# Research Papers — 2025-12 · bundle page 48 of 175 > Full-text markdown of papers #2351–2400 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/48 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/47.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/49.md) ### Comparing Dynamical Models Through Diffeomorphic Vector Field Alignment Authors: Ruiqi Chen, Giacomo Vedovati, Todd Braver, ShiNung Ching Published: 2025-12-21 Categories: cs.LG, eess.SY, q-bio.NC arXiv: https://arxiv.org/abs/2512.18566v1 Dynamical systems models such as recurrent neural networks (RNNs) are increasingly popular in theoretical neuroscience for hypothesis-generation and data analysis. Evaluating the dynamics in such models is key to understanding their learned generative mechanisms. However, such evaluation is impeded by two major challenges: First, comparison of learned dynamics across models is difficult because there is no enforced equivalence of their coordinate systems. Second, identification of mechanistically important low-dimensional motifs (e.g., limit sets) is intractable in high-dimensional nonlinear models such as RNNs. Here, we propose a comprehensive framework to address these two issues, termed Diffeomorphic vector field alignment FOR learned Models (DFORM). DFORM learns a nonlinear coordinate transformation between the state spaces of two dynamical systems, which aligns their trajectories in a maximally one-to-one manner. In so doing, DFORM enables an assessment of whether two models exhibit topological equivalence, i.e., similar mechanisms despite differences in coordinate systems. A byproduct of this method is a means to locate dynamical motifs on low-dimensional manifolds embedded within higher-dimensional systems. We verified DFORM's ability to identify linear and nonlinear coordinate transformations using canonical topologically equivalent systems, RNNs, and systems related by nonlinear flows. DFORM was also shown to provide a quantification of similarity between topologically distinct systems. We then demonstrated that DFORM can locate important dynamical motifs including invariant manifolds and saddle limit sets within high-dimensional models. Finally, using a set of RNN models trained on human functional MRI (fMRI) recordings, we illustrated that DFORM can identify limit cycles from high-dimensional data-driven models, which agreed well with prior numerical analysis. --- ### Vox Deorum: A Hybrid LLM Architecture for 4X / Grand Strategy Game AI -- Lessons from Civilization V Authors: John Chen, Sihan Cheng, Can Gurkan, Ryan Lay, Moez Salahuddin Published: 2025-12-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.18564v2 Large Language Models' capacity to reason in natural language makes them uniquely promising for 4X and grand strategy games, enabling more natural human-AI gameplay interactions such as collaboration and negotiation. However, these games present unique challenges due to their complexity and long-horizon nature, while latency and cost factors may hinder LLMs' real-world deployment. Working on a classic 4X strategy game, Sid Meier's Civilization V with the Vox Populi mod, we introduce Vox Deorum, a hybrid LLM+X architecture. Our layered technical design empowers LLMs to handle macro-strategic reasoning, delegating tactical execution to subsystems (e.g., algorithmic AI or reinforcement learning AI in the future). We validate our approach through 2,327 complete games, comparing two open-source LLMs with a simple prompt against Vox Populi's enhanced AI. Results show that LLMs achieve competitive end-to-end gameplay while exhibiting play styles that diverge substantially from algorithmic AI and from each other. Our work establishes a viable architecture for integrating LLMs in commercial 4X games, opening new opportunities for game design and agentic AI research. --- ### OpenView: Empowering MLLMs with Out-of-view VQA Authors: Qixiang Chen, Cheng Zhang, Chi-Wing Fu, Jingwen Ye, Jianfei Cai Published: 2025-12-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18563v1 Recent multimodal large language models (MLLMs) show great potential in natural image understanding. Yet, they perform well, mainly on reasoning in-view contents within the image frame. This paper presents the first study on out-of-view (OOV) understanding, i.e., the ability to reason objects, activities, and scenes beyond the visible frame of a perspective view. Our technical contributions are threefold. First, we design OpenView, a four-stage pipeline to massively generate multi-choice VQA by leveraging panoramic imagery to enable context-rich and spatial-grounded VQA synthesis with free-view framing. Second, we curate OpenView-Dataset, a high-quality synthetic dataset from diverse real-world panoramas to empower MLLMs upon supervised fine-tuning. Third, we build OpenView-Bench, a benchmark that jointly measures choice and rationale accuracy for interpretable and diagnosable evaluation. Experimental results show that despite having a large gap from human performance in OOV VQA answer selection, upon empowered by OpenView, multiple MLLMs can consistently boost their performance, uplifted from 48.6% to 64.1% on average. Code, benchmark, and data will be available at https://github.com/q1xiangchen/OpenView. --- ### Adaptive Accountability in Networked MAS: Tracing and Mitigating Emergent Norms at Scale Authors: Saad Alqithami Published: 2025-12-21 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2512.18561v3 Large-scale networked multi-agent systems increasingly underpin critical infrastructure, yet their collective behavior can drift toward undesirable emergent norms such as collusion, resource hoarding, and implicit unfairness. We present the Adaptive Accountability Framework (AAF), an end-to-end runtime layer that (i) records cryptographically verifiable interaction provenance, (ii) detects distributional change points in streaming traces, (iii) attributes responsibility via a causal influence graph, and (iv) applies cost-bounded interventions-reward shaping and targeted policy patching-to steer the system back toward compliant behavior. We establish a bounded-compromise guarantee: if the expected cost of intervention exceeds an adversary's expected payoff, the long-run fraction of compromised interactions converges to a value strictly below one. We evaluate AAF in a large-scale factorial simulation suite (87,480 runs across two tasks; up to 100 agents plus a 500-agent scaling sweep; full and partial observability; Byzantine rates up to 10%; 10 seeds per regime). Across 324 regimes, AAF lowers the executed compromise ratio relative to a Proximal Policy Optimization baseline in 96% of regimes (median relative reduction 11.9%) while preserving social welfare (median change 0.4%). Under adversarial injections, AAF detects norm violations with a median delay of 71 steps (interquartile range 39-177) and achieves a mean top-ranked attribution accuracy of 0.97 at 10% Byzantine rate. --- ### Enhancing Medical Large Vision-Language Models via Alignment Distillation Authors: Aofei Chang, Ting Wang, Fenglong Ma Published: 2025-12-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.18554v1 Medical Large Vision-Language Models (Med-LVLMs) have shown promising results in clinical applications, but often suffer from hallucinated outputs due to misaligned visual understanding. In this work, we identify two fundamental limitations contributing to this issue: insufficient visual representation learning and poor visual attention alignment. To address these problems, we propose MEDALIGN, a simple, lightweight alignment distillation framework that transfers visual alignment knowledge from a domain-specific Contrastive Language-Image Pre-training (CLIP) model to Med-LVLMs. MEDALIGN introduces two distillation losses: a spatial-aware visual alignment loss based on visual token-level similarity structures, and an attention-aware distillation loss that guides attention toward diagnostically relevant regions. Extensive experiments on medical report generation and medical visual question answering (VQA) benchmarks show that MEDALIGN consistently improves both performance and interpretability, yielding more visually grounded outputs. --- ### Hierarchical Bayesian Framework for Multisource Domain Adaptation Authors: Alexander M. Glandon, Khan M. Iftekharuddin Published: 2025-12-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18553v1 Multisource domain adaptation (MDA) aims to use multiple source datasets with available labels to infer labels on a target dataset without available labels for target supervision. Prior works on MDA in the literature is ad-hoc as the pretraining of source models is either based on weight sharing or uses independently trained models. This work proposes a Bayesian framework for pretraining in MDA by considering that the distributions of different source domains are typically similar. The Hierarchical Bayesian Framework uses similarity between the different source data distributions to optimize the pretraining for MDA. Experiments using the proposed Bayesian framework for MDA show that our framework improves accuracy on recognition tasks for a large benchmark dataset. Performance comparison with state-of-the-art MDA methods on the challenging problem of human action recognition in multi-domain benchmark Daily-DA RGB video shows the proposed Bayesian Framework offers a 17.29% improvement in accuracy when compared to the state-of-the-art methods in the literature. --- ### Toward Training Superintelligent Software Agents through Self-Play SWE-RL Authors: Yuxiang Wei, Zhiqing Sun, Emily McMilin, Jonas Gehring, David Zhang, Gabriel Synnaeve, Daniel Fried, Lingming Zhang, Sida Wang Published: 2025-12-21 Categories: cs.SE, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.18552v3 While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g., pass-to-pass and fail-to-pass tests) heavily depend on human knowledge or curation, posing a fundamental barrier to superintelligence. In