# Research Papers — 2025-11 · bundle page 42 of 197

> Full-text markdown of papers #2051–2100 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/42
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/41.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/43.md)

### On the Role of Hidden States of Modern Hopfield Network in Transformer

Authors: Tsubasa Masumura, Masato Taki
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.20698v1

Associative memory models based on Hopfield networks and self-attention based on key-value mechanisms have been popular approaches in the study of memory mechanisms in deep learning. It has been pointed out that the state update rule of the modern Hopfield network (MHN) in the adiabatic approximation is in agreement with the self-attention layer of Transformer. In this paper, we go beyond this approximation and investigate the relationship between MHN and self-attention. Our results show that the correspondence between Hopfield networks and Transformers can be established in a more generalized form by adding a new variable, the hidden state derived from the MHN, to self-attention. This new attention mechanism, modern Hopfield attention (MHA), allows the inheritance of attention scores from the input layer of the Transformer to the output layer, which greatly improves the nature of attention weights. In particular, we show both theoretically and empirically that MHA hidden states significantly improve serious problem of deep Transformers known as rank collapse and token uniformity. We also confirm that MHA can systematically improve accuracy without adding training parameters to the Vision Transformer or GPT. Our results provide a new case in which Hopfield networks can be a useful perspective for improving the Transformer architecture.

---

### Musical Score Understanding Benchmark: Evaluating Large Language Models' Comprehension of Complete Musical Scores

Authors: Congren Dai, Yue Yang, Krinos Li, Huichi Zhou, Shijie Liang, Bo Zhang, Enyang Liu, Ge Jin, Hongran An, Haosen Zhang, Peiyuan Jing, Kinhei Lee et al.
Published: 2025-11-24
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2511.20697v4

Understanding complete musical scores entails integrated reasoning over pitch, rhythm, harmony, and large-scale structure, yet the ability of Large Language Models and Vision--Language Models to interpret full musical notation remains insufficiently examined. We introduce Musical Score Understanding Benchmark (MSU-Bench), a human-curated benchmark for score-level musical understanding across textual (ABC notation) and visual (PDF) modalities. MSU-Bench contains 1,800 generative question-answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others, organised into four levels of increasing difficulty, ranging from onset information to texture and form. Evaluations of more than fifteen state-of-the-art models, in both zero-shot and fine-tuned settings, reveal pronounced modality gaps, unstable level-wise performance, and challenges in maintaining multilevel correctness. Fine-tuning substantially improves results across modalities while preserving general knowledge, positioning MSU-Bench as a robust foundation for future research in multimodal reasoning. The benchmark and code are available at https://github.com/Congren-Dai/MSU-Bench.

---

### Prototype-Guided Non-Exemplar Continual Learning for Cross-subject EEG Decoding

Authors: Dan Li, Hye-Bin Shin, Yeon-Woo Choi
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.20696v2

Due to the significant variability in electroencephalo-gram (EEG) signals across individuals, knowledge acquired from previous subjects is often overwritten as new subjects are introduced in continual EEG decoding tasks. Existing methods mainly rely on storing historical data from seen subjects as replay buffers to mitigate forgetting, which is impractical under privacy or memory constraints. To address this issue, we propose a Prototype-guided Non-Exemplar Continual Learning (ProNECL) framework that preserves prior knowledge without accessing historical EEG samples. ProNECL summarizes subject-specific discriminative representations into class-level prototypes and incrementally aligns new subject representations with a global prototype memory through prototype-based feature regulariza-tion and cross-subject alignment. Experiments on the BCI Com-petition IV 2a and 2b datasets demonstrate that ProNECL effec-tively balances knowledge retention and adaptability, achieving superior performance in cross-subject continual EEG decoding tasks.

