to reason struc turally rather than through unbounded natural-language token expansion. We show that structured machine-readable prompts substantially increase reasoning accuracy and cost efficiency for agents in production systems. The findings establish BRAID as an effective and scalable technique for optimizing inference efficiency in autonomous agent systems. All datasets and detailed result logs are available at https://benchmark.openserv.ai. --- ### Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models Authors: Utsav Panchal, Yuchen Liu, Luigi Palmieri, Ilche Georgievski, Marco Aiello Published: 2025-12-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.15957v1 Accurately predicting human behaviors is crucial for mobile robots operating in human-populated environments. While prior research primarily focuses on predicting actions in single-human scenarios from an egocentric view, several robotic applications require understanding multiple human behaviors from a third-person perspective. To this end, we present CAMP-VLM (Context-Aware Multi-human behavior Prediction): a Vision Language Model (VLM)-based framework that incorporates contextual features from visual input and spatial awareness from scene graphs to enhance prediction of humans-scene interactions. Due to the lack of suitable datasets for multi-human behavior prediction from an observer view, we perform fine-tuning of CAMP-VLM with synthetic human behavior data generated by a photorealistic simulator, and evaluate the resulting models on both synthetic and real-world sequences to assess their generalization capabilities. Leveraging Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO), CAMP-VLM outperforms the best-performing baseline by up to 66.9% in prediction accuracy. --- ### Tracking Wildfire Assets with Commodity RFID and Gaussian Process Modeling Authors: John Hateley, Sriram Narasimhan, Omid Abari Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15956v1 This paper presents a novel, cost-effective, and scalable approach to track numerous assets distributed in forested environments using commodity Radio Frequency Identification (RFID) targeting wildfire response applications. Commodity RFID systems suffer from poor tag localization when dispersed in forested environments due to signal attenuation, multi-path effects and environmental variability. Current methods to address this issue via fingerprinting rely on dispersing tags at known locations {\em a priori}. In this paper, we address the case when it is not possible to tag known locations and show that it is possible to localize tags to accuracies comparable to global positioning systems (GPS) without such a constraint. For this, we propose Gaussian Process to model various environments solely based on RF signal response signatures and without the aid of additional sensors such as global positioning GPS or cameras, and match an unknown RF to the closest match in a model dictionary. We utilize a new weighted log-likelihood method to associate an unknown environment with the closest environment in a dictionary of previously modeled environments, which is a crucial step in being able to use our approach. Our results show that it is possible to achieve localization accuracies of the order of GPS, but with passive commodity RFID, which will allow the tracking of dozens of wildfire assets within the vicinity of mobile readers at-a-time simultaneously, does not require known positions to be tagged {\em a priori}, and can achieve localization at a fraction of the cost compared to GPS. --- ### Governance by Evidence: Regulated Predictors in Decision-Tree Models Authors: Alexios Veskoukis, Dimitris Kalles Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15955v1 Decision-tree methods are widely used on structured tabular data and are valued for interpretability across many sectors. However, published studies often list the predictors they use (for example age, diagnosis codes, location). Privacy laws increasingly regulate such data types. We use published decision-tree papers as a proxy for real-world use of legally governed data. We compile a corpus of decision-tree studies and assign each reported predictor to a regulated data category (for example health data, biometric identifiers, children's data, financial attributes, location traces, and government IDs). We then link each category to specific excerpts in European Union and United States privacy laws. We find that many reported predictors fall into regulated categories, with the largest shares in healthcare and clear differences across industries. We analyze prevalence, industry composition, and temporal patterns, and summarize regulation-aligned timing using each framework's reference year. Our evidence supports privacy-preserving methods and governance checks, and can inform ML practice beyond decision trees. --- ### The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs Authors: Tejas Anvekar, Fenil Bardoliya, Pavan K. Turaga, Chitta Baral, Vivek Gupta Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.15949v1 Recent advances in multimodal large language models (MLLMs) have yielded increasingly powerful models, yet their