# Research Papers — 2025-12 · bundle page 19 of 175

> Full-text markdown of papers #901–950 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/19
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/18.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/20.md)

### A Micro-Macro Machine Learning Framework for Predicting Childhood Obesity Risk Using NHANES and Environmental Determinants

Authors: Eswarasanthosh Kumar Mamillapalli, Nishtha Sharma
Published: 2025-12-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.22758v1

Childhood obesity remains a major public health challenge in the United States, strongly influenced by a combination of individual-level, household-level, and environmental-level risk factors. Traditional epidemiological studies typically analyze these levels independently, limiting insights into how structural environmental conditions interact with individual-level characteristics to influence health outcomes. In this study, we introduce a micro-macro machine learning framework that integrates (1) individual-level anthropometric and socioeconomic data from NHANES and (2) macro-level structural environment features, including food access, air quality, and socioeconomic vulnerability extracted from USDA and EPA datasets. Four machine learning models Logistic Regression, Random Forest, XGBoost, and LightGBM were trained to predict obesity using NHANES microdata. XGBoost achieved the strongest performance. A composite environmental vulnerability index (EnvScore) was constructed using normalized indicators from USDA and EPA at the state level. Multi-level comparison revealed strong geographic similarity between states with high environmental burden and the nationally predicted micro-level obesity risk distribution. This demonstrates the feasibility of integrating multi-scale datasets to identify environment-driven disparities in obesity risk. This work contributes a scalable, data-driven, multi-level modeling pipeline suitable for public health informatics, demonstrating strong potential for expansion into causal modeling, intervention planning, and real-time analytics.

---

### Active Constraint Learning in High Dimensions from Demonstrations

Authors: Zheng Qiu, Chih-Yuan Chiu, Glen Chou
Published: 2025-12-28
Categories: cs.RO, cs.AI, cs.LG, eess.SY, math.OC
arXiv: https://arxiv.org/abs/2512.22757v1

We present an iterative active constraint learning (ACL) algorithm, within the learning from demonstrations (LfD) paradigm, which intelligently solicits informative demonstration trajectories for inferring an unknown constraint in the demonstrator's environment. Our approach iteratively trains a Gaussian process (GP) on the available demonstration dataset to represent the unknown constraints, uses the resulting GP posterior to query start/goal states, and generates informative demonstrations which are added to the dataset. Across simulation and hardware experiments using high-dimensional nonlinear dynamics and unknown nonlinear constraints, our method outperforms a baseline, random-sampling based method at accurately performing constraint inference from an iteratively generated set of sparse but informative demonstrations.

---

### From Confounding to Learning: Dynamic Service Fee Pricing on Third-Party Platforms

Authors: Rui Ai, David Simchi-Levi, Feng Zhu
Published: 2025-12-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.22749v2

We study the pricing behavior of third-party platforms facing strategic agents. Assuming the platform is a revenue maximizer, it observes market features that generally affect demand. Since only transacted quantities and prices can be observed, this presents a general demand learning problem under confounding. Mathematically, we develop an algorithm with optimal regret of $\Tilde{\mathcal{O}}(\sqrt{T}\wedgeσ_S^{-2})$. Our results reveal that supply-side noise fundamentally affects the learnability of demand, leading to a phase transition in regret. Technically, we show that non-i.i.d. actions can serve as instrumental variables for learning demand. We also propose a novel homeomorphic construction that allows us to establish estimation bounds without assuming star-shapedness, providing the first efficiency guarantee for learning demand with deep neural networks. Finally, we use simulations and offline counterfactuals from Talabat and Lyft data to illustrate the potential revenue implications of our approach.

---

### TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts

Authors: Hao Zhang, Mengsi Lyu, Bo Huang, Yulong Ao, Yonghua Lin
Published: 2025-12-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.22748v2

Large Multimodal Models (LMMs) have proven effective on various tasks. They typically encode visual inputs into Original Model sequences of tokens, which are then concatenated with textual tokens and jointly processed by the language model. However, the growing number of visual tokens greatly increases inference cost. Visual token pruning has emerged as a promising solution. However, existing methods often overlook scenarios involving long context inputs with multiple images. In this paper, we analyze the challenges of visual token pruning in long context, multi-image settings and introduce an adaptive pruning method tailored for such scenarios. We decompose redundancy into intra-image and inter-image components and quantify them through intra-image diversity and inter-image variation, which jointly guide dynamic budget allocation. Our approach consists of two stages. The intra-image stage allocates each image a content-aware token budget and greedily selects its most representative tokens. The inter-image stage performs global diversity filtering to form a candidate pool and then applies a Pareto selection procedure that balances diversity with text alignment. Extensive experiments show that our approach can reduce up to 80% of visual tokens while maintaining performance in long context settings.

---

### Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation

Authors: Yongzhen Hu, Yihui Yang, Haotong Lin, Yifan Wang, Junting Dong, Yifu Deng, Xinyu Zhu, Fan Jia, Hujun Bao, Xiaowei Zhou, Sida Peng
Published: 2025-12-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.22745v1

This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore, they heavily rely on the quality of video segmentation maps, which are often unstable, leading to unreliable reconstruction results. To overcome this challenge, our key idea is to represent the decomposed 4D scene with the Freetime FeatureGS and design a streaming feature learning strategy to accurately recover it from per-image segmentation maps, eliminating the need for video segmentation. Freetime FeatureGS models the dynamic scene as a set of Gaussian primitives with learnable features and linear motion ability, allowing them to move to neighboring regions over time. We apply a contrastive loss to Freetime FeatureGS, forcing primitive features to be close or far apart based on whether their projections belong to the same instance in the 2D segmentation map. As our Gaussian primitives can move across time, it naturally extends the feature learning to the temporal dimension, achieving 4D segmentation. Furthermore, we sample observations for training in a temporally ordered manner, enabling the streaming propagation of features over time and effectively avoiding local minima during the optimization process. Experimental results on several datasets show that the reconstruction quality of our method outperforms recent methods by a large margin.

---

### Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQL

Authors: Rihong Qiu, Zhibang Yang, Xinke Jiang, Weibin Liao, Xin Gao, Xu Chu, Junfeng Zhao, Yasha Wang
Published: 2025-12-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.22744v1

Text-to-SQL translates natural language questions into SQL statements grounded in a target database schema. Ensuring the reliability and executability of such systems requires validating generated SQL, but most existing approaches focus only on syntactic correctness, with few addressing semantic validation (detecting misalignments between questions and SQL). As a consequence, effective semantic validation still faces two key challenges: capturing both global user intent and SQL structural details, and constructing high-quality fine-grained sub-SQL annotations. To tackle these, we introduce HEROSQL, a hierarchical SQL representation approach that integrates global intent (via Logical Plans, LPs) and local details (via Abstract Syntax Trees, ASTs). To enable better information propagation, we employ a Nested Message Passing Neural Network (NMPNN) to capture inherent relational information in SQL and aggregate schema-guided semantics across LPs and ASTs. Additionally, to generate high-quality negative samples, we propose an AST-driven sub-SQL augmentation strategy, supporting robust optimization of fine-grained semantic inconsistencies. Extensive experiments conducted on Text-to-SQL validation benchmarks (both in-domain and out-of-domain settings) demonstrate that our approach outperforms existing state-of-the-art methods, achieving an average 9.40% improvement of AUPRC and 12.35% of AUROC in identifying semantic inconsistencies. It excels at detecting fine-grained semantic errors, provides large language models with more granular feedback, and ultimately enhances the reliability and interpretability of data querying platforms.

