# Research Papers — 2025-12 · bundle page 159 of 175 > Full-text markdown of papers #7901–7950 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/159 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/158.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/160.md) ### YOLOA: Real-Time Affordance Detection via LLM Adapter Authors: Yuqi Ji, Junjie Ke, Lihuo He, Jun Liu, Kaifan Zhang, Yu-Kun Lai, Guiguang Ding, Xinbo Gao Published: 2025-12-03 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2512.03418v1 Affordance detection aims to jointly address the fundamental "what-where-how" challenge in embodied AI by understanding "what" an object is, "where" the object is located, and "how" it can be used. However, most affordance learning methods focus solely on "how" objects can be used while neglecting the "what" and "where" aspects. Other affordance detection methods treat object detection and affordance learning as two independent tasks, lacking effective interaction and real-time capability. To overcome these limitations, we introduce YOLO Affordance (YOLOA), a real-time affordance detection model that jointly handles these two tasks via a large language model (LLM) adapter. Specifically, YOLOA employs a lightweight detector consisting of object detection and affordance learning branches refined through the LLM Adapter. During training, the LLM Adapter interacts with object and affordance preliminary predictions to refine both branches by generating more accurate class priors, box offsets, and affordance gates. Experiments on our relabeled ADG-Det and IIT-Heat benchmarks demonstrate that YOLOA achieves state-of-the-art accuracy (52.8 / 73.1 mAP on ADG-Det / IIT-Heat) while maintaining real-time performance (up to 89.77 FPS, and up to 846.24 FPS for the lightweight variant). This indicates that YOLOA achieves an excellent trade-off between accuracy and efficiency. --- ### BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents Authors: Shu Wang, Yingli Zhou, Yixiang Fang Published: 2025-12-03 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.03413v1 As an effective method to boost the performance of Large Language Models (LLMs) on the question answering (QA) task, Retrieval-Augmented Generation (RAG), which queries highly relevant information from external complex documents, has attracted tremendous attention from both industry and academia. Existing RAG approaches often focus on general documents, and they overlook the fact that many real-world documents (such as books, booklets, handbooks, etc.) have a hierarchical structure, which organizes their content from different granularity levels, leading to poor performance for the QA task. To address these limitations, we introduce BookRAG, a novel RAG approach targeted for documents with a hierarchical structure, which exploits logical hierarchies and traces entity relations to query the highly relevant information. Specifically, we build a novel index structure, called BookIndex, by extracting a hierarchical tree from the document, which serves as the role of its table of contents, using a graph to capture the intricate relationships between entities, and mapping entities to tree nodes. Leveraging the BookIndex, we then propose an agent-based query method inspired by the Information Foraging Theory, which dynamically classifies queries and employs a tailored retrieval workflow. Extensive experiments on three widely adopted benchmarks demonstrate that BookRAG achieves state-of-the-art performance, significantly outperforming baselines in both retrieval recall and QA accuracy while maintaining competitive efficiency. --- ### ViDiC: Video Difference Captioning Authors: Jiangtao Wu, Shihao Li, Zhaozhou Bian, Jialu Chen, Runzhe Wen, An Ping, Yiwen He, Jiakai Wang, Yuanxing Zhang, Jiaheng Liu Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03405v3 Understanding visual differences between dynamic scenes requires the comparative perception of compositional, spatial, and temporal changes--a capability that remains underexplored in existing vision-language systems. While prior work on Image Difference Captioning (IDC) has enabled models to describe semantic changes between static images, these approaches fail to capture motion continuity, event evolution, or editing consistency over time. We introduce the ViDiC (Video Difference Captioning) task and its corresponding ViDiC-1K dataset, designed to evaluate the ability of Multimodal Large Language Models (MLLMs) to provide fine-grained descriptions of similarities and differences between video pairs. ViDiC-1K comprises 1,000 curated video pairs annotated with over 4,000 comparative checklist items, covering seven categories: subject, style, background, cinematography, motion, location, and playback techniques. To ensure reliable evaluation, we propose a dual-checklist framework that measures the accuracy of similarity and difference separately, based on the LLM-as-a-Judge protocol. Experiments on nineteen representative multimodal models reveal a significant performance gap in their comparative description and difference perception abilities. We hope ViDiC-1K can be a challenging benchmark that lays a solid foundation for advancing video understanding, edit awareness, and comparative reasoning in multimodal intelligence. --- ### MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification Authors: Yujian Zhao, Hankun Liu, Guanglin Niu Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03404v1 Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery has recently emerged as a critical yet underexplored task in maritime intelligence and surveillance. However, the substantial modality gap between optical and SAR images poses a major challenge for robust identification. To address this issue, we propose MOS, a novel framework designed to mitigate the optical-SAR modality gap and achieve modality-consistent feature learning for optical-SAR cross-modal ship ReID. MOS consists of two core components: (1) Modality-Consistent Representation Learning (MCRL) applies denoise SAR image procession and a class-wise modality alignment loss to align intra-identity feature distributions across modalities. (2) Cross-modal Data Generation and Feature fusion (CDGF) leverages a brownian bridge diffusion model to synthesize cross-modal samples, which are subsequently fused with original features during inference to enhance alignment and discriminability. Extensive experiments on the HOSS ReID dataset demonstrate that MOS significantly surpasses state-of-the-art methods across all evaluation protocols, achieving notable improvements of +3.0%, +6.2%, and +16.4% in R1 accuracy under the ALL to ALL, Optical to SAR, and SAR to Optical settings, respectively. The code and trained models will be released upon publication. --- ### Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates Authors: Yixing Xu, Chao Li, Xuanwu Yin, Spandan Tiwari, Dong Li, Ashish Sirasao, Emad Barsoum Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03402v4 Low-rank adaptation (LoRA) is one of the most popular methods among parameter-efficient fine-tuning (PEFT) methods to adapt pre-trained large language models (LLMs) to specific downstream tasks. However, the model trained based on LoRA often has an unsatisfactory performance due to its low-rank assumption. In this paper, we propose a novel method called Dual LoRA to improve the performance by incorporating an inductive bias into the original LoRA. Specifically, we separate low-rank matrices into two groups: the magnitude group to control whether or not and how far we should update a parameter and the direction group to decide whether this parameter should move forward or backward, to better simulate the parameter updating process of the full fine-tuning based on gradient-based optimization algorithms. We show that this can be simply achieved by adding a ReLU function to the magnitude group and a sign function to the direction group. We conduct several experiments over a wide range of NLP tasks, including natural language understanding (NLU) and commonsense reasoning datasets on RoBERTa, DeBERTa, and LLaMA-1/2/3 as baseline models. The results show that we consistently outperform LoRA and its state-of-the-art variants with the same number of trainable parameters. --- ### Better World Models Can Lead to Better Post-Training Performance Authors: Prakhar Gupta, Henry Conklin, Sarah-Jane Leslie, Andrew Lee Published: 2025-12-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.03400v2 We study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers, using Rubik's Cubes as our training domain. We ask: (1) how does explicitly pretraining a world model affect a model's latent representations, (2) how does world-model quality affect post-training performance, and (3) how should a finite data budget be split between pretraining and task-specific fine-tuning? We compare standard action-prediction fine-tuning with two strategies that add explicit state-prediction supervision: state pretraining followed by fine-tuning, and joint action and state training. We measure task accuracy after Group Relative Policy Optimization (GRPO). We further find that explicit world-modeling yields better representations in terms of higher probing accuracy and steerability of the model, and that better representations yield larger gains from GRPO, especially on harder cube states. Finally, when the fine-tuning budget is held fixed, probe accuracy strongly predicts the GRPO improvement. Under a fixed total data budget, accuracy is maximized by allocating only a small fraction to pretraining. --- ### Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value Authors: Joe Edelman, Tan Zhi-Xuan, Ryan Lowe, Oliver Klingefjord, Vincent Wang-Mascianica, Matija Franklin, Ryan Othniel Kearns, Ellie Hain, Atrisha Sarkar, Michiel Bakker, Fazl Barez, David Duvenaud et