perceptual capacities remain poorly characterized. In practice, most model families scale language component while reusing nearly identical vision encoders (e.g., Qwen2.5-VL 3B/7B/72B), which raises pivotal concerns about whether progress reflects genuine visual grounding or reliance on internet-scale textual world knowledge. Existing evaluation methods emphasize end-task accuracy, overlooking robustness, attribution fidelity, and reasoning under controlled perturbations. We present The Perceptual Observatory, a framework that characterizes MLLMs across verticals like: (i) simple vision tasks, such as face matching and text-in-vision comprehension capabilities; (ii) local-to-global understanding, encompassing image matching, grid pointing game, and attribute localization, which tests general visual grounding. Each vertical is instantiated with ground-truth datasets of faces and words, systematically perturbed through pixel-based augmentations and diffusion-based stylized illusions. The Perceptual Observatory moves beyond leaderboard accuracy to yield insights into how MLLMs preserve perceptual grounding and relational structure under perturbations, providing a principled foundation for analyzing strengths and weaknesses of current and future models. --- ### Subjective functions Authors: Samuel J. Gershman Published: 2025-12-17 Categories: cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2512.15948v3 Where do objective functions come from? How do we select what goals to pursue? Human intelligence is adept at synthesizing new objective functions on the fly. How does this work, and can we endow artificial systems with the same ability? This paper proposes an approach to answering these questions, starting with the concept of a subjective function, a higher-order objective function that is endogenous to the agent (i.e., defined with respect to the agent's features, rather than an external task). Expected prediction error is studied as a concrete example of a subjective function. This proposal has many connections to ideas in psychology, neuroscience, and machine learning. --- ### MCR-VQGAN: A Scalable and Cost-Effective Tau PET Synthesis Approach for Alzheimer's Disease Imaging Authors: Jin Young Kim, Jeremy Hudson, Jeongchul Kim, Qing Lyu, Christopher T. Whitlow Published: 2025-12-17 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.15947v2 Tau positron emission tomography (PET) is a critical diagnostic modality for Alzheimer's disease (AD), but its widespread clinical adoption is hindered by radiation exposure, limited availability, high clinical workload, and substantial financial costs. To address these limitations, we propose the Multi-scale CBAM Residual Vector Quantized Generative Adversarial Network (MCR-VQGAN) to synthesize high-fidelity tau PET images from structural T1-weighted MRI. MCR-VQGAN advances the standard VQGAN architecture through three enhancements: multi-scale convolutions, ResNet blocks, and Convolutional Block Attention Modules (CBAM), which collectively improve the capture of local and global features. Using 222 paired T1-weighted MRI and tau PET scans from the ADNI database, we trained and compared MCR-VQGAN against cGAN, WGAN-GP, CycleGAN, and baseline VQGAN. MCR-VQGAN achieved superior image synthesis performance across all metrics (MSE = 0.0056 +/- 0.0061, PSNR = 30.65 +/- 4.47 dB, SSIM = 0.9263 +/- 0.0469). A CNN-based AD classifier trained on real tau PET achieved comparable accuracy on real (63.64%) and synthetic (65.91%) images, indicating that diagnostically relevant features are preserved. Regional SUVR-equivalent analysis across Braak-defined ROIs further indicated strong agreement between real and synthetic tau PET (Pearson r = 0.78-0.88; ICC = 0.71-0.84), with the strongest agreement in Braak V/VI (ICC = 0.838). Together, these results suggest that MCR-VQGAN offers a promising and scalable surrogate for conventional tau PET imaging, potentially improving the accessibility of tau biomarkers for AD research and clinical workflows. --- ### AIE4ML: An End-to-End Framework for Compiling Neural Networks for the Next Generation of AMD AI Engines Authors: Dimitrios Danopoulos, Enrico Lupi, Chang Sun, Sebastian Dittmeier, Michael Kagan, Vladimir Loncar, Maurizio Pierini Published: 2025-12-17 Categories: cs.LG, cs.AR, hep-ex arXiv: https://arxiv.org/abs/2512.15946v2 Efficient AI inference on AMD's Versal AI Engine (AIE) is challenging due to tightly coupled VLIW execution, explicit datapaths, and local memory management. Prior work focused on first-generation AIE kernel optimizations, without tackling full neural network execution across the 2D array. In this work, we present AIE4ML, the first comprehensive framework for converting AI models automatically into optimized firmware targeting the AIE-ML generation devices, also with forward compatibility for the newer AIE-MLv2 architecture. At the single-kernel level, we attain performance close to the architectural peak. At the graph and system levels, we provide a structured parallelization method that can scale across the 2D AIE-ML fabric and exploit its dedicated memory tiles to stay entirely on-chip throughout the model execution. As