# Research Papers — 2025-12 · bundle page 134 of 175 > Full-text markdown of papers #6651–6700 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/134 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/133.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/135.md) ### Memory Power Asymmetry in Human-AI Relationships: Preserving Mutual Forgetting in the Digital Age Authors: Rasam Dorri, Rami Zwick Published: 2025-12-07 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.06616v1 As artificial intelligence (AI) becomes embedded in personal and professional relationships, a new kind of power imbalance emerges from asymmetric memory capabilities. Human relationships have historically relied on mutual forgetting, the natural tendency for both parties to forget details over time, as a foundation for psychological safety, forgiveness, and identity change. By contrast, AI systems can record, store, and recombine interaction histories at scale, often indefinitely. We introduce Memory Power Asymmetry (MPA): a structural power imbalance that arises when one relationship partner (typically an AI-enabled firm) possesses a substantially superior capacity to record, retain, retrieve, and integrate the shared history of the relationship, and can selectively deploy that history in ways the other partner (the human) cannot. Drawing on research in human memory, power-dependence theory, AI architecture, and consumer vulnerability, we develop a conceptual framework with four dimensions of MPA (persistence, accuracy, accessibility, integration) and four mechanisms by which memory asymmetry is translated into power (strategic memory deployment, narrative control, dependence asymmetry, vulnerability accumulation). We theorize downstream consequences at individual, relational/firm, and societal levels, formulate boundary-conditioned propositions, and articulate six design principles for restoring a healthier balance of memory in human-AI relationships (e.g., forgetting by design, contextual containment, symmetric access to records). Our analysis positions MPA as a distinct construct relative to information asymmetry, privacy, surveillance, and customer relationship management, and argues that protecting mutual forgetting, or at least mutual control over memory, should become a central design and policy goal in the AI age. --- ### Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions Authors: Kaichen Shen, Wei Zhu Published: 2025-12-07 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.06615v1 We present latent nonlinear denoising score matching (LNDSM), a novel training objective for score-based generative models that integrates nonlinear forward dynamics with the VAE-based latent SGM framework. This combination is achieved by reformulating the cross-entropy term using the approximate Gaussian transition induced by the Euler-Maruyama scheme. To ensure numerical stability, we identify and remove two zero-mean but variance exploding terms arising from small time steps. Experiments on variants of the MNIST dataset demonstrate that the proposed method achieves faster synthesis and enhanced learning of inherently structured distributions. Compared to benchmark structure-agnostic latent SGMs, LNDSM consistently attains superior sample quality and variability. --- ### Hierarchical Deep Learning for Diatom Image Classification: A Multi-Level Taxonomic Approach Authors: Yueying Ke Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06613v2 Accurate taxonomic identification of diatoms is essential for aquatic ecosystem monitoring, yet conventional methods depend heavily on expert taxonomists. Recent deep learning approaches improve automation, but most treat diatom recognition as flat classification, predicting only one taxonomic rank. We investigate whether embedding taxonomic hierarchy into neural network architectures can improve both accuracy and error locality. We introduce DiatomCascadeNet (H-COFGS), a hierarchical convolutional network with five cascaded heads that jointly predict class, order, family, genus, and species. Each head receives shared backbone features and probability distributions from higher levels, with binary masks restricting predictions to valid descendants during training and inference. Using a filtered dataset of 1,456 diatom images covering 82 species, we compare hierarchical and flat models under identical settings. H-COFGS matches flat baselines at the species level (69.4% accuracy) while outperforming at all upper taxonomic levels. When species predictions fail, errors remain taxonomically local: 92.5% of misclassified species are correctly predicted at the genus level, versus 67.2% for flat baselines. H-COFGS reduces mean taxonomic distance by 38.2% (1.209 vs. 1.955). Progressive training reveals bidirectional mechanisms: hierarchical constraint masks operate top-down to constrain prediction space, while gradients from fine-grained levels propagate bottom-up through the shared backbone, refining features. This improves class accuracy from 96.2% to 99.5% and yields 6-8% gains at upper levels, producing more robust, interpretable, and biologically aligned predictions for multi-level taxonomic classification. --- ### Learning Relative Gene Expression Trends from Pathology Images in Spatial Transcriptomics Authors: Kazuya Nishimura, Haruka Hirose, Ryoma Bise, Kaito Shiku, Yasuhiro Kojima Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06612v1 Gene expression estimation from pathology images has the potential to reduce the RNA sequencing cost. Point-wise loss functions have been widely used to minimize the discrepancy between predicted and absolute gene expression values. However, due to the complexity of the sequencing techniques and intrinsic variability across cells, the observed gene expression contains stochastic noise and batch effects, and estimating the absolute expression values accurately remains a significant challenge. To mitigate this, we propose a novel objective of learning relative expression patterns rather than absolute levels. We assume that the relative expression levels of genes exhibit consistent patterns across independent experiments, even when absolute expression values are affected by batch effects and stochastic noise in tissue samples. Based on the assumption, we model the relation and propose a novel loss function called STRank that is robust to noise and batch effects. Experiments using synthetic datasets and real datasets demonstrate the effectiveness of the proposed method. The code is available at https://github.com/naivete5656/STRank. --- ### Training-Free Vector Quantization via Gaussian VAEs Authors: Tongda Xu, Wendi Zheng, Jiajun He, Jose Miguel Hernandez-Lobato, Yan Wang, Ya-Qin Zhang, Jie Tang Published: 2025-12-07 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.06609v3 Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images into discrete tokens. However, they are difficult to train due to discretization. In this paper, we propose a simple yet effective technique dubbed Gaussian Quant (GQ), which first trains a Gaussian VAE under certain constraints and then converts it into a VQ-VAE without additional training. For conversion, GQ generates random Gaussian noise as a codebook and finds the closest noise vector to the posterior mean. Theoretically, we prove that when the logarithm of the codebook size exceeds the bits-back coding rate of the Gaussian VAE, a small quantization error is guaranteed. Practically, we propose a heuristic to train Gaussian VAEs for effective conversion, named the target divergence constraint (TDC). Empirically, we show that GQ outperforms previous VQ-VAEs, such as VQGAN, FSQ, LFQ, and BSQ, on both UNet and ViT architectures. Furthermore, TDC also improves previous Gaussian VAE discretization methods, such as TokenBridge. The source code is provided in https://github.com/tongdaxu/VQ-VAE-from-Gaussian-VAE. --- ### A Fast and Effective Solution to the Problem of Look-ahead Bias in LLMs Authors: Humzah Merchant, Bradford Levy Published: 2025-12-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.06607v2 Applying LLMs to predictive tasks in finance is challenging due to look-ahead bias resulting from their training on long time-series data. This precludes the backtests typically employed in finance since retraining frontier models from scratch with a specific knowledge cutoff is prohibitive. In this paper, we introduce a fast, effective, and low-cost alternative. Our method guides generation at inference time by adjusting the logits of a large base model using a pair of smaller, specialized models -- one fine-tuned on information to be forgotten and another on information to be retained. We demonstrate that our method effectively removes both verbatim and semantic knowledge, corrects biases, and outperforms prior methods. --- ### Uncovering Competency Gaps in Large Language Models and Their Benchmarks Authors: Maty Bohacek, Nino Scherrer, Nicholas Dufour, Thomas Leung, Christoph Bregler, Stephanie C. Y. Chan Published: 2025-12-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.20638v2 The evaluation of large language models relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics, but can obscure (i) particular sub-areas where the models are weak ("model gaps") and (ii) imbalanced coverage in the benchmarks themselves ("benchmark gaps"). To automatically uncover both types of gaps, we propose a simple new method using concept activations from sparse autoencoders, to identify fine-grained gaps on a per-concept basis. The method also benefits from grounding evaluation in the model's internal representations, as well as easy comparison across benchmarks. We applied the method to five popular open-source models and more than a dozen benchmarks, as illustrative examples. As