al. Published: 2025-12-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.03399v1 Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad outcomes if the goals of that organization are misaligned with those of other institutions and individuals. For this reason, we need full-stack alignment, the concurrent alignment of AI systems and the institutions that shape them with what people value. This can be done without imposing a particular vision of individual or collective flourishing. We argue that current approaches for representing values, such as utility functions, preference orderings, or unstructured text, struggle to address these and other issues effectively. They struggle to distinguish values from other signals, to support principled normative reasoning, and to model collective goods. We propose thick models of value will be needed. These structure the way values and norms are represented, enabling systems to distinguish enduring values from fleeting preferences, to model the social embedding of individual choices, and to reason normatively, applying values in new domains. We demonstrate this approach in five areas: AI value stewardship, normatively competent agents, win-win negotiation systems, meaning-preserving economic mechanisms, and democratic regulatory institutions. --- ### VS-Graph: Scalable and Efficient Graph Classification Using Hyperdimensional Computing Authors: Hamed Poursiami, Shay Snyder, Guojing Cong, Thomas Potok, Maryam Parsa Published: 2025-12-03 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2512.03394v1 Graph classification is a fundamental task in domains ranging from molecular property prediction to materials design. While graph neural networks (GNNs) achieve strong performance by learning expressive representations via message passing, they incur high computational costs, limiting their scalability and deployment on resource-constrained devices. Hyperdimensional Computing (HDC), also known as Vector Symbolic Architectures (VSA), offers a lightweight, brain-inspired alternative, yet existing HDC-based graph methods typically struggle to match the predictive performance of GNNs. In this work, we propose VS-Graph, a vector-symbolic graph learning framework that narrows the gap between the efficiency of HDC and the expressive power of message passing. VS-Graph introduces a Spike Diffusion mechanism for topology-driven node identification and an Associative Message Passing scheme for multi-hop neighborhood aggregation entirely within the high-dimensional vector space. Without gradient-based optimization or backpropagation, our method achieves competitive accuracy with modern GNNs, outperforming the prior HDC baseline by 4-5% on standard benchmarks such as MUTAG and DD. It also matches or exceeds the performance of the GNN baselines on several datasets while accelerating the training by a factor of up to 450x. Furthermore, VS-Graph maintains high accuracy even with the hypervector dimensionality reduced to D=128, demonstrating robustness under aggressive dimension compression and paving the way for ultra-efficient execution on edge and neuromorphic hardware. --- ### Tuning-Free Structured Sparse Recovery of Multiple Measurement Vectors using Implicit Regularization Authors: Lakshmi Jayalal, Sheetal Kalyani Published: 2025-12-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.03393v2 Recovering jointly sparse signals in the multiple measurement vectors (MMV) setting is a fundamental problem in machine learning, but traditional methods often require careful parameter tuning or prior knowledge of the sparsity of the signal and/or noise variance. We propose a tuning-free framework that leverages implicit regularization (IR) from overparameterization to overcome this limitation. Our approach reparameterizes the estimation matrix into factors that decouple the shared row-support from individual vector entries and applies gradient descent to a standard least-squares objective. We prove that with a sufficiently small and balanced initialization, the optimization dynamics exhibit a "momentum-like" effect where the true support grows significantly faster. Leveraging a Lyapunov-based analysis of the gradient flow, we further establish formal guarantees that the solution trajectory converges towards an idealized row-sparse solution. Empirical results demonstrate that our tuning-free approach achieves performance comparable to optimally tuned established methods. Furthermore, our framework significantly outperforms these baselines in scenarios where accurate priors are unavailable to the baselines. --- ### UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs Authors: Hung-Yueh Chiang, Chi-Chih Chang, Yu-Chen Lu, Chien-Yu Lin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu Published: 2025-12-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.03383v3 Deploying large language models (LLMs) on mobile platforms faces significant challenges due to the limited memory and shared computational resources of the device. Resource availability may be an issue as it is directly impacted by the current device workload, adding to the uncertainty of model deployment. We introduce UniQL, a unified post-training quantization and low-rank compression framework with on-device configurable pruning rates for edge LLMs. UniQL is a general framework that integrates quantization and low-rank compression for Transformers, State Space Models (SSMs), and hybrid models to support diverse edge applications. In our proposed joint framework, we introduce an efficient structured weight-sorting method that speeds up computation by 20x, quantization-aware singular value decomposition (SVD) to minimize quantization errors, state-aware weight sorting for SSMs, and a fused rotary positional embedding (RoPE) kernel for pruned models. Our framework performs weight-sorting, fine-tuning, and quantization in the cloud in a single-pass workflow, while enabling on-device configurable pruning rates up to 35%. Our experiments show that quantized and pruned models achieve a memory reduction of 4x-5.7x and a token-throughput improvement of 2.7x-3.4x, maintaining accuracy within 5% of the original models at 15% pruning across Transformers (Llama3 and Qwen2.5), SSMs (Mamba2), and hybrid models (Nemotron-H and Bamba-v2). The code and quantized models are available at: https://github.com/enyac-group/UniQL. --- ### Characterizing Language Use in a Collaborative Situated Game Authors: Nicholas Tomlin, Naitian Zhou, Eve Fleisig, Liangyuan Chen, Téa Wright, Lauren Vinh, Laura X. Ma, Seun Eisape, Ellie French, Tingting Du, Tianjiao Zhang, Alexander Koller et al. Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03381v2 Cooperative video games, where multiple participants must coordinate by communicating and reasoning under uncertainty in complex environments, yield a rich source of language data. We collect the Portal Dialogue Corpus: a corpus of 11.5 hours of spoken human dialogue in the co-op mode of the popular Portal 2 virtual puzzle game, comprising 24.5K total utterances. We analyze player language and behavior, identifying a number of linguistic phenomena that rarely appear in most existing chitchat or task-oriented dialogue corpora, including complex spatial reference, clarification and repair, and ad-hoc convention formation. To support future analyses of language use in complex, situated, collaborative problem-solving scenarios, we publicly release the corpus, which comprises player videos, audio, transcripts, game state data, and both manual and automatic annotations of language data. --- ### Nexus: Higher-Order Attention Mechanisms in Transformers Authors: Hanting Chen, Chong Zhu, Kai Han, Yuchuan Tian, Yuchen Liang, Tianyu Guo, Xinghao Chen, Dacheng Tao, Yunhe Wang Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03377v2 Transformers have achieved significant success across various domains, relying on self-attention to capture dependencies. However, the standard first-order attention mechanism is often limited by a low-rank bottleneck, struggling to capture intricate, multi-hop relationships within a single layer. In this paper, we propose the Nexus, a novel architecture designed to enhance representational power through a recursive framework. Unlike standard approaches that use static linear projections for Queries and Keys, Nexus dynamically refines these representations via nested self-attention mechanisms. Specifically, the Query and Key vectors are themselves outputs of inner attention loops, allowing tokens to aggregate global context and model high-order correlations \textit{prior} to the final attention computation. We enforce a parameter-efficient weight-sharing strategy across recursive steps, ensuring that this enhanced expressivity incurs $\mathcal{O}(1)$ additional parameters. We provide theoretical analysis demonstrating that our method breaks the linear bottleneck of standard attention. Empirically, Nexus outperforms standard Transformers on multiple benchmarks. --- ### MAGE-ID: A Multimodal Generative Framework for Intrusion Detection Systems Authors: Mahdi Arab Loodaricheh, Mohammad Hossein Manshaei, Anita Raja Published: 2025-12-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.03375v1 Modern Intrusion Detection Systems (IDS) face severe challenges due to heterogeneous network traffic, evolving cyber threats, and pronounced data imbalance between benign and attack flows. While generative models have shown promise in data augmentation, existing approaches are limited to single modalities and fail to capture cross-domain dependencies. This paper introduces MAGE-ID (Multimodal Attack Generator for Intrusion Detection), a diffusion-based generative framework that couples tabular flow features with their transformed images through a unified latent prior. By jointly training Transformer and CNN-based variational encoders with