---

### Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuning

Authors: Hanze Meng, Jianhao Cao, Rachel Pottinger
Published: 2025-12-28
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2512.22742v1

Column Type Annotation (CTA) is a fundamental step towards enabling schema alignment and semantic understanding of tabular data. Existing encoder-only language models achieve high accuracy when fine-tuned on labeled columns, but their applicability is limited to in-domain settings, as distribution shifts in tables or label spaces require costly re-training from scratch. Recent work has explored prompting generative large language models (LLMs) by framing CTA as a multiple-choice task, but these approaches face two key challenges: (1) model performance is highly sensitive to subtle changes in prompt wording and structure, and (2) annotation F1 scores remain modest. A natural extension is to fine-tune large language models. However, fully fine-tuning these models incurs prohibitive computational costs due to their scale, and the sensitivity to prompts is not eliminated. In this paper, we present a parameter-efficient framework for CTA that trains models over prompt-augmented data via Low-Rank Adaptation (LoRA). Our approach mitigates sensitivity to prompt variations while drastically reducing the number of necessary trainable parameters, achieving robust performance across datasets and templates. Experimental results on recent benchmarks demonstrate that models fine-tuned with our prompt augmentation strategy maintain stable performance across diverse prompt patterns during inference and yield higher weighted F1 scores than those fine-tuned on a single prompt template. These results highlight the effectiveness of parameter-efficient training and augmentation strategies in developing practical and adaptable CTA systems.

---

### Text-Routed Sparse Mixture-of-Experts Model with Explanation and Temporal Alignment for Multi-Modal Sentiment Analysis

Authors: Dongning Rao, Yunbiao Zeng, Zhihua Jiang, Jujian Lv
Published: 2025-12-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.22741v1

Human-interaction-involved applications underscore the need for Multi-modal Sentiment Analysis (MSA). Although many approaches have been proposed to address the subtle emotions in different modalities, the power of explanations and temporal alignments is still underexplored. Thus, this paper proposes the Text-routed sparse mixture-of-Experts model with eXplanation and Temporal alignment for MSA (TEXT). TEXT first augments explanations for MSA via Multi-modal Large Language Models (MLLM), and then novelly aligns the epresentations of audio and video through a temporality-oriented neural network block. TEXT aligns different modalities with explanations and facilitates a new text-routed sparse mixture-of-experts with gate fusion. Our temporal alignment block merges the benefits of Mamba and temporal cross-attention. As a result, TEXT achieves the best performance cross four datasets among all tested models, including three recently proposed approaches and three MLLMs. TEXT wins on at least four metrics out of all six metrics. For example, TEXT decreases the mean absolute error to 0.353 on the CH-SIMS dataset, which signifies a 13.5% decrement compared with recently proposed approaches.

---

### Multi-Task Learning for Metal Alloy Property Prediction: An Empirical Study of Negative Transfer and Mitigation Strategies

Authors: Sungwoo Kang
Published: 2025-12-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.22740v3

Multi-task learning (MTL) in materials science relies on the assumption that physically related properties share learnable representations. We challenge this assumption using a 54,028-sample metal alloy dataset exhibiting extreme task-level imbalance. Our results reveal a striking dichotomy: MTL significantly degrades regression performance for resistivity and hardness but improves classification recall for amorphous-forming ability. We trace this divergence to mismatched functional forms--such as resistivity's polynomial dependence versus hardness's complex interactions--which cause severe gradient misalignment during optimization. Evaluating Deep Imbalanced Regression techniques, we find that projecting conflicting gradients (PCGrad) recovers single-task performance, while combining label distribution smoothing with gradient normalization achieves the best overall balance. Consequently, we propose a strategic framework: utilize independent models for high-precision characterization, but employ MTL for high-throughput screening where recall is paramount. These findings support a "materials property clustering" hypothesis, suggesting that distinct physical mechanisms require specialized optimization strategies to overcome negative transfer.

---

### Harnessing Large Language Models for Biomedical Named Entity Recognition

Authors: Jian Chen, Leilei Su, Cong Sun
Published: 2025-12-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.22738v1

Background and Objective: Biomedical Named Entity Recognition (BioNER) is a foundational task in medical informatics, crucial for downstream applications like drug discovery and clinical trial matching. However, adapting general-domain Large Language Models (LLMs) to this task is often hampered by their lack of domain-specific knowledge and the performance degradation caused by low-quality training data. To address these challenges, we introduce BioSelectTune, a highly efficient, data-centric framework for fine-tuning LLMs that prioritizes data quality over quantity. Methods and Results: BioSelectTune reformulates BioNER as a structured JSON generation task and leverages our novel Hybrid Superfiltering strategy, a weak-to-strong data curation method that uses a homologous weak model to distill a compact, high-impact training dataset. Conclusions: Through extensive experiments, we demonstrate that BioSelectTune achieves state-of-the-art (SOTA) performance across multiple BioNER benchmarks. Notably, our model, trained on only 50% of the curated positive data, not only surpasses the fully-trained baseline but also outperforms powerful domain-specialized models like BioMedBERT.

---

### WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference

Authors: Aiwei Liu, Minghua He, Shaoxun Zeng, Sijun Zhang, Linhao Zhang, Chuhan Wu, Wei Jia, Yuan Liu, Xiao Zhou, Jie Zhou
Published: 2025-12-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.22737v1

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering multiple masked tokens per step; however, in practice they often fail to translate this parallelism into deployment speed gains over optimized AR engines (e.g., vLLM). A key reason is that many DLLMs rely on bidirectional attention, which breaks standard prefix KV caching and forces repeated contextualization, undermining efficiency. We propose WeDLM, a diffusion decoding framework built entirely on standard causal attention to make parallel generation prefix-cache friendly. The core idea is to let each masked position condition on all currently observed tokens while keeping a strict causal mask, achieved by Topological Reordering that moves observed tokens to the physical prefix while preserving their logical positions. Building on this property, we introduce a streaming decoding procedure that continuously commits confident tokens into a growing left-to-right prefix and maintains a fixed parallel workload, avoiding the stop-and-wait behavior common in block diffusion methods. Experiments show that WeDLM preserves the quality of strong AR backbones while delivering substantial speedups, approaching 3x on challenging reasoning benchmarks and up to 10x in low-entropy generation regimes; critically, our comparisons are against AR baselines served by vLLM under matched deployment settings, demonstrating that diffusion-style decoding can outperform an optimized AR engine in practice.

---

### FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agents

Authors: Jiaqi Shao, Yufeng Miao, Wei Zhang, Bing Luo
Published: 2025-12-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.22733v1

Long-horizon reinforcement learning (RL) for large language models faces critical scalability challenges from unbounded context growth, leading to context folding methods that compress interaction history during task execution. However, existing approaches treat summary actions as standard actions, overlooking that summaries fundamentally modify the agent's future observation space, creating a policy-dependent, non-stationary observation distribution that violates core RL assumptions. This introduces three fundamental challenges: (1) gradient dilution where summary tokens receive insufficient training signal, (2) self-conditioning where policy updates change summary distributions, creating a vicious cycle of training collapse, and (3) computational cost from processing unique contexts at each turn. We introduce \textbf{FoldAct}\footnote{https://github.com/SHAO-Jiaqi757/FoldAct}, a framework that explicitly addresses these challenges through three key innovations: separated loss computation for independent gradient signals on summary and action tokens, full context consistency loss to reduce distribution shift, and selective segment training to reduce computational cost. Our method enables stable training of long-horizon search agents with context folding, addressing the non-stationary observation problem while improving training efficiency with 5.19$\times$ speedup.