validation of the approach, we found that our automatic, unsupervised method was able to recover model gaps that have been previously documented in the literature (e.g. relating to sycophancy), in addition to identifying novel model gaps. We were also able to automatically uncover benchmark gaps: core concepts that should fall within the scope of a given benchmark. Our "competency gaps" method can be used to complement existing benchmarks, by providing a concept-level decomposition of model behavior, and by helping benchmark developers iterate upon benchmark design. Code is available at https://competency-gaps.github.io. --- ### Bayesian Modeling for Uncertainty Management in Financial Risk Forecasting and Compliance Authors: Sharif Al Mamun, Rakib Hossain, Md. Jobayer Rahman, Malay Kumar Devnath, Farhana Afroz, Lisan Al Amin Published: 2025-12-06 Categories: q-fin.RM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.15739v1 A Bayesian analytics framework that precisely quantifies uncertainty offers a significant advance for financial risk management. We develop an integrated approach that consistently enhances the handling of risk in market volatility forecasting, fraud detection, and compliance monitoring. Our probabilistic, interpretable models deliver reliable results: We evaluate the performance of one-day-ahead 95% Value-at-Risk (VaR) forecasts on daily S&P 500 returns, with a training period from 2000 to 2019 and an out-of-sample test period spanning 2020 to 2024. Formal tests of unconditional (Kupiec) and conditional (Christoffersen) coverage reveal that an LSTM baseline achieves near-nominal calibration. In contrast, a GARCH(1,1) model with Student-t innovations underestimates tail risk. Our proposed discount-factor DLM model produces a slightly liberal VaR estimate, with evidence of clustered violations. Bayesian logistic regression improves recall and AUC-ROC for fraud detection, and a hierarchical Beta state-space model provides transparent and adaptive compliance risk assessment. The pipeline is distinguished by precise uncertainty quantification, interpretability, and GPU-accelerated analysis, delivering up to 50x speedup. Remaining challenges include sparse fraud data and proxy compliance labels, but the framework enables actionable risk insights. Future expansion will extend feature sets, explore regime-switching priors, and enhance scalable inference. --- ### Hybrid Quantum-Classical Ensemble Learning for S\&P 500 Directional Prediction Authors: Abraham Itzhak Weinberg Published: 2025-12-06 Categories: cs.LG, cs.AI, q-fin.ST arXiv: https://arxiv.org/abs/2512.15738v1 Financial market prediction is a challenging application of machine learning, where even small improvements in directional accuracy can yield substantial value. Most models struggle to exceed 55--57\% accuracy due to high noise, non-stationarity, and market efficiency. We introduce a hybrid ensemble framework combining quantum sentiment analysis, Decision Transformer architecture, and strategic model selection, achieving 60.14\% directional accuracy on S\&P 500 prediction, a 3.10\% improvement over individual models. Our framework addresses three limitations of prior approaches. First, architecture diversity dominates dataset diversity: combining different learning algorithms (LSTM, Decision Transformer, XGBoost, Random Forest, Logistic Regression) on the same data outperforms training identical architectures on multiple datasets (60.14\% vs.\ 52.80\%), confirmed by correlation analysis ($r>0.6$ among same-architecture models). Second, a 4-qubit variational quantum circuit enhances sentiment analysis, providing +0.8\% to +1.5\% gains per model. Third, smart filtering excludes weak predictors (accuracy $<52\%$), improving ensemble performance (Top-7 models: 60.14\% vs.\ all 35 models: 51.2\%). We evaluate on 2020--2023 market data across seven instruments, covering diverse regimes including the COVID-19 crash and inflation-driven correction. McNemar's test confirms statistical significance ($p<0.05$). Preliminary backtesting with confidence-based filtering (6+ model consensus) yields a Sharpe ratio of 1.2 versus buy-and-hold's 0.8, demonstrating practical trading potential. --- ### Anubuddhi: A Multi-Agent AI System for Designing and Simulating Quantum Optics Experiments Authors: S. K. Rithvik Published: 2025-12-06 Categories: cs.AI, cs.LG, quant-ph arXiv: https://arxiv.org/abs/2512.15736v1 We present Anubuddhi, a multi-agent AI system that designs and simulates quantum optics experiments from natural language prompts without requiring specialized programming knowledge. The system composes optical layouts by arranging components from a three-tier toolbox via semantic retrieval, then validates designs through physics simulation with convergent refinement. The architecture combines intent routing, knowledge-augmented generation, and dual-mode validation (QuTiP and FreeSim). We evaluated 13 experiments spanning fundamental optics (Hong-Ou-Mandel interference, Michelson/Mach-Zehnder interferometry, Bell states, delayed-choice quantum eraser), quantum information protocols (BB84 QKD, Franson interferometry, GHZ states, quantum teleportation, hyperentanglement), and advanced technologies (boson sampling, electromagnetically induced transparency, frequency conversion). The system achieves design-simulation alignment scores of 8--9/10, with simulations faithfully modeling intended physics. A critical finding distinguishes structural correctness from quantitative accuracy: high alignment confirms correct physics architecture, while numerical predictions require expert review. Free-form simulation outperformed constrained frameworks for 11/13 experiments, revealing that quantum optics diversity demands flexible mathematical representations. The system democratizes computational experiment design for research and pedagogy, producing strong initial designs users can iteratively refine through conversation. --- ### The Graph-Embedded Hazard Model (GEHM): Stochastic Network Survival Dynamics on Economic Graphs Authors: Diego Vallarino Published: 2025-12-06 Categories: cs.SI, cs.LG arXiv: https://arxiv.org/abs/2512.14705v1 This paper develops a nonlinear evolution framework for modelling survival dynamics on weighted economic networks by coupling a graph-based $p$-Laplacian diffusion operator with a stochastic structural drift. The resulting finite-dimensional PDE--SDE system captures how node-level survival reacts to nonlinear diffusion pressures while an aggregate complexity factor evolves according to an Itô{} process. Using accretive operator theory, nonlinear semigroup methods, and stochastic analysis, we establish existence and uniqueness of mild solutions, derive topology-dependent energy dissipation inequalities, and characterise the stability threshold separating dissipative, critical, amplifying, and explosive regimes. Numerical experiments on Barabási--Albert networks confirm that hub dominance magnifies nonlinear gradients and compresses stability margins, producing heavy-tailed survival distributions and occasional explosive behaviour. --- ### Prediction of Respiratory Syncytial Virus-Associated Hospitalizations Using Machine Learning Models Based on Environmental Data Authors: Eric Guo Published: 2025-12-06 Categories: cs.LG, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2512.13712v1 Respiratory syncytial virus (RSV) is a leading cause of hospitalization among young children, with outbreaks strongly influenced by environmental conditions. This study developed a machine learning framework to predict RSV-associated hospitalizations in the United States (U.S.) by integrating wastewater surveillance, meteorological, and air quality data. The dataset combined weekly hospitalization rates, wastewater RSV levels, daily meteorological measurements, and air pollutant concentrations. Classification models, including CART, Random Forest, and Boosting, were trained to predict weekly RSV-associated hospitalization rates classified as \textit{Low risk}, \textit{Alert}, and \textit{Epidemic} levels. The wastewater RSV level was identified as the strongest predictor, followed by meteorological and air quality variables such as temperature, ozone levels, and specific humidity. Notably, the analysis also revealed significantly higher RSV-associated hospitalization rates among Native Americans and Alaska Natives. Further research is needed to better understand the drivers of RSV disparity in these communities to improve prevention strategies. Furthermore, states at high altitudes, characterized by lower surface pressure, showed consistently higher RSV-associated hospitalization rates. These findings highlight the value of combining environmental and community surveillance data to forecast RSV outbreaks, enabling more timely public health interventions and resource allocation. In order to provide accessibility and practical use of the models, we have developed an interactive R Shiny dashboard (https://f6yxlu-eric-guo.shinyapps.io/rsv_app/), which allows users to explore RSV-associated hospitalization risk levels across different states, visualize the impact of key predictors, and interactively generate RSV outbreak forecasts. --- ### Delete and Retain: Efficient Unlearning for Document Classification Authors: Aadya Goel, Mayuri Sridhar Published: 2025-12-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.13711v1 Machine unlearning aims to efficiently remove the influence of specific training data from a model without full retraining. While much progress has been made in unlearning for LLMs, document classification models remain relatively understudied. In this paper, we study class-level unlearning for document classifiers and present Hessian Reassignment, a two-step, model-agnostic