an EDM style denoiser, MAGE-ID achieves balanced and coherent multimodal synthesis. Evaluations on CIC-IDS-2017 and NSL-KDD demonstrate significant improvements in fidelity, diversity, and downstream detection performance over TabSyn and TabDDPM, highlighting the effectiveness of MAGE-ID for multimodal IDS augmentation. --- ### LLM-Generated Ads: From Personalization Parity to Persuasion Superiority Authors: Elyas Meguellati, Stefano Civelli, Lei Han, Abraham Bernstein, Shazia Sadiq, Gianluca Demartini Published: 2025-12-03 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2512.03373v1 As large language models (LLMs) become increasingly capable of generating persuasive content, understanding their effectiveness across different advertising strategies becomes critical. This paper presents a two-part investigation examining LLM-generated advertising through complementary lenses: (1) personality-based and (2) psychological persuasion principles. In our first study (n=400), we tested whether LLMs could generate personalized advertisements tailored to specific personality traits (openness and neuroticism) and how their performance compared to human experts. Results showed that LLM-generated ads achieved statistical parity with human-written ads (51.1% vs. 48.9%, p > 0.05), with no significant performance differences for matched personalities. Building on these insights, our second study (n=800) shifted focus from individual personalization to universal persuasion, testing LLM performance across four foundational psychological principles: authority, consensus, cognition, and scarcity. AI-generated ads significantly outperformed human-created content, achieving a 59.1% preference rate (vs. 40.9%, p < 0.001), with the strongest performance in authority (63.0%) and consensus (62.5%) appeals. Qualitative analysis revealed AI's advantage stems from crafting more sophisticated, aspirational messages and achieving superior visual-narrative coherence. Critically, this quality advantage proved robust: even after applying a 21.2 percentage point detection penalty when participants correctly identified AI-origin, AI ads still outperformed human ads, and 29.4% of participants chose AI content despite knowing its origin. These findings demonstrate LLMs' evolution from parity in personalization to superiority in persuasive storytelling, with significant implications for advertising practice given LLMs' near-zero marginal cost and time requirements compared to human experts. --- ### ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding Authors: Lingjun Zhao, Yandong Luo, James Hays, Lu Gan Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03370v3 We introduce ShelfGaussian, an open-vocabulary multi-modal Gaussian-based 3D scene understanding framework supervised by off-the-shelf vision foundation models (VFMs). Gaussian-based methods have demonstrated superior performance and computational efficiency across a wide range of scene understanding tasks. However, existing methods either model objects as closed-set semantic Gaussians supervised by annotated 3D labels, neglecting their rendering ability, or learn open-set Gaussian representations via purely 2D self-supervision, leading to degraded geometry and limited to camera-only settings. To fully exploit the potential of Gaussians, we propose a Multi-Modal Gaussian Transformer that enables Gaussians to query features from diverse sensor modalities, and a Shelf-Supervised Learning Paradigm that efficiently optimizes Gaussians with VFM features jointly at 2D image and 3D scene levels. We evaluate ShelfGaussian on various perception and planning tasks. Experiments on Occ3D-nuScenes demonstrate its state-of-the-art zero-shot semantic occupancy prediction performance. ShelfGaussian is further evaluated on an unmanned ground vehicle (UGV) to assess its in the-wild performance across diverse urban scenarios. Project website: https://lunarlab-gatech.github.io/ShelfGaussian/. --- ### FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting Authors: Nan Zhou, Huandong Wang, Jiahao Li, Han Li, Yali Song, Qiuhua Wang, Yong Li, Xinlei Chen Published: 2025-12-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.03369v1 Fine-grained wildfire spread prediction is crucial for enhancing emergency response efficacy and decision-making precision. However, existing research predominantly focuses on coarse spatiotemporal scales and relies on low-resolution satellite data, capturing only macroscopic fire states while fundamentally constraining high-precision localized fire dynamics modeling capabilities. To bridge this gap, we present FireSentry, a provincial-scale multi-modal wildfire dataset characterized by sub-meter spatial and sub-second temporal resolution. Collected using synchronized UAV platforms, FireSentry provides visible and infrared video streams, in-situ environmental measurements, and manually validated fire masks. Building on FireSentry, we establish a comprehensive benchmark encompassing physics-based, data-driven, and generative models, revealing the limitations of existing mask-only approaches. Our analysis proposes FiReDiff, a novel dual-modality paradigm that first predicts future video sequences in the infrared modality, and then precisely segments fire masks in the mask modality based on the generated dynamics. FiReDiff achieves state-of-the-art performance, with video quality gains of 39.2% in PSNR, 36.1% in SSIM, 50.0% in LPIPS, 29.4% in FVD, and mask accuracy gains of 3.3% in AUPRC, 59.1% in F1 score, 42.9% in IoU, and 62.5% in MSE when applied to generative models. The FireSentry benchmark dataset and FiReDiff paradigm collectively advance fine-grained wildfire forecasting and dynamic disaster simulation. The processed benchmark dataset is publicly available at: https://github.com/Munan222/FireSentry-Benchmark-Dataset. --- ### Adaptive Aggregation with Two Gains in QFL Authors: S Nanayakkara Published: 2025-12-03 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2512.03363v2 Federated learning (FL) deployed over quantum enabled and heterogeneous classical networks faces significant performance degradation due to uneven client quality, stochastic teleportation fidelity, device instability, and geometric mismatch between local and global models. Classical aggregation rules assume euclidean topology and uniform communication reliability, limiting their suitability for emerging quantum federated systems. This paper introduces A2G (Adaptive Aggregation with Two Gains), a dual gain framework that jointly regulates geometric blending through a geometry gain and modulates client importance using a QoS gain derived from teleportation fidelity, latency, and instability. --- ### From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation Authors: Qingchuan Li, Mingyue Cheng, Zirui Liu, Daoyu Wang, Yuting Zeng, Tongxuan Liu Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03360v1 Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical theorem proving, and complex decision-making. Despite the remarkable progress of large language models (LLMs), most current approaches still rely on forward reasoning paradigms, generating step-by-step rationales from premises to conclusions. However, such methods often suffer from redundant inference paths, hallucinated steps, and semantic drift, resulting in inefficient and unreliable reasoning. In this paper, we propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR). The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning. In the translation phase, only high-confidence spans are converted into logical form, such as First-Order Logic (FOL), while uncertain content remains in natural language. A translation reflection module further ensures semantic fidelity by evaluating symbolic outputs and reverting lossy ones back to text when necessary. In the reasoning phase, HBLR simulates human deductive thinking by assuming the conclusion is true and recursively verifying its premises. A reasoning reflection module further identifies and corrects flawed inference steps, enhancing logical coherence. Extensive experiments on five reasoning benchmarks demonstrate that HBLR consistently outperforms strong baselines in both accuracy and efficiency. --- ### A Hybrid Deep Learning Framework with Explainable AI for Lung Cancer Classification with DenseNet169 and SVM Authors: Md Rashidul Islam, Bakary Gibba, Altagi Abdallah Bakheit Abdelgadir Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03359v1 Lung cancer is a very deadly disease worldwide, and its early diagnosis is crucial for increasing patient survival rates. Computed tomography (CT) scans are widely used for lung cancer diagnosis as they can give detailed lung structures. However, manual interpretation is time-consuming and prone to human error. To surmount this challenge, the study proposes a deep learning-based automatic lung cancer classification system to enhance detection accuracy and interpretability. The IQOTHNCCD lung cancer dataset is utilized, which is a public CT scan dataset consisting of cases categorized into Normal, Benign, and Malignant and used DenseNet169, which includes Squeezeand-Excitation blocks for attention-based feature extraction, Focal Loss for handling class imbalance, and a Feature Pyramid Network (FPN) for multi-scale feature fusion. In addition, an SVM model was developed using MobileNetV2 for feature extraction, improving its classification performance. For model interpretability enhancement, the study integrated Grad-CAM for the visualization of decision-making regions in CT scans and SHAP (Shapley Additive Explanations) for explanation of feature contributions within the SVM model. Intensive evaluation was performed, and it was found that both DenseNet169 and SVM models achieved 98% accuracy, suggesting their robustness for real-world medical practice. These results open up