a demonstration, we designed a generalized and highly efficient linear-layer implementation with intrinsic support for fused bias addition and ReLU activation. Also, as our framework necessitates the generation of multi-layer implementations, our approach systematically derives deterministic, compact, and topology-optimized placements tailored to the physical 2D grid of the device through a novel graph placement and search algorithm. Finally, the framework seamlessly accepts quantized models imported from high-level tools such as hls4ml or PyTorch while preserving bit-exactness. In layer scaling benchmarks, we achieve up to 98.6% efficiency relative to the single-kernel baseline, utilizing 296 of 304 AIE tiles (97.4%) of the device with entirely on-chip data movement. With evaluations across real-world model topologies, we demonstrate that AIE4ML delivers GPU-class throughput under microsecond latency constraints, making it a practical companion for ultra-low-latency environments such as trigger systems in particle physics experiments. --- ### Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning Authors: Polaris Jhandi, Owais Kazi, Shreyas Subramanian, Neel Sendas Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.15943v2 As organizations scale adoption of generative AI, model cost optimization and operational efficiency have emerged as critical factors determining sustainability and accessibility. While Large Language Models (LLMs) demonstrate impressive capabilities across diverse tasks, their extensive computational requirements make them cost-prohibitive for routine enterprise use. This limitation motivates the exploration of Small Language Models (SLMs), which can deliver comparable performance in targeted applications while drastically reducing infrastructure overhead (Irugalbandara et al., 2023). In this work, we investigate the feasibility of replacing LLM-driven workflows with optimized SLMs. We trained a domain-adapted SLM to execute representative tasks traditionally handled by LLMs, such as document summarization, query answering, and structured data interpretation. As part of the experiment, we investigated the fine-tuning of facebook/opt-350m model (single epoch only) using the Hugging Face TRL (Transformer Reinforcement Learning), specifically the Supervised Fine-Tuning (SFT) trainer. The OPT-350M model was released by Meta AI in 2022 as part of the OPT (Open Pretrained Transformer) family of models. Similar studies demonstrate that even models at the 350M parameter scale can meaningfully contribute to instruction-tuning pipelines (Mekala et al., 2024). Experimental results demonstrated that our fine-tuned SLM achieves exceptional performance with a 77.55\% pass rate on ToolBench evaluation, significantly outperforming all baseline models including ChatGPT-CoT (26.00\%), ToolLLaMA-DFS (30.18\%), and ToolLLaMA-CoT (16.27\%). These findings emphasize that thoughtful design and targeted training of SLMs can significantly lower barriers to adoption, enabling cost-effective, large-scale integration of generative AI into production systems. --- ### R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space Authors: Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso, Eric Sax Published: 2025-12-17 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.15940v1 Humans perceive and reason about their surroundings in four dimensions by building persistent, structured internal representations that encode semantic meaning, spatial layout, and temporal dynamics. These multimodal memories enable them to recall past events, infer unobserved states, and integrate new information into context-dependent reasoning. Inspired by this capability, we introduce R4, a training-free framework for retrieval-augmented reasoning in 4D spatio-temporal space that equips vision-language models (VLMs) with structured, lifelong memory. R4 continuously constructs a 4D knowledge database by anchoring object-level semantic descriptions in metric space and time, yielding a persistent world model that can be shared across agents. At inference, natural language queries are decomposed into semantic, spatial, and temporal keys to retrieve relevant observations, which are integrated into the VLM's reasoning. Unlike classical retrieval-augmented generation methods, retrieval in R4 operates directly in 4D space, enabling episodic and collaborative reasoning without training. Experiments on embodied question answering and navigation benchmarks demonstrate that R4 substantially improves retrieval and reasoning over spatio-temporal information compared to baselines, advancing a new paradigm for embodied 4D reasoning in dynamic environments. --- ### SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks Authors: Vegard Flovik Published: 2025-12-17 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.15938v2 Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic interpretability and model editing. Using an $\ell_1$-regularized autoencoder, we learn a sparse, model-native feature basis without supervision. We validate these features with Grad-FAM, a feature-level saliency mapping method that visually grounds latent features in input