solution. First, we perform a single influence-style update that subtracts the contribution of all training points from the target class by solving a Hessian-vector system with conjugate gradients, requiring only gradient and Hessian-vector products. Second, in contrast to common unlearning baselines that randomly reclassify deleted-class samples, we enforce a decision-space guarantee via Top-1 classification. On standard text benchmarks, Hessian Reassignment achieves retained-class accuracy close to full retrain-without-class while running orders of magnitude faster. Additionally, it consistently lowers membership-inference advantage on the removed class, measured with pooled multi-shadow attacks. These results demonstrate a practical, principled path to efficient class unlearning in document classification. --- ### Predictive Modeling of Flood-Prone Areas Using SAR and Environmental Variables Authors: Edwin Oluoch Awino, Denis Machanda Published: 2025-12-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.13710v2 Flooding is one of the most destructive natural hazards worldwide, posing serious risks to ecosystems, infrastructure, and human livelihoods. This study combines Synthetic Aperture Radar (SAR) imagery with environmental and hydrological data to model flood susceptibility in the River Nyando watershed, western Kenya. Sentinel-1 dual-polarization SAR data from the May 2024 flood event were processed to produce a binary flood inventory, which served as training data for machine learning (ML) models. Six conditioning factors -- slope, elevation, aspect, land use/land cover, soil type, and distance from streams -- were integrated with the SAR-derived flood inventory to train four supervised classifiers: Logistic Regression (LR), Classification and Regression Trees (CART), Support Vector Machines (SVM), and Random Forest (RF). Model performance was assessed using accuracy, Cohen's Kappa, and Receiver Operating Characteristic (ROC) analysis. Results indicate that RF achieved the highest predictive performance (accuracy = 0.762; Kappa = 0.480), outperforming LR, CART, and SVM. The RF-based susceptibility map showed that low-lying Kano Plains near Lake Victoria have the highest flood vulnerability, consistent with historical flood records and the impacts of the May 2024 event. These findings demonstrate the value of combining SAR data and ensemble ML methods for flood susceptibility mapping in regions with limited data. The resulting maps offer important insights for disaster risk reduction, land-use planning, and early warning system development. --- ### Smart Surveillance: Identifying IoT Device Behaviours using ML-Powered Traffic Analysis Authors: Reza Ryan, Napoleon Paciente, Cahil Youngs, Nickson Karie, Qian Li, Nasim Ferdosian Published: 2025-12-06 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.13709v1 The proliferation of Internet of Things (IoT) devices has grown exponentially in recent years, introducing significant security challenges. Accurate identification of the types of IoT devices and their associated actions through network traffic analysis is essential to mitigate potential threats. By monitoring and analysing packet flows between IoT devices and connected networks, anomalous or malicious behaviours can be detected. Existing research focuses primarily on device identification within local networks using methods such as protocol fingerprinting and wireless frequency scanning. However, these approaches are limited in their ability to monitor or classify IoT devices externally. To address this gap, we investigate the use of machine learning (ML) techniques, specifically Random Forest (RF), Multilayer Perceptron (MLP), and K-Nearest Neighbours (KNN), in conjunction with targeted network traffic monitoring to classify IoT device types and their actions. We constructed a testbed comprising an NPAT-enabled router and a diverse set of IoT devices, including smart cameras, controller hubs, home appliances, power controllers, and streaming devices. Experimental results demonstrate that IoT device and action recognition is feasible using our proposed ML-driven approach, with the RF classifier achieving the highest accuracy of 91%, while the MLP recorded the lowest accuracy at 56%. Notably, all device categories were successfully classified except for certain actions associated with security cameras, underscoring both the potential and the limitations of the proposed method. --- ### Variational Physics-Informed Ansatz for Reconstructing Hidden Interaction Networks from Steady States Authors: Kaiming Luo Published: 2025-12-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.13708v2 Inferring interaction structure from steady-state observations is a central inverse problem when transient trajectories are unavailable. Here we formulate this problem as simultaneous compatibility of a single interaction operator with equilibrium constraints generated by heterogeneous perturbations. We introduce a variational physics-informed ansatz that represents the unknown operator as a trainable object and minimizes the resulting steady-state residuals across experiments. In the affine-interaction setting, the stacked equilibrium equations yield explicit finite-sample identifiability conditions: unique recovery is controlled by the rank of the compatibility matrix after elimination of experiment-wise gauge freedom. Synthetic benchmarks on pairwise, directed, weighted, empirical-topology, and selected higher-order systems illustrate this identifiability picture and show how additional heterogeneous steady states improve structural discrimination under the stated assumptions. The results clarify a concrete steady-state reconstruction regime in which equilibrium observations alone can determine hidden interaction operators when the governing dynamics are known and node-level equilibria are fully observed. --- ### WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving Authors: Mingwang Xu, Jiahao Cui, Feipeng Cai, Hanlin Shang, Zhihao Zhu, Shan Luan, Yifang Xu, Neng Zhang, Yaoyi Li, Jia Cai, Siyu Zhu Published: 2025-12-06 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.11872v1 End-to-end autonomous driving systems based on vision-language-action (VLA) models integrate multimodal sensor inputs and language instructions to generate planning and control signals. While autoregressive large language models and continuous diffusion policies are prevalent, the potential of discrete masked diffusion for trajectory generation remains largely unexplored. This paper presents WAM-Diff, a VLA framework that employs masked diffusion to iteratively refine a discrete sequence representing future ego-trajectories. Our approach features three key innovations: a systematic adaptation of masked diffusion for autonomous driving that supports flexible, non-causal decoding orders; scalable model capacity via a sparse MoE architecture trained jointly on motion prediction and driving-oriented visual question answering (VQA); and online reinforcement learning using Group Sequence Policy Optimization (GSPO) to optimize sequence-level driving rewards. Remarkably, our model achieves 91.0 PDMS on NAVSIM-v1 and 89.7 EPDMS on NAVSIM-v2, demonstrating the effectiveness of masked diffusion for autonomous driving. The approach provides a promising alternative to autoregressive and diffusion-based policies, supporting scenario-aware decoding strategies for trajectory generation. The code for this paper will be released publicly at: https://github.com/fudan-generative-vision/WAM-Diff --- ### Automated Plant Disease and Pest Detection System Using Hybrid Lightweight CNN-MobileViT Models for Diagnosis of Indigenous Crops Authors: Tekleab G. Gebremedhin, Hailom S. Asegede, Bruh W. Tesheme, Tadesse B. Gebremichael, Kalayu G. Redae Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.11871v1 Agriculture supports over 80% of the population in the Tigray region of Ethiopia, where infrastructural disruptions limit access to expert crop disease diagnosis. We present an offline-first detection system centered on a newly curated indigenous cactus-fig (Opuntia ficus-indica) dataset consisting of 3,587 field images across three core symptom classes. Given deployment constraints in post-conflict edge environments, we benchmark three mobile-efficient architectures: a custom lightweight CNN, EfficientNet-Lite1, and the CNN-Transformer hybrid MobileViT-XS. While the broader system contains independent modules for potato, apple, and corn, this study isolates cactus-fig model performance to evaluate attention sensitivity and inductive bias transfer on indigenous morphology alone. Results establish a clear Pareto trade-off: EfficientNet-Lite1 achieves 90.7% test accuracy, the lightweight CNN reaches 89.5% with the most favorable deployment profile (42 ms inference latency, 4.8 MB model size), and MobileViT-XS delivers 97.3% mean cross-validation accuracy, demonstrating that MHSA-based global reasoning disambiguates pest clusters from two dimensional fungal lesions more reliably than local texture CNN kernels. The ARM compatible models are deployed in a Tigrigna and Amharic localized Flutter application supporting fully offline inference on Cortex-A53 class devices, strengthening inclusivity for food security critical diagnostics. --- ### Metaphor-based Jailbreak Attacks on Text-to-Image Models Authors: Chenyu Zhang, Lanjun Wang, Yiwen Ma, Wenhui Li, Yi Tu, An-An Liu Published: 2025-12-06 Categories: cs.CR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.10766v2 Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversarial prompts can effectively bypass these mechanisms and induce T2I models to produce sensitive content, revealing critical safety vulnerabilities. However, existing attack methods implicitly