this paper, we present Self-play SWE-RL (SSR), a first step toward training paradigms for superintelligent software agents. Our approach takes minimal data assumptions, only requiring access to sandboxed repositories with source code and installed dependencies, with no need for human-labeled issues or tests. Grounded in these real-world codebases, a single LLM agent is trained via reinforcement learning in a self-play setting to iteratively inject and repair software bugs of increasing complexity, with each bug formally specified by a test patch rather than a natural language issue description. On the SWE-bench Verified and SWE-Bench Pro benchmarks, SSR achieves notable self-improvement (+10.4 and +7.8 points, respectively) and consistently outperforms the human-data baseline over the entire training trajectory, despite being evaluated on natural language issues absent from self-play. Our results, albeit early, suggest a path where agents autonomously gather extensive learning experiences from real-world software repositories, ultimately enabling superintelligent systems that exceed human capabilities in understanding how systems are constructed, solving novel challenges, and autonomously creating new software from scratch. --- ### Neologism Learning as a Parameter-Efficient Alternative to Fine-Tuning for Model Steering Authors: Sungjoon Park, Varun Ramamurthi, Owen Terry Published: 2025-12-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18551v1 In language modeling, neologisms are new tokens trained to represent a concept not already included in a given model's vocabulary. Neologisms can be used to encourage specific behavior in models, for example by appending prompts with "Give me a neologism answer." Behavioral steering can also be achieved through fine-tuning, albeit with more compute and less flexibility: learning a neologism only trains d parameters and allows the user to still access the model's default behavior. We compare the performance of neologism learning against low-rank adaptation (LoRA) fine-tuning, finding that neologisms outperform fine-tuned models under a matched training setup (same data and hyperparameters). We also investigate self-verbalizations of neologisms, and observe that the model will occasionally make up its own new words when asked about a neologism. --- ### LLMs on Drugs: Language Models Are Few-Shot Consumers Authors: Alexander Doudkin Published: 2025-12-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18546v1 Large language models (LLMs) are sensitive to the personas imposed on them at inference time, yet prompt-level "drug" interventions have never been benchmarked rigorously. We present the first controlled study of psychoactive framings on GPT-5-mini using ARC-Challenge. Four single-sentence prompts -- LSD, cocaine, alcohol, and cannabis -- are compared against a sober control across 100 validation items per condition, with deterministic decoding, full logging, Wilson confidence intervals, and Fisher exact tests. Control accuracy is 0.45; alcohol collapses to 0.10 (p = 3.2e-8), cocaine to 0.21 (p = 4.9e-4), LSD to 0.19 (p = 1.3e-4), and cannabis to 0.30 (p = 0.041), largely because persona prompts disrupt the mandated "Answer: <LETTER>" template. Persona text therefore behaves like a "few-shot consumable" that can destroy reliability without touching model weights. All experimental code, raw results, and analysis scripts are available at https://github.com/lexdoudkin/llms-on-drugs. --- ### Resisting Correction: How RLHF Makes Language Models Ignore External Safety Signals in Natural Conversation Authors: Felipe Biava Cataneo Published: 2025-12-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.08842v1 Safety architectures for language models increasingly rely on external monitors to detect errors and inject corrective signals at inference time. For such systems to function in interactive settings, models must be able to incorporate externally provided confidence information into their verbal responses. In this work, we test whether instruction-tuned language models preserve this controllability across different interaction modes. Using Llama-3.2-3B on GSM8K, we perform a causal intervention study in which explicit external confidence signals are injected and model compliance is measured under multiple prompt strategies. We find that base models exhibit near-perfect controllability (Spearman rho close to 1.0), while instruction-tuned models display a striking context dependence: they fully comply with external corrections under explicit command prompts (bias approximately 0 percent, rho = 0.93), yet systematically ignore the same signals in natural conversational queries (bias plus 40 percent, rho = 0.04). This behavior is not a capability failure; the model can process the signal, but an emergent property of RLHF optimization that prioritizes conversational fluency over external calibration cues in natural dialogue. We further show that internal token-level confidence in small models is uninformative (r = 0.035), underscoring the necessity of external supervision. Our findings highlight a deployment-critical failure mode: the interaction style users expect is precisely where safety corrections are least effective. --- ### Attachment Styles and AI Chatbot Interactions Among College Students Authors: Ziqi Lin, Taiyu Hou Published: 2025-12-20 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.04217v1 The use of large language model (LLM)-based AI chatbots among college students has increased rapidly, yet little is known about how individual psychological attributes shape students' interaction patterns with these technologies. This qualitative study explored how college students with different attachment styles describe their interactions with ChatGPT. Using semi-structured interviews with seven undergraduate students and grounded theory analysis, we identified three main themes: (1) AI as a low-risk emotional space, where participants across attachment styles valued the non-judgmental and low-stakes nature of AI interactions; (2) attachment-congruent patterns of AI engagement, where securely attached students integrated AI as a supplementary tool within their existing support systems, while avoidantly attached students used AI to buffer vulnerability and maintain interpersonal boundaries; and (3) the paradox of AI intimacy, capturing the tension between students' willingness to disclose personal information to AI while simultaneously recognizing its limitations as a relational partner. These findings suggest that attachment orientations play an important role in shaping how students experience and interpret their interactions with AI chatbots, extending attachment theory to the domain of human-AI interaction. --- ### Computable Gap Assessment of Artificial Intelligence Governance in Children's Centres: Evidence-Mechanism-Governance-Indicator Modelling of UNICEF's Guidance on AI and Children 3.0 Based on the Graph-GAP Framework Authors: Wei Meng Published: 2025-12-20 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.04216v1 This paper tackles practical challenges in governing child centered artificial intelligence: policy texts state principles and requirements but often lack reproducible evidence anchors, explicit causal pathways, executable governance toolchains, and computable audit metrics. We propose Graph-GAP, a methodology that decomposes requirements from authoritative policy texts into a four layer graph of evidence, mechanism, governance, and indicator, and that computes two metrics, GAP score and mitigation readiness, to identify governance gaps and prioritise actions. Using the UNICEF Innocenti Guidance on AI and Children 3.0 as primary material, we define reproducible extraction units, coding manuals, graph patterns, scoring scales, and consistency checks, and we demonstrate exemplar gap profiles and governance priority matrices for ten requirements. Results suggest that compared with privacy and data protection, requirements related to child well being and development, explainability and accountability, and cross agency implementation and resource allocation are more prone to indicator gaps and mechanism gaps. We recommend translating requirements into auditable closed loop governance that integrates child rights impact assessments, continuous monitoring metrics, and grievance redress procedures. At the coding level, we introduce a multi algorithm review aggregation revision workflow that runs rule based encoders, statistical or machine learning evaluators, and large model evaluators with diverse prompt configurations as parallel coders. Each extraction unit outputs evidence, mechanism, governance, and indicator labels plus readiness scores with evidence anchors. Reliability, stability, and uncertainty are assessed using Krippendorff alpha, weighted kappa, intraclass correlation, and bootstrap confidence intervals. --- ### Modeling Day-Long ECG Signals to Predict Heart Failure Risk with Explainable AI Authors: Eran Zvuloni, Ronit Almog, Michael Glikson, Shany Brimer Biton, Ilan Green, Izhar Laufer, Offer Amir, Joachim A. Behar Published: 2025-12-20 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.00014v2 Heart failure (HF) affects 11.8% of adults aged 65 and older, reducing quality of life and longevity. Preventing HF can reduce morbidity and mortality. We hypothesized that artificial intelligence (AI) applied to 24-hour single-lead electrocardiogram (ECG) data could predict the risk of HF within five years. To research this, the Technion-Leumit Holter ECG (TLHE) dataset, including 69,663 recordings from 47,729 patients, collected over 20 years was used. Our deep learning model, DeepHHF, trained on 24-hour ECG recordings, achieved an area under the receiver operating characteristic curve of 0.80 that outperformed a model using 30-second segments and a clinical score. High-risk individuals identified by DeepHHF had a two-fold chance of hospitalization or death incidents. Explainability