the potential for deep learning to improve the diagnosis of lung cancer by a higher level of accuracy, transparency, and robustness. --- ### Breaking Determinism: Stochastic Modeling for Reliable Off-Policy Evaluation in Ad Auctions Authors: Hongseon Yeom, Jaeyoul Shin, Soojin Min, Jeongmin Yoon, Seunghak Yu, Dongyeop Kang Published: 2025-12-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.03354v1 Online A/B testing, the gold standard for evaluating new advertising policies, consumes substantial engineering resources and risks significant revenue loss from deploying underperforming variations. This motivates the use of Off-Policy Evaluation (OPE) for rapid, offline assessment. However, applying OPE to ad auctions is fundamentally more challenging than in domains like recommender systems, where stochastic policies are common. In online ad auctions, it is common for the highest-bidding ad to win the impression, resulting in a deterministic, winner-takes-all setting. This results in zero probability of exposure for non-winning ads, rendering standard OPE estimators inapplicable. We introduce the first principled framework for OPE in deterministic auctions by repurposing the bid landscape model to approximate the propensity score. This model allows us to derive robust approximate propensity scores, enabling the use of stable estimators like Self-Normalized Inverse Propensity Scoring (SNIPS) for counterfactual evaluation. We validate our approach on the AuctionNet simulation benchmark and against 2-weeks online A/B test from a large-scale industrial platform. Our method shows remarkable alignment with online results, achieving a 92\% Mean Directional Accuracy (MDA) in CTR prediction, significantly outperforming the parametric baseline. MDA is the most critical metric for guiding deployment decisions, as it reflects the ability to correctly predict whether a new model will improve or harm performance. This work contributes the first practical and validated framework for reliable OPE in deterministic auction environments, offering an efficient alternative to costly and risky online experiments. --- ### SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation Authors: Yu Yuan, Tharindu Wickremasinghe, Zeeshan Nadir, Xijun Wang, Yiheng Chi, Stanley H. Chan Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03350v2 Images and videos are discrete 2D projections of the 4D world (3D space + time). Most visual understanding, prediction, and generation operate directly on 2D observations, leading to suboptimal performance. We propose SeeU, a novel approach that learns the continuous 4D dynamics and generate the unseen visual contents. The principle behind SeeU is a new 2D$\to$4D$\to$2D learning framework. SeeU first reconstructs the 4D world from sparse and monocular 2D frames (2D$\to$4D). It then learns the continuous 4D dynamics on a low-rank representation and physical constraints (discrete 4D$\to$continuous 4D). Finally, SeeU rolls the world forward in time, re-projects it back to 2D at sampled times and viewpoints, and generates unseen regions based on spatial-temporal context awareness (4D$\to$2D). By modeling dynamics in 4D, SeeU achieves continuous and physically-consistent novel visual generation, demonstrating strong potentials in multiple tasks including unseen temporal generation, unseen spatial generation, and video editing. All data and code will be public at https://yuyuanspace.com/SeeU/ --- ### Hierarchical Attention for Sparse Volumetric Anomaly Detection in Subclinical Keratoconus Authors: Lynn Kandakji, William Woof, Nikolas Pontikos Published: 2025-12-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.03346v2 The detection of weak, spatially distributed anomalies in volumetric medical imaging remains challenging due to the difficulty of integrating subtle signals across non-adjacent regions. This study presents a controlled comparison of sixteen architectures spanning convolutional, hybrid, and transformer families for subclinical keratoconus detection from three-dimensional anterior segment optical coherence tomography (AS-OCT). The results demonstrate that hierarchical architectures achieve 21-23% higher sensitivity and specificity, particularly in the difficult subclinical regime, outperforming both convolutional neural networks (CNNs) and global-attention Vision Transformer (ViT) baselines. Mechanistic analyses indicate that this advantage arises from spatial scale alignment: hierarchical windowing produces effective receptive fields matched to the intermediate extent of subclinical abnormalities, avoiding the excessive locality observed in convolutional models and the diffuse integration characteristic of pure global attention. Attention-distance measurements show that subclinical cases require longer spatial integration than healthy or overtly pathological volumes, with hierarchical models exhibiting lower variance and more anatomically coherent focus. Representational similarity further indicates that hierarchical attention learns a distinct feature space that balances local structure sensitivity with flexible long-range interactions. Auxiliary age and sex prediction tasks demonstrate moderately high cross-task consistency, supporting the generalizability of these inductive principles. The findings provide design guidance for volumetric anomaly detection and highlight hierarchical attention as a principled approach for early pathological change analysis in medical imaging. --- ### HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration Authors: Seunghoi Kim, Henry F. J. Tregidgo, Chen Jin, Matteo Figini, Daniel C. Alexander Published: 2025-12-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.03345v1 Generative models are prone to hallucinations: plausible but incorrect structures absent in the ground truth. This issue is problematic in image restoration for safety-critical domains such as medical imaging, industrial inspection, and remote sensing, where such errors undermine reliability and trust. For example, in low-field MRI, widely used in resource-limited settings, restoration models are essential for enhancing low-quality scans, yet hallucinations can lead to serious diagnostic errors. Progress has been hindered by a circular dependency: evaluating hallucinations requires labeled data, yet such labels are costly and subjective. We introduce HalluGen, a diffusion-based framework that synthesizes realistic hallucinations with controllable type, location, and severity, producing perceptually realistic but semantically incorrect outputs (segmentation IoU drops from 0.86 to 0.36). Using HalluGen, we construct the first large-scale hallucination dataset comprising 4,350 annotated images derived from 1,450 brain MR images for low-field enhancement, enabling systematic evaluation of hallucination detection and mitigation. We demonstrate its utility in two applications: (1) benchmarking image quality metrics and developing Semantic Hallucination Assessment via Feature Evaluation (SHAFE), a feature-based metric with soft-attention pooling that improves hallucination sensitivity over traditional metrics; and (2) training reference-free hallucination detectors that generalize to real restoration failures. Together, HalluGen and its open dataset establish the first scalable foundation for evaluating hallucinations in safety-critical image restoration. --- ### Idea-Gated Transformers: Enforcing Semantic Coherence via Differentiable Vocabulary Pruning Authors: Darshan Fofadiya Published: 2025-12-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.03343v2 Autoregressive Language Models (LLMs) trained on Next-Token Prediction (NTP) often suffer from Topic Drift where the generation wanders away from the initial prompt due to a reliance on local associations rather than global planning. While scaling model size mitigates this, the fundamental myopia of the NTP objective remains. In this work, we introduce the Idea-Gated Transformer, a novel architecture that separates semantic planning from syntactic generation. We introduce an auxiliary Idea Head trained to predict the bag-of-words distribution for a future context window, creating a latent ``Concept Vector'' that actively gates the main vocabulary during generation. We propose a differentiable gating mechanism that suppresses semantically irrelevant tokens, effectively pruning the search space in real-time. Experiments on WikiText-103 demonstrate that while the Idea-Gated model achieves comparable validation perplexity to a standard GPT-2 baseline, it exhibits significantly superior Domain Retention. Qualitative and quantitative analysis reveals that the gating mechanism successfully locks generation into specific semantic clusters (e.g., Finance, Science) and resists associative drift, offering a parameter-efficient path toward more controllable language modeling. --- ### PERCS: Persona-Guided Controllable Biomedical Summarization Dataset Authors: Rohan Charudatt Salvi, Chirag Chawla, Dhruv Jain, Swapnil Panigrahi, Md Shad Akhtar, Shweta Yadav Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03340v1 Automatic medical text simplification plays a key role in improving health literacy by making complex biomedical research accessible to diverse readers. However, most existing resources assume a single generic audience, overlooking the wide variation in medical literacy and information needs across user groups. To address this limitation, we introduce PERCS (Persona-guided Controllable Summarization), a dataset of biomedical abstracts paired with summaries tailored to four personas: Laypersons, Premedical Students, Non-medical Researchers, and Medical Experts. These personas represent different levels of medical literacy and information needs, emphasizing the need for targeted, audience-specific summarization. Each summary in PERCS was reviewed by physicians for