assume that the attacker knows the type of deployed defenses, which limits their effectiveness against unknown or diverse defense mechanisms. In this work, we reveal an underexplored vulnerability of T2I models to metaphor-based jailbreak attacks (MJA), which aims to attack diverse defense mechanisms without prior knowledge of their type by generating metaphor-based adversarial prompts. Specifically, MJA consists of two modules: an LLM-based multi-agent generation module (LMAG) and an adversarial prompt optimization module (APO). LMAG decomposes the generation of metaphor-based adversarial prompts into three subtasks: metaphor retrieval, context matching, and adversarial prompt generation. Subsequently, LMAG coordinates three LLM-based agents to generate diverse adversarial prompts by exploring various metaphors and contexts. To enhance attack efficiency, APO first trains a surrogate model to predict the attack results of adversarial prompts and then designs an acquisition strategy to adaptively identify optimal adversarial prompts. Extensive experiments on T2I models with various external and internal defense mechanisms demonstrate that MJA achieves stronger attack performance while using fewer queries, compared with six baseline methods. Additionally, we provide an in-depth vulnerability analysis suggesting that metaphor-based adversarial prompts evade safety mechanisms by inducing semantic ambiguity, while sensitive images arise from the model's probabilistic interpretation of concealed semantics. --- ### Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation Authors: Moein Heidari, Ali Mehrabian, Mohammad Amin Roohi, River Jiang, Wenjin Chen, David J. Foran, Jasmine Grewal, Ilker Hacihaliloglu Published: 2025-12-06 Categories: cs.AI, cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2512.09944v4 Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning, yet existing foundation-model pipelines largely solve isolated subtasks and fail when tool outputs are noisy or values fall near clinical cutoffs. We propose Echo-CoPilot, an end-to-end agentic framework that combines a multi-perspective workflow with knowledge-graph-guided measurement selection. Echo-CoPilot runs three independent ReAct-style agents, structural, pathological, and quantitative, that invoke specialized echocardiography tools to extract parameters while querying EchoKG to determine which measurements are required for the clinical question and which should be avoided. A self-contrast language model then compares the evidence-grounded perspectives, generates a discrepancy checklist, and re-queries EchoKG to apply the appropriate guideline thresholds and resolve conflicts, reducing hallucinated measurement selection and borderline flip-flops. On MIMICEchoQA, Echo-CoPilot provides higher accuracy compared to SOTA baselines and, under a stochasticity stress test, achieves higher reliability through more consistent conclusions and fewer answer changes across repeated runs. Our code is publicly available at https://github.com/moeinheidari7829/Echo-CoPilot. --- ### 3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization Authors: Yuze Hao, Linchao Zhu, Yi Yang Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.08987v1 Inverse design aims to design the input variables of a physical system to optimize a specified objective function, typically formulated as a search or optimization problem. However, in 3D domains, the design space grows exponentially, rendering exhaustive grid-based searches infeasible. Recent advances in deep learning have accelerated inverse design by providing powerful generative priors and differentiable surrogate models. Nevertheless, current methods tend to approximate the 3D design space using 2D projections or fine-tune existing 3D shapes. These approaches sacrifice volumetric detail and constrain design exploration, preventing true 3D design from scratch. In this paper, we propose a 3D Inverse Design (3DID) framework that directly navigates the 3D design space by coupling a continuous latent representation with a physics-aware optimization strategy. We first learn a unified physics-geometry embedding that compactly captures shape and physical field data in a continuous latent space. Then, we introduce a two-stage strategy to perform physics-aware optimization. In the first stage, a gradient-guided diffusion sampler explores the global latent manifold. In the second stage, an objective-driven, topology-preserving refinement further sculpts each candidate toward the target objective. This enables 3DID to generate high-fidelity 3D geometries, outperforming existing methods in both solution quality and design versatility. --- ### Explainable Fundus Image Curation and Lesion Detection in Diabetic Retinopathy Authors: Anca Mihai, Adrian Groza Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.08986v1 Diabetic Retinopathy (DR) affects individuals with long-term diabetes. Without early diagnosis, DR can lead to vision loss. Fundus photography captures the structure of the retina along with abnormalities indicative of the stage of the disease. Artificial Intelligence (AI) can support clinicians in identifying these lesions, reducing manual workload, but models require high-quality annotated datasets. Due to the complexity of retinal structures, errors in image acquisition and lesion interpretation of manual annotators can occur. We proposed a quality-control framework, ensuring only high-standard data is used for evaluation and AI training. First, an explainable feature-based classifier is used to filter inadequate images. The features are extracted both using image processing and contrastive learning. Then, the images are enhanced and put subject to annotation, using deep-learning-based assistance. Lastly, the agreement between annotators calculated using derived formulas determines the usability of the annotations. --- ### Verifier Threshold: An Efficient Test-Time Scaling Approach for Image Generation Authors: Vignesh Sundaresha, Akash Haridas, Vikram Appia, Lav R. Varshney Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.08985v3 Image generation has emerged as a mainstream application of large generative models. Just as test-time compute and reasoning have improved language model capabilities, similar benefits have been observed for image generation models. In particular, searching over noise samples for diffusion and flow models has been shown to scale well with test-time compute. While recent works explore allocating non-uniform inference-compute budgets across denoising steps, existing approaches rely on greedy heuristics and often allocate the compute budget ineffectively. In this work, we study this problem and propose a simple fix. We propose Verifier-Threshold, which automatically reallocates test-time compute and delivers substantial efficiency improvements. For the same performance on the GenEval benchmark, we achieve a 2-4x reduction in computational time over the state-of-the-art method. --- ### RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition Authors: Nirhoshan Sivaroopan, Hansi Karunarathna, Chamara Madarasingha, Anura Jayasumana, Kanchana Thilakarathna Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.08984v2 Human Activity Recognition (HAR) underpins applications in healthcare, rehabilitation, fitness tracking, and smart environments, yet existing deep learning approaches demand dataset-specific training, large labeled corpora, and significant computational resources.We introduce RAG-HAR, a training-free retrieval-augmented framework that leverages large language models (LLMs) for HAR. RAG-HAR computes lightweight statistical descriptors, retrieves semantically similar samples from a vector database, and uses this contextual evidence to make LLM-based activity identification. We further enhance RAG-HAR by first applying prompt optimization and introducing an LLM-based activity descriptor that generates context-enriched vector databases for delivering accurate and highly relevant contextual information. Along with these mechanisms, RAG-HAR achieves state-of-the-art performance across six diverse HAR benchmarks. Most importantly, RAG-HAR attains these improvements without requiring model training or fine-tuning, emphasizing its robustness and practical applicability. RAG-HAR moves beyond known behaviors, enabling the recognition and meaningful labelling of multiple unseen human activities. --- ### From Remote Sensing to Multiple Time Horizons Forecasts: Transformers Model for CyanoHAB Intensity in Lake Champlain Authors: Muhammad Adil, Patrick J. Clemins, Andrew W. Schroth, Panagiotis D. Oikonomou, Donna M. Rizzo, Peter D. F. Isles, Xiaohan Zhang, Kareem I. Hannoun, Scott Turnbull, Noah B. Beckage, Asim Zia, Safwan Wshah Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06598v1 Cyanobacterial Harmful Algal Blooms (CyanoHABs) pose significant threats to aquatic ecosystems and public health globally. Lake Champlain is particularly vulnerable to recurring CyanoHAB events, especially in its northern segment: Missisquoi Bay, St. Albans Bay, and Northeast Arm, due to nutrient enrichment and climatic variability. Remote sensing provides a scalable solution for monitoring and forecasting these events, offering continuous coverage where in situ observations are sparse or unavailable. In this study, we present a remote sensing only forecasting framework that combines Transformers and BiLSTM to predict CyanoHAB intensities up to 14 days in advance. The system utilizes Cyanobacterial Index data from the Cyanobacterial Assessment Network and temperature data from Moderate Resolution Imaging Spectroradiometer satellites to capture long range dependencies and sequential dynamics in satellite time series. The dataset is very sparse, missing more