analysis showed DeepHHF focused on arrhythmias and heart abnormalities. This study highlights the feasibility of deep learning to model 24-hour continuous ECG data, capturing paroxysmal events essential for reliable risk prediction. Artificial intelligence applied to single-lead Holter ECG is non-invasive, inexpensive, and widely accessible, making it a promising tool for HF risk prediction. --- ### Neural Brain Fields: A NeRF-Inspired Approach for Generating Nonexistent EEG Electrodes Authors: Shahar Ain Kedem, Itamar Zimerman, Eliya Nachmani Published: 2025-12-20 Categories: eess.SP, cs.AI, cs.CV, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2601.00012v1 Electroencephalography (EEG) data present unique modeling challenges because recordings vary in length, exhibit very low signal to noise ratios, differ significantly across participants, drift over time within sessions, and are rarely available in large and clean datasets. Consequently, developing deep learning methods that can effectively process EEG signals remains an open and important research problem. To tackle this problem, this work presents a new method inspired by Neural Radiance Fields (NeRF). In computer vision, NeRF techniques train a neural network to memorize the appearance of a 3D scene and then uses its learned parameters to render and edit the scene from any viewpoint. We draw an analogy between the discrete images captured from different viewpoints used to learn a continuous 3D scene in NeRF, and EEG electrodes positioned at different locations on the scalp, which are used to infer the underlying representation of continuous neural activity. Building on this connection, we show that a neural network can be trained on a single EEG sample in a NeRF style manner to produce a fixed size and informative weight vector that encodes the entire signal. Moreover, via this representation we can render the EEG signal at previously unseen time steps and spatial electrode positions. We demonstrate that this approach enables continuous visualization of brain activity at any desired resolution, including ultra high resolution, and reconstruction of raw EEG signals. Finally, our empirical analysis shows that this method can effectively simulate nonexistent electrodes data in EEG recordings, allowing the reconstructed signal to be fed into standard EEG processing networks to improve performance. --- ### Emergent Persuasion: Will LLMs Persuade Without Being Prompted? Authors: Vincent Chang, Thee Ho, Sunishchal Dev, Kevin Zhu, Shi Feng, Kellin Pelrine, Matthew Kowal Published: 2025-12-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.22201v1 With the wide-scale adoption of conversational AI systems, AI are now able to exert unprecedented influence on human opinion and beliefs. Recent work has shown that many Large Language Models (LLMs) comply with requests to persuade users into harmful beliefs or actions when prompted and that model persuasiveness increases with model scale. However, this prior work looked at persuasion from the threat model of $\textit{misuse}$ (i.e., a bad actor asking an LLM to persuade). In this paper, we instead aim to answer the following question: Under what circumstances would models persuade $\textit{without being explicitly prompted}$, which would shape how concerned we should be about such emergent persuasion risks. To achieve this, we study unprompted persuasion under two scenarios: (i) when the model is steered (through internal activation steering) along persona traits, and (ii) when the model is supervised-finetuned (SFT) to exhibit the same traits. We showed that steering towards traits, both related to persuasion and unrelated, does not reliably increase models' tendency to persuade unprompted, however, SFT does. Moreover, SFT on general persuasion datasets containing solely benign topics admits a model that has a higher propensity to persuade on controversial and harmful topics--showing that emergent harmful persuasion can arise and should be studied further. --- ### Emotion-Inspired Learning Signals (EILS): A Homeostatic Framework for Adaptive Autonomous Agents Authors: Dhruv Tiwari Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22200v1 The ruling method in modern Artificial Intelligence spanning from Deep Reinforcement Learning (DRL) to Large Language Models (LLMs) relies on a surge of static, externally defined reward functions. While this "extrinsic maximization" approach has rendered superhuman performance in closed, stationary fields, it produces agents that are fragile in open-ended, real-world environments. Standard agents lack internal autonomy: they struggle to explore without dense feedback, fail to adapt to distribution shifts (non-stationarity), and require extensive manual tuning of static hyperparameters. This paper proposes that the unaddressed factor in robust autonomy is a functional analog to biological emotion, serving as a high-level homeostatic control mechanism. We introduce Emotion-Inspired Learning Signals (EILS), a unified framework that replaces scattered optimization heuristics with a coherent, bio-inspired internal feedback engine. Unlike traditional methods that treat emotions as semantic labels, EILS models them as continuous, homeostatic appraisal signals such as Curiosity, Stress, and Confidence. We formalize these signals as vector-valued internal states derived from interaction history. These states dynamically modulate the agent's optimization landscape in real time: curiosity regulates entropy to prevent mode collapse, stress modulates plasticity to overcome inactivity, and confidence adapts trust regions to stabilize convergence. We hypothesize that this closed-loop homeostatic regulation can enable EILS agents to outperform standard baselines in terms of sample efficiency and non-stationary adaptation. --- ### Bidirectional RAG: Safe Self-Improving Retrieval-Augmented Generation Through Multi-Stage Validation Authors: Teja Chinthala Published: 2025-12-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.22199v1 Retrieval-Augmented Generation RAG systems enhance large language models by grounding responses in external knowledge bases, but conventional RAG architectures operate with static corpora that cannot evolve from user interactions. We introduce Bidirectional RAG, a novel RAG architecture that enables safe corpus expansion through validated write back of high quality generated responses. Our system employs a multi stage acceptance layer combining grounding verification (NLI based entailment, attribution checking, and novelty detection to prevent hallucination pollution while enabling knowledge accumulation. Across four datasets Natural Questions, TriviaQA, HotpotQA, Stack Overflow with three random seeds 12 experiments per system, Bidirectional RAG achieves 40.58% average coverage nearly doubling Standard RAG 20.33% while adding 72% fewer documents than naive write back 140 vs 500. Our work demonstrates that self improving RAG is feasible and safe when governed by rigorous validation, offering a practical path toward RAG systems that learn from deployment. --- ### Quadrant Segmentation VLM with Few-Shot Adaptation and OCT Learning-based Explainability Methods for Diabetic Retinopathy Authors: Shivum Telang Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22197v1 Diabetic Retinopathy (DR) is a leading cause of vision loss worldwide, requiring early detection to preserve sight. Limited access to physicians often leaves DR undiagnosed. To address this, AI models utilize lesion segmentation for interpretability; however, manually annotating lesions is impractical for clinicians. Physicians require a model that explains the reasoning for classifications rather than just highlighting lesion locations. Furthermore, current models are one-dimensional, relying on a single imaging modality for explainability and achieving limited effectiveness. In contrast, a quantitative-detection system that identifies individual DR lesions in natural language would overcome these limitations, enabling diverse applications in screening, treatment, and research settings. To address this issue, this paper presents a novel multimodal explainability model utilizing a VLM with few-shot learning, which mimics an ophthalmologist's reasoning by analyzing lesion distributions within retinal quadrants for fundus images. The model generates paired Grad-CAM heatmaps, showcasing individual neuron weights across both OCT and fundus images, which visually highlight the regions contributing to DR severity classification. Using a dataset of 3,000 fundus images and 1,000 OCT images, this innovative methodology addresses key limitations in current DR diagnostics, offering a practical and comprehensive tool for improving patient outcomes. --- ### AETAS: Analysis of Evolving Temporal Affect and Semantics for Legal History Authors: Qizhi Wang Published: 2025-12-20 Categories: cs.DL, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2512.22196v2 Digital-humanities work on semantic shift often alternates between handcrafted close readings and opaque embedding machinery. We present a reproducible expert-system style pipeline that quantifies lexical drift and its instability in the Old Bailey Corpus (1674-1913), coupling interpretable trajectories with legally meaningful axes. We bin proceedings by decade with dynamic merging for low-resource slices, train skip-gram embeddings, align spaces through orthogonal Procrustes to a 1900s anchor, and measure both geometric displacement and neighborhood turnover. We add split-half baselines and seed-sensitivity checks to separate within-bin instability from temporal change. Three visual analytics outputs (drift magnitudes, semantic trajectories, and movement along a mercy-versus-retribution axis) expose how justice, crime, poverty, and insanity evolve with penal reforms, transportation debates, and Victorian moral politics. The pipeline is implemented as auditable scripts so results can be reproduced in other