factual accuracy and persona alignment using a detailed error taxonomy. Technical validation shows clear differences in readability, vocabulary, and content depth across personas. Along with describing the dataset, we benchmark four large language models on PERCS using automatic evaluation metrics that assess comprehensiveness, readability, and faithfulness, establishing baseline results for future research. The dataset, annotation guidelines, and evaluation materials are publicly available to support research on persona-specific communication and controllable biomedical summarization. --- ### ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography Authors: Yeganeh Ghamary, Victoria Wu, Hooman Vaseli, Christina Luong, Teresa Tsang, Siavash Bigdeli, Purang Abolmaesumi Published: 2025-12-03 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.03339v1 Ejection fraction (EF) is a crucial metric for assessing cardiac function and diagnosing conditions such as heart failure. Traditionally, EF estimation requires manual tracing and domain expertise, making the process time-consuming and subject to interobserver variability. Most current deep learning methods for EF prediction are black-box models with limited transparency, which reduces clinical trust. Some post-hoc explainability methods have been proposed to interpret the decision-making process after the prediction is made. However, these explanations do not guide the model's internal reasoning and therefore offer limited reliability in clinical applications. To address this, we introduce ProtoEFNet, a novel video-based prototype learning model for continuous EF regression. The model learns dynamic spatiotemporal prototypes that capture clinically meaningful cardiac motion patterns. Additionally, the proposed Prototype Angular Separation (PAS) loss enforces discriminative representations across the continuous EF spectrum. Our experiments on the EchonetDynamic dataset show that ProtoEFNet can achieve accuracy on par with its non-interpretable counterpart while providing clinically relevant insight. The ablation study shows that the proposed loss boosts performance with a 2% increase in F1 score from 77.67$\pm$2.68 to 79.64$\pm$2.10. Our source code is available at: https://github.com/DeepRCL/ProtoEF --- ### Epistemic Substitution: How Grokipedia's AI-Generated Encyclopedia Restructures Authority Authors: Aliakbar Mehdizadeh, Martin Hilbert Published: 2025-12-03 Categories: cs.SI, cs.CL, cs.CY, cs.DL arXiv: https://arxiv.org/abs/2512.03337v1 A quarter century ago, Wikipedia's decentralized, crowdsourced, and consensus-driven model replaced the centralized, expert-driven, and authority-based standard for encyclopedic knowledge curation. The emergence of generative AI encyclopedias, such as Grokipedia, possibly presents another potential shift in epistemic evolution. This study investigates whether AI- and human-curated encyclopedias rely on the same foundations of authority. We conducted a multi-scale comparative analysis of the citation networks from 72 matched article pairs, which cite a total of almost 60,000 sources. Using an 8-category epistemic classification, we mapped the "epistemic profiles" of the articles on each platform. Our findings reveal several quantitative and qualitative differences in how knowledge is sourced and encyclopedia claims are epistemologically justified. Grokipedia replaces Wikipedia's heavy reliance on peer-reviewed "Academic & Scholarly" work with a notable increase in "User-generated" and "Civic organization" sources. Comparative network analyses further show that Grokipedia employs very different epistemological profiles when sourcing leisure topics (such as Sports and Entertainment) and more societal sensitive civic topics (such as Politics & Conflicts, Geographical Entities, and General Knowledge & Society). Finally, we find a "scaling-law for AI-generated knowledge sourcing" that shows a linear relationship between article length and citation density, which is distinct from collective human reference sourcing. We conclude that this first implementation of an LLM-based encyclopedia does not merely automate knowledge production but restructures it. Given the notable changes and the important role of encyclopedias, we suggest the continuation and deepening of algorithm audits, such as the one presented here, in order to understand the ongoing epistemological shifts. --- ### Single-Round Scalable Analytic Federated Learning Authors: Alan T. L. Bacellar, Mustafa Munir, Felipe M. G. França, Priscila M. V. Lima, Radu Marculescu, Lizy K. John Published: 2025-12-03 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.03336v2 Federated Learning (FL) is plagued by two key challenges: high communication overhead and performance collapse on heterogeneous (non-IID) data. Analytic FL (AFL) provides a single-round, data distribution invariant solution, but is limited to linear models. Subsequent non-linear approaches, like DeepAFL, regain accuracy but sacrifice the single-round benefit. In this work, we break this trade-off. We propose SAFLe, a framework that achieves scalable non-linear expressivity by introducing a structured head of bucketed features and sparse, grouped embeddings. We prove this non-linear architecture is mathematically equivalent to a high-dimensional linear regression. This key equivalence allows SAFLe to be solved with AFL's single-shot, invariant aggregation law. Empirically, SAFLe establishes a new state-of-the-art for analytic FL, significantly outperforming both linear AFL and multi-round DeepAFL in accuracy across all benchmarks, demonstrating a highly efficient and scalable solution for federated vision. --- ### Step-by-step Layered Design Generation Authors: Faizan Farooq Khan, K J Joseph, Koustava Goswami, Mohamed Elhoseiny, Balaji Vasan Srinivasan Published: 2025-12-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.03335v1 Design generation, in its essence, is a step-by-step process where designers progressively refine and enhance their work through careful modifications. Despite this fundamental characteristic, existing approaches mainly treat design synthesis as a single-step generation problem, significantly underestimating the inherent complexity of the creative process. To bridge this gap, we propose a novel problem setting called Step-by-Step Layered Design Generation, which tasks a machine learning model with generating a design that adheres to a sequence of instructions from a designer. Leveraging recent advancements in multi-modal LLMs, we propose SLEDGE: Step-by-step LayEred Design GEnerator to model each update to a design as an atomic, layered change over its previous state, while being grounded in the instruction. To complement our new problem setting, we introduce a new evaluation suite, including a dataset and a benchmark. Our exhaustive experimental analysis and comparison with state-of-the-art approaches tailored to our new setup demonstrate the efficacy of our approach. We hope our work will attract attention to this pragmatic and under-explored research area. --- ### Modeling Topics and Sociolinguistic Variation in Code-Switched Discourse: Insights from Spanish-English and Spanish-Guaraní Authors: Nemika Tyagi, Nelvin Licona Guevara, Olga Kellert Published: 2025-12-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.03334v1 This study presents an LLM-assisted annotation pipeline for the sociolinguistic and topical analysis of bilingual discourse in two typologically distinct contexts: Spanish-English and Spanish-Guaraní. Using large language models, we automatically labeled topic, genre, and discourse-pragmatic functions across a total of 3,691 code-switched sentences, integrated demographic metadata from the Miami Bilingual Corpus, and enriched the Spanish-Guaraní dataset with new topic annotations. The resulting distributions reveal systematic links between gender, language dominance, and discourse function in the Miami data, and a clear diglossic division between formal Guaraní and informal Spanish in Paraguayan texts. These findings replicate and extend earlier interactional and sociolinguistic observations with corpus-scale quantitative evidence. The study demonstrates that large language models can reliably recover interpretable sociolinguistic patterns traditionally accessible only through manual annotation, advancing computational methods for cross-linguistic and low-resource bilingual research. --- ### Sketch Tomography: Hybridizing Classical Shadow and Matrix Product State Authors: Xun Tang, Haoxuan Chen, Yuehaw Khoo, Lexing Ying Published: 2025-12-03 Categories: quant-ph, math.NA, math.ST, physics.comp-ph, stat.ML arXiv: https://arxiv.org/abs/2512.03333v2 We introduce Sketch Tomography, an efficient procedure for quantum state tomography based on the classical shadow protocol used for quantum observable estimations. The procedure applies to the case where the ground truth quantum state is a matrix product state (MPS). The density matrix of the ground truth state admits a tensor train ansatz as a result of the MPS assumption, and we estimate the tensor components of the ansatz through a series of observable estimations, thus outputting an approximation of the density matrix. The procedure is provably convergent with a sample complexity that scales quadratically in the system size. We conduct extensive numerical experiments to show that the procedure outputs an accurate approximation to the quantum state. For observable estimation tasks involving moderately large subsystems, we show that our procedure gives rise to a more accurate estimation than the classical shadow protocol. We also show that sketch tomography is more accurate in observable estimation than quantum states trained from the maximum likelihood estimation formulation. --- ### When does Gaussian equivalence fail and how to fix it: Non-universal behavior of random features with quadratic scaling Authors: Garrett G. Wen, Hong Hu, Yue M. Lu, Zhou Fan, Theodor Misiakiewicz Published: 2025-12-03 Categories: math.ST, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.03325v1 A major effort in modern high-dimensional statistics has been devoted to the analysis of linear predictors trained on nonlinear feature embeddings via empirical risk minimization (ERM). Gaussian equivalence theory (GET) has emerged as a powerful universality principle in this context: it states that the behavior of high-dimensional, complex features can be captured by Gaussian surrogates, which are more amenable to analysis. Despite its remarkable successes, numerical experiments show that this equivalence can fail even for simple embeddings -- such as polynomial maps -- under general scaling regimes. We investigate this breakdown in the setting of random feature (RF) models in the quadratic scaling regime, where both the number of features and the sample size grow quadratically with the data dimension. We show that when the target function depends on a low-dimensional projection of the data, such as generalized linear models, GET yields incorrect predictions. To capture the correct asymptotics, we introduce a Conditional Gaussian Equivalent (CGE) model, which can be viewed as appending a low-dimensional non-Gaussian component to an otherwise high-dimensional Gaussian model. This hybrid model retains the tractability of the Gaussian framework and accurately describes RF models in the quadratic scaling regime. We derive sharp asymptotics for the training and test errors in this setting, which continue to agree with numerical simulations even when GET fails. Our analysis combines general results on CLT for Wiener chaos expansions and a careful two-phase Lindeberg swapping argument. Beyond RF models and quadratic scaling, our work hints at a rich landscape of universality phenomena in high-dimensional ERM. --- ### Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs Authors: Ngoc Bui, Shubham Sharma, Simran Lamba, Saumitra Mishra, Rex Ying Published: 2025-12-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.03324v2 Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization, offloading, or heuristic KV eviction, either incur high orchestration costs or rely on unreliable attention-based proxies of importance. We propose TRIM-KV, a novel approach that learns each token's intrinsic importance at creation time via a lightweight retention gate. Each gate predicts a scalar retention score that decays over time, reflecting the long-term utility of the token for a specific layer and head. Tokens with low scores are evicted when the memory budget is exceeded, ensuring that the cache always contains the most critical tokens. TRIM-KV is trained efficiently through distillation from a frozen LLM combined with a capacity loss, requiring only gate fine-tuning and adding negligible inference overhead. Across mathematical reasoning (GSM8K, MATH-500, AIME24), procedural generation (LongProc), conversational long-memory benchmarks (LongMemEval), and long-context understanding (LongBenchV2 and SCBench), TRIM-KV consistently outperforms strong eviction and learnable retrieval baselines, especially in low-memory regimes. Remarkably, it even surpasses full-cache models in some settings, showing that selective retention can serve as a form of regularization, suppressing noise from uninformative tokens. Qualitative analyses further reveal that learned retention scores align with human intuition, naturally recovering heuristics such as sink tokens, sliding windows, and gist compression without explicit design. Beyond efficiency, retention scores provide insights into layer- and head-specific roles, suggesting a new path toward LLM interpretability. --- ### SSLfmm: An R Package for Semi-Supervised Learning with Mixed Missingness Authors: Geoffrey J. McLachlan, Jinran Wu Published: 2025-12-03 Categories: stat.CO, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.03322v5 Partially labelled samples arise when features are observed for data, but class labels are available for only a subset. In such settings, the mechanism governing label availability may itself contain information relevant to classification, yet it is typically left unmodelled in standard semi-supervised learning procedures. The SSLfmm package implements likelihood-based Gaussian finite-mixture classification in which the label-missingness process is modelled jointly with the class distribution. It supports complete-case, missing completely at random (MCAR), entropy-based missing at random (MAR), and mixed analyses in which MCAR and MAR mechanisms may both contribute. For the mixed mechanism, the source of a missing label may be known or unknown. A common R interface is provided for model fitting, prediction, performance assessment, and simulation. We describe the statistical formulation and software implementation and demonstrate its use through reproducible simulation and a semi-synthetic Blood Transfusion application. --- ### Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia Authors: Chandler Smith, Marwa Abdulhai, Manfred Diaz, Marko Tesic, Rakshit S. Trivedi, Alexander Sasha Vezhnevets, Lewis Hammond, Jesse Clifton, Minsuk Chang, Edgar A. Duéñez-Guzmán, John P. Agapiou, Jayd Matyas et al. Published: 2025-12-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.03318v1 Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement. --- ### NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction Authors: Thomas Monninger, Zihan Zhang, Steffen Staab, Sihao Ding Published: 2025-12-03 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2512.03317v1 Accurate environmental representations are essential for autonomous driving, providing the foundation for safe and efficient navigation. Traditionally, high-definition (HD) maps are providing this representation of the static road infrastructure to the autonomous system a priori. However, because the real world is constantly changing, such maps must be constructed online from on-board sensor data. Navigation-grade standard-definition (SD) maps are widely available, but their resolution is insufficient for direct deployment. Instead, they can be used as coarse prior to guide the online map construction process. We propose NavMapFusion, a diffusion-based framework that performs iterative denoising conditioned on high-fidelity sensor data and on low-fidelity navigation maps. This paper strives to answer: (1) How can coarse, potentially outdated navigation maps guide online map construction? (2) What advantages do diffusion models offer for map fusion? We demonstrate that diffusion-based map construction provides a robust framework for map fusion. Our key insight is that discrepancies between the prior map and online perception naturally correspond to noise within the diffusion process; consistent regions reinforce the map construction, whereas outdated segments are suppressed. On the nuScenes benchmark, NavMapFusion conditioned on coarse road lines from OpenStreetMap data reaches a 21.4% relative improvement on 100 m, and even stronger improvements on larger perception ranges, while maintaining real-time capabilities. By fusing low-fidelity priors with high-fidelity sensor data, the proposed method generates accurate and up-to-date environment representations, guiding towards safer and more reliable autonomous driving. The code is available at https://github.com/tmonnin/navmapfusion --- ### Virtual Parameter Sharpening: Dynamic Low-Rank Perturbations for Inference-Time Reasoning Enhancement Authors: Saba Kublashvili Published: 2025-12-02 Categories: cs.LG, cs.AI, cs.MS, math.PR arXiv: https://arxiv.org/abs/2602.19169v1 I introduce Virtual Parameter Sharpening (VPS), an inference-time technique that augments frozen transformer linear layers with dynamic, activation-conditioned low-rank perturbations. Unlike parameter-efficient fine-tuning methods such as LoRA, which learn static low-rank adapters, VPS constructs its perturbation factors on the fly from batch activation statistics and optional gradient signals, enabling test-time adaptation without persistent parameter updates. The perturbation takes the form Delta W = gamma * W^T V U^T W, where selector matrices U and V are constructed via sparse activation-guided selection or Sylvester-coupled regression. We provide a theoretical analysis of the perturbation's spectral properties and describe an adaptive policy system that modulates perturbation magnitude based on activation energy and token-level entropy. This system incorporates multi-objective verification with iterative refinement for tasks with ground-truth supervision. We present the complete algorithmic framework, analyze its mathematical foundations, and discuss the mechanisms by which activation-conditioned computation may enhance reasoning capabilities in large language models. Implementation and experimental code are available at https://github.com/Saba-Kublashvili/vps-virtual-parameter-synthesis . --- ### Adaptive Multi-Agent Reasoning for Text-to-Video Retrieval Authors: Jiaxin Wu, Xiao-Yong Wei, Qing Li Published: 2025-12-02 Categories: cs.IR, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2602.19040v1 The rise of short-form video platforms and the emergence of multimodal large language models (MLLMs) have amplified the need for scalable, effective, zero-shot text-to-video retrieval systems. While recent advances in large-scale pretraining have improved zero-shot cross-modal alignment, existing methods still struggle with query-dependent temporal reasoning, limiting their effectiveness on complex queries involving temporal, logical, or causal relationships. To address these limitations, we propose an adaptive multi-agent retrieval framework that dynamically orchestrates specialized agents over