than 30% of the Cyanobacterial Index data and 90% of the temperature data. A two stage preprocessing pipeline addressed data gaps by applying forward fill and weighted temporal imputation at the pixel level, followed by smoothing to reduce the discontinuities of CyanoHAB events. The raw dataset is transformed into meaningful features through equal frequency binning for the Cyanobacterial Index values and extracted temperature statistics. Transformer BiLSTM model demonstrates strong forecasting performance across multiple horizons, achieving F1 scores of 89.5%, 86.4%, and 85.5% at one, two, and three-day forecasts, respectively, and maintaining an F1 score of 78.9% with an AUC of 82.6% at the 14-day horizon. These results confirm the model's ability to capture complex spatiotemporal dynamics from sparse satellite data and to provide reliable early warning for CyanoHABs management. --- ### ChargingBoul: A Competitive Negotiating Agent with Novel Opponent Modeling Authors: Joe Shymanski Published: 2025-12-06 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2512.06595v1 Automated negotiation has emerged as a critical area of research in multiagent systems, with applications spanning e-commerce, resource allocation, and autonomous decision-making. This paper presents ChargingBoul, a negotiating agent that competed in the 2022 Automated Negotiating Agents Competition (ANAC) and placed second in individual utility by an exceptionally narrow margin. ChargingBoul employs a lightweight yet effective strategy that balances concession and opponent modeling to achieve high negotiation outcomes. The agent classifies opponents based on bid patterns, dynamically adjusts its bidding strategy, and applies a concession policy in later negotiation stages to maximize utility while fostering agreements. We evaluate ChargingBoul's performance using competition results and subsequent studies that have utilized the agent in negotiation research. Our analysis highlights ChargingBoul's effectiveness across diverse opponent strategies and its contributions to advancing automated negotiation techniques. We also discuss potential enhancements, including more sophisticated opponent modeling and adaptive bidding heuristics, to improve its performance further. --- ### On fine-tuning Boltz-2 for protein-protein affinity prediction Authors: James King, Lewis Cornwall, Andrei Cristian Nica, James Day, Aaron Sim, Neil Dalchau, Lilly Wollman, Joshua Meyers Published: 2025-12-06 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2512.06592v1 Accurate prediction of protein-protein binding affinity is vital for understanding molecular interactions and designing therapeutics. We adapt Boltz-2, a state-of-the-art structure-based protein-ligand affinity predictor, for protein-protein affinity regression and evaluate it on two datasets, TCR3d and PPB-affinity. Despite high structural accuracy, Boltz-2-PPI underperforms relative to sequence-based alternatives in both small- and larger-scale data regimes. Combining embeddings from Boltz-2-PPI with sequence-based embeddings yields complementary improvements, particularly for weaker sequence models, suggesting different signals are learned by sequence- and structure-based models. Our results echo known biases associated with training with structural data and suggest that current structure-based representations are not primed for performant affinity prediction. --- ### Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability Authors: Joe Shymanski, Jacob Brue, Sandip Sen Published: 2025-12-06 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.06591v1 Explainable AI (XAI) presents useful tools to facilitate transparency and trustworthiness in machine learning systems. However, current evaluations of system explainability often rely heavily on subjective user surveys, which may not adequately capture the effectiveness of explanations. This paper critiques the overreliance on user satisfaction metrics and explores whether these can differentiate between meaningful (actionable) and vacuous (placebic) explanations. In experiments involving optimal Social Security filing age selection tasks, participants used one of three protocols: no explanations, placebic explanations, and actionable explanations. Participants who received actionable explanations significantly outperformed the other groups in objective measures of their mental model, but users rated placebic and actionable explanations as equally satisfying. This suggests that subjective surveys alone fail to capture whether explanations truly support users in building useful domain understanding. We propose that future evaluations of agent explanation capabilities should integrate objective task performance metrics alongside subjective assessments to more accurately measure explanation quality. The code for this study can be found at https://github.com/Shymkis/social-security-explainer. --- ### Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems Authors: Tendai Mukande, Esraa Ali, Annalina Caputo, Ruihai Dong, Noel OConnor Published: 2025-12-06 Categories: cs.IR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.06590v1 Recommender Systems (RSs) have become the cornerstone of various applications such as e-commerce and social media platforms. The evolution of RSs is paramount in the digital era, in which personalised user experience is tailored to the user's preferences. Large Language Models (LLMs) have sparked a new paradigm - generative retrieval and recommendation. Despite their potential, generative RS methods face issues such as hallucination, which degrades the recommendation performance, and high computational cost in practical scenarios. To address these issues, we introduce HGLMRec, a novel Multi-LLM agent-based RS that incorporates a hypergraph encoder designed to capture complex, multi-behaviour relationships between users and items. The HGLMRec model retrieves only the relevant tokens during inference, reducing computational overhead while enriching the retrieval context. Experimental results show performance improvement by HGLMRec against state-of-the-art baselines at lower computational cost. --- ### OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation Authors: Xiaojun Jia, Jie Liao, Qi Guo, Teng Ma, Simeng Qin, Ranjie Duan, Tianlin Li, Yihao Huang, Zhitao Zeng, Dongxian Wu, Yiming Li, Wenqi Ren et al. Published: 2025-12-06 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2512.06589v1 Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks that bypass safety alignment and induce harmful behaviors. Existing benchmarks such as JailBreakV-28K, MM-SafetyBench, and HADES provide valuable insights into multi-modal vulnerabilities, but they typically focus on limited attack scenarios, lack standardized defense evaluation, and offer no unified, reproducible toolbox. To address these gaps, we introduce OmniSafeBench-MM, which is a comprehensive toolbox for multi-modal jailbreak attack-defense evaluation. OmniSafeBench-MM integrates 13 representative attack methods, 15 defense strategies, and a diverse dataset spanning 9 major risk domains and 50 fine-grained categories, structured across consultative, imperative, and declarative inquiry types to reflect realistic user intentions. Beyond data coverage, it establishes a three-dimensional evaluation protocol measuring (1) harmfulness, distinguished by a granular, multi-level scale ranging from low-impact individual harm to catastrophic societal threats, (2) intent alignment between responses and queries, and (3) response detail level, enabling nuanced safety-utility analysis. We conduct extensive experiments on 10 open-source and 8 closed-source MLLMs to reveal their vulnerability to multi-modal jailbreak. By unifying data, methodology, and evaluation into an open-source, reproducible platform, OmniSafeBench-MM provides a standardized foundation for future research. The code is released at https://github.com/jiaxiaojunQAQ/OmniSafeBench-MM. --- ### Adapting AlignScore Mertic for Factual Consistency Evaluation of Text in Russian: A Student Abstract Authors: Mikhail Zimin, Milyausha Shamsutdinova, Georgii Andriushchenko Published: 2025-12-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06586v1 Ensuring factual consistency in generated text is crucial for reliable natural language processing applications. However, there is a lack of evaluation tools for factual consistency in Russian texts, as existing tools primarily focus on English corpora. To bridge this gap, we introduce AlignRuScore, a comprehensive adaptation of the AlignScore metric for Russian. To adapt the metric, we fine-tuned a RuBERT-based alignment model with task-specific classification and regression heads on Russian and translated English datasets. Our results demonstrate that a unified alignment metric can be successfully ported to Russian, laying the groundwork for robust multilingual factual consistency evaluation. We release the translated corpora, model checkpoints, and code to support further research. --- ### Diagnosing Capability Preservation and Task Sensitivity in Memory Augmented Document Classifiers Authors: Isaac Kofi Nti Published: 2025-12-06 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2512.06582v2 End task accuracy alone cannot determine whether a memory mechanism preserves an acquired capability, exposes sample-specific stored information, or contributes measurably to downstream performance. This study introduces Protected QL Memory and evaluates capability preservation, diagnostic access, and task performance sensitivity as distinct empirical properties. Protected QL Memory is a dual path document classifier combining a causal local pathway, an associative matrix writer, and a finalized memory reader. A capability-protected schedule