historical corpora. --- ### MatKV: Trading Compute for Flash Storage in LLM Inference Authors: Kun-Woo Shin, Jay H. Park, Moonwook Oh, Yohan Jo, Jaeyoung Do, Sang-Won Lee Published: 2025-12-20 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.22195v1 We observe two major trends in LLM-based generative AI: (1) inference is becoming the dominant factor in terms of cost and power consumption, surpassing training, and (2) retrieval augmented generation (RAG) is becoming prevalent. When processing long inputs in RAG, the prefill phase of computing the key-value vectors of input text is energy-intensive and time-consuming even with high-end GPUs. Thus, it is crucial to make the prefill phase in RAG inference efficient. To address this issue, we propose MatKV, a scheme that precomputes the key-value vectors (KVs) of RAG objects (e.g., documents), materializes them in inexpensive but fast and power-efficient flash storage, and reuses them at inference time instead of recomputing the KVs using costly and power-inefficient GPU. Experimental results using Hugging Face's Transformers library across state-of-the-art GPUs and flash memory SSDs confirm that, compared to full KV computation on GPUs, MatKV reduces both inference time and power consumption by half for RAG workloads, without severely impacting accuracy in the question-answering task. Furthermore, we demonstrate that MatKV enables additional optimizations in two ways. First, a GPU can decode text while simultaneously loading the materialized KVs for the next instance, reducing load latency. Second, since decoding speed is less sensitive to GPU performance than KV computation, low-end GPUs can be leveraged for decoding without significantly compromising speed once the materialized KVs are loaded into GPU memory. These findings underscore MatKV's potential to make large-scale generative AI applications more cost-effective, power-efficient, and accessible across a wider range of tasks and hardware environments. --- ### Tiny-YOLOSAM: Fast Hybrid Image Segmentation Authors: Kenneth Xu, Songhan Wu Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22193v1 The Segment Anything Model (SAM) enables promptable, high-quality segmentation but is often too computationally expensive for latency-critical settings. TinySAM is a lightweight, distilled SAM variant that preserves strong zero-shot mask quality, yet its "segment-everything" mode still requires hundreds of prompts and remains slow in practice. We first replicate TinySAM on COCO val2017 using official checkpoints, matching the reported AP within 0.03%, establishing a reliable experimental baseline. Building on this, we propose Tiny-YOLOSAM, a fast hybrid pipeline that uses a recent YOLO detector (YOLOv12) to generate box prompts for TinySAM on salient foreground objects, and supplements uncovered regions with sparse point prompts sampled only where YOLO-guided masks provide no coverage. On COCO val2017, the hybrid system substantially improves class-agnostic coverage (AR from 16.4% to 77.1%, mIoU from 19.2% to 67.8%) while reducing end-to-end runtime from 49.20s/image to 10.39s/image (4.7x) on an Apple M1 Pro CPU. These results suggest detector-guided prompting combined with targeted sparse sampling as an effective alternative to dense "segment-everything" prompting for practical full-scene segmentation. --- ### Frequency Regularization: Unveiling the Spectral Inductive Bias of Deep Neural Networks Authors: Jiahao Lu Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22192v1 Regularization techniques such as L2 regularization (Weight Decay) and Dropout are fundamental to training deep neural networks, yet their underlying physical mechanisms regarding feature frequency selection remain poorly understood. In this work, we investigate the Spectral Bias of modern Convolutional Neural Networks (CNNs). We introduce a Visual Diagnostic Framework to track the dynamic evolution of weight frequencies during training and propose a novel metric, the Spectral Suppression Ratio (SSR), to quantify the "low-pass filtering" intensity of different regularizers. By addressing the aliasing issue in small kernels (e.g., 3x3) through discrete radial profiling, our empirical results on ResNet-18 and CIFAR-10 demonstrate that L2 regularization suppresses high-frequency energy accumulation by over 3x compared to unregularized baselines. Furthermore, we reveal a critical Accuracy-Robustness Trade-off: while L2 models are sensitive to broadband Gaussian noise due to over-specialization in low frequencies, they exhibit superior robustness against high-frequency information loss (e.g., low resolution), outperforming baselines by >6% in blurred scenarios. This work provides a signal-processing perspective on generalization, confirming that regularization enforces a strong spectral inductive bias towards low-frequency structures. --- ### Physics-Informed Machine Learning for Transformer Condition Monitoring -- Part I: Basic Concepts, Neural Networks, and Variants Authors: Jose I. Aizpurua Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22190v1 Power transformers are critical assets in power networks, whose reliability directly impacts grid resilience and stability. Traditional condition monitoring approaches, often rule-based or purely physics-based, struggle with uncertainty, limited data availability, and the complexity of modern operating conditions. Recent advances in machine learning (ML) provide powerful tools to complement and extend these methods, enabling more accurate diagnostics, prognostics, and control. In this two-part series, we examine the role of Neural Networks (NNs) and their extensions in transformer condition monitoring and health management tasks. This first paper introduces the basic concepts of NNs, explores Convolutional Neural Networks (CNNs) for condition monitoring using diverse data modalities, and discusses the integration of NN concepts within the Reinforcement Learning (RL) paradigm for decision-making and control. Finally, perspectives on emerging research directions are also provided. --- ### Physics-Informed Machine Learning for Transformer Condition Monitoring -- Part II: Physics-Informed Neural Networks and Uncertainty Quantification Authors: Jose I. Aizpurua Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22189v1 The integration of physics-based knowledge with machine learning models is increasingly shaping the monitoring, diagnostics, and prognostics of electrical transformers. In this two-part series, the first paper introduced the foundations of Neural Networks (NNs) and their variants for health assessment tasks. This second paper focuses on integrating physics and uncertainty into the learning process. We begin with the fundamentals of Physics-Informed Neural Networks (PINNs), applied to spatiotemporal thermal modeling and solid insulation ageing. Building on this, we present Bayesian PINNs as a principled framework to quantify epistemic uncertainty and deliver robust predictions under sparse data. Finally, we outline emerging research directions that highlight the potential of physics-aware and trustworthy machine learning for critical power assets. --- ### HookMIL: Revisiting Context Modeling in Multiple Instance Learning for Computational Pathology Authors: Xitong Ling, Minxi Ouyang, Xiaoxiao Li, Jiawen Li, Ying Chen, Yuxuan Sun, Xinrui Chen, Tian Guan, Xiaoping Liu, Yonghong He Published: 2025-12-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.22188v1 Multiple Instance Learning (MIL) has enabled weakly supervised analysis of whole-slide images (WSIs) in computational pathology. However, traditional MIL approaches often lose crucial contextual information, while transformer-based variants, though more expressive, suffer from quadratic complexity and redundant computations. To address these limitations, we propose HookMIL, a context-aware and computationally efficient MIL framework that leverages compact, learnable hook tokens for structured contextual aggregation. These tokens can be initialized from (i) key-patch visual features, (ii) text embeddings from vision-language pathology models, and (iii) spatially grounded features from spatial transcriptomics-vision models. This multimodal initialization enables Hook Tokens to incorporate rich textual and spatial priors, accelerating convergence and enhancing representation quality. During training, Hook tokens interact with instances through bidirectional attention with linear complexity. To further promote specialization, we introduce a Hook Diversity Loss that encourages each token to focus on distinct histopathological patterns. Additionally, a hook-to-hook communication mechanism refines contextual interactions while minimizing redundancy. Extensive experiments on four public pathology datasets demonstrate that HookMIL achieves state-of-the-art performance, with improved computational efficiency and interpretability. Codes are available at https://github.com/lingxitong/HookMIL. --- ### Learning Tennis Strategy Through Curriculum-Based Dueling Double Deep Q-Networks Authors: Vishnu Mohan Published: 2025-12-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22186v1 Tennis strategy optimization is a challenging sequential decision-making problem involving hierarchical scoring, stochastic outcomes, long-horizon credit assignment, physical fatigue, and adaptation to opponent skill. I present a reinforcement learning framework that integrates a custom tennis simulation environment with a Dueling Double Deep Q-Network(DDQN) trained using curriculum learning. The environment models complete tennis scoring at the level of points, games, and sets, rally-level tactical decisions across ten discrete action categories, symmetric fatigue dynamics, and a continuous opponent skill parameter. The dueling architecture decomposes action-value estimation into state-value and advantage components, while double Q-learning reduces overestimation bias and improves training stability in this long-horizon