---

### Data Augmentation for Classification of Negative Pregnancy Outcomes in Imbalanced Data

Authors: Md Badsha Biswas
Published: 2025-12-28
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.22732v1

Infant mortality remains a significant public health concern in the United States, with birth defects identified as a leading cause. Despite ongoing efforts to understand the causes of negative pregnancy outcomes like miscarriage, stillbirths, birth defects, and premature birth, there is still a need for more comprehensive research and strategies for intervention. This paper introduces a novel approach that uses publicly available social media data, especially from platforms like Twitter, to enhance current datasets for studying negative pregnancy outcomes through observational research. The inherent challenges in utilizing social media data, including imbalance, noise, and lack of structure, necessitate robust preprocessing techniques and data augmentation strategies. By constructing a natural language processing (NLP) pipeline, we aim to automatically identify women sharing their pregnancy experiences, categorizing them based on reported outcomes. Women reporting full gestation and normal birth weight will be classified as positive cases, while those reporting negative pregnancy outcomes will be identified as negative cases. Furthermore, this study offers potential applications in assessing the causal impact of specific interventions, treatments, or prenatal exposures on maternal and fetal health outcomes. Additionally, it provides a framework for future health studies involving pregnant cohorts and comparator groups. In a broader context, our research showcases the viability of social media data as an adjunctive resource in epidemiological investigations about pregnancy outcomes.

---

### Improved cystic hygroma detection from prenatal imaging using ultrasound-specific self-supervised representation learning

Authors: Youssef Megahed, Robin Ducharme, Inok Lee, Inbal Willner, Adrian D. C. Chan, Mark Walker, Steven Hawken
Published: 2025-12-28
Categories: cs.CV, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2512.22730v2

Cystic hygroma is a high-risk prenatal ultrasound finding that portends high rates of chromosomal abnormalities, structural malformations, and adverse pregnancy outcomes. Automated detection can increase reproducibility and support scalable early screening programs, but supervised deep learning methods are limited by small labelled datasets. This study assesses whether ultrasound-specific self-supervised pretraining can facilitate accurate, robust deep learning detection of cystic hygroma in first-trimester ultrasound images. We fine-tuned the Ultrasound Self-Supervised Foundation Model with Masked Autoencoding (USF-MAE), pretrained on over 370,000 unlabelled ultrasound images, for binary classification of normal controls and cystic hygroma cases used in this study. Performance was evaluated on the same curated ultrasound dataset, preprocessing pipeline, and 4-fold cross-validation protocol as for the DenseNet-169 baseline, using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (ROC-AUC). Model interpretability was analyzed qualitatively using Score-CAM visualizations. USF-MAE outperformed the DenseNet-169 baseline on all evaluation metrics. The proposed model yielded a mean accuracy of 0.96, sensitivity of 0.94, specificity of 0.98, and ROC-AUC of 0.98 compared to 0.93, 0.92, 0.94, and 0.94 for the DenseNet-169 baseline, respectively. Qualitative Score-CAM visualizations of model predictions demonstrated clinical relevance by highlighting expected regions in the fetal neck for both positive and negative cases. Paired statistical analysis using a Wilcoxon signed-rank test confirmed that performance improvements achieved by USF-MAE were statistically significant (p = 0.0057).

---

### Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA

Authors: Qizhi Wang
Published: 2025-12-27
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.23372v1

GraphRAG systems improve multi-hop retrieval by modeling structure, but many approaches rely on expensive LLM-based graph construction and GPU-heavy inference. We present SPRIG (Seeded Propagation for Retrieval In Graphs), a CPU-only, linear-time, token-free GraphRAG pipeline that replaces LLM graph building with lightweight NER-driven co-occurrence graphs and uses Personalized PageRank (PPR) for 28% with negligible Recall@10 changes. The results characterize when CPU-friendly graph retrieval helps multi-hop recall and when strong lexical hybrids (RRF) are sufficient, outlining a realistic path to democratizing GraphRAG without token costs or GPU requirements.

---

### AdaFRUGAL: Adaptive Memory-Efficient Training with Dynamic Control

Authors: Quang-Hung Bui, Anh Son Ta
Published: 2025-12-27
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.11568v2

Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gradient splitting, but its static hyperparameters -- the subspace ratio ($ρ$) and update frequency ($T$) -- require costly manual tuning, limiting adaptability. We present AdaFRUGAL, which automates this process by introducing two dynamic controls: (i) a linear decay for $ρ$ to progressively reduce memory, and (ii) a loss-aware schedule for $T$ to lower computational overhead. Experiments across large-scale pre-training (English C4, Vietnamese VietVault) and fine-tuning (GLUE) demonstrate that AdaFRUGAL achieves a compelling trade-off. It maintains competitive performance against AdamW and static FRUGAL while significantly reducing both GPU memory and training time, offering a more practical, autonomous solution for resource-constrained LLM training.

---

### Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisions

Authors: Katherine Elkins, Jon Chun
Published: 2025-12-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09724v2

Large language models exhibit systematic negation sensitivity, yet no operational framework exists to measure this vulnerability at deployment scale, especially in high-stakes decisions. We introduce Syntactic Framing Fragility (SFF), a framework for quantifying decision consistency under logically equivalent syntactic transformations. SFF isolates syntactic effects via Logical Polarity Normalization, enabling direct comparison across positive and negative framings while controlling for polarity inversion, and provides the Syntactic Variation Index (SVI) as a robustness metric suitable for CI/CD integration. Auditing 23 models across 14 high-stakes scenarios (39,975 decisions), we establish ground-truth effect sizes for a phenomenon previously characterized only qualitatively and find that open-source models exhibit $2.2x higher fragility than commercial counterparts. Negation-bearing syntax is the dominant failure mode, with some models endorsing actions at 80-97% rates even when asked whether agents not act. These patterns are consistent with negation suppression failure documented in prior work, with chain-of-thought reasoning reducing fragility in some but not all cases. We provide scenario-stratified risk profiles and offer an operational checklist compatible with EU AI Act and NIST RMF requirements. Code, data, and scenarios will be released upon publication.

---

### SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novels

Authors: Guancheng Du, Yong Hu, Wenqing Wang, Yaming Yang, Jiaheng Gao
Published: 2025-12-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09723v1

Large Language Models (LLMs) have shown significant progress, but understanding long and complex documents remains challenging. Many long-context benchmarks have been proposed, but they face several limitations, including task realism, data scalability, and data quality. To this end, we introduce SagaScale, a realistic, scalable, and high-quality long-context benchmark built from full-length novels. The entire benchmark is constructed using an automated data collection pipeline that utilizes external resources (e.g., Wikipedia pages) to curate question-answer pairs. Critically, these external resources are provided only for benchmark construction and not during evaluation, which allows LLMs to curate complex questions that go beyond what they can answer during evaluation. SagaScale is also bilingual and offers the largest context length to date, with average token counts exceeding 250K for English novels and 320K for Chinese novels. Our evaluation across 12 frontier LLMs and three long-context methods -- Naïve RAG, Agentic RAG, and Long Context -- yields key insights, including: (1) Directly supplying the full context to the LLM can outperform other methods by a large margin; (2) Most LLMs still struggle with lengthy contexts, but Gemini-2.5-Pro stands out as an exception; and (3) Agentic RAG effectively addresses the retrieval bottleneck in Naïve RAG. Finally, we publicly release the SagaScale benchmark and our data collection codebase to facilitate future research.

---

### ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language

Authors: Franciszek Górski, Andrzej Czyżewski
Published: 2025-12-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09722v2

In this work, we present an annotation framework that demonstrates how a multilingual LLM pretrained on a large corpus can be used as a teacher model to distill the expert knowledge needed for tagging medical texts in Polish. This work is part of a larger project called ADMEDVOICE, within which we collected an extensive corpus of medical texts representing five clinical categories - Radiology, Oncology, Cardiology, Hypertension, and Pathology. Using this data, we had to develop a multi-class classifier, but the fundamental problem turned out to be the lack of resources for annotating an adequate number of texts. Therefore, in our solution, we used the multilingual Llama3.1 model to annotate an extensive corpus of medical texts in Polish. Using our limited annotation resources, we verified only a portion of these labels, creating a test set from them. The data annotated in this way were then used for training and validation of 3 different types of classifiers based on the BERT architecture - the distilled DistilBERT model, BioBERT fine-tuned on medical data, and HerBERT fine-tuned on the Polish language corpus. Among the models we trained, the DistilBERT model achieved the best results, reaching an F1 score > 0.80 for each clinical category and an F1 score > 0.93 for 3 of them. In this way, we obtained a series of highly effective classifiers that represent an alternative to large language models, due to their nearly 500 times smaller size, 300 times lower GPU VRAM consumption, and several hundred times faster inference.