multiple reasoning iterations based on the demands of each query. The framework includes: (1) a retrieval agent for scalable retrieval over large video corpora, (2) a reasoning agent for zero-shot contextual temporal reasoning, and (3) a query reformulation agent for refining ambiguous queries and recovering performance for those that degrade over iterations. These agents are dynamically coordinated by an orchestration agent, which leverages intermediate feedback and reasoning outcomes to guide execution. We also introduce a novel communication mechanism that incorporates retrieval-performance memory and historical reasoning traces to improve coordination and decision-making. Experiments on three TRECVid benchmarks spanning eight years show that our framework achieves a twofold improvement over CLIP4Clip and significantly outperforms state-of-the-art methods by a large margin. --- ### Medication counseling with large language models: balancing flexibility and rigidity Authors: Joar Sabel, Mattias Wingren, Andreas Lundell, Sören Andersson, Sara Rosenberg, Susanne Hägglund, Linda Estman, Malin Andtfolk Published: 2025-12-02 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.11544v1 The introduction of large language models (LLMs) has greatly enhanced the capabilities of software agents. Instead of relying on rule-based interactions, agents can now interact in flexible ways akin to humans. However, this flexibility quickly becomes a problem in fields where errors can be disastrous, such as in a pharmacy context, but the opposite also holds true; a system that is too inflexible will also lead to errors, as it can become too rigid to handle situations that are not accounted for. Work using LLMs in a pharmacy context have adopted a wide scope, accounting for many different medications in brief interactions -- our strategy is the opposite: focus on a more narrow and long task. This not only enables a greater understanding of the task at hand, but also provides insight into what challenges are present in an interaction of longer nature. The main challenge, however, remains the same for a narrow and wide system: it needs to strike a balance between adherence to conversational requirements and flexibility. In an effort to strike such a balance, we present a prototype system meant to provide medication counseling while juggling these two extremes. We also cover our design in constructing such a system, with a focus on methods aiming to fulfill conversation requirements, reduce hallucinations and promote high-quality responses. The methods used have the potential to increase the determinism of the system, while simultaneously not removing the dynamic conversational abilities granted by the usage of LLMs. However, a great deal of work remains ahead, and the development of this kind of system needs to involve continuous testing and a human-in-the-loop. It should also be evaluated outside of commonly used benchmarks for LLMs, as these do not adequately capture the complexities of this kind of conversational system. --- ### Investigating Anthropometric Fidelity in SAM 3D Body Authors: Aizierjiang Aiersilan, Ruting Cheng, James Hahn Published: 2025-12-02 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2601.06035v2 The release of SAM 3D Body is a recent development in human mesh recovery, demonstrating improved performance in producing clean, topologically coherent meshes from single images. By leveraging the Momentum Human Rig (MHR), it achieves robustness to occlusion and diverse poses. However, our evaluation reveals a specific and consistent limitation: the model struggles to reconstruct detailed anthropometric deviations, particularly in populations exhibiting distinctive morphological alterations such as geriatric muscle atrophy, scoliosis, or pregnancy, even when these features are prominent in the input image. In this paper, we investigate this phenomenon not as a failure of the model's capacity, but as a byproduct of the "perception-distortion trade-off". We posit that the architectural reliance on the low-dimensional parametric MHR representation, combined with semantic-invariant conditioning (DINOv3) and annotation-based alignment, creates a pervasive "regression to the mean" effect. We analyze these mechanisms to understand why individual biological details are smoothed out. Furthermore, we state our contributions by proposing specific, constructive pathways for future work, such as implicit-explicit hybrid representations and Medical-in-the-Loop alignment, to extend the baseline performance of SAM 3D Body into the high-precision medical domain. --- ### MedPI: Evaluating AI Systems in Medical Patient-facing Interactions Authors: Diego Fajardo V., Oleksii Proniakin, Victoria-Elisabeth Gruber, Razvan Marinescu Published: 2025-12-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.04195v1 We present MedPI, a high-dimensional benchmark for evaluating large language models (LLMs) in patient-clinician conversations. Unlike single-turn question-answer (QA) benchmarks, MedPI evaluates the medical dialogue across 105 dimensions comprising the medical process, treatment safety, treatment outcomes and doctor-patient communication across a granular, accreditation-aligned rubric. MedPI comprises five layers: (1) Patient Packets (synthetic EHR-like ground truth); (2) an AI Patient instantiated through an LLM with memory and affect; (3) a Task Matrix spanning encounter reasons (e.g. anxiety, pregnancy, wellness checkup) x encounter objectives (e.g. diagnosis, lifestyle advice, medication advice); (4) an Evaluation Framework with 105 dimensions on a 1-4 scale mapped to the Accreditation Council for Graduate Medical Education (ACGME) competencies; and (5) AI Judges that are calibrated, committee-based LLMs providing scores, flags, and evidence-linked rationales. We evaluate 9 flagship models -- Claude Opus 4.1, Claude Sonnet 4, MedGemma, Gemini 2.5 Pro, Llama 3.3 70b Instruct, GPT-5, GPT OSS 120b, o3, Grok-4 -- across 366 AI Patients and 7,097 conversations using a standardized "vanilla clinician" prompt. For all LLMs, we observe low performance across a variety of dimensions, in particular on differential diagnosis. Our work can help guide future use of LLMs for diagnosis and treatment recommendations. --- ### Variance-Aware LLM Annotation for Strategy Research: Sources, Diagnostics, and a Protocol for Reliable Measurement Authors: Arnaldo Camuffo, Alfonso Gambardella, Saeid Kazemi, Jakub Malachowski, Abhinav Pandey Published: 2025-12-02 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2601.02370v3 Large language models (LLMs) offer strategy researchers powerful tools for annotating text at scale, but treating LLM-generated labels as deterministic overlooks substantial instability. Grounded in content analysis and generalizability theory, we diagnose five variance sources: construct specification, interface effects, model preferences, output extraction, and system-level aggregation. Empirical demonstrations show that minor design choices-prompt phrasing, model selection-can shift outcomes by 12-85 percentage points. Such variance threatens not only reproducibility but econometric identification: annotation errors correlated with covariates bias parameter estimates regardless of average accuracy. We develop a variance-aware protocol specifying sampling budgets, aggregation rules, and reporting standards, and delineate scope conditions where LLM annotation should not be used. These contributions transform LLM-based annotation from ad hoc practice into auditable measurement infrastructure. --- ### Noise-Driven Persona Formation in Reflexive Neural Language Generation Authors: Toshiyuki Shigemura Published: 2025-12-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.23716v1 This paper introduces the Luca-Noise Reflex Protocol (LN-RP), a computational framework for analyzing noise-driven persona emergence in large language models. By injecting stochastic noise seeds into the initial generation state, we observe nonlinear transitions in linguistic behavior across 152 generation cycles. Our results reveal three stable persona modes with distinct entropy signatures, and demonstrate that external noise sources can reliably induce phase transitions in reflexive generation dynamics. Quantitative evaluation confirms consistent persona retention and significant differences across modes (p < 0.01). The protocol provides a reproducible method for studying reflexive generation, emergent behavior, and longrange linguistic coherence in LLMs. --- ### Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning Authors: Weiwei Wang Published: 2025-12-02 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.20634v1 Catastrophic forgetting remains a fundamental challenge in continual learning for large language models. Recent work revealed that performance degradation may stem from spurious forgetting caused by task alignment disruption rather than true knowledge loss. However, this work only qualitatively describes alignment, relies on post-hoc analysis, and lacks automatic distinction mechanisms. We introduce the shallow versus deep alignment framework, providing the first quantitative characterization of alignment depth. We identify that current task alignment approaches suffer from shallow alignment - maintained only over the first few output tokens (approximately 3-5) - making models vulnerable to forgetting. This explains why spurious forgetting occurs, why it is reversible, and why fine-tuning attacks are effective. We propose a comprehensive framework addressing all gaps: (1) quantitative metrics (0-1 scale) to measure alignment depth across token positions; (2) real-time detection methods for identifying shallow alignment during training; (3) specialized analysis tools for visualization and recovery prediction; and (4) adaptive mitigation strategies that