stochastic domain. Curriculum learning progressively increases opponent difficulty from 0.40 to 0.50, enabling robust skill acquisition without the training collapse observed under fixed opponents. Across extensive evaluations, the trained agent achieves win rates between 98 and 100 percent against balanced opponents and maintains strong performance against more challenging opponents. Serve efficiency ranges from 63.0 to 67.5 percent, and return efficiency ranges from 52.8 to 57.1 percent. Ablation studies demonstrate that both the dueling architecture and curriculum learning are necessary for stable convergence, while a standard DQN baseline fails to learn effective policies. Despite strong performance, tactical analysis reveals a pronounced defensive bias, with the learned policy prioritizing error avoidance and prolonged rallies over aggressive point construction. These results highlight a limitation of win-rate driven optimization in simplified sports simulations and emphasize the importance of reward design for realistic sports reinforcement learning. --- ### Beyond Augmentation: Cross-Modal Transformer Fusion with Bi-directional Attention for Low-Data Aneurysm Screening Authors: Antara Titikhsha, Divyanshu Tak Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22185v2 Intracranial aneurysm rupture causes subarachnoid hemorrhage with mortality near 50%, making early detection critical. Although CTA enables rapid screening, detecting small aneurysms within the complex three-dimensional branching of the Circle of Willis remains expertise-dependent. Existing automated systems are constrained by class imbalance, skull-base artifacts that mimic vascular contrast, and reliance on global binary classification without structured localization, limiting surgical relevance and interpretability. We propose CMTF-Net, a cross-modal target fusion framework that reframes aneurysm screening as anatomically structured reasoning. By supervising 14 vascular territories independently, the network encodes Circle of Willis geometry while allowing multi-segment activation, aligning model design with clinical workflow. CMTF-Net achieves near-perfect AUC-ROC with narrow confidence intervals and sustained precision under imbalance. Grad-CAM and causal maps show spatially localized activation along major arteries, supporting interpretable, anatomically grounded screening in low-data settings. --- ### CosmoCore-Evo: Evolutionary Dream-Replay Reinforcement Learning for Adaptive Code Generation Authors: Santhosh Kumar Ravindran Published: 2025-12-20 Categories: cs.SE, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2512.21351v1 Building on the affective dream-replay reinforcement learning framework of CosmoCore, we introduce CosmoCore-Evo, an extension that incorporates evolutionary algorithms to enhance adaptability and novelty in code generation tasks. Inspired by anthropological aspects of human evolution, such as natural selection and adaptation in early hominids, CosmoCore-Evo treats RL trajectories as ``genomes'' that undergo mutation and selection during the nocturnal replay phase. This mechanism allows agents to break free from trained patterns, fostering emergent behaviors and improved performance in distribution-shifted environments, such as changing APIs or novel libraries. We augment the Dream Queue with evolutionary operations, including mutation of high-fitness trajectories and enterprise-tuned fitness functions that incorporate efficiency, compliance, and scalability metrics. Evaluated on extended benchmarks including HumanEval variants with shifts, BigCodeBench, and a custom PySpark pipeline simulation, CosmoCore-Evo achieves up to 35% higher novelty in solutions and 25% faster adaptation compared to the original CosmoCore and baselines like PPO and REAMER. Ablations confirm the role of evolutionary components in bridging the sentient gap for LLM agents. Code for replication, including a toy simulation, is provided. --- ### Physics-Informed Neural Solvers for Periodic Quantum Eigenproblems Authors: Haaris Mian Published: 2025-12-20 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2512.21349v1 This thesis presents a physics-informed machine learning framework for solving the Floquet-Bloch eigenvalue problem associated with particles in two-dimensional periodic potentials, with a focus on honeycomb lattice geometry, due to its distinctive band topology featuring Dirac points and its relevance to materials such as graphene. By leveraging neural networks to learn complex Bloch functions and their associated eigenvalues (energies) simultaneously, we develop a mesh-free solver enforcing the governing Schrödinger equation, Bloch periodicity, and normalization constraints through a composite loss function without supervision. The model is trained over the Brillouin zone to recover band structures and Bloch modes, with numerical validation against traditional plane-wave expansion methods. We further explore transfer learning techniques to adapt the solver from nearly-free electron potentials to strongly varying potentials, demonstrating its ability to capture changes in band structure topology. This work contributes to the growing field of physics-informed machine learning for quantum eigenproblems, providing insights into the interplay between symmetry, band structure, and neural architectures. --- ### Revisiting the Learning Objectives of Vision-Language Reward Models Authors: Simon Roy, Samuel Barbeau, Giovanni Beltrame, Christian Desrosiers, Nicolas Thome Published: 2025-12-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.20675v1 Learning generalizable reward functions is a core challenge in embodied intelligence. Recent work leverages contrastive vision language models (VLMs) to obtain dense, domain-agnostic rewards without human supervision. These methods adapt VLMs into reward models through increasingly complex learning objectives, yet meaningful comparison remains difficult due to differences in training data, architectures, and evaluation settings. In this work, we isolate the impact of the learning objective by evaluating recent VLM-based reward models under a unified framework with identical backbones, finetuning data, and evaluation environments. Using Meta-World tasks, we assess modeling accuracy by measuring consistency with ground truth reward and correlation with expert progress. Remarkably, we show that a simple triplet loss outperforms state-of-the-art methods, suggesting that much of the improvements in recent approaches could be attributed to differences in data and architectures. --- ### HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model Authors: Yuanhao Xi, Xiaohuan Bing, Ramin Yahyapour Published: 2025-12-20 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.20674v1 Vision Language Models (VLMs) have undergone significant advancements, particularly with the emergence of mobile-oriented VLMs, which offer a wide range of application scenarios. However, the substantial computational requirements for training these models present a significant obstacle to their practical application. To address this issue, Low-Rank Adaptation (LoRA) has been proposed. Nevertheless, the standard LoRA with a fixed rank lacks sufficient capability for training mobile VLMs that process both text and image modalities. In this work, we introduce HyDRA, a parameter-efficient fine-tuning framework designed to implement hierarchical and dynamic rank scheduling for mobile VLMs. This framework incorporates two essential optimization strategies: (1) hierarchical optimization, which involves a coarse-grained approach that assigns different ranks to various layers, as well as a fine-grained method that adjusts ranks within individual layers, and (2) dynamic adjustment, which employs an end-to-end automatic optimization using a lightweight performance model to determine and adjust ranks during the fine-tuning process. Comprehensive experiments conducted on popular benchmarks demonstrate that HyDRA consistently outperforms the baseline, achieving a 4.7\% improvement across various model sizes without increasing the number of trainable parameters. In some tasks, it even surpasses full-parameter fine-tuning. --- ### SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models Authors: Scott Thornton Published: 2025-12-20 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.18542v3 AI coding assistants produce vulnerable code in 45\% of security-relevant scenarios~\cite{veracode2025}, yet no public training dataset teaches both traditional web security and AI/ML-specific defenses in a format suitable for instruction tuning. We present SecureCode, a production-grade dataset of 2,185 multi-turn security training examples spanning two domains: web application security (1,435 examples covering the OWASP Top 10 2021 across 11 languages and 9 frameworks, 100\% grounded in documented CVEs and security incidents) and AI/ML security (750 examples covering all 10 OWASP LLM Top 10 2025 categories across more than 40 frameworks, including LangChain, OpenAI, and Hugging Face). Every example follows a 4-turn conversational structure -- feature request; vulnerable and secure implementations with attack demonstrations; advanced probing; and defense-in-depth operational guidance -- designed for direct use in instruction tuning pipelines. Quality assurance combines automated structural validation with multi-agent review from seven specialist AI perspectives (more than 10{,}500 assessments) and an 8-phase remediation pipeline, producing a rubric-calibrated mean quality score of 93.8/100 ($σ= 0.93$) for the AI/ML component. Each example provides SIEM integration strategies, infrastructure hardening recommendations, and testing approaches using production frameworks. We release the unified dataset on Hugging Face with domain-specific loading configurations (web, aiml, default), alongside eight fine-tuned open-source models (3B--20B parameters, QLoRA), and an evaluation framework with