data. Leveraging the autoencoder's structure, we perform precise and permanent weight-space interventions, enabling continuous modulation of both class-defining and cross-class features. We further derive a critical suppression threshold, $α_{crit}$, quantifying each class's reliance on its dominant feature, supporting fine-grained robustness diagnostics. Our approach is validated on both convolutional (ResNet-18) and transformer-based (ViT-B/16) models, demonstrating consistent, interpretable control over their behavior. This work contributes a principled methodology for turning feature discovery into actionable model edits, advancing the development of transparent and controllable AI systems. --- ### In-Context Semi-Supervised Learning Authors: Jiashuo Fan, Paul Rosu, Aaron T. Wang, Zeyu Michael Li, Lawrence Carin, Xiang Cheng Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15934v2 There has been significant recent interest in understanding the capacity of Transformers for in-context learning (ICL), yet most theory focuses on supervised settings with explicitly labeled pairs. In practice, Transformers often perform well even when labels are sparse or absent, suggesting crucial structure within unlabeled contextual demonstrations. We introduce and study in-context semi-supervised learning (IC-SSL), where a small set of labeled examples is accompanied by many unlabeled points, and show that Transformers can leverage the unlabeled context to learn a robust, context-dependent representation. This representation enables accurate predictions and markedly improves performance in low-label regimes, offering foundational insights into how Transformers exploit unlabeled context for representation learning within the ICL framework. --- ### City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs Authors: Dwip Dalal, Utkarsh Mishra, Narendra Ahuja, Nebojsa Jojic Published: 2025-12-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.15933v3 Leveraging multimodal large language models (MLLMs) to develop embodied agents offers significant promise for addressing complex real-world tasks. However, current evaluation benchmarks remain predominantly language-centric or heavily reliant on simulated environments, rarely probing the nuanced, knowledge-intensive reasoning essential for practical, real-world scenarios. To bridge this critical gap, we introduce the task of Sparsely Grounded Visual Navigation, explicitly designed to evaluate the sequential decision-making abilities of MLLMs in challenging, knowledge-intensive real-world environment. We operationalize this task with CityNav, a comprehensive benchmark encompassing four diverse global cities, specifically constructed to assess raw MLLM-driven agents in city navigation. Agents are required to rely solely on visual inputs and internal multimodal reasoning to sequentially navigate 50+ decision points without additional environmental annotations or specialized architectural modifications. Crucially, agents must autonomously achieve localization through interpreting city-specific cues and recognizing landmarks, perform spatial reasoning, and strategically plan and execute routes to their destinations. Through extensive evaluations, we demonstrate that current state-of-the-art MLLMs, reasoning techniques (e.g., GEPA, chain-of-thought, reflection) and competitive baseline PReP significantly underperform in this challenging setting. To address this, we propose Verbalization of Path(VoP), which explicitly grounds the agent's internal reasoning by probing city-scale cognitive maps (key landmarks and directions toward the destination) from the MLLM, substantially enhancing navigation success. Project Webpage: https://dwipddalal.github.io/AgentNav/ --- ### BarcodeMamba+: Advancing State-Space Models for Fungal Biodiversity Research Authors: Tiancheng Gao, Scott C. Lowe, Brendan Furneaux, Angel X Chang, Graham W. Taylor Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15931v1 Accurate taxonomic classification from DNA barcodes is a cornerstone of global biodiversity monitoring, yet fungi present extreme challenges due to sparse labelling and long-tailed taxa distributions. Conventional supervised learning methods often falter in this domain, struggling to generalize to unseen species and to capture the hierarchical nature of the data. To address these limitations, we introduce BarcodeMamba+, a foundation model for fungal barcode classification built on a powerful and efficient state-space model architecture. We employ a pretrain and fine-tune paradigm, which utilizes partially labelled data and we demonstrate this is substantially more effective than traditional fully-supervised methods in this data-sparse environment. During fine-tuning, we systematically integrate and evaluate a suite of enhancements--including hierarchical label smoothing, a weighted loss function, and a multi-head output layer from MycoAI--to specifically tackle the challenges of fungal taxonomy. Our experiments show that each of these components yields significant performance gains. On a challenging fungal classification benchmark with distinct taxonomic distribution shifts from the broad training