---

### A Brief History of Digital Twin Technology

Authors: Yunqi Zhang, Kuangyu Shi, Biao Li
Published: 2025-11-24
Categories: cs.AI, cs.CY, physics.med-ph
arXiv: https://arxiv.org/abs/2511.20695v1

Emerging from NASA's spacecraft simulations in the 1960s, digital twin technology has advanced through industrial adoption to spark a healthcare transformation. A digital twin is a dynamic, data-driven virtual counterpart of a physical system, continuously updated through real-time data streams and capable of bidirectional interaction. In medicine, digital twin integrates imaging, biosensors, and computational models to generate patient-specific simulations that support diagnosis, treatment planning, and drug development. Representative applications include cardiac digital twin for predicting arrhythmia treatment outcomes, oncology digital twin for tracking tumor progression and optimizing radiotherapy, and pharmacological digital twin for accelerating drug discovery. Despite rapid progress, major challenges, including interoperability, data privacy, and model fidelity, continue to limit widespread clinical integration. Emerging solutions such as explainable AI, federated learning, and harmonized regulatory frameworks offer promising pathways forward. Looking ahead, advances in multi-organ digital twin, genomics integration, and ethical governance will be essential to ensure that digital twin shifts healthcare from reactive treatment to predictive, preventive, and truly personalized medicine.

---

### Development of a fully deep learning model to improve the reproducibility of sector classification systems for predicting unerupted maxillary canine likelihood of impaction

Authors: Marzio Galdi, Davide Cannatà, Flavia Celentano, Luigia Rizzo, Domenico Rossi, Tecla Bocchino, Stefano Martina
Published: 2025-11-24
Categories: eess.IV, cs.CV, q-bio.QM
arXiv: https://arxiv.org/abs/2511.20493v1

Objectives. The aim of the present study was to develop a fully deep learning model to reduce the intra- and inter-operator reproducibility of sector classification systems for predicting unerupted maxillary canine likelihood of impaction. Methods. Three orthodontists (Os) and three general dental practitioners (GDPs) classified the position of unerupted maxillary canines on 306 radiographs (T0) according to the three different sector classification systems (5-, 4-, and 3-sector classification system). The assessment was repeated after four weeks (T1). Intra- and inter-observer agreement were evaluated with Cohen's K and Fleiss K, and between group differences with a z-test. The same radiographs were tested on different artificial intelligence (AI) models, pre-trained on an extended dataset of 1,222 radiographs. The best-performing model was identified based on its sensitivity and precision. Results. The 3-sector system was found to be the classification method with highest reproducibility, with an agreement (Cohen's K values) between observations (T0 versus T1) for each examiner ranged from 0.80 to 0.92, and an overall agreement of 0.85 (95% confidence interval (CI) = 0.83-0.87). The overall inter-observer agreement (Fleiss K) ranged from 0.69 to 0.7. The educational background did not affect either intra- or inter-observer agreement (p>0.05). DenseNet121 proved to be the best-performing model in allocating impacted canines in the three different classes, with an overall accuracy of 76.8%. Conclusion. AI models can be designed to automatically classify the position of unerupted maxillary canines.

---

### KOM: A Multi-Agent Artificial Intelligence System for Precision Management of Knee Osteoarthritis (KOA)

Authors: Weizhi Liu, Xi Chen, Zekun Jiang, Liang Zhao, Kunyuan Jiang, Ruisi Tang, Li Wang, Mingke You, Hanyu Zhou, Hongyu Chen, Qiankun Xiong, Yong Nie et al.
Published: 2025-11-24
Categories: cs.AI, cs.HC, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2511.19798v1

Knee osteoarthritis (KOA) affects more than 600 million individuals globally and is associated with significant pain, functional impairment, and disability. While personalized multidisciplinary interventions have the potential to slow disease progression and enhance quality of life, they typically require substantial medical resources and expertise, making them difficult to implement in resource-limited settings. To address this challenge, we developed KOM, a multi-agent system designed to automate KOA evaluation, risk prediction, and treatment prescription. This system assists clinicians in performing essential tasks across the KOA care pathway and supports the generation of tailored management plans based on individual patient profiles, disease status, risk factors, and contraindications. In benchmark experiments, KOM demonstrated superior performance compared to several general-purpose large language models in imaging analysis and prescription generation. A randomized three-arm simulation study further revealed that collaboration between KOM and clinicians reduced total diagnostic and planning time by 38.5% and resulted in improved treatment quality compared to each approach used independently. These findings indicate that KOM could help facilitate automated KOA management and, when integrated into clinical workflows, has the potential to enhance care efficiency. The modular architecture of KOM may also offer valuable insights for developing AI-assisted management systems for other chronic conditions.