four security-specific metrics. To our knowledge, SecureCode is the first public dataset that jointly provides OWASP Top 10 2021 web coverage and OWASP LLM Top 10 2025 AI/ML coverage in a unified conversational schema suitable for instruction tuning. --- ### Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies Authors: John Cao, Luca Furieri Published: 2025-12-20 Categories: eess.SY, cs.LG, math.OC arXiv: https://arxiv.org/abs/2512.18540v2 We study distributed control of networked systems through reinforcement learning, where neural policies must be simultaneously scalable, expressive and stabilizing. We introduce a policy parameterization that embeds Graph Neural Networks (GNNs) into a Youla-like magnitude-direction parameterization, yielding distributed stochastic controllers that guarantee network-level closed-loop stability by design. The magnitude is implemented as a stable operator consisting of a GNN acting on disturbance feedback, while the direction is a GNN acting on local observations. We prove robustness of the policy to perturbations in both the graph topology and model parameters. Numerical experiments validate the effectiveness of the proposed approach. --- ### Generalization Gaps in Political Fake News Detection: An Empirical Study on the LIAR Dataset Authors: S Mahmudul Hasan, Shaily Roy, Akib Jawad Nafis Published: 2025-12-20 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.18533v1 The proliferation of linguistically subtle political disinformation poses a significant challenge to automated fact-checking systems. Despite increasing emphasis on complex neural architectures, the empirical limits of text-only linguistic modeling remain underexplored. We present a systematic diagnostic evaluation of nine machine learning algorithms on the LIAR benchmark. By isolating lexical features (Bag-of-Words, TF-IDF) and semantic embeddings (GloVe), we uncover a hard "Performance Ceiling", with fine-grained classification not exceeding a Weighted F1-score of 0.32 across models. Crucially, a simple linear SVM (Accuracy: 0.624) matches the performance of pre-trained Transformers such as RoBERTa (Accuracy: 0.620), suggesting that model capacity is not the primary bottleneck. We further diagnose a massive "Generalization Gap" in tree-based ensembles, which achieve more than 99% training accuracy but collapse to approximately 25% on test data, indicating reliance on lexical memorization rather than semantic inference. Synthetic data augmentation via SMOTE yields no meaningful gains, confirming that the limitation is semantic (feature ambiguity) rather than distributional. These findings indicate that for political fact-checking, increasing model complexity without incorporating external knowledge yields diminishing returns. --- ### Pushing the limits of one-dimensional NMR spectroscopy for automated structure elucidation using artificial intelligence Authors: Frank Hu, Jonathan M. Tubb, Dimitris Argyropoulos, Sergey Golotvin, Mikhail Elyashberg, Grant M. Rotskoff, Matthew W. Kanan, Thomas E. Markland Published: 2025-12-20 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2512.18531v2 One-dimensional NMR spectroscopy is one of the most widely used techniques for the characterization of organic compounds and natural products. For molecules with up to 36 non-hydrogen atoms, the number of possible structures has been estimated to range from $10^{20} - 10^{60}$. The task of determining the structure (formula and connectivity) of a molecule of this size using only its one-dimensional $^1$H and/or $^{13}$C NMR spectrum, i.e. de novo structure generation, thus appears completely intractable. Here we show how it is possible to achieve this task for systems with up to 40 non-hydrogen atoms across the full elemental coverage typically encountered in organic chemistry (C, N, O, H, P, S, Si, B, and the halogens) using a deep learning framework, thus covering a vast portion of the drug-like chemical space. Leveraging insights from natural language processing, we show that our transformer-based architecture predicts the correct molecule with 60.4% accuracy within the first 15 predictions using only the $^1$H and $^{13}$C NMR spectra, thus overcoming the combinatorial growth of the chemical space while also being extensible to experimental data via fine-tuning. --- ### WoundNet-Ensemble: A Novel IoMT System Integrating Self-Supervised Deep Learning and Multi-Model Fusion for Automated, High-Accuracy Wound Classification and Healing Progression Monitoring Authors: Moses Kiprono Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18528v1 Chronic wounds, including diabetic foot ulcers which affect up to one-third of people with diabetes, impose a substantial clinical and economic burden, with U.S. healthcare costs exceeding 25 billion dollars annually. Current wound assessment remains predominantly subjective, leading to inconsistent classification and delayed interventions. We present WoundNet-Ensemble, an Internet of Medical Things system leveraging a novel ensemble of three complementary deep learning architectures: ResNet-50, the self-supervised Vision Transformer DINOv2, and Swin Transformer, for automated classification of six clinically distinct wound types. Our system achieves 99.90 percent ensemble accuracy on a comprehensive dataset of 5,175 wound images spanning diabetic foot ulcers, pressure ulcers, venous ulcers, thermal burns, pilonidal sinus wounds, and fungating malignant tumors. The weighted fusion strategy demonstrates a 3.7 percent improvement over previous state-of-the-art methods. Furthermore, we implement a longitudinal wound healing tracker that computes healing rates, severity scores, and generates clinical alerts. This work demonstrates a robust, accurate, and clinically deployable tool for modernizing wound care through artificial intelligence, addressing critical needs in telemedicine and remote patient monitoring. The implementation and trained models will be made publicly available to support reproducibility. --- ### Detection of AI Generated Images Using Combined Uncertainty Measures and Particle Swarm Optimised Rejection Mechanism Authors: Rahul Yumlembam, Biju Issac, Nauman Aslam, Eaby Kollonoor Babu, Josh Collyer, Fraser Kennedy Published: 2025-12-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.18527v1 As AI-generated images become increasingly photorealistic, distinguishing them from natural images poses a growing challenge. This paper presents a robust detection framework that leverages multiple uncertainty measures to decide whether to trust or reject a model's predictions. We focus on three complementary techniques: Fisher Information, which captures the sensitivity of model parameters to input variations; entropy-based uncertainty from Monte Carlo Dropout, which reflects predictive variability; and predictive variance from a Deep Kernel Learning framework using a Gaussian Process classifier. To integrate these diverse uncertainty signals, Particle Swarm Optimisation is used to learn optimal weightings and determine an adaptive rejection threshold. The model is trained on Stable Diffusion-generated images and evaluated on GLIDE, VQDM, Midjourney, BigGAN, and StyleGAN3, each introducing significant distribution shifts. While standard metrics such as prediction probability and Fisher-based measures perform well in distribution, their effectiveness degrades under shift. In contrast, the Combined Uncertainty measure consistently achieves an incorrect rejection rate of approximately 70 percent on unseen generators, successfully filtering most misclassified AI samples. Although the system occasionally rejects correct predictions from newer generators, this conservative behaviour is acceptable, as rejected samples can support retraining. The framework maintains high acceptance of accurate predictions for natural images and in-domain AI data. Under adversarial attacks using FGSM and PGD, the Combined Uncertainty method rejects around 61 percent of successful attacks, while GP-based uncertainty alone achieves up to 80 percent. Overall, the results demonstrate that multi-source uncertainty fusion provides a resilient and adaptive solution for AI-generated image detection. --- ### A Formal Descriptive Language for Learning Dynamics: A Five-Layer Structural Coordinate System Authors: Miyuki T. Nakata Published: 2025-12-20 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.18525v2 Understanding learning as a dynamic process is challenging due to the interaction of multiple factors, including cognitive load, internal state change, and subjective evaluation. Existing approaches often address these elements in isolation, limiting the ability to describe learning phenomena within a unified and structurally explicit framework. This paper proposes a multi-layer formal descriptive framework for learning dynamics. Rather than offering a predictive or prescriptive model, the framework introduces a symbolic language composed of state variables, mappings, and layer-specific responsibilities, enabling consistent description of learning processes without commitment to specific functional forms or optimization objectives. This descriptive framework is intended to serve as a structural substrate for analyzing learning processes in human learners, and by extension, in adaptive and Al-assisted learning systems. A central design principle is the explicit separation of descriptive responsibilities across layers, distinguishing load generation, internal understanding transformation, observation, and evaluation. Within this structure, cognitive load is treated as a relational quantity arising from interactions between external input and internal organization, while subjective evaluation is modeled as a minimal regulatory interface responding to learning dynamics and environmental conditions. By emphasizing descriptive clarity and extensibility, the framework provides a common language for organizing existing theories and supporting future empirical and