---

### Topic Segmentation Using Generative Language Models

Authors: Pierre Mackenzie, Maya Shah, Patrick Frenett
Published: 2025-12-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03276v1

Topic segmentation using generative Large Language Models (LLMs) remains relatively unexplored. Previous methods use semantic similarity between sentences, but such models lack the long range dependencies and vast knowledge found in LLMs. In this work, we propose an overlapping and recursive prompting strategy using sentence enumeration. We also support the adoption of the boundary similarity evaluation metric. Results show that LLMs can be more effective segmenters than existing methods, but issues remain to be solved before they can be relied upon for topic segmentation.

---

### Evolutionary Algorithms for Computing Nash Equilibria in Dynamic Games

Authors: Alireza Rezaee
Published: 2025-12-27
Categories: cs.NE, cs.GT, cs.MA
arXiv: https://arxiv.org/abs/2601.02397v1

Dynamic nonzero sum games are widely used to model multi agent decision making in control, economics, and related fields. Classical methods for computing Nash equilibria, especially in linear quadratic settings, rely on strong structural assumptions and become impractical for nonlinear dynamics, many players, or long horizons, where multiple local equilibria may exist. We show through examples that such methods can fail to reach the true global Nash equilibrium even in relatively small games. To address this, we propose two population based evolutionary algorithms for general dynamic games with linear or nonlinear dynamics and arbitrary objective functions: a co evolutionary genetic algorithm and a hybrid genetic algorithm particle swarm optimization scheme. Both approaches search directly over joint strategy spaces without restrictive assumptions and are less prone to getting trapped in local Nash equilibria, providing more reliable approximations to global Nash solutions.

---

### SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes

Authors: Bharath Nunepalli
Published: 2025-12-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.00841v1

Retrieval-augmented generation (RAG) introduces a practical control problem: retrieval depth and generation behavior must be chosen per query to satisfy service-level objectives (SLOs) such as cost, refusal rate, and hallucination risk. This work models per-query control as a small discrete action: choose a retrieval depth and a generation mode (guarded vs. auto), or refuse. An offline logged dataset is constructed from SQuAD 2.0 by executing each action and recording accuracy, token cost, hallucination/refusal indicators, and an SLO-weighted reward. Two simple policy-learning objectives are evaluated: supervised classification of the per-state best action (Argmax-CE) and a reward-weighted variant (Argmax-CE-WT). Across the evaluated settings, a strong fixed baseline (low k, guarded prompting) performs competitively; learned policies mainly provide additional cost savings under a quality-focused SLO and can exhibit refusal collapse under a cheap SLO when refusal is heavily rewarded. The contribution is a reproducible case study of SLO-aware control for RAG pipelines, emphasizing failure modes and reporting conventions rather than proposing a new retriever or language model.

---

### A Global Atlas of Digital Dermatology to Map Innovation and Disparities

Authors: Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Lea Habermacher, Labelling Consortium, Ludovic Amruthalingam, Matthew Groh, Marc Pouly, Alexander A. Navarini
Published: 2025-12-27
Categories: cs.DL, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.00840v2

The adoption of artificial intelligence in dermatology promises democratized access to healthcare, but model reliability depends on the quality and comprehensiveness of the data fueling these models. Despite rapid growth in publicly available dermatology images, the field lacks quantitative key performance indicators to measure whether new datasets expand clinical coverage or merely replicate what is already known. Here we present SkinMap, a multi-modal framework for the first comprehensive audit of the field's entire data basis. We unify the publicly available dermatology datasets into a single, queryable semantic atlas comprising more than 1.1 million images of skin conditions and quantify (i) informational novelty over time, (ii) dataset redundancy, and (iii) representation gaps across demographics and diagnoses. Despite exponential growth in dataset sizes, informational novelty across time has somewhat plateaued: Some clusters, such as common neoplasms on fair skin, are densely populated, while underrepresented skin types and many rare diseases remain unaddressed. We further identify structural gaps in coverage: Darker skin tones (Fitzpatrick V-VI) constitute only 5.8% of images and pediatric patients only 3.0%, while many rare diseases and phenotype combinations remain sparsely represented. SkinMap provides infrastructure to measure blind spots and steer strategic data acquisition toward undercovered regions of clinical space.

---

### Unified Review and Benchmark of Deep Segmentation Architectures for Cardiac Ultrasound on CAMUS

Authors: Zahid Ullah, Muhammad Hilal, Eunsoo Lee, Dragan Pamucar, Jihie Kim
Published: 2025-12-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00839v1

Several review papers summarize cardiac imaging and DL advances, few works connect this overview to a unified and reproducible experimental benchmark. In this study, we combine a focused review of cardiac ultrasound segmentation literature with a controlled comparison of three influential architectures, U-Net, Attention U-Net, and TransUNet, on the Cardiac Acquisitions for Multi-Structure Ultrasound Segmentation (CAMUS) echocardiography dataset. Our benchmark spans multiple preprocessing routes, including native NIfTI volumes, 16-bit PNG exports, GPT-assisted polygon-based pseudo-labels, and self-supervised pretraining (SSL) on thousands of unlabeled cine frames. Using identical training splits, losses, and evaluation criteria, a plain U-Net achieved a 94% mean Dice when trained directly on NIfTI data (preserving native dynamic range), while the PNG-16-bit workflow reached 91% under similar conditions. Attention U-Net provided modest improvements on small or low-contrast regions, reducing boundary leakage, whereas TransUNet demonstrated the strongest generalization on challenging frames due to its ability to model global spatial context, particularly when initialized with SSL. Pseudo-labeling expanded the training set and improved robustness after confidence filtering. Overall, our contributions are threefold: a harmonized, apples-to-apples benchmark of U-Net, Attention U-Net, and TransUNet under standardized CAMUS preprocessing and evaluation; practical guidance on maintaining intensity fidelity, resolution consistency, and alignment when preparing ultrasound data; and an outlook on scalable self-supervision and emerging multimodal GPT-based annotation pipelines for rapid labeling, quality assurance, and targeted dataset curation.

---

### Leveraging Machine Learning for Early Detection of Lung Diseases

Authors: Bahareh Rahmani, Harsha Reddy Bindela, Rama Kanth Reddy Gosula, Krishna Yedubati, Mohammad Amir Salari, Leslie Hinyard, Payam Norouzzadeh, Eli Snir, Martin Schoen
Published: 2025-12-27
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2512.23757v1

A combination of traditional image processing methods with advanced neural networks concretes a predictive and preventive healthcare paradigm. This study offers rapid, accurate, and non-invasive diagnostic solutions that can significantly impact patient outcomes, particularly in areas with limited access to radiologists and healthcare resources. In this project, deep learning methods apply in enhancing the diagnosis of respiratory diseases such as COVID-19, lung cancer, and pneumonia from chest x-rays. We trained and validated various neural network models, including CNNs, VGG16, InceptionV3, and EfficientNetB0, with high accuracy, precision, recall, and F1 scores to highlight the models' reliability and potential in real-world diagnostic applications.