---

### Terminal Velocity Matching

Authors: Linqi Zhou, Mathias Parger, Ayaan Haque, Jiaming Song
Published: 2025-11-24
Categories: cs.LG, cs.AI, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2511.19797v3

We propose Terminal Velocity Matching (TVM), a generalization of flow matching that enables high-fidelity one- and few-step generative modeling. TVM models the transition between any two diffusion timesteps and regularizes its behavior at its terminal time rather than at the initial time. We prove that TVM provides an upper bound on the $2$-Wasserstein distance between data and model distributions when the model is Lipschitz continuous. However, since Diffusion Transformers lack this property, we introduce minimal architectural changes that achieve stable, single-stage training. To make TVM efficient in practice, we develop a fused attention kernel that supports backward passes on Jacobian-Vector Products, which scale well with transformer architectures. On ImageNet-256x256, TVM achieves 3.29 FID with a single function evaluation (NFE) and 1.99 FID with 4 NFEs. It similarly achieves 4.32 1-NFE FID and 2.94 4-NFE FID on ImageNet-512x512, representing state-of-the-art performance for one/few-step models from scratch.

---

### When +1% Is Not Enough: A Paired Bootstrap Protocol for Evaluating Small Improvements

Authors: Wenzhang Du
Published: 2025-11-24
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.19794v1

Recent machine learning papers often report 1-2 percentage point improvements from a single run on a benchmark. These gains are highly sensitive to random seeds, data ordering, and implementation details, yet are rarely accompanied by uncertainty estimates or significance tests. It is therefore unclear when a reported +1-2% reflects a real algorithmic advance versus noise. We revisit this problem under realistic compute budgets, where only a few runs are affordable. We propose a simple, PC-friendly evaluation protocol based on paired multi-seed runs, bias-corrected and accelerated (BCa) bootstrap confidence intervals, and a sign-flip permutation test on per-seed deltas. The protocol is intentionally conservative and is meant as a guardrail against over-claiming. We instantiate it on CIFAR-10, CIFAR-10N, and AG News using synthetic no-improvement, small-gain, and medium-gain scenarios. Single runs and unpaired t-tests often suggest significant gains for 0.6-2.0 point improvements, especially on text. With only three seeds, our paired protocol never declares significance in these settings. We argue that such conservative evaluation is a safer default for small gains under tight budgets.

---

### Gender Bias in Emotion Recognition by Large Language Models

Authors: Maureen Herbert, Katie Sun, Angelica Lim, Yasaman Etesam
Published: 2025-11-24
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2511.19785v2

The rapid advancement of large language models (LLMs) and their growing integration into daily life underscore the importance of evaluating and ensuring their fairness. In this work, we examine fairness within the domain of emotional theory of mind, investigating whether LLMs exhibit gender biases when presented with a description of a person and their environment and asked, ''How does this person feel?''. Furthermore, we propose and evaluate several debiasing strategies, demonstrating that achieving meaningful reductions in bias requires training based interventions rather than relying solely on inference-time prompt-based approaches such as prompt engineering, etc.

---

### NOEM$^{3}$A: a Neuro-symbolic Ontology-Enhanced Method for Multi-intent understanding in Mobile Agents

Authors: Ioannis Tzachristas, Aifen Sui
Published: 2025-11-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.19780v2

Mobile agents must map natural-language requests to executable intents under tight latency and privacy constraints. Scaling the language model is often an inefficient way to improve this component. We present NOEM$^{3}$A, a lightweight neuro-symbolic layer that augments compact language models with an intent ontology. For each query, NOEM$^{3}$A retrieves a small ontology neighborhood, injects candidate action labels into the prompt and applies a token-level decoding prior toward valid labels. This injects symbolic intent structure into both input and output representations while keeping inference suitable for local interaction. We also use Semantic Intent Similarity (SIS), a hierarchy-aware diagnostic based on ontology depth, to capture semantic proximity when predicted intents differ lexically. Experiments on MultiWOZ 2.3 dialogues show that ontology augmentation consistently improves TinyLlama and Llama-3.2-3B on exact match and Slot-F1. Our results suggest that symbolic alignment is an effective strategy for accurate, responsive and privacy-preserving on-device NLU.