theoretical work. --- ### Feature-Enhanced Graph Neural Networks for Classification of Synthetic Graph Generative Models: A Benchmarking Study Authors: Janek Dyer, Jagdeep Ahluwalia, Javad Zarrin Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18524v1 The ability to discriminate between generative graph models is critical to understanding complex structural patterns in both synthetic graphs and the real-world structures that they emulate. While Graph Neural Networks (GNNs) have seen increasing use to great effect in graph classification tasks, few studies explore their integration with interpretable graph theoretic features. This paper investigates the classification of synthetic graph families using a hybrid approach that combines GNNs with engineered graph-theoretic features. We generate a large and structurally diverse synthetic dataset comprising graphs from five representative generative families, Erdos-Renyi, Watts-Strogatz, Barab'asi-Albert, Holme-Kim, and Stochastic Block Model. These graphs range in size up to 1x10^4 nodes, containing up to 1.1x10^5 edges. A comprehensive range of node and graph level features is extracted for each graph and pruned using a Random Forest based feature selection pipeline. The features are integrated into six GNN architectures: GCN, GAT, GATv2, GIN, GraphSAGE and GTN. Each architecture is optimised for hyperparameter selection using Optuna. Finally, models were compared against a baseline Support Vector Machine (SVM) trained solely on the handcrafted features. Our evaluation demonstrates that GraphSAGE and GTN achieve the highest classification performance, with 98.5% accuracy, and strong class separation evidenced by t-SNE and UMAP visualisations. GCN and GIN also performed well, while GAT-based models lagged due to limitations in their ability to capture global structures. The SVM baseline confirmed the importance of the message passing functionality for performance gains and meaningful class separation. --- ### Prediction and Forecast of Short-Term Drought Impacts Using Machine Learning to Support Mitigation and Adaptation Efforts Authors: Hatim M. E. Geli, Islam Omar, Mona Y. Elshinawy, David W. DuBios, Lara Prehodko, Kelly H Smith, Abdel-Hameed A. Badawy Published: 2025-12-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.18522v1 Drought is a complex natural hazard that affects ecological and human systems, often resulting in substantial environmental and economic losses. Recent increases in drought severity, frequency, and duration underscore the need for effective monitoring and mitigation strategies. Predicting drought impacts rather than drought conditions alone offers opportunities to support early warning systems and proactive decision-making. This study applies machine learning techniques to link drought indices with historical drought impact records (2005:2024) to generate short-term impact forecasts. By addressing key conceptual and data-driven challenges regarding temporal scale and impact quantification, the study aims to improve the predictability of drought impacts at actionable lead times. The Drought Severity and Coverage Index (DSCI) and the Evaporative Stress Index (ESI) were combined with impact data from the Drought Impact Reporter (DIR) to model and forecast weekly drought impacts. Results indicate that Fire and Relief impacts were predicted with the highest accuracy, followed by Agriculture and Water, while forecasts for Plants and Society impacts showed greater variability. County and state level forecasts for New Mexico were produced using an eXtreme Gradient Boosting (XGBoost) model that incorporated both DSCI and ESI. The model successfully generated forecasts up to eight weeks in advance using the preceding eight weeks of data for most impact categories. This work supports the development of an Ecological Drought Information Communication System (EcoDri) for New Mexico and demonstrates the potential for broader application in similar drought-prone regions. The findings can aid stakeholders, land managers, and decision-makers in developing and implementing more effective drought mitigation and adaptation strategies. --- ### Selection-Induced Contraction of Innovation Statistics in Gated Kalman Filters Authors: Barak Or Published: 2025-12-20 Categories: stat.ME, cs.AI, eess.SP, eess.SY arXiv: https://arxiv.org/abs/2512.18508v3 Validation gating is a fundamental component of classical Kalman-based tracking systems. Only measurements whose normalized innovation squared (NIS) falls below a prescribed threshold are considered for state update. While this procedure is statistically motivated by the chi-square distribution, it implicitly replaces the unconditional innovation process with a conditionally observed one, restricted to the validation event. This paper shows that innovation statistics computed after gating converge to gate-conditioned rather than nominal quantities. Under classical linear--Gaussian assumptions, we derive exact expressions for the first- and second-order moments of the innovation conditioned on ellipsoidal gating, and show that gating induces a deterministic, dimension-dependent contraction of the innovation covariance. The analysis is extended to NN association, which is shown to act as an additional statistical selection operator. We prove that selecting the minimum-norm innovation among multiple in-gate measurements introduces an unavoidable energy contraction, implying that nominal innovation statistics cannot be preserved under nontrivial gating and association. Closed-form results in the two-dimensional case quantify the combined effects and illustrate their practical significance. --- ### Teaching and Critiquing Conceptualization and Operationalization in NLP Authors: Vagrant Gautam Published: 2025-12-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18505v1 NLP researchers regularly invoke abstract concepts like "interpretability," "bias," "reasoning," and "stereotypes," without defining them. Each subfield has a shared understanding or conceptualization of what these terms mean and how we should treat them, and this shared understanding is the basis on which operational decisions are made: Datasets are built to evaluate these concepts, metrics are proposed to quantify them, and claims are made about systems. But what do they mean, what should they mean, and how should we measure them? I outline a seminar I created for students to explore these questions of conceptualization and operationalization, with an interdisciplinary reading list and an emphasis on discussion and critique. --- ### GTMA: Dynamic Representation Optimization for OOD Vision-Language Models Authors: Jensen Zhang, Ningyuan Liu, Keze Wang Published: 2025-12-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.18504v1 Vision-language models (VLMs) struggle in open-world applications, where out-of-distribution (OOD) concepts often trigger cross-modal alignment collapse and severely degrade zero-shot performance. We identify the root cause as modal asymmetry: while the visual encoder can extract discriminative features from unseen images, the text encoder is constrained by a fixed discrete vocabulary and cannot synthesize new semantic anchors. Existing approaches such as CoOp or LoRA provide only partial remedies, as they remain confined to the pre-trained semantic space. To overcome this bottleneck, we propose dynamic representation optimization, realized through the Guided Target-Matching Adaptation (GTMA) framework. At inference time, GTMA constructs a continuous pseudo-word embedding that best aligns with an OOD image's visual anchor, effectively bypassing vocabulary limitations. The optimization is driven by an adaptive gradient-based representation policy optimization algorithm, which incorporates semantic regularization to preserve plausibility and compatibility with the model's prior knowledge. Experiments on ImageNet-R and the VISTA-Beyond benchmark demonstrate that GTMA improves zero-shot and few-shot OOD accuracy by up to 15-20 percent over the base VLM while maintaining performance on in-distribution concepts. Ablation studies further confirm the necessity of pseudo-word optimization. --- ### NASTaR: NovaSAR Automated Ship Target Recognition Dataset Authors: Benyamin Hosseiny, Kamirul Kamirul, Odysseas Pappas, Alin Achim Published: 2025-12-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.18503v3 Synthetic Aperture Radar (SAR) offers a unique capability for all-weather, space-based maritime activity monitoring by capturing and imaging strong reflections from ships at sea. A well-defined challenge in this domain is ship type classification. Due to the high diversity and complexity of ship types, accurate recognition is difficult and typically requires specialized deep learning models. These models, however, depend on large, high-quality ground-truth datasets to achieve robust performance and generalization. Furthermore, the growing variety of SAR satellites operating at different frequencies and spatial resolutions has amplified the need for more annotated datasets to enhance model accuracy. To address this, we present the NovaSAR Automated Ship Target Recognition (NASTaR) dataset. This dataset comprises of 3415 ship patches extracted from NovaSAR S-band imagery, with labels matched to AIS data. It includes distinctive features such as 23 unique classes, inshore/offshore separation, and an auxiliary wake dataset for patches where ship wakes are visible. We validated the dataset applicability across prominent ship-type classification scenarios using benchmark deep learning models. Results demonstrate over 60% accuracy for classifying four major ship types, over 70% for a three-class scenario, more than 75% for distinguishing cargo from tanker ships, and over 87% for identifying fishing vessels. The NASTaR dataset is available at https://doi.org/10.5523/bris.2tfa6x37oerz2lyiw6hp47058, while relevant codes for benchmarking and analysis are available at