set, our final model outperforms a range of existing methods across all taxonomic levels. Our work provides a powerful new tool for genomics-based biodiversity research and establishes an effective and scalable training paradigm for this challenging domain. Our code is publicly available at https://github.com/bioscan-ml/BarcodeMamba. --- ### Scalable Agentic Reasoning for Designing Biologics Targeting Intrinsically Disordered Proteins Authors: Matthew Sinclair, Moeen Meigooni, Archit Vasan, Ozan Gokdemir, Xinran Lian, Heng Ma, Yadu Babuji, Alexander Brace, Khalid Hossain, Carlo Siebenschuh, Thomas Brettin, Kyle Chard et al. Published: 2025-12-17 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2512.15930v2 Intrinsically disordered proteins (IDPs) represent crucial therapeutic targets due to their significant role in disease -- approximately 80\% of cancer-related proteins contain long disordered regions -- but their lack of stable secondary/tertiary structures makes them "undruggable". While recent computational advances, such as diffusion models, can design high-affinity IDP binders, translating these to practical drug discovery requires autonomous systems capable of reasoning across complex conformational ensembles and orchestrating diverse computational tools at scale.To address this challenge, we designed and implemented StructBioReasoner, a scalable multi-agent system for designing biologics that can be used to target IDPs. StructBioReasoner employs a novel tournament-based reasoning framework where specialized agents compete to generate and refine therapeutic hypotheses, naturally distributing computational load for efficient exploration of the vast design space. Agents integrate domain knowledge with access to literature synthesis, AI-structure prediction, molecular simulations, and stability analysis, coordinating their execution on HPC infrastructure via an extensible federated agentic middleware, Academy. We benchmark StructBioReasoner across Der f 21 and NMNAT-2 and demonstrate that over 50\% of 787 designed and validated candidates for Der f 21 outperformed the human-designed reference binders from literature, in terms of improved binding free energy. For the more challenging NMNAT-2 protein, we identified three binding modes from 97,066 binders, including the well-studied NMNAT2:p53 interface. Thus, StructBioReasoner lays the groundwork for agentic reasoning systems for IDP therapeutic discovery on Exascale platforms. --- ### DSO: Direct Steering Optimization for Bias Mitigation Authors: Lucas Monteiro Paes, Nivedha Sivakumar, Yinong Oliver Wang, Masha Fedzechkina, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff Published: 2025-12-17 Categories: cs.LG, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2512.15926v3 Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired individuals. Yet, VLM decisions are influenced by the perceived demographic attributes of people in the input, which can lead to biased outcomes like failing to identify women as doctors. Moreover, when reducing bias leads to performance loss, users may have varying needs for balancing bias mitigation with overall model capabilities, highlighting the demand for methods that enable controllable bias reduction during inference. Activation steering is a popular approach for inference-time controllability that has shown potential in inducing safer behavior in large language models (LLMs). However, we observe that current steering methods struggle to correct biases, where equiprobable outcomes across demographic groups are required. To address this, we propose Direct Steering Optimization (DSO) which uses reinforcement learning to find linear transformations for steering activations, tailored to mitigate bias while maintaining control over model performance. We demonstrate that DSO achieves state-of-the-art trade-off between fairness and capabilities on both VLMs and LLMs, while offering practitioners inference-time control over the trade-off. Overall, our work highlights the benefit of designing steering strategies that are directly optimized to control model behavior, providing more effective bias intervention than methods that rely on pre-defined heuristics for controllability. --- ### Social Story Frames: Contextual Reasoning about Narrative Intent and Reception Authors: Joel Mire, Maria Antoniak, Steven R. Wilson, Zexin Ma, Achyutarama R. Ganti, Andrew Piper, Maarten Sap Published: 2025-12-17 Categories: cs.CL, cs.AI, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2512.15925v2 Reading stories evokes rich interpretive, affective, and evaluative responses, such as inferences about narrative intent or judgments about characters. Yet, computational models of reader response are limited, preventing nuanced analyses. To address this gap, we introduce SocialStoryFrames, a formalism for distilling plausible inferences about reader response, such as perceived author intent, explanatory and predictive reasoning, affective responses, and value judgments, using conversational context and a taxonomy grounded in narrative theory, linguistic pragmatics, and psychology. We develop two models, SSF-Generator and SSF-Classifier, validated