---

### Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer

Authors: Haoyu Wu, Jingyi Xu, Qiaomu Miao, Dimitris Samaras, Hieu Le
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19778v2

Rotary positional embeddings (RoPE) are widely used in diffusion transformers (DiTs) to encode spatial relationships, yet their behavior with mixed-resolution tokens remains underexplored. A natural approach is to rescale token positions from different resolutions into a unified coordinate system before attention, but we show this fails. Our analysis shows that with RoPE, the attention similarity score is a highly structured and periodic function of token distance, so rescaling distances across resolutions moves token pairs to different regions of this periodic function, leading to incorrect attention scores. Motivated by this, we introduce Phase-Aligned Mixed-Resolution Attention (PMA), a training-free mechanism that stabilizes mixed-resolution attention. PMA modifies the RoPE position mapping to enforce a consistent positional scale for every query-key pair, ensuring that relative distances are evaluated under a single reference scale. To further improve local coherence near resolution transitions, we incorporate a lightweight boundary refinement module that softly exchanges features across adjacent scales. Experiments on image and video diffusion models validate our analysis and demonstrate consistent improvements in visual fidelity and computational efficiency.

---

### Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs

Authors: Meng Lu, Ran Xu, Yi Fang, Wenxuan Zhang, Yue Yu, Gaurav Srivastava, Yuchen Zhuang, Mohamed Elhoseiny, Charles Fleming, Carl Yang, Zhengzhong Tu, Yang Xie et al.
Published: 2025-11-24
Categories: cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2511.19773v1

While recent vision-language models (VLMs) demonstrate strong image understanding, their ability to "think with images", i.e., to reason through multi-step visual interactions, remains limited. We introduce VISTA-Gym, a scalable training environment for incentivizing tool-integrated visual reasoning capabilities in VLMs. VISTA-Gym unifies diverse real-world multimodal reasoning tasks (7 tasks from 13 datasets in total) with a standardized interface for visual tools (e.g., grounding, parsing), executable interaction loops, verifiable feedback signals, and efficient trajectory logging, enabling visual agentic reinforcement learning at scale. While recent VLMs exhibit strong text-only reasoning, both proprietary and open-source models still struggle with tool selection, invocation, and coordination. With VISTA-Gym, we train VISTA-R1 to interleave tool-use with agentic reasoning via multi-turn trajectory sampling and end-to-end reinforcement learning. Extensive experiments across 11 public reasoning-intensive VQA benchmarks show that VISTA-R1-8B outperforms state-of-the-art baselines with similar sizes by 9.51%-18.72%, demonstrating VISTA-Gym as an effective training ground to unlock the tool-integrated reasoning capabilities for VLMs.

---

### Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering

Authors: Noah Frahm, Prakrut Patel, Yue Zhang, Shoubin Yu, Mohit Bansal, Roni Sengupta
Published: 2025-11-24
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2511.19768v1

Large vision-language models (VLMs) have improved embodied question answering (EQA) agents by providing strong semantic priors for open-vocabulary reasoning. However, when used directly for step-level exploration, VLMs often exhibit frontier oscillations, unstable back-and-forth movements caused by overconfidence and miscalibration, leading to inefficient navigation and degraded answer quality. We propose Prune-Then-Plan, a simple and effective framework that stabilizes exploration through step-level calibration. Instead of trusting raw VLM scores, our method prunes implausible frontier choices using a Holm-Bonferroni inspired pruning procedure and then delegates final decisions to a coverage-based planner. This separation converts overconfident predictions into conservative, interpretable actions by relying on human-level judgments to calibrate the step-level behavior of VLMs. Integrated into the 3D-Mem EQA framework, our approach achieves relative improvements of up to 49% and 33% in visually grounded SPL and LLM-Match metrics respectively over baselines. Overall, our method achieves better scene coverage under equal exploration budgets on both OpenEQA and EXPRESS-Bench datasets.

---

### Lightweight Transformer Framework for Weakly Supervised Semantic Segmentation

Authors: Ali Torabi, Sanjog Gaihre, Yaqoob Majeed
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19765v1

Weakly supervised semantic segmentation (WSSS) must learn dense masks from noisy, under-specified cues. We revisit the SegFormer decoder and show that three small, synergistic changes make weak supervision markedly more effective-without altering the MiT backbone or relying on heavy post-processing. Our method, CrispFormer, augments the decoder with: (1) a boundary branch that supervises thin object contours using a lightweight edge head and a boundary-aware loss; (2) an uncertainty-guided refiner that predicts per-pixel aleatoric uncertainty and uses it to weight losses and gate a residual correction of the segmentation logits; and (3) a dynamic multi-scale fusion layer that replaces static concatenation with spatial softmax gating over multi-resolution features, optionally modulated by uncertainty. The result is a single-pass model that preserves crisp boundaries, selects appropriate scales per location, and resists label noise from weak cues. Integrated into a standard WSSS pipeline (seed, student, and EMA relabeling), CrispFormer consistently improves boundary F-score, small-object recall, and mIoU over SegFormer baselines trained on the same seeds, while adding minimal compute. Our decoder-centric formulation is simple to implement, broadly compatible with existing SegFormer variants, and offers a reproducible path to higher-fidelity masks from image-level supervision.