https://github.com/benyaminhosseiny/nastar. --- ### PlantDiseaseNet-RT50: A Fine-tuned ResNet50 Architecture for High-Accuracy Plant Disease Detection Beyond Standard CNNs Authors: Santwana Sagnika, Manav Malhotra, Ishtaj Kaur Deol, Soumyajit Roy, Swarnav Kumar Published: 2025-12-20 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.18500v1 Plant diseases pose a significant threat to agricultural productivity and global food security, accounting for 70-80% of crop losses worldwide. Traditional detection methods rely heavily on expert visual inspection, which is time-consuming, labour-intensive, and often impractical for large-scale farming operations. In this paper, we present PlantDiseaseNet-RT50, a novel fine-tuned deep learning architecture based on ResNet50 for automated plant disease detection. Our model features strategically unfrozen layers, a custom classification head with regularization mechanisms, and dynamic learning rate scheduling through cosine decay. Using a comprehensive dataset of distinct plant disease categories across multiple crop species, PlantDiseaseNet-RT50 achieves exceptional performance with approximately 98% accuracy, precision, and recall. Our architectural modifications and optimization protocol demonstrate how targeted fine-tuning can transform a standard pretrained model into a specialized agricultural diagnostic tool. We provide a detailed account of our methodology, including the systematic unfreezing of terminal layers, implementation of batch normalization and dropout regularization and application of advanced training techniques. PlantDiseaseNet-RT50 represents a significant advancement in AI-driven agricultural tools, offering a computationally efficient solution for rapid and accurate plant disease diagnosis that can be readily implemented in practical farming contexts to support timely interventions and reduce crop losses. --- ### Adaptive-VoCo: Complexity-Aware Visual Token Compression for Vision-Language Models Authors: Xiaoyang Guo, Keze Wang Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18496v1 In recent years, large-scale vision-language models (VLMs) have demonstrated remarkable performance on multimodal understanding and reasoning tasks. However, handling high-dimensional visual features often incurs substantial computational and memory costs. VoCo-LLaMA alleviates this issue by compressing visual patch tokens into a few VoCo tokens, reducing computational overhead while preserving strong cross-modal alignment. Nevertheless, such approaches typically adopt a fixed compression rate, limiting their ability to adapt to varying levels of visual complexity. To address this limitation, we propose Adaptive-VoCo, a framework that augments VoCo-LLaMA with a lightweight predictor for adaptive compression. This predictor dynamically selects an optimal compression rate by quantifying an image's visual complexity using statistical cues from the vision encoder, such as patch token entropy and attention map variance. Furthermore, we introduce a joint loss function that integrates rate regularization with complexity alignment. This enables the model to balance inference efficiency with representational capacity, particularly in challenging scenarios. Experimental results show that our method consistently outperforms fixed-rate baselines across multiple multimodal tasks, highlighting the potential of adaptive visual compression for creating more efficient and robust VLMs. --- ### Enhancing Decision-Making in Windows PE Malware Classification During Dataset Shifts with Uncertainty Estimation Authors: Rahul Yumlembam, Biju Issac, Seibu Mary Jacob Published: 2025-12-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.18495v1 Artificial intelligence techniques have achieved strong performance in classifying Windows Portable Executable (PE) malware, but their reliability often degrades under dataset shifts, leading to misclassifications with severe security consequences. To address this, we enhance an existing LightGBM (LGBM) malware detector by integrating Neural Networks (NN), PriorNet, and Neural Network Ensembles, evaluated across three benchmark datasets: EMBER, BODMAS, and UCSB. The UCSB dataset, composed mainly of packed malware, introduces a substantial distributional shift relative to EMBER and BODMAS, making it a challenging testbed for robustness. We study uncertainty-aware decision strategies, including probability thresholding, PriorNet, ensemble-derived estimates, and Inductive Conformal Evaluation (ICE). Our main contribution is the use of ensemble-based uncertainty estimates as Non-Conformity Measures within ICE, combined with a novel threshold optimisation method. On the UCSB dataset, where the shift is most severe, the state-of-the-art probability-based ICE (SOTA) yields an incorrect acceptance rate (IA%) of 22.8%. In contrast, our method reduces this to 16% a relative reduction of about 30% while maintaining competitive correct acceptance rates (CA%). These results demonstrate that integrating ensemble-based uncertainty with conformal prediction provides a more reliable safeguard against misclassifications under extreme dataset shifts, particularly in the presence of packed malware, thereby offering practical benefits for real-world security operations. --- ### Large Language Models as Discounted Bayesian Filters Authors: Jensen Zhang, Jing Yang, Keze Wang Published: 2025-12-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.18489v1 Large Language Models (LLMs) demonstrate strong few-shot generalization through in-context learning, yet their reasoning in dynamic and stochastic environments remains opaque. Prior studies mainly focus on static tasks and overlook the online adaptation required when beliefs must be continuously updated, which is a key capability for LLMs acting as world models or agents. We introduce a Bayesian filtering framework to evaluate online inference in LLMs. Our probabilistic probe suite spans both multivariate discrete distributions, such as dice rolls, and continuous distributions, such as Gaussian processes, where ground-truth parameters shift over time. We find that while LLM belief updates resemble Bayesian posteriors, they are more accurately characterized by an exponential forgetting filter with a model-specific discount factor smaller than one. This reveals systematic discounting of older evidence that varies significantly across model architectures. Although inherent priors are often miscalibrated, the updating mechanism itself remains structured and principled. We further validate these findings in a simulated agent task and propose prompting strategies that effectively recalibrate priors with minimal computational cost. --- ### Insider Threat Detection Using GCN and Bi-LSTM with Explicit and Implicit Graph Representations Authors: Rahul Yumlembam, Biju Issac, Seibu Mary Jacob, Longzhi Yang, Deepa Krishnan Published: 2025-12-20 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2512.18483v1 Insider threat detection (ITD) is challenging due to the subtle and concealed nature of malicious activities performed by trusted users. This paper proposes a post-hoc ITD framework that integrates explicit and implicit graph representations with temporal modelling to capture complex user behaviour patterns. An explicit graph is constructed using predefined organisational rules to model direct relationships among user activities. To mitigate noise and limitations in this hand-crafted structure, an implicit graph is learned from feature similarities using the Gumbel-Softmax trick, enabling the discovery of latent behavioural relationships. Separate Graph Convolutional Networks (GCNs) process the explicit and implicit graphs to generate node embeddings, which are concatenated and refined through an attention mechanism to emphasise threat-relevant features. The refined representations are then passed to a bidirectional Long Short-Term Memory (Bi-LSTM) network to capture temporal dependencies in user behaviour. Activities are flagged as anomalous when their probability scores fall below a predefined threshold. Extensive experiments on CERT r5.2 and r6.2 datasets demonstrate that the proposed framework outperforms state-of-the-art methods. On r5.2, the model achieves an AUC of 98.62, a detection rate of 100%, and a false positive rate of 0.05. On the more challenging r6.2 dataset, it attains an AUC of 88.48, a detection rate of 80.15%, and a false positive rate of 0.15, highlighting the effectiveness of combining graph-based and temporal representations for robust ITD. --- ### STORM: Search-Guided Generative World Models for Robotic Manipulation Authors: Wenjun Lin, Jensen Zhang, Kaitong Cai, Keze Wang Published: 2025-12-20 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.18477v1 We present STORM (Search-Guided Generative World Models), a novel framework for spatio-temporal reasoning in robotic manipulation that unifies diffusion-based action generation, conditional video prediction, and search-based planning. Unlike prior Vision-Language-Action (VLA) models that rely on abstract latent dynamics or delegate reasoning to language components, STORM grounds planning in explicit visual rollouts, enabling interpretable and foresight-driven decision-making. A diffusion-based VLA policy proposes diverse candidate actions, a generative video world model simulates their visual and reward outcomes, and Monte Carlo Tree Search (MCTS) selectively refines plans through lookahead evaluation. Experiments on the SimplerEnv manipulation benchmark demonstrate that STORM achieves a new state-of-the-art average success rate of 51.0 percent, outperforming strong baselines such as CogACT. Reward-augmented video prediction substantially improves spatio-temporal fidelity and task relevance, reducing Frechet Video Distance by over 75 percent. Moreover, STORM exhibits robust re-planning and failure recovery behavior, highlighting the advantages of search-guided generative world models for long-horizon robotic manipulation. ---