---

### HINTS: Extraction of Human Insights from Time-Series Without External Sources

Authors: Sheo Yon Jhin, Noseong Park
Published: 2025-12-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.23755v1

Human decision-making, emotions, and collective psychology are complex factors that shape the temporal dynamics observed in financial and economic systems. Many recent time series forecasting models leverage external sources (e.g., news and social media) to capture human factors, but these approaches incur high data dependency costs in terms of financial, computational, and practical implications. In this study, we propose HINTS, a self-supervised learning framework that extracts these latent factors endogenously from time series residuals without external data. HINTS leverages the Friedkin-Johnsen (FJ) opinion dynamics model as a structural inductive bias to model evolving social influence, memory, and bias patterns. The extracted human factors are integrated into a state-of-the-art backbone model as an attention map. Experimental results using nine real-world and benchmark datasets demonstrate that HINTS consistently improves forecasting accuracy. Furthermore, multiple case studies and ablation studies validate the interpretability of HINTS, demonstrating strong semantic alignment between the extracted factors and real-world events, demonstrating the practical utility of HINTS.

---

### Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation

Authors: Deep Shankar Pandey, Hyomin Choi, Qi Yu
Published: 2025-12-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.23753v1

Evidential deep learning (EDL) models, based on Subjective Logic, introduce a principled and computationally efficient way to make deterministic neural networks uncertainty-aware. The resulting evidential models can quantify fine-grained uncertainty using learned evidence. However, the Subjective-Logic framework constrains evidence to be non-negative, requiring specific activation functions whose geometric properties can induce activation-dependent learning-freeze behavior: a regime where gradients become extremely small for samples mapped into low-evidence regions. We theoretically characterize this behavior and analyze how different evidential activations influence learning dynamics. Building on this analysis, we design a general family of activation functions and corresponding evidential regularizers that provide an alternative pathway for consistent evidence updates across activation regimes. Extensive experiments on four benchmark classification problems (MNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet), two few-shot classification problems, and blind face restoration problem empirically validate the developed theory and demonstrate the effectiveness of the proposed generalized regularized evidential models.

---

### Geometric Scaling of Bayesian Inference in LLMs

Authors: Naman Agarwal, Siddhartha R. Dalal, Vishal Misra
Published: 2025-12-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.23752v5

Recent work has shown that small transformers trained in controlled "wind-tunnel'' settings can implement exact Bayesian inference, and that their training dynamics produce a geometric substrate -- low-dimensional value manifolds and progressively orthogonal keys -- that encodes posterior structure. We investigate whether this geometric signature persists in production-grade language models. Across Pythia, Phi-2, Llama-3, and Mistral families, we find that last-layer value representations organize along a single dominant axis whose position strongly correlates with predictive entropy, and that domain-restricted prompts collapse this structure into the same low-dimensional manifolds observed in synthetic settings. To probe the role of this geometry, we perform targeted interventions on the entropy-aligned axis of Pythia-410M during in-context learning. Removing or perturbing this axis selectively disrupts the local uncertainty geometry, whereas matched random-axis interventions leave it intact. However, these single-layer manipulations do not produce proportionally specific degradation in Bayesian-like behavior, indicating that the geometry is a privileged readout of uncertainty rather than a singular computational bottleneck. Taken together, our results show that modern language models preserve the geometric substrate that enables Bayesian inference in wind tunnels, and organize their approximate Bayesian updates along this substrate.

---

### Mitigating Social Desirability Bias in Random Silicon Sampling

Authors: Sashank Chapala, Maksym Mironov, Songgaojun Deng
Published: 2025-12-27
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2512.22725v2

Large Language Models (LLMs) are increasingly used to simulate population responses, a method known as ``Silicon Sampling''. However, responses to socially sensitive questions frequently exhibit Social Desirability Bias (SDB), diverging from real human data toward socially acceptable answers. Existing studies on social desirability bias in LLM-based sampling remain limited. In this work, we investigate whether minimal, psychologically grounded prompt wording can mitigate this bias and improve alignment between silicon and human samples. We conducted a study using data from the American National Election Study (ANES) on three LLMs from two model families: the open-source Llama-3.1 series and GPT-4.1-mini. We first replicate a baseline silicon sampling study, confirming the persistent Social Desirability Bias. We then test four prompt-based mitigation methods: \emph{reformulated} (neutral, third-person phrasing), \emph{reverse-coded} (semantic inversion), and two meta-instructions, \emph{priming} and \emph{preamble}, respectively encouraging analytics and sincerity. Alignment with ANES is evaluated using Jensen-Shannon Divergence with bootstrap confidence intervals. Our results demonstrate that reformulated prompts most effectively improve alignment by reducing distribution concentration on socially acceptable answers and achieving distributions closer to ANES. Reverse-coding produced mixed results across eligible items, while the Priming and Preamble encouraged response uniformity and showed no systematic benefit for bias mitigation. Our findings validate the efficacy of prompt-based framing controls in mitigating inherent Social Desirability Bias in LLMs, providing a practical path toward more representative silicon samples.

---

### Memento 2: Learning by Stateful Reflective Memory

Authors: Jun Wang
Published: 2025-12-27
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.22716v3

We present a theoretical study of continual and experiential learning in large language model agents that combine episodic memory with reinforcement learning. We argue that the key mechanism for continual adaptation, without updating model parameters, is reflection: the agent's ability to use past experience to guide future actions. Empirical findings suggest that episodic, experience-driven reflection enables generalised adaptation across a wide range of open-ended, long-horizon tasks. This indicates that efficient learning can occur during deployment and weakens the traditional separation between training and testing. Motivated by this, we introduce the Stateful Reflective Decision Process, a formal model of reflective memory dynamics. In this abstraction, an agent maintains an episodic memory and performs two core operations. Writing stores interaction outcomes and plays the role of policy evaluation. Reading retrieves relevant past cases to inform decisions and plays the role of policy improvement. This perspective treats reflective memory as a control object that can be analysed using classical reinforcement learning tools. We then develop a read-write reflective learning framework by integrating retrieval into soft policy iteration and establish convergence guarantees. We show that as memory grows and provides denser coverage of the state space, the resulting composite policy converges to the optimal solution. Overall, this framework connects practical memory-based methods with principled reinforcement learning, providing a rigorous mathematical basis for building reflective, memory-embedded agents capable of continual general-purpose learning.

---

### Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages

Authors: Anaelia Ovalle, Candace Ross, Sebastian Ruder, Adina Williams, Karen Ullrich, Mark Ibrahim, Levent Sagun
Published: 2025-12-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.22712v3

Large language models demonstrate strong reasoning capabilities through chain-of-thought prompting, but whether this reasoning quality transfers across languages remains underexplored. We introduce a human-validated framework to evaluate whether model-generated reasoning traces logically support their conclusions across languages. Analyzing 65k reasoning traces from GlobalMMLU questions across 6 languages and 6 frontier models, we uncover a critical blind spot: while models achieve high task accuracy, their reasoning can fail to support their conclusions. Reasoning traces in non-Latin scripts show at least twice as much misalignment between their reasoning and conclusions than those in Latin scripts. We develop an error taxonomy through human annotation to characterize these failures, finding they stem primarily from evidential errors (unsupported claims, ambiguous facts) followed by illogical reasoning steps. Our findings demonstrate that current multilingual evaluation practices provide an incomplete picture of model reasoning capabilities and highlight the need for reasoning-aware evaluation frameworks.