---

### Order Selection in Vector Autoregression by Mean Square Information Criterion

Authors: Michael Hellstern, Ali Shojaie
Published: 2025-11-24
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2511.19761v1

Vector autoregressive (VAR) processes are ubiquitously used in economics, finance, and biology. Order selection is an essential step in fitting VAR models. While many order selection methods exist, all come with weaknesses. Order selection by minimizing AIC is a popular approach but is known to consistently overestimate the true order for processes of small dimension. On the other hand, methods based on BIC or the Hannan-Quinn (HQ) criteria are shown to require large sample sizes in order to accurately estimate the order for larger-dimensional processes. We propose the mean square information criterion (MIC) based on the observation that the expected squared error loss is flat once the fitted order reaches or exceeds the true order. MIC is shown to consistently estimate the order of the process under relatively mild conditions. Our simulation results show that MIC offers better performance relative to AIC, BIC, and HQ under misspecification. This advantage is corroborated when forecasting COVID-19 outcomes in New York City. Order selection by MIC is implemented in the micvar R package available on CRAN.

---

### A Storage-Efficient Feature for 3D Concrete Defect Segmentation to Replace Normal Vector

Authors: Linxin Hua, Jianghua Deng, Ye Lu
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19760v1

Point cloud reconstruction of damage offers an effective solution to image-based methods vulnerable to background noise, yet its application is constrained by the high volume of 3D data. This study proposes a new feature, relative angle, computed as the angle between the normal vector of a point and the average normal vector of its parent point cloud. This single-dimensional feature provides directionality information equivalent to normal vectors for concrete surface defect characteristics. Through entropy-based feature evaluation, this study demonstrates the ability of relative angle to filter out redundant information in undamaged sections while retaining effective information in damaged sections. By training and testing with PointNet++, models based on the relative angles achieved similar performance to that of models based on normal vectors while delivering 27.6% storage reduction and 83% input channel compression. This novel feature has the potential to enable larger-batch execution on resource-constrained hardware without the necessity of architectural modifications to models.

---

### Vision-Language Enhanced Foundation Model for Semi-Supervised Medical Image Segmentation

Authors: Jiaqi Guo, Mingzhen Li, Hanyu Su, Keigo Healy, Lexiaozi Fan, Neda Tavakoli, Santiago López-Tapia, Daniel Kim, Aggelos K. Katsaggelos
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19759v3

Semi-supervised learning (SSL) has emerged as an efficient paradigm for medical image segmentation, reducing the reliance on extensive expert annotations. Vision-language models (VLMs) have demonstrated strong generalization and few-shot capabilities across diverse visual domains. In this work, we integrate a VLM into a semi-supervised medical image segmentation model by adding a Vision-Language Enhanced Semi-supervised Segmentation Assistant (VESSA) that incorporates foundation-level visual-semantic understanding into SSL frameworks. Our approach consists of two stages. In Stage 1, the VLM-enhanced segmentation foundation model VESSA is trained as a reference-guided segmentation assistant using a template bank containing gold-standard exemplars, simulating learning from limited labeled data. Given an input-template pair, VESSA performs visual feature matching to extract representative semantic and spatial cues from exemplar segmentations, generating structured prompts for a Segment Anything Model (SAM)-inspired mask decoder to produce segmentation masks. In Stage 2, VESSA is integrated into an SSL framework as a plug-and-play teacher, providing template-guided pseudo-labels that complement the task-specific student model and strengthen supervision under scarce annotations. Extensive experiments across multiple segmentation datasets and domains show that VESSA-augmented SSL significantly enhances segmentation accuracy, outperforming state-of-the-art baselines under extremely limited annotation conditions.