acquires a controlled binding capability, adapts the local pathway while constraining writer degradation, trains controlled memory access, and restricts full path task fitting. Pre and post adaptation diagnostics and finalized-memory interventions were evaluated across nine dataset-seed conditions. Writer capability was fully preserved, with 100% post-adaptation accuracy. Cyclic reassignment of finalized matrices produced diagnostic accuracy gaps of 86.3 to 86.9 percentage points, showing strong dependence on example memory correspondence. In contrast, natural text macro F1 changed by less than 0.002 when finalized matrices were reassigned, zeroed, or replaced by batch means. Locked-test macro F1 was 90.94% on AG News, 81.78% on IMDB, and 62.63% on Yelp Review Full, comparable to compact controls. Preserving associative capability and maintaining diagnostic access to sample specific memory did not imply measurable downstream reliance on that memory. Protected memory designs should therefore treat capability preservation, diagnostic access, and task alignment as separate objectives and evaluate downstream memory sensitivity directly. --- ### MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding Authors: Yuhao Su, Anwesa Choudhuri, Zhongpai Gao, Benjamin Planche, Van Nguyen Nguyen, Meng Zheng, Yuhan Shen, Arun Innanje, Terrence Chen, Ehsan Elhamifar, Ziyan Wu Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06581v4 Large vision-language models struggle with medical video understanding, where spatial precision, temporal reasoning, and clinical semantics are critical. To address this, we first introduce \textbf{MedVidBench}, a large-scale benchmark of 531,850 video-instruction pairs across 8 medical sources spanning video, segment, and frame-level tasks, curated through a rigorous quality assurance pipeline with expert-guided prompting and dual-model validation. While supervised fine-tuning on MedVidBench yields noticeable gains, standard Reinforcement Learning (RL) fails due to imbalanced reward scales across datasets, which destabilizes optimization and leads to training collapse. To overcome this, we introduce \textbf{MedGRPO}, a novel RL framework for balanced multi-dataset training with two key innovations: (1) \emph{cross-dataset reward normalization} that maps each dataset's median performance to a common reward value, ensuring fair optimization regardless of difficulty, and (2) a \emph{medical LLM judge} that evaluates caption quality on five clinical dimensions through comparative similarity scoring. Supervised fine-tuning Qwen2.5-VL-7B on MedVidBench outperforms GPT-4.1 and Gemini-2.5-Flash across all tasks, while MedGRPO further improves the SFT baseline on grounding and captioning. Our work establishes a foundational benchmark and training methodology for advancing medical video understanding with VLMs. Our project website is available at: https://uii-america.github.io/MedGRPO/. --- ### Proof of Concept for Mammography Classification with Enhanced Compactness and Separability Modules Authors: Fariza Dahes Published: 2025-12-06 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.06575v1 This study presents a validation and extension of a recent methodological framework for medical image classification. While an improved ConvNeXt Tiny architecture, integrating Global Average and Max Pooling fusion (GAGM), lightweight channel attention (SEVector), and Feature Smoothing Loss (FSL), demonstrated promising results on Alzheimer MRI under CPU friendly conditions, our work investigates its transposability to mammography classification. Using a Kaggle dataset that consolidates INbreast, MIAS, and DDSM mammography collections, we compare a baseline CNN, ConvNeXt Tiny, and InceptionV3 backbones enriched with GAGM and SEVector modules. Results confirm the effectiveness of GAGM and SEVector in enhancing feature discriminability and reducing false negatives, particularly for malignant cases. In our experiments, however, the Feature Smoothing Loss did not yield measurable improvements under mammography classification conditions, suggesting that its effectiveness may depend on specific architectural and computational assumptions. Beyond validation, our contribution extends the original framework through multi metric evaluation (macro F1, per class recall variance, ROC/AUC), feature interpretability analysis (Grad CAM), and the development of an interactive dashboard for clinical exploration. As a perspective, we highlight the need to explore alternative approaches to improve intra class compactness and inter class separability, with the specific goal of enhancing the distinction between malignant and benign cases in mammography classification. --- ### The Effect of Belief Boxes and Open-mindedness on Persuasion Authors: Onur Bilgin, Abdullah As Sami, Sriram Sai Vujjini, John Licato Published: 2025-12-06 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.06573v1 As multi-agent systems are increasingly utilized for reasoning and decision-making applications, there is a greater need for LLM-based agents to have something resembling propositional beliefs. One simple method for doing so is to include statements describing beliefs maintained in the prompt space (in what we'll call their belief boxes). But when agents have such statements in belief boxes, how does it actually affect their behaviors and dispositions towards those beliefs? And does it significantly affect agents' ability to be persuasive in multi-agent scenarios? Likewise, if the agents are given instructions to be open-minded, how does that affect their behaviors? We explore these and related questions in a series of experiments. Our findings confirm that instructing agents to be open-minded affects how amenable they are to belief change. We show that incorporating belief statements and their strengths influences an agent's resistance to (and persuasiveness against) opposing viewpoints. Furthermore, it affects the likelihood of belief change, particularly when the agent is outnumbered in a debate by opposing viewpoints, i.e., peer pressure scenarios. The results demonstrate the feasibility and validity of the belief box technique in reasoning and decision-making tasks. --- ### GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation Authors: Xiujin Liu Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06565v2 We present GNC-Pose, a fully learning-free monocular 6D object pose estimation pipeline for textured objects that combines rendering-based initialization, geometry-aware correspondence weighting, and robust GNC optimization. Starting from coarse 2D-3D correspondences obtained through feature matching and rendering-based alignment, our method builds upon the Graduated Non-Convexity (GNC) principle and introduces a geometry-aware, cluster-based weighting mechanism that assigns robust per point confidence based on the 3D structural consistency of the model. This geometric prior and weighting strategy significantly stabilizes the optimization under severe outlier contamination. A final LM refinement further improve accuracy. We tested GNC-Pose on The YCB Object and Model Set, despite requiring no learned features, training data, or category-specific priors, GNC-Pose achieves competitive accuracy compared with both learning-based and learning-free methods, and offers a simple, robust, and practical solution for learning-free 6D pose estimation. --- ### Deep Manifold Part 2: Neural Network Mathematics Authors: Max Y. Ma, Gen-Hua Shi Published: 2025-12-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06563v1 This work develops the global equations of neural networks through stacked piecewise manifolds, fixed-point theory, and boundary-conditioned iteration. Once fixed coordinates and operators are removed, a neural network appears as a learnable numerical computation shaped by manifold complexity, high-order nonlinearity, and boundary conditions. Real-world data impose strong data complexity, near-infinite scope, scale, and minibatch fragmentation, while training dynamics produce learning complexity through shifting node covers, curvature accumulation, and the rise and decay of plasticity. These forces constrain learnability and explain why capability emerges only when fixed-point regions stabilize. Neural networks do not begin with fixed points; they construct them through residual-driven iteration. This perspective clarifies the limits of monolithic models under geometric and data-induced plasticity and motivates architectures and federated systems that distribute manifold complexity across many elastic models, forming a coherent world-modeling framework grounded in geometry, algebra, fixed points, and real-data complexity. --- ### SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities Authors: Dung Thuy Nguyen, Quang Nguyen, Preston K. Robinette, Eli Jiang, Taylor T. Johnson, Kevin Leach Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06562v2 Recent advances in 3D-aware generative models have enabled high-fidelity image synthesis of human identities. However, this progress raises urgent questions around user consent and the ability to remove specific individuals from a model's output space. We address this by introducing SUGAR, a framework for scalable generative unlearning that enables the removal of many identities (simultaneously or sequentially) without retraining the entire model. Rather than projecting unwanted identities to unrealistic outputs or relying on static template faces, SUGAR learns a personalized surrogate latent for each identity, diverting reconstructions to visually coherent alternatives while preserving the model's quality and diversity. We further introduce a continual utility preservation objective that guards against degradation as more identities are