---

### SCPainter: A Unified Framework for Realistic 3D Asset Insertion and Novel View Synthesis

Authors: Paul Dobre, Jackson Cooper, Xin Wang, Hongzhou Yang
Published: 2025-12-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.22706v1

3D Asset insertion and novel view synthesis (NVS) are key components for autonomous driving simulation, enhancing the diversity of training data. With better training data that is diverse and covers a wide range of situations, including long-tailed driving scenarios, autonomous driving models can become more robust and safer. This motivates a unified simulation framework that can jointly handle realistic integration of inserted 3D assets and NVS. Recent 3D asset reconstruction methods enable reconstruction of dynamic actors from video, supporting their re-insertion into simulated driving scenes. While the overall structure and appearance can be accurate, it still struggles to capture the realism of 3D assets through lighting or shadows, particularly when inserted into scenes. In parallel, recent advances in NVS methods have demonstrated promising results in synthesizing viewpoints beyond the originally recorded trajectories. However, existing approaches largely treat asset insertion and NVS capabilities in isolation. To allow for interaction with the rest of the scene and to enable more diverse creation of new scenarios for training, realistic 3D asset insertion should be combined with NVS. To address this, we present SCPainter (Street Car Painter), a unified framework which integrates 3D Gaussian Splat (GS) car asset representations and 3D scene point clouds with diffusion-based generation to jointly enable realistic 3D asset insertion and NVS. The 3D GS assets and 3D scene point clouds are projected together into novel views, and these projections are used to condition a diffusion model to generate high quality images. Evaluation on the Waymo Open Dataset demonstrate the capability of our framework to enable 3D asset insertion and NVS, facilitating the creation of diverse and realistic driving data.

---

### GHaLIB: A Multilingual Framework for Hope Speech Detection in Low-Resource Languages

Authors: Ahmed Abdullah, Sana Fatima, Haroon Mahmood
Published: 2025-12-27
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.22705v1

Hope speech has been relatively underrepresented in Natural Language Processing (NLP). Current studies are largely focused on English, which has resulted in a lack of resources for low-resource languages such as Urdu. As a result, the creation of tools that facilitate positive online communication remains limited. Although transformer-based architectures have proven to be effective in detecting hate and offensive speech, little has been done to apply them to hope speech or, more generally, to test them across a variety of linguistic settings. This paper presents a multilingual framework for hope speech detection with a focus on Urdu. Using pretrained transformer models such as XLM-RoBERTa, mBERT, EuroBERT, and UrduBERT, we apply simple preprocessing and train classifiers for improved results. Evaluations on the PolyHope-M 2025 benchmark demonstrate strong performance, achieving F1-scores of 95.2% for Urdu binary classification and 65.2% for Urdu multi-class classification, with similarly competitive results in Spanish, German, and English. These results highlight the possibility of implementing existing multilingual models in low-resource environments, thus making it easier to identify hope speech and helping to build a more constructive digital discourse.

---

### Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting

Authors: Valentina Moretti, Ivan Marisca, Cesare Alippi, Andrea Cini
Published: 2025-12-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.22702v2

Deep learning models have grown popular in time series applications. However, the large quantity of newly proposed architectures and the often contradictory empirical results make it difficult to assess which design choice and model component drives performance. In this position paper, we argue that current benchmarking practices fail to identify the factors responsible for performance differences, thus slowing down progress in the field. In particular, differences in crucial design dimensions are overlooked when comparing architectures, ultimately leading to inconsistent outcomes. To support our position, we show that such differences-often treated as mere implementation details-can have a greater impact than adopting specific sequence modeling layers. We discuss how overlooked aspects (such as globality and locality) can (1) fundamentally change the class of the forecasting method and (2) drastically affect empirical results. Our findings suggest rethinking our benchmarking practices and focusing on the foundational aspects of the forecasting problem when designing and comparing architectures. As a concrete step, we propose an auxiliary forecasting model card, i.e., a template with a set of fields to characterize existing and new forecasting architectures based on key design choices.

---

### Predictive Modeling of Power Outages during Extreme Events: Integrating Weather and Socio-Economic Factors

Authors: Nina Fatehi, Antar Kumar Biswas, Masoud H. Nazari
Published: 2025-12-27
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.22699v3

This paper presents a novel learning based framework for predicting power outages caused by extreme events. The proposed approach targets low-probability high-consequence outage scenarios and leverages a comprehensive set of features derived from publicly available data sources. We integrate EAGLE-I outage records from 2014 to 2024 with weather, socioeconomic, infrastructure, and seasonal event data. Incorporating social and demographic indicators reveals patterns of community vulnerability and improves understanding of outage risk during extreme conditions. Four machine learning models are evaluated, including Random Forest (RF), Graph Neural Network (GNN), Adaptive Boosting (AdaBoost), and Long Short-Term Memory (LSTM). Experimental validation is performed on a large-scale dataset covering counties in the lower peninsula of Michigan. Among all models tested, the LSTM network achieves higher accuracy.

---

### Canonical correlation regression with noisy data

Authors: Isaac Meza, Rahul Singh
Published: 2025-12-27
Categories: econ.EM, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2512.22697v1

We study instrumental variable regression in data rich environments. The goal is to estimate a linear model from many noisy covariates and many noisy instruments. Our key assumption is that true covariates and true instruments are repetitive, though possibly different in nature; they each reflect a few underlying factors, however those underlying factors may be misaligned. We analyze a family of estimators based on two stage least squares with spectral regularization: canonical correlations between covariates and instruments are learned in the first stage, which are used as regressors in the second stage. As a theoretical contribution, we derive upper and lower bounds on estimation error, proving optimality of the method with noisy data. As a practical contribution, we provide guidance on which types of spectral regularization to use in different regimes.

---

### Learning with the $p$-adics

Authors: André F. T. Martins
Published: 2025-12-27
Categories: cs.LG, cs.AI, cs.DM
arXiv: https://arxiv.org/abs/2512.22692v1

Existing machine learning frameworks operate over the field of real numbers ($\mathbb{R}$) and learn representations in real (Euclidean or Hilbert) vector spaces (e.g., $\mathbb{R}^d$). Their underlying geometric properties align well with intuitive concepts such as linear separability, minimum enclosing balls, and subspace projection; and basic calculus provides a toolbox for learning through gradient-based optimization. But is this the only possible choice? In this paper, we study the suitability of a radically different field as an alternative to $\mathbb{R}$ -- the ultrametric and non-archimedean space of $p$-adic numbers, $\mathbb{Q}_p$. The hierarchical structure of the $p$-adics and their interpretation as infinite strings make them an appealing tool for code theory and hierarchical representation learning. Our exploratory theoretical work establishes the building blocks for classification, regression, and representation learning with the $p$-adics, providing learning models and algorithms. We illustrate how simple Quillian semantic networks can be represented as a compact $p$-adic linear network, a construction which is not possible with the field of reals. We finish by discussing open problems and opportunities for future research enabled by this new framework.

---

### Mesquite MoCap: Democratizing Real-Time Motion Capture with Affordable, Bodyworn IoT Sensors and WebXR SLAM

Authors: Poojan Vanani, Darsh Patel, Danyal Khorami, Siva Munaganuru, Pavan Reddy, Varun Reddy, Bhargav Raghunath, Ishrat Lallmamode, Romir Patel, Assegid Kidané, Tejaswi Gowda
Published: 2025-12-27
Categories: cs.MM, cs.CV
arXiv: https://arxiv.org/abs/2512.22690v2

Motion capture remains costly and complex to deploy, limiting use outside specialized laboratories. We present Mesquite, an open-source, low-cost inertial motion-capture system that combines a body-worn network of 15 IMU sensor nodes with a hip-worn Android smartphone for position tracking. A low-power wireless link streams quaternion orientations to a central USB dongle and a browser-based application for real-time visualization and recording. Built on modern web technologies -- WebGL for rendering, WebXR for SLAM, WebSerial and WebSockets for device and network I/O, and Progressive Web Apps for packaging -- the system runs cross-platform entirely in the browser. In benchmarks against a commercial optical system, Mesquite achieves mean joint-angle error of 2-5 degrees while operating at approximately 5% of the cost. The system sustains 30 frames per second with end-to-end latency under 15ms and a packet delivery rate of at least 99.7% in standard indoor environments. By leveraging IoT principles, edge processing, and a web-native stack, Mesquite lowers the barrier to motion capture for applications in entertainment, biomechanics, healthcare monitoring, human-computer interaction, and virtual reality. We release hardware designs, firmware, and software under an open-source license (GNU GPL).