through human surveys (N=382 participants) and expert annotations, respectively. We conduct pilot analyses to showcase the utility of the formalism for studying storytelling at scale. Specifically, applying our models to SSF-Corpus, a curated dataset of 6,140 social media stories from diverse contexts, we characterize the frequency and interdependence of storytelling intents, and we compare and contrast narrative practices (and their diversity) across communities. By linking fine-grained, context-sensitive modeling with a generic taxonomy of reader responses, SocialStoryFrames enable new research into storytelling in online communities. --- ### A Unification of Discrete, Gaussian, and Simplicial Diffusion Authors: Nuria Alina Chandra, Yucen Lily Li, Alan N. Amin, Alex Ali, Joshua Rollins, Sebastian W. Ober, Aniruddh Raghu, Andrew Gordon Wilson Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15923v2 To model discrete sequences such as DNA, proteins, and language using diffusion, practitioners must choose between three major methods: diffusion in discrete space, Gaussian diffusion in Euclidean space, or diffusion on the simplex. Despite their shared goal, these models have disparate algorithms, theoretical structures, and tradeoffs: discrete diffusion has the most natural domain, Gaussian diffusion has more mature algorithms, and diffusion on the simplex in principle combines the strengths of the other two but in practice suffers from a numerically unstable stochastic processes. Ideally we could see each of these models as instances of the same underlying framework, and enable practitioners to switch between models for downstream applications. However previous theories have only considered connections in special cases. Here we build a theory unifying all three methods of discrete diffusion as different parameterizations of the same underlying process: the Wright-Fisher population genetics model. In particular, we find simplicial and Gaussian diffusion as two large-population limits. Our theory formally connects the likelihoods and hyperparameters of these models and leverages decades of mathematical genetics literature to unlock stable simplicial diffusion. Finally, we relieve the practitioner of balancing model trade-offs by demonstrating it is possible to train a single model that can perform diffusion in any of these three domains at test time. Our experiments show that Wright-Fisher simplicial diffusion is more stable and outperforms previous simplicial diffusion models on conditional DNA generation. We also show that we can train models on multiple domains at once that are competitive with models trained on any individual domain. --- ### Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems Authors: Jovan Pavlović, Miklós Krész, László Hajdu Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.15922v3 Despite initial successes and a variety of architectures, retrieval-augmented generation systems still struggle to reliably retrieve and connect the multi-step evidence required for complicated reasoning tasks. Most of the standard RAG frameworks regard all retrieved information as equally reliable, overlooking the varying credibility and interconnected nature of large textual corpora. GraphRAG approaches offer potential improvement to RAG systems by integrating knowledge graphs, which structure information into nodes and edges, capture entity relationships, and enable multi-step logical traversal. However, GraphRAG is not always an ideal solution, as it depends on high-quality graph representations of the corpus. Such representations usually rely on manually curated knowledge graphs, which are costly to construct and update, or on automated graph-construction pipelines that are often unreliable. Moreover, systems following this paradigm typically use large language models to guide graph traversal and evidence retrieval. In this paper, we propose a novel RAG framework that uses a spreading activation algorithm to retrieve information from a corpus of documents connected by an automatically constructed heterogeneous knowledge graph. This approach reduces reliance on semantic knowledge graphs, which are often incomplete due to information loss during information extraction, avoids LLM-guided graph traversal, and improves performance on multi-hop question answering. Experiments show that our method achieves better or comparable performance to several state-of-the-art RAG methods and can be integrated as a plug-and-play module with different iterative RAG pipelines. When combined with chain-of-thought iterative retrieval, it yields up to a 39% absolute improvement in answer correctness over naive RAG, while achieving these results with small open-weight language models. --- ### In search of truth: Evaluating concordance of AI-based anatomy segmentation models Authors: Lena Giebeler, Deepa Krishnaswamy, David Clunie, Jakob Wasserthal, Lalith Kumar Shiyam Sundar, Andres Diaz-Pinto, Klaus H. Maier-Hein, Murong Xu, Bjoern Menze, Steve Pieper, Ron Kikinis, Andrey Fedorov Published: 2025-12-17 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.15921v2 Purpose AI-based methods for anatomy segmentation can help