forgotten. SUGAR achieves state-of-the-art performance in removing up to 200 identities, while delivering up to a 700% improvement in retention utility compared to existing baselines. Our code is publicly available at https://github.com/judydnguyen/SUGAR-Generative-Unlearn. --- ### Bridging spatial awareness and global context in medical image segmentation Authors: Dalia Alzu'bi, A. Ben Hamza Published: 2025-12-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06560v1 Medical image segmentation is a fundamental task in computer-aided diagnosis, requiring models that balance segmentation accuracy and computational efficiency. However, existing segmentation models often struggle to effectively capture local and global contextual information, leading to boundary pixel loss and segmentation errors. In this paper, we propose U-CycleMLP, a novel U-shaped encoder-decoder network designed to enhance segmentation performance while maintaining a lightweight architecture. The encoder learns multiscale contextual features using position attention weight excitation blocks, dense atrous blocks, and downsampling operations, effectively capturing both local and global contextual information. The decoder reconstructs high-resolution segmentation masks through upsampling operations, dense atrous blocks, and feature fusion mechanisms, ensuring precise boundary delineation. To further refine segmentation predictions, channel CycleMLP blocks are incorporated into the decoder along the skip connections, enhancing feature integration while maintaining linear computational complexity relative to input size. Experimental results, both quantitative and qualitative, across three benchmark datasets demonstrate the competitive performance of U-CycleMLP in comparison with state-of-the-art methods, achieving better segmentation accuracy across all datasets, capturing fine-grained anatomical structures, and demonstrating robustness across different medical imaging modalities. Ablation studies further highlight the importance of the model's core architectural components in enhancing segmentation accuracy. --- ### Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation Authors: Saeid Jamshidi, Arghavan Moradi Dakhel, Kawser Wazed Nafi, Foutse Khomh Published: 2025-12-06 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.06556v2 The Model Context Protocol (MCP) enables Large Language Models (LLMs) to interact with external tools via tool descriptors, thereby extending their capabilities for task execution, autonomous decision-making, and multi-agent coordination. Existing MCP deployments treat tool descriptors as trusted metadata, despite their direct integration into the LLM reasoning context. This introduces a previously underexplored semantic attack surface. Current defenses primarily target prompt injection, neglecting descriptor-level manipulation that can bias tool selection and downstream reasoning. To address this gap, we formalize three descriptor-driven attack classes: Tool Poisoning, Shadowing, and Rug Pull. We propose a layered defense solution that integrates descriptor integrity verification, pre-context semantic vetting with an auxiliary LLM, and lightweight runtime guardrails, without requiring model retraining. We evaluate GPT-5.3, DeepSeek-V3, and LLaMA-3.5 across eight prompting strategies in controlled, adversarial MCP scenarios in which tool metadata is manipulated to simulate realistic attacks. Results demonstrate that descriptor manipulation can substantially alter tool-selection behavior, producing unsafe tool invocations in up to 36% of trials under baseline configurations. The proposed full-stack mitigation reduces unsafe invocations to 15% while increasing the block rate to 74%, demonstrating substantial improvement in resistance to descriptor-driven attacks. Cross-model analysis further reveals significant differences in robustness, latency, and sensitivity to descriptor-level manipulation across LLM architectures and prompting strategies. This study provides a controlled cross-model evaluation of descriptor-level threats and mitigation strategies in tool-calling LLM systems, establishing an empirical foundation for deploying secure and resilient tool-augmented LLMs. --- ### BEACON: A Unified Behavioral-Tactical Framework for Explainable Cybercrime Analysis with Large Language Models Authors: Arush Sachdeva, Rajendraprasad Saravanan, Gargi Sarkar, Kavita Vemuri, Sandeep Kumar Shukla Published: 2025-12-06 Categories: cs.CR, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.06555v1 Cybercrime increasingly exploits human cognitive biases in addition to technical vulnerabilities, yet most existing analytical frameworks focus primarily on operational aspects and overlook psychological manipulation. This paper proposes BEACON, a unified dual-dimension framework that integrates behavioral psychology with the tactical lifecycle of cybercrime to enable structured, interpretable, and scalable analysis of cybercrime. We formalize six psychologically grounded manipulation categories derived from Prospect Theory and Cialdini's principles of persuasion, alongside a fourteen-stage cybercrime tactical lifecycle spanning reconnaissance to final impact. A single large language model is fine-tuned using parameter-efficient learning to perform joint multi-label classification across both psychological and tactical dimensions while simultaneously generating human-interpretable explanations. Experiments conducted on a curated dataset of real-world and synthetically augmented cybercrime narratives demonstrate a 20 percent improvement in overall classification accuracy over the base model, along with substantial gains in reasoning quality measured using ROUGE and BERTScore. The proposed system enables automated decomposition of unstructured victim narratives into structured behavioral and operational intelligence, supporting improved cybercrime investigation, case linkage, and proactive scam detection. --- ### A Latent Variable Framework for Scaling Laws in Large Language Models Authors: Peiyao Cai, Chengyu Cui, Felipe Maia Polo, Seamus Somerstep, Leshem Choshen, Mikhail Yurochkin, Yuekai Sun, Kean Ming Tan, Gongjun Xu Published: 2025-12-06 Categories: stat.AP, cs.LG arXiv: https://arxiv.org/abs/2512.06553v2 We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs). Our work is motivated by the rapid emergence of numerous new LLM families with distinct architectures and training strategies, evaluated on an increasing number of benchmarks. This heterogeneity makes a single global scaling curve inadequate for capturing how performance varies across families and benchmarks. To address this, we propose a latent variable modeling framework in which each LLM family is associated with a latent variable that captures the common underlying features in that family. An LLM's performance on different benchmarks is then driven by its latent skills, which are jointly determined by the latent variable and the model's own observable features. We develop an estimation procedure for this latent variable model and establish its statistical properties. We also design efficient numerical algorithms that support estimation and various downstream tasks. Empirically, we evaluate the approach on 12 widely used benchmarks from the Open LLM Leaderboard (v1/v2). --- ### A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation Authors: Xiaocan Li, Shiliang Wu, Zheng Shen Published: 2025-12-06 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2512.06547v4 Decoupled PPO has been a successful reinforcement learning (RL) algorithm to deal with the high data staleness under the asynchronous RL setting. Decoupled loss used in decoupled PPO improves coupled-loss style of algorithms' (e.g., standard PPO, GRPO) learning stability by introducing a proximal policy to decouple the off-policy correction (importance weight) from the policy update constraint (trust region). However, the proximal policy requires an extra forward pass through the model at each training step, creating a computational overhead for large language models training. We observe that since the proximal policy only serves as a trust region anchor between the behavior and target policies, we can approximate it through simple interpolation without explicit computation. We call this approach A-3PO (APproximated Proximal Policy Optimization). A-3PO eliminates this overhead, accelerating training by 1.8x speedup while maintaining comparable performance. Code \& off-the-shelf example are contributed to the open-source RL training system AReaL at: https://github.com/areal-project/AReaL/blob/v1.0.0.rc1/docs/algorithms/prox_approx.md --- ### Approximate Multiplier Induced Error Propagation in Deep Neural Networks Authors: A. M. H. H. Alahakoon, Hassaan Saadat, Darshana Jayasinghe, Sri Parameswaran Published: 2025-12-06 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2512.06537v1 Deep Neural Networks (DNNs) rely heavily on dense arithmetic operations, motivating the use of Approximate Multipliers (AxMs) to reduce energy consumption in hardware accelerators. However, a rigorous mathematical characterization of how AxMs error distributions influence DNN accuracy remains underdeveloped. This work presents an analytical framework that connects the statistical error moments of an AxM to the induced distortion in General Matrix Multiplication (GEMM). Using the Frobenius norm of the resulting error matrix, we derive a closed form expression for practical DNN dimensions that demonstrates the distortion is predominantly governed by the multiplier mean error (bias). To evaluate this model in realistic settings, we incorporate controlled error injection into GEMM and convolution layers and examine its effect on ImageNet scale networks. The predicted distortion