---

### Multimodal Diffeomorphic Registration with Neural ODEs and Structural Descriptors

Authors: Salvador Rodriguez-Sanz, Monica Hernandez
Published: 2025-12-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.22689v1

This work proposes a multimodal diffeomorphic registration method using Neural Ordinary Differential Equations (Neural ODEs). Nonrigid registration algorithms exhibit tradeoffs between their accuracy, the computational complexity of their deformation model, and its proper regularization. In addition, they also assume intensity correlation in anatomically homologous regions of interest among image pairs, limiting their applicability to the monomodal setting. Unlike learning-based models, we propose an instance-specific framework that is not subject to high scan requirements for training and does not suffer performance degradation at inference time on modalities unseen during training. Our method exploits the potential of continuous-depth networks in the Neural ODE paradigm with structural descriptors, widely adopted as modality-agnostic metric models which exploit self-similarities on parameterized neighborhood geometries. We propose three different variants that integrate image-based or feature-based structural descriptors and nonstructural image similarities computed by local mutual information. We conduct extensive evaluations on different experiments formed by scan dataset combinations and show surpassing qualitative and quantitative results compared to state-of-the-art baselines adequate for large or small deformations, and specific of multimodal registration. Lastly, we also demonstrate the underlying robustness of the proposed framework to varying levels of explicit regularization while maintaining low error, its suitability for registration at varying scales, and its efficiency with respect to other methods targeted to large-deformation registration.

---

### Autoregressive Flow Matching for Motion Prediction

Authors: Johnathan Xie, Stefan Stojanov, Cristobal Eyzaguirre, Daniel L. K. Yamins, Jiajun Wu
Published: 2025-12-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.22688v1

Motion prediction has been studied in different contexts with models trained on narrow distributions and applied to downstream tasks in human motion prediction and robotics. Simultaneously, recent efforts in scaling video prediction have demonstrated impressive visual realism, yet they struggle to accurately model complex motions despite massive scale. Inspired by the scaling of video generation, we develop autoregressive flow matching (ARFM), a new method for probabilistic modeling of sequential continuous data and train it on diverse video datasets to generate future point track locations over long horizons. To evaluate our model, we develop benchmarks for evaluating the ability of motion prediction models to predict human and robot motion. Our model is able to predict complex motions, and we demonstrate that conditioning robot action prediction and human motion prediction on predicted future tracks can significantly improve downstream task performance. Code and models publicly available at: https://github.com/Johnathan-Xie/arfm-motion-prediction.

---

### Conformal Prediction Sets for Next-Token Prediction in Large Language Models: Balancing Coverage Guarantees with Set Efficiency

Authors: Yoshith Roy Kotla, Varshith Roy Kotla
Published: 2025-12-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.22682v1

Deploying large language models (LLMs) in high-stakes domains requires rigorous uncertainty quantification, yet standard softmax probabilities are often poorly calibrated. We present a systematic study of Adaptive Prediction Sets (APS) applied to next-token prediction in transformer-based models with large vocabularies (greater than 250,000 tokens). Our central contribution is the identification of a coverage-efficiency tradeoff: while naive conformal prediction achieves valid coverage, it produces prediction sets of hundreds of tokens, rendering them uninformative. We propose Vocabulary-Aware Conformal Prediction (VACP), a framework that leverages semantic masking and temperature-adjusted scoring to reduce the effective prediction space while provably maintaining marginal coverage. Experiments on Gemma-2B using SQUAD and WikiText benchmarks demonstrate that VACP achieves 89.7 percent empirical coverage (90 percent target) while reducing the mean prediction set size from 847 tokens to 4.3 tokens -- a 197x improvement in efficiency. We provide a theoretical analysis of vocabulary reduction and release our implementation for reproducibility.

---

### CritiFusion: Semantic Critique and Spectral Alignment for Faithful Text-to-Image Generation

Authors: ZhenQi Chen, TsaiChing Ni, YuanFu Yang
Published: 2025-12-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.22681v2

Recent text-to-image diffusion models have achieved remarkable visual fidelity but often struggle with semantic alignment to complex prompts. We introduce CritiFusion, a novel inference-time framework that integrates a multimodal semantic critique mechanism with frequency-domain refinement to improve text-to-image consistency and detail. The proposed CritiCore module leverages a vision-language model and multiple large language models to enrich the prompt context and produce high-level semantic feedback, guiding the diffusion process to better align generated content with the prompt's intent. Additionally, SpecFusion merges intermediate generation states in the spectral domain, injecting coarse structural information while preserving high-frequency details. No additional model training is required. CritiFusion serves as a plug-in refinement stage compatible with existing diffusion backbones. Experiments on standard benchmarks show that our method notably improves human-aligned metrics of text-to-image correspondence and visual quality. CritiFusion consistently boosts performance on human preference scores and aesthetic evaluations, achieving results on par with state-of-the-art reward optimization approaches. Qualitative results further demonstrate superior detail, realism, and prompt fidelity, indicating the effectiveness of our semantic critique and spectral alignment strategy.

---

### Beyond Centralization: Provable Communication Efficient Decentralized Multi-Task Learning

Authors: Donghwa Kang, Shana Moothedath
Published: 2025-12-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.22675v1

Representation learning is a widely adopted framework for learning in data-scarce environments, aiming to extract common features from related tasks. While centralized approaches have been extensively studied, decentralized methods remain largely underexplored. We study decentralized multi-task representation learning in which the features share a low-rank structure. We consider multiple tasks, each with a finite number of data samples, where the observations follow a linear model with task-specific parameters. In the decentralized setting, task data are distributed across multiple nodes, and information exchange between nodes is constrained by a communication network. The goal is to recover the underlying feature matrix whose rank is much smaller than both the parameter dimension and the number of tasks. We propose a new alternating projected gradient and minimization algorithm with provable accuracy guarantees. We provide comprehensive characterizations of the time, communication, and sample complexities. Importantly, the communication complexity is independent of the target accuracy, which significantly reduces communication cost compared to prior methods. Numerical simulations validate the theoretical analysis across different dimensions and network topologies, and demonstrate regimes in which decentralized learning outperforms centralized federated approaches.

---

### Semantic contrastive learning for orthogonal X-ray computed tomography reconstruction

Authors: Jiashu Dong, Jiabing Xiang, Lisheng Geng, Suqing Tian, Wei Zhao
Published: 2025-12-27
Categories: eess.IV, cs.CV, physics.med-ph
arXiv: https://arxiv.org/abs/2512.22674v1

X-ray computed tomography (CT) is widely used in medical imaging, with sparse-view reconstruction offering an effective way to reduce radiation dose. However, ill-posed conditions often result in severe streak artifacts. Recent advances in deep learning-based methods have improved reconstruction quality, but challenges still remain. To address these challenges, we propose a novel semantic feature contrastive learning loss function that evaluates semantic similarity in high-level latent spaces and anatomical similarity in shallow latent spaces. Our approach utilizes a three-stage U-Net-based architecture: one for coarse reconstruction, one for detail refinement, and one for semantic similarity measurement. Tests on a chest dataset with orthogonal projections demonstrate that our method achieves superior reconstruction quality and faster processing compared to other algorithms. The results show significant improvements in image quality while maintaining low computational complexity, making it a practical solution for orthogonal CT reconstruction.