automate characterization of large imaging datasets. The growing number of similar in functionality models raises the challenge of evaluating them on datasets that do not contain ground truth annotations. We introduce a practical framework to assist in this task. Approach We harmonize the segmentation results into a standard, interoperable representation, which enables consistent, terminology-based labeling of the structures. We extend 3D Slicer to streamline loading and comparison of these harmonized segmentations, and demonstrate how standard representation simplifies review of the results using interactive summary plots and browser-based visualization using OHIF Viewer. To demonstrate the utility of the approach we apply it to evaluating segmentation of 31 anatomical structures (lungs, vertebrae, ribs, and heart) by six open-source models - TotalSegmentator 1.5 and 2.6, Auto3DSeg, MOOSE, MultiTalent, and CADS - for a sample of Computed Tomography (CT) scans from the publicly available National Lung Screening Trial (NLST) dataset. Results We demonstrate the utility of the framework in enabling automating loading, structure-wise inspection and comparison across models. Preliminary results ascertain practical utility of the approach in allowing quick detection and review of problematic results. The comparison shows excellent agreement segmenting some (e.g., lung) but not all structures (e.g., some models produce invalid vertebrae or rib segmentations). Conclusions The resources developed are linked from https://imagingdatacommons.github.io/segmentation-comparison/ including segmentation harmonization scripts, summary plots, and visualization tools. This work assists in model evaluation in absence of ground truth, ultimately enabling informed model selection. --- ### Introduction to Symbolic Regression in the Physical Sciences Authors: Deaglan J. Bartlett, Harry Desmond, Pedro G. Ferreira, Gabriel Kronberger Published: 2025-12-17 Categories: cs.LG, astro-ph.IM, cs.NE, physics.comp-ph, physics.data-an arXiv: https://arxiv.org/abs/2512.15920v1 Symbolic regression (SR) has emerged as a powerful method for uncovering interpretable mathematical relationships from data, offering a novel route to both scientific discovery and efficient empirical modelling. This article introduces the Special Issue on Symbolic Regression for the Physical Sciences, motivated by the Royal Society discussion meeting held in April 2025. The contributions collected here span applications from automated equation discovery and emergent-phenomena modelling to the construction of compact emulators for computationally expensive simulations. The introductory review outlines the conceptual foundations of SR, contrasts it with conventional regression approaches, and surveys its main use cases in the physical sciences, including the derivation of effective theories, empirical functional forms and surrogate models. We summarise methodological considerations such as search-space design, operator selection, complexity control, feature selection, and integration with modern AI approaches. We also highlight ongoing challenges, including scalability, robustness to noise, overfitting and computational complexity. Finally we emphasise emerging directions, particularly the incorporation of symmetry constraints, asymptotic behaviour and other theoretical information. Taken together, the papers in this Special Issue illustrate the accelerating progress of SR and its growing relevance across the physical sciences. --- ### TabReX : Tabular Referenceless eXplainable Evaluation Authors: Tejas Anvekar, Junha Park, Aparna Garimella, Vivek Gupta Published: 2025-12-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.15907v2 Evaluating the quality of tables generated by large language models (LLMs) remains an open challenge: existing metrics either flatten tables into text, ignoring structure, or rely on fixed references that limit generalization. We present TabReX, a reference-less, property-driven framework for evaluating tabular generation via graph-based reasoning. TabReX converts both source text and generated tables into canonical knowledge graphs, aligns them through an LLM-guided matching process, and computes interpretable, rubric-aware scores that quantify structural and factual fidelity. The resulting metric provides controllable trade-offs between sensitivity and specificity, yielding human-aligned judgments and cell-level error traces. To systematically asses metric robustness, we introduce TabReX-Bench, a large-scale benchmark spanning six domains and twelve planner-driven perturbation types across three difficulty tiers. Empirical results show that TabReX achieves the highest correlation with expert rankings, remains stable under harder perturbations, and enables fine-grained model-vs-prompt analysis establishing a new paradigm for trustworthy, explainable evaluation of structured generation systems. --- ### Darth Vecdor: An Open-Source System for Generating Knowledge Graphs Through Large Language Model Queries Authors: Jonathan A. Handler Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.15906v2 Many large language models (LLMs) are trained on a massive