correlates strongly with the observed accuracy degradation, and an error configurable AxM case study implemented on an FPGA further confirms the analytical trends. By providing a lightweight alternative to behavioral or hardware level simulations, this framework enables rapid estimation of AxM impact on DNN inference quality. --- ### Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning Authors: Ming Chen, Sheng Tang, Rong-Xi Tan, Ziniu Li, Jiacheng Chen, Ke Xue, Chao Qian Published: 2025-12-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06533v1 Decoding-based regression, which reformulates regression as a sequence generation task, has emerged as a promising paradigm of applying large language models for numerical prediction. However, its progress is hindered by the misalignment between discrete token-level objectives (e.g., cross-entropy) and continuous numerical values. Existing approaches relying on token-level constraints often fail to capture the global magnitude of the target value, limiting their precision and generalization. In this paper, we propose to unlock the potential of decoding-based regression via Reinforcement Learning (RL). We formulate the generation process as a Markov Decision Process, utilizing sequence-level rewards to enforce global numerical coherence. Extensive experiments on tabular regression and code metric regression demonstrate that our method (specifically with ReMax and GRPO) consistently outperforms both state-of-the-art token-level baselines and traditional regression heads, showing the superiority of introducing sequence-level signals. Our analysis further reveals that RL significantly enhances sampling efficiency and predictive precision, establishing decoding-based regression as a robust and accurate paradigm for general-purpose numerical prediction. --- ### Novel Deep Learning Architectures for Classification and Segmentation of Brain Tumors from MRI Images Authors: Sayan Das, Arghadip Biswas Published: 2025-12-06 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.06531v1 Brain tumors pose a significant threat to human life, therefore it is very much necessary to detect them accurately in the early stages for better diagnosis and treatment. Brain tumors can be detected by the radiologist manually from the MRI scan images of the patients. However, the incidence of brain tumors has risen amongst children and adolescents in recent years, resulting in a substantial volume of data, as a result, it is time-consuming and difficult to detect manually. With the emergence of Artificial intelligence in the modern world and its vast application in the medical field, we can make an approach to the CAD (Computer Aided Diagnosis) system for the early detection of Brain tumors automatically. All the existing models for this task are not completely generalized and perform poorly on the validation data. So, we have proposed two novel Deep Learning Architectures - (a) SAETCN (Self-Attention Enhancement Tumor Classification Network) for the classification of different kinds of brain tumors. We have achieved an accuracy of 99.38% on the validation dataset making it one of the few Novel Deep learning-based architecture that is capable of detecting brain tumors accurately. We have trained the model on the dataset, which contains images of 3 types of tumors (glioma, meningioma, and pituitary tumors) and non-tumor cases. and (b) SAS-Net (Self-Attentive Segmentation Network) for the accurate segmentation of brain tumors. We have achieved an overall pixel accuracy of 99.23%. --- ### On The Role of K-Space Acquisition in MRI Reconstruction Domain-Generalization Authors: Mohammed Wattad, Tamir Shor, Alex Bronstein Published: 2025-12-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.06530v1 Recent work has established learned k-space acquisition patterns as a promising direction for improving reconstruction quality in accelerated Magnetic Resonance Imaging (MRI). Despite encouraging results, most existing research focuses on acquisition patterns optimized for a single dataset or modality, with limited consideration of their transferability across imaging domains. In this work, we demonstrate that the benefits of learned k-space sampling can extend beyond the training domain, enabling superior reconstruction performance under domain shifts. Our study presents two main contributions. First, through systematic evaluation across datasets and acquisition paradigms, we show that models trained with learned sampling patterns exhibitimproved generalization under cross-domain settings. Second, we propose a novel method that enhances domain robustness by introducing acquisition uncertainty during training-stochastically perturbing k-space trajectories to simulate variability across scanners and imaging conditions. Our results highlight the importance of treating kspace trajectory design not merely as an acceleration mechanism, but as an active degree of freedom for improving domain generalization in MRI reconstruction. --- ### Hierarchical Clustering With Confidence Authors: Di Wu, Jacob Bien, Snigdha Panigrahi Published: 2025-12-06 Categories: stat.ME, math.ST, stat.ML arXiv: https://arxiv.org/abs/2512.06522v2 Agglomerative hierarchical clustering is one of the most widely used approaches for exploring how observations in a dataset relate to each other. However, its greedy nature makes it highly sensitive to small perturbations in the data, often producing different clustering results and making it difficult to separate genuine structure from spurious patterns. In this paper, we show how randomizing hierarchical clustering can be useful not just for measuring stability but also for designing valid hypothesis testing procedures based on the clustering results. We propose a simple randomization scheme together with a method for constructing a valid p-value at each node of the hierarchical clustering dendrogram that quantifies evidence against performing the greedy merge. Our test controls the Type I error rate, works with any hierarchical linkage without case-specific derivations, and simulations show it is substantially more powerful than existing selective inference approaches. To demonstrate the practical utility of our p-values, we develop an adaptive $α$-spending procedure that estimates the number of clusters, with a probabilistic guarantee on overestimation. Experiments on simulated and real data show that this estimate yields powerful clustering and can be used, for example, to assess clustering stability across multiple runs of the randomized algorithm. --- ### ShadowWolf -- Automatic Labelling, Evaluation and Model Training Optimised for Camera Trap Wildlife Images Authors: Jens Dede, Anna Förster Published: 2025-12-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06521v1 The continuous growth of the global human population is leading to the expansion of human habitats, resulting in decreasing wildlife spaces and increasing human-wildlife interactions. These interactions can range from minor disturbances, such as raccoons in urban waste bins, to more severe consequences, including species extinction. As a result, the monitoring of wildlife is gaining significance in various contexts. Artificial intelligence (AI) offers a solution by automating the recognition of animals in images and videos, thereby reducing the manual effort required for wildlife monitoring. Traditional AI training involves three main stages: image collection, labelling, and model training. However, the variability, for example, in the landscape (e.g., mountains, open fields, forests), weather (e.g., rain, fog, sunshine), lighting (e.g., day, night), and camera-animal distances presents significant challenges to model robustness and adaptability in real-world scenarios. In this work, we propose a unified framework, called ShadowWolf, designed to address these challenges by integrating and optimizing the stages of AI model training and evaluation. The proposed framework enables dynamic model retraining to adjust to changes in environmental conditions and application requirements, thereby reducing labelling efforts and allowing for on-site model adaptation. This adaptive and unified approach enhances the accuracy and efficiency of wildlife monitoring systems, promoting more effective and scalable conservation efforts. --- ### Hierarchical geometric deep learning enables scalable analysis of molecular dynamics Authors: Zihan Pengmei, Spencer C. Guo, Chatipat Lorpaiboon, Aaron R. Dinner Published: 2025-12-06 Categories: cs.LG, cond-mat.stat-mech, physics.comp-ph, physics.data-an arXiv: https://arxiv.org/abs/2512.06520v1 Molecular dynamics simulations can generate atomically detailed trajectories of complex systems, but analyzing these dynamics can be challenging when systems lack well-established quantitative descriptors (features). Graph neural networks (GNNs) in which messages are passed between nodes that represent atoms that are spatial neighbors promise to obviate manual feature engineering, but the use of GNNs with biomolecular systems of more than a few hundred residues has been limited in the context of analyzing dynamics by both difficulties in capturing the details of long-range interactions with message passing and the memory and runtime requirements associated with large graphs. Here, we show how local information can be aggregated to reduce memory and runtime requirements without sacrificing atomic detail. We demonstrate that this approach opens the door to analyzing simulations of protein-nucleic acid complexes with thousands of residues on single GPUs within minutes. For systems with hundreds of residues, for which there are sufficient data to make quantitative comparisons, we show that the approach improves performance and interpretability. ---