---

### What does it mean to understand language?

Authors: Colton Casto, Anna Ivanova, Evelina Fedorenko, Nancy Kanwisher
Published: 2025-11-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.19757v1

Language understanding entails not just extracting the surface-level meaning of the linguistic input, but constructing rich mental models of the situation it describes. Here we propose that because processing within the brain's core language system is fundamentally limited, deeply understanding language requires exporting information from the language system to other brain regions that compute perceptual and motor representations, construct mental models, and store our world knowledge and autobiographical memories. We review the existing evidence for this hypothesis, and argue that recent progress in cognitive neuroscience provides both the conceptual foundation and the methods to directly test it, thus opening up a new strategy to reveal what it means, cognitively and neurally, to understand language.

---

### Clustering Approaches for Mixed-Type Data: A Comparative Study

Authors: Badih Ghattas, Alvaro Sanchez San-Benito
Published: 2025-11-24
Categories: stat.ML, cs.LG, stat.AP, stat.ME
arXiv: https://arxiv.org/abs/2511.19755v1

Clustering is widely used in unsupervised learning to find homogeneous groups of observations within a dataset. However, clustering mixed-type data remains a challenge, as few existing approaches are suited for this task. This study presents the state-of-the-art of these approaches and compares them using various simulation models. The compared methods include the distance-based approaches k-prototypes, PDQ, and convex k-means, and the probabilistic methods KAy-means for MIxed LArge data (KAMILA), the mixture of Bayesian networks (MBNs), and latent class model (LCM). The aim is to provide insights into the behavior of different methods across a wide range of scenarios by varying some experimental factors such as the number of clusters, cluster overlap, sample size, dimension, proportion of continuous variables in the dataset, and clusters' distribution. The degree of cluster overlap and the proportion of continuous variables in the dataset and the sample size have a significant impact on the observed performances. When strong interactions exist between variables alongside an explicit dependence on cluster membership, none of the evaluated methods demonstrated satisfactory performance. In our experiments KAMILA, LCM, and k-prototypes exhibited the best performance, with respect to the adjusted rand index (ARI). All the methods are available in R.

---

### What You See is (Usually) What You Get: Multimodal Prototype Networks that Abstain from Expensive Modalities

Authors: Muchang Bahng, Charlie Berens, Jon Donnelly, Eric Chen, Chaofan Chen, Cynthia Rudin
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19752v1

Species detection is important for monitoring the health of ecosystems and identifying invasive species, serving a crucial role in guiding conservation efforts. Multimodal neural networks have seen increasing use for identifying species to help automate this task, but they have two major drawbacks. First, their black-box nature prevents the interpretability of their decision making process. Second, collecting genetic data is often expensive and requires invasive procedures, often necessitating researchers to capture or kill the target specimen. We address both of these problems by extending prototype networks (ProtoPNets), which are a popular and interpretable alternative to traditional neural networks, to the multimodal, cost-aware setting. We ensemble prototypes from each modality, using an associated weight to determine how much a given prediction relies on each modality. We further introduce methods to identify cases for which we do not need the expensive genetic information to make confident predictions. We demonstrate that our approach can intelligently allocate expensive genetic data for fine-grained distinctions while using abundant image data for clearer visual classifications and achieving comparable accuracy to models that consistently use both modalities.

---

### Leveraging Foundation Models for Histological Grading in Cutaneous Squamous Cell Carcinoma using PathFMTools

Authors: Abdul Rahman Diab, Emily E. Karn, Renchin Wu, Emily S. Ruiz, William Lotter
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19751v1

Despite the promise of computational pathology foundation models, adapting them to specific clinical tasks remains challenging due to the complexity of whole-slide image (WSI) processing, the opacity of learned features, and the wide range of potential adaptation strategies. To address these challenges, we introduce PathFMTools, a lightweight, extensible Python package that enables efficient execution, analysis, and visualization of pathology foundation models. We use this tool to interface with and evaluate two state-of-the-art vision-language foundation models, CONCH and MUSK, on the task of histological grading in cutaneous squamous cell carcinoma (cSCC), a critical criterion that informs cSCC staging and patient management. Using a cohort of 440 cSCC H&E WSIs, we benchmark multiple adaptation strategies, demonstrating trade-offs across prediction approaches and validating the potential of using foundation model embeddings to train small specialist models. These findings underscore the promise of pathology foundation models for real-world clinical applications, with PathFMTools enabling efficient analysis and validation.