automatically distinguish forgetting types and promote deep alignment. Extensive experiments on multiple datasets and model architectures (Qwen2.5-3B to Qwen2.5-32B) demonstrate 86.2-90.6% identification accuracy and show that promoting deep alignment improves robustness against forgetting by 3.3-7.1% over baselines. --- ### Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under Compression Authors: Rahul Baxi Published: 2025-12-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.17920v1 Large language models (LLMs) exhibit degraded performance under prompt compression, but the mechanisms remain poorly understood. We introduce the Compression-Decay Comprehension Test (CDCT), a benchmark that independently measures constraint compliance (CC) and semantic accuracy (SA) across compression levels. We evaluate 9 frontier LLMs across 8 concepts using 5 compression levels from extreme (c=0.0, ~2 words) to none (c=1.0, ~135 words). A three-judge LLM jury achieves almost perfect inter-rater agreement on CC (Fleiss' \k{appa}=0.90). We observe a universal U-curve pattern in constraint compliance (97.2% prevalence), with violations peaking at medium compression (c=0.5, ~27 words). Counterintuitively, models perform better at extreme compression than medium lengths. The dimensions are statistically orthogonal (r=0.193, p=0.084), with constraint effects 2.9x larger than semantic effects. Experimental validation via RLHF ablation confirms our constraint salience hypothesis: removing "helpfulness" signals improves CC by 598% on average (71/72 trials, p<0.001), with 79% achieving perfect compliance. This demonstrates that RLHF-trained helpfulness behaviors are the dominant cause of constraint violations at medium compression. Reasoning models outperform efficient models by 27.5% (Cohen's d=0.96). Our findings reveal a fundamental tension between RLHF alignment and instruction-following, providing actionable guidelines for improving deployed systems. --- ### Assessing Greenspace Attractiveness with ChatGPT, Claude, and Gemini: Do AI Models Reflect Human Perceptions? Authors: Milad Malekzadeh, Magdalena Biernacka, Elias Willberg, Jussi Torkko, Edyta Łaszkiewicz, Tuuli Toivonen Published: 2025-12-02 Categories: cs.CY, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.11827v2 Understanding greenspace attractiveness is essential for designing livable and inclusive urban environments, yet existing assessment approaches often overlook informal or transient spaces and remain too resource intensive to capture subjective perceptions at scale. This study examines the ability of multimodal large language models (MLLMs), ChatGPT GPT-4o, Claude 3.5 Haiku, and Gemini 2.0 Flash, to assess greenspace attractiveness similarly to humans using Google Street View imagery. We compared model outputs with responses from a geo-questionnaire of residents in Lodz, Poland, across both formal (for example, parks and managed greenspaces) and informal (for example, meadows and wastelands) greenspaces. Survey respondents and models indicated whether each greenspace was attractive or unattractive and provided up to three free text explanations. Analyses examined how often their attractiveness judgments aligned and compared their explanations after classifying them into shared reasoning categories. Results show high AI human agreement for attractive formal greenspaces and unattractive informal spaces, but low alignment for attractive informal and unattractive formal greenspaces. Models consistently emphasized aesthetic and design oriented features, underrepresenting safety, functional infrastructure, and locally embedded qualities valued by survey respondents. While these findings highlight the potential for scalable pre-assessment, they also underscore the need for human oversight and complementary participatory approaches. We conclude that MLLMs can support, but not replace, context sensitive greenspace evaluation in planning practice. --- ### Agent-Based Modular Learning for Multimodal Emotion Recognition in Human-Agent Systems Authors: Matvey Nepomnyaschiy, Oleg Pereziabov, Anvar Tliamov, Stanislav Mikhailov, Ilya Afanasyev Published: 2025-12-02 Categories: cs.LG, cs.AI, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2512.10975v1 Effective human-agent interaction (HAI) relies on accurate and adaptive perception of human emotional states. While multimodal deep learning models - leveraging facial expressions, speech, and textual cues - offer high accuracy in emotion recognition, their training and maintenance are often computationally intensive and inflexible to modality changes. In this work, we propose a novel multi-agent framework for training multimodal emotion recognition systems, where each modality encoder and the fusion classifier operate as autonomous agents coordinated by a central supervisor. This architecture enables modular integration of new modalities (e.g., audio features via emotion2vec), seamless replacement of outdated components, and reduced computational overhead during training. We demonstrate the feasibility of our approach through a proof-of-concept implementation supporting vision, audio, and text modalities, with the classifier serving as a shared decision-making agent. Our framework not only improves training efficiency but also contributes to the design of more flexible, scalable, and maintainable perception modules for embodied and virtual agents in HAI scenarios. --- ### TECM*: A Data-Driven Assessment to Reinforcement Learning Methods and Application to Heparin Treatment Strategy for Surgical Sepsis Authors: Jiang Liu, Yujie Li, Chan Zhou, Yihao Xie, Qilong Sun, Xin Shu, Peiwei Li, Chunyong Yang, Yiziting Zhu, Jiaqi Zhu, Yuwen Chen, Bo An et al. Published: 2025-12-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10973v1 Objective: Sepsis is a life-threatening condition caused by severe infection leading to acute organ dysfunction. This study proposes a data-driven metric and a continuous reward function to optimize personalized heparin therapy in surgical sepsis patients. Methods: Data from the MIMIC-IV v1.0 and eICU v2.0 databases were used for model development and evaluation. The training cohort consisted of abdominal surgery patients receiving unfractionated heparin (UFH) after postoperative sepsis onset. We introduce a new RL-based framework: converting the discrete SOFA score to a continuous cxSOFA for more nuanced state and reward functions; Second, defining "good" or "bad" strategies based on cxSOFA by a stepwise manner; Third, proposing a Treatment Effect Comparison Matrix (TECM), analogous to a confusion matrix for classification tasks, to evaluate the treatment strategies. We applied different RL algorithms, Q-Learning, DQN, DDQN, BCQ and CQL to optimize the treatment and comprehensively evaluated the framework. Results: Among the AI-derived strategies, the cxSOFA-CQL model achieved the best performance, reducing mortality from 1.83% to 0.74% with the average hospital stay from 11.11 to 9.42 days. TECM demonstrated consistent outcomes across models, highlighting robustness. Conclusion: The proposed RL framework enables interpretable and robust optimization of heparin therapy in surgical sepsis. Continuous cxSOFA scoring and TECM-based evaluation provide nuanced treatment assessment, showing promise for improving clinical outcomes and decision-support reliability. --- ### Enhancing Automatic Speech Recognition Through Integrated Noise Detection Architecture Authors: Karamvir Singh Published: 2025-12-02 Categories: cs.SD, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2512.08973v1 This research presents a novel approach to enhancing automatic speech recognition systems by integrating noise detection capabilities directly into the recognition architecture. Building upon the wav2vec2 framework, the proposed method incorporates a dedicated noise identification module that operates concurrently with speech transcription. Experimental validation using publicly available speech and environmental audio datasets demonstrates substantial improvements in transcription quality and noise discrimination. The enhanced system achieves superior performance in word error rate, character error rate, and noise detection accuracy compared to conventional architectures. Results indicate that joint optimization of transcription and noise classification objectives yields more reliable speech recognition in challenging acoustic conditions. --- ### CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models Authors: Ryan Feng Lin, Keyu Tian, Hanming Zheng, Congjing Zhang, Li Zeng, Shuai Huang Published: 2025-12-02 Categories: cs.MA, cs.AI, cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.07890v1 The emergence of large language models (LLMs) has sparked much interest in creating LLM-based digital populations that can be applied to many applications such as social simulation, crowdsourcing, marketing, and recommendation systems. A digital population can reduce the cost of recruiting human participants and alleviate many concerns related to human subject study. However, research has found that most of the existing works rely solely on LLMs and could not sufficiently capture the accuracy and diversity of a real human population. To address this limitation, we propose CrowdLLM that integrates pretrained LLMs and generative models to enhance the diversity and fidelity of the digital population. We conduct theoretical analysis of CrowdLLM regarding its great potential in creating cost-effective, sufficiently representative, scalable digital populations that can match the quality of a real crowd. Comprehensive experiments are also conducted across multiple domains (e.g., crowdsourcing, voting, user rating) and simulation studies which demonstrate that CrowdLLM achieves promising performance in both accuracy and distributional fidelity to human data. ---