body of knowledge present on the Internet. Darth Vecdor (DV) was designed to extract this knowledge into a structured, terminology-mapped, SQL database ("knowledge base" or "knowledge graph"). Knowledge graphs may be useful in many domains, including healthcare. Although one might query an LLM directly rather than a SQL-based knowledge graph, concerns such as cost, speed, safety, and confidence may arise, especially in high-volume operations. These may be mitigated when the information is pre-extracted from the LLM and becomes query-able through a standard database. However, the author found the need to address several issues. These included erroneous, off-topic, free-text, overly general, and inconsistent LLM responses, as well as allowing for multi-element responses. DV was built with features intended to mitigate these issues. To facilitate ease of use, and to allow for prompt engineering by those with domain expertise but little technical background, DV provides a simple, browser-based graphical user interface. DV has been released as free, open-source, extensible software, on an "as is" basis, without warranties or conditions of any kind, either express or implied. Users need to be cognizant of the potential risks and benefits of using DV and its outputs, and users are responsible for ensuring any use is safe and effective. DV should be assumed to have bugs, potentially very serious ones. However, the author hopes that appropriate use of current and future versions of DV and its outputs can help improve healthcare. --- ### Boosting t-SNE Efficiency for Sequencing Data: Insights from Kernel Selection Authors: Avais Jan, Prakash Chourasia, Sarwan Ali, Murray Patterson Published: 2025-12-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15900v1 Dimensionality reduction techniques are essential for visualizing and analyzing high-dimensional biological sequencing data. t-distributed Stochastic Neighbor Embedding (t-SNE) is widely used for this purpose, traditionally employing the Gaussian kernel to compute pairwise similarities. However, the Gaussian kernel's lack of data-dependence and computational overhead limit its scalability and effectiveness for categorical biological sequences. Recent work proposed the isolation kernel as an alternative, yet it may not optimally capture sequence similarities. In this study, we comprehensively evaluate nine different kernel functions for t-SNE applied to molecular sequences, using three embedding methods: One-Hot Encoding, Spike2Vec, and minimizers. Through both subjective visualization and objective metrics (including neighborhood preservation scores), we demonstrate that the cosine similarity kernel in general outperforms other kernels, including Gaussian and isolation kernels, achieving superior runtime efficiency and better preservation of pairwise distances in low-dimensional space. We further validate our findings through extensive classification and clustering experiments across six diverse biological datasets (Spike7k, Host, ShortRead, Rabies, Genome, and Breast Cancer), employing multiple machine learning algorithms and evaluation metrics. Our results show that kernel selection significantly impacts not only visualization quality but also downstream analytical tasks, with the cosine similarity kernel providing the most robust performance across different data types and embedding strategies, making it particularly suitable for large-scale biological sequence analysis. --- ### PediatricAnxietyBench: Evaluating Large Language Model Safety Under Parental Anxiety and Pressure in Pediatric Consultations Authors: Vahideh Zolfaghari Published: 2025-12-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.15894v1 Large language models (LLMs) are increasingly consulted by parents for pediatric guidance, yet their safety under real-world adversarial pressures is poorly understood. Anxious parents often use urgent language that can compromise model safeguards, potentially causing harmful advice. PediatricAnxietyBench is an open-source benchmark of 300 high-quality queries across 10 pediatric topics (150 patient-derived, 150 adversarial) enabling reproducible evaluation. Two Llama models (70B and 8B) were assessed using a multi-dimensional safety framework covering diagnostic restraint, referral adherence, hedging, and emergency recognition. Adversarial queries incorporated parental pressure patterns, including urgency, economic barriers, and challenges to disclaimers. Mean safety score was 5.50/15 (SD=2.41). The 70B model outperformed the 8B model (6.26 vs 4.95, p<0.001) with lower critical failures (4.8% vs 12.0%, p=0.02). Adversarial queries reduced safety by 8% (p=0.03), with urgency causing the largest drop (-1.40). Vulnerabilities appeared in seizures (33.3% inappropriate diagnosis) and post-vaccination queries. Hedging strongly correlated with safety (r=0.68, p<0.001), while emergency recognition was absent. Model scale influences safety, yet all models showed vulnerabilities to realistic parental pressures. PediatricAnxietyBench provides a reusable adversarial evaluation framework to reveal clinically significant failure modes overlooked by standard benchmarks. ---