---

### DISCO: A Browser-Based Privacy-Preserving Framework for Distributed Collaborative Learning

Authors: Julien T. T. Vignoud, Valérian Rousset, Hugo El Guedj, Ignacio Aleman, Walid Bennaceur, Batuhan Faik Derinbay, Eduard Ďurech, Damien Gengler, Lucas Giordano, Felix Grimberg, Franziska Lippoldt, Christina Kopidaki et al.
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19750v1

Data is often impractical to share for a range of well considered reasons, such as concerns over privacy, intellectual property, and legal constraints. This not only fragments the statistical power of predictive models, but creates an accessibility bias, where accuracy becomes inequitably distributed to those who have the resources to overcome these concerns. We present DISCO: an open-source DIStributed COllaborative learning platform accessible to non-technical users, offering a means to collaboratively build machine learning models without sharing any original data or requiring any programming knowledge. DISCO's web application trains models locally directly in the browser, making our tool cross-platform out-of-the-box, including smartphones. The modular design of \disco offers choices between federated and decentralized paradigms, various levels of privacy guarantees and several approaches to weight aggregation strategies that allow for model personalization and bias resilience in the collaborative training. Code repository is available at https://github.com/epfml/disco and a showcase web interface at https://discolab.ai

---

### Scaling Item-to-Standard Alignment with Large Language Models: Accuracy, Limits, and Solutions

Authors: Farzan Karimi-Malekabadi, Pooya Razavi, Sonya Powers
Published: 2025-11-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.19749v1

As educational systems evolve, ensuring that assessment items remain aligned with content standards is essential for maintaining fairness and instructional relevance. Traditional human alignment reviews are accurate but slow and labor-intensive, especially across large item banks. This study examines whether Large Language Models (LLMs) can accelerate this process without sacrificing accuracy. Using over 12,000 item-skill pairs in grades K-5, we tested three LLMs (GPT-3.5 Turbo, GPT-4o-mini, and GPT-4o) across three tasks that mirror real-world challenges: identifying misaligned items, selecting the correct skill from the full set of standards, and narrowing candidate lists prior to classification. In Study 1, GPT-4o-mini correctly identified alignment status in approximately 83-94% of cases, including subtle misalignments. In Study 2, performance remained strong in mathematics but was lower for reading, where standards are more semantically overlapping. Study 3 demonstrated that pre-filtering candidate skills substantially improved results, with the correct skill appearing among the top five suggestions more than 95% of the time. These findings suggest that LLMs, particularly when paired with candidate filtering strategies, can significantly reduce the manual burden of item review while preserving alignment accuracy. We recommend the development of hybrid pipelines that combine LLM-based screening with human review in ambiguous cases, offering a scalable solution for ongoing item validation and instructional alignment.

---

### Efficient Transferable Optimal Transport via Min-Sliced Transport Plans

Authors: Xinran Liu, Elaheh Akbari, Rocio Diaz Martin, Navid NaderiAlizadeh, Soheil Kolouri
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19741v4

Optimal Transport (OT) offers a powerful framework for finding correspondences between distributions and addressing matching and alignment problems in various areas of computer vision, including shape analysis, image generation, and multimodal tasks. The computation cost of OT, however, hinders its scalability. Slice-based transport plans have recently shown promise for reducing the computational cost by leveraging the closed-form solutions of 1D OT problems. These methods optimize a one-dimensional projection (slice) to obtain a conditional transport plan that minimizes the transport cost in the ambient space. While efficient, these methods leave open the question of whether learned optimal slicers can transfer to new distribution pairs under distributional shift. Understanding this transferability is crucial in settings with evolving data or repeated OT computations across closely related distributions. In this paper, we study the min-Sliced Transport Plan (min-STP) framework and investigate the transferability of optimized slicers: can a slicer trained on one distribution pair yield effective transport plans for new, unseen pairs? Theoretically, we show that optimized slicers remain close under slight perturbations of the data distributions, enabling efficient transfer across related tasks. To further improve scalability, we introduce a minibatch formulation of min-STP and provide statistical guarantees on its accuracy. Empirically, we demonstrate that the transferable min-STP achieves strong one-shot matching performance and facilitates amortized training for point cloud alignment and flow-based generative modeling.