---

### Beyond Itinerary Planning-A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks

Authors: Xiang Cheng, Yulan Hu, Xiangwen Zhang, Lu Xu, Lide Tan, Zheng Pan, Xin Li, Yong Liu
Published: 2025-12-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.22673v3

Travel planning is a natural real-world task to test large language models' (LLMs) planning and tool-use abilities. Although prior work has studied LLM performance on travel planning, existing settings still differ from real-world needs, mainly due to limited domain coverage, insufficient modeling of users' implicit preferences in multi-turn conversations, and a lack of evaluation of agents' capability boundaries. To mitigate these gaps, we propose $\textbf{TravelBench}$, a benchmark for $\textit{truly real-world}$ travel planning. We collect user queries, user preferences, and tools from real scenarios, and construct three subtasks -- $\textit{Single-Turn}$, $\textit{Multi-Turn}$, and $\textit{Unsolvable}$ -- to evaluate agents' three core capabilities in real settings: (1) solving problems independently, (2) interacting with users to elicit implicit preferences, and (3) recognizing the capability boundaries. To enable stable tool invocation and reproducible evaluation, we cache real tool-call results and build a sandbox environment which integrates ten travel-related tools, enabling agents to combine these tools to solve most practical travel planning problems. We evaluate multiple LLMs on TravelBench and find that even advanced models exhibit imbalanced performance across different capabilities. Our further systematic verification demonstrates the stability of the proposed benchmark. TravelBench provides a practical and reproducible benchmark to advance research on LLM agents for real-world travel planning.

---

### Quantum Generative Models for Computational Fluid Dynamics: A First Exploration of Latent Space Learning in Lattice Boltzmann Simulations

Authors: Achraf Hsain, Fouad Mohammed Abbou
Published: 2025-12-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.22672v1

This paper presents the first application of quantum generative models to learned latent space representations of computational fluid dynamics (CFD) data. While recent work has explored quantum models for learning statistical properties of fluid systems, the combination of discrete latent space compression with quantum generative sampling for CFD remains unexplored. We develop a GPU-accelerated Lattice Boltzmann Method (LBM) simulator to generate fluid vorticity fields, which are compressed into a discrete 7-dimensional latent space using a Vector Quantized Variational Autoencoder (VQ-VAE). The central contribution is a comparative analysis of quantum and classical generative approaches for modeling this physics-derived latent distribution: we evaluate a Quantum Circuit Born Machine (QCBM) and Quantum Generative Adversarial Network (QGAN) against a classical Long Short-Term Memory (LSTM) baseline. Under our experimental conditions, both quantum models produced samples with lower average minimum distances to the true distribution compared to the LSTM, with the QCBM achieving the most favorable metrics. This work provides: (1)~a complete open-source pipeline bridging CFD simulation and quantum machine learning, (2)~the first empirical study of quantum generative modeling on compressed latent representations of physics simulations, and (3)~a foundation for future rigorous investigation at this intersection.

---

### Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2

Authors: Pere Martra
Published: 2025-12-27
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.22671v3

Structured width pruning of GLU-MLP layers in Llama-3.2 models, guided by the Peak-to-Peak Magnitude (PPM) criterion, reveals a systematic dichotomy in how reducing the expansion ratio affects different model capabilities. While performance on tasks relying on parametric knowledge (e.g., MMLU, GSM8K) and perplexity metrics degrades predictably with decreasing expansion ratios, instruction-following capabilities improve at the 2.4x equilibrium ratio (IFEval: +4.8 points / +46% in Llama-3.2-1B and +3.7 points / +39% in Llama-3.2-3B), and multi-step reasoning remains robust (MUSR). This pattern, observed consistently across both evaluated model sizes, challenges the prevailing assumption in compression research that pruning induces uniform degradation. To investigate this, we evaluated seven expansion ratio configurations using comprehensive benchmark suites that assess factual knowledge, mathematical reasoning, language comprehension, instruction-following, and truthfulness. Our analysis identifies the expansion ratio as a critical architectural parameter that selectively reshapes the model's task performance profile, rather than merely serving as a compression metric.

---

### INTERACT-CMIL: Multi-Task Shared Learning and Inter-Task Consistency for Conjunctival Melanocytic Intraepithelial Lesion Grading

Authors: Mert Ikinci, Luna Toma, Karin U. Loeffler, Leticia Ussem, Daniela Süsskind, Julia M. Weller, Yousef Yeganeh, Martina C. Herwig-Carl, Shadi Albarqouni
Published: 2025-12-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.22666v1

Accurate grading of Conjunctival Melanocytic Intraepithelial Lesions (CMIL) is essential for treatment and melanoma prediction but remains difficult due to subtle morphological cues and interrelated diagnostic criteria. We introduce INTERACT-CMIL, a multi-head deep learning framework that jointly predicts five histopathological axes; WHO4, WHO5, horizontal spread, vertical spread, and cytologic atypia, through Shared Feature Learning with Combinatorial Partial Supervision and an Inter-Dependence Loss enforcing cross-task consistency. Trained and evaluated on a newly curated, multi-center dataset of 486 expert-annotated conjunctival biopsy patches from three university hospitals, INTERACT-CMIL achieves consistent improvements over CNN and foundation-model (FM) baselines, with relative macro F1 gains up to 55.1% (WHO4) and 25.0% (vertical spread). The framework provides coherent, interpretable multi-criteria predictions aligned with expert grading, offering a reproducible computational benchmark for CMIL diagnosis and a step toward standardized digital ocular pathology.

---

### Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains

Authors: Qiankun Li, Feng He, Huabao Chen, Xin Ning, Kun Wang, Zengfu Wang
Published: 2025-12-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.22664v1

In the big data era, the computer vision field benefits from large-scale datasets such as LAION-2B, LAION-400M, and ImageNet-21K, Kinetics, on which popular models like the ViT and ConvNeXt series have been pre-trained, acquiring substantial knowledge. However, numerous downstream tasks in specialized and data-limited scientific domains continue to pose significant challenges. In this paper, we propose a novel Cluster Attention Adapter (CLAdapter), which refines and adapts the rich representations learned from large-scale data to various data-limited downstream tasks. Specifically, CLAdapter introduces attention mechanisms and cluster centers to personalize the enhancement of transformed features through distribution correlation and transformation matrices. This enables models fine-tuned with CLAdapter to learn distinct representations tailored to different feature sets, facilitating the models' adaptation from rich pre-trained features to various downstream scenarios effectively. In addition, CLAdapter's unified interface design allows for seamless integration with multiple model architectures, including CNNs and Transformers, in both 2D and 3D contexts. Through extensive experiments on 10 datasets spanning domains such as generic, multimedia, biological, medical, industrial, agricultural, environmental, geographical, materials science, out-of-distribution (OOD), and 3D analysis, CLAdapter achieves state-of-the-art performance across diverse data-limited scientific domains, demonstrating its effectiveness in unleashing the potential of foundation vision models via adaptive transfer. Code is available at https://github.com/qklee-lz/CLAdapter.

---

### Machine learning models for predicting catastrophe bond coupons using climate data

Authors: Julia Kończal, Michał Balcerek, Krzysztof Burnecki
Published: 2025-12-27
Categories: q-fin.PR, cs.LG
arXiv: https://arxiv.org/abs/2512.22660v1

In recent years, the growing frequency and severity of natural disasters have increased the need for effective tools to manage catastrophe risk. Catastrophe (CAT) bonds allow the transfer of part of this risk to investors, offering an alternative to traditional reinsurance. This paper examines the role of climate variability in CAT bond pricing and evaluates the predictive performance of various machine learning models in forecasting CAT bond coupons. We combine features typically used in the literature with a new set of climate indicators, including Oceanic Ni{ñ}o Index, Arctic Oscillation, North Atlantic Oscillation, Outgoing Longwave Radiation, Pacific-North American pattern, Pacific Decadal Oscillation, Southern Oscillation Index, and sea surface temperatures. We compare the performance of linear regression with several machine learning algorithms, such as random forest, gradient boosting, extremely randomized trees, and extreme gradient boosting. Our results show that including climate-related variables improves predictive accuracy across all models, with extremely randomized trees achieving the lowest root mean squared error (RMSE). These findings suggest that large-scale climate variability has a measurable influence on CAT bond pricing and that machine learning methods can effectively capture these complex relationships.

---