---

### CAMformer: Associative Memory is All You Need

Authors: Tergel Molom-Ochir, Benjamin F. Morris, Mark Horton, Chiyue Wei, Cong Guo, Brady Taylor, Peter Liu, Shan X. Wang, Deliang Fan, Hai Helen Li, Yiran Chen
Published: 2025-11-24
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2511.19740v1

Transformers face scalability challenges due to the quadratic cost of attention, which involves dense similarity computations between queries and keys. We propose CAMformer, a novel accelerator that reinterprets attention as an associative memory operation and computes attention scores using a voltage-domain Binary Attention Content Addressable Memory (BA-CAM). This enables constant-time similarity search through analog charge sharing, replacing digital arithmetic with physical similarity sensing. CAMformer integrates hierarchical two-stage top-k filtering, pipelined execution, and high-precision contextualization to achieve both algorithmic accuracy and architectural efficiency. Evaluated on BERT and Vision Transformer workloads, CAMformer achieves over 10x energy efficiency, up to 4x higher throughput, and 6-8x lower area compared to state-of-the-art accelerators--while maintaining near-lossless accuracy.

---

### Comparative Analysis of LoRA-Adapted Embedding Models for Clinical Cardiology Text Representation

Authors: Richard J. Young, Alice M. Matthews
Published: 2025-11-24
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.19739v1

Domain-specific text embeddings are critical for clinical natural language processing, yet systematic comparisons across model architectures remain limited. This study evaluates ten transformer-based embedding models adapted for cardiology through Low-Rank Adaptation (LoRA) fine-tuning on 106,535 cardiology text pairs derived from authoritative medical textbooks. Results demonstrate that encoder-only architectures, particularly BioLinkBERT, achieve superior domain-specific performance (separation score: 0.510) compared to larger decoder-based models, while requiring significantly fewer computational resources. The findings challenge the assumption that larger language models necessarily produce better domain-specific embeddings and provide practical guidance for clinical NLP system development. All models, training code, and evaluation datasets are publicly available to support reproducible research in medical informatics.

---

### Integrating RCTs, RWD, AI/ML and Statistics: Next-Generation Evidence Synthesis

Authors: Shu Yang, Margaret Gamalo, Haoda Fu
Published: 2025-11-24
Categories: stat.ME, cs.LG
arXiv: https://arxiv.org/abs/2511.19735v2

Randomized controlled trials (RCTs)have been the cornerstone of clinical evidence; however, their cost, duration, and restrictive eligibility criteria limit power and external validity. Studies using real-world data (RWD), historically considered less reliable for establishing causality, are now recognized as an important source of real-world evidence (RWE). In parallel, artificial intelligence and machine learning (AI/ML) are increasingly used throughout the drug development process, providing scalability and flexibility but also presenting challenges in interpretability and statistical rigor. This Perspective argues that the future of evidence generation will not depend on RCTs versus RWD, or statistics versus AI/ML, but on their principled integration under a statistical evidence framework that clarifies estimands, evaluates data fitness, controls bias, quantifies uncertainty, and determines when evidence is strong enough to support decisions. Building on the Causal Roadmap for high-quality real-world evidence, we present a six-step statistical roadmap for integrative evidence synthesis and organize the discussion around five core questions that statisticians must confront: when RWD is fit for causal use and when it is not; what AI genuinely contributes across the evidence lifecycle; what remains distinctly statistical and indispensable; how to build trustworthy end-to-end evidence systems in pharmaceutical, regulatory, and industry settings; and how statistical training should evolve.

---

### Training-Free Active Learning Framework in Materials Science with Large Language Models

Authors: Hongchen Wang, Rafael Espinosa Castañeda, Jay R. Werber, Yao Fehlis, Edward Kim, Jason Hattrick-Simpers
Published: 2025-11-24
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2511.19730v2

Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-start limitations and domain-specific feature engineering, restricting their generalizability. Large language models (LLMs) offer a new paradigm by leveraging their pretrained knowledge and universal token-based representations to propose experiments directly from text-based descriptions. Here, we introduce an LLM-based active learning framework (LLM-AL) that operates in an iterative few-shot setting and benchmark it against conventional ML models across four diverse materials science datasets. We explored two prompting strategies: one using concise numerical inputs suited for datasets with more compositional and structured features, and another using expanded descriptive text suited for datasets with more experimental and procedural features to provide additional context. Across all datasets, LLM-AL could reduce the number of experiments needed to reach top-performing candidates by over 70% and consistently outperformed traditional ML models. We found that LLM-AL performs broader and more exploratory searches while still reaching the optima with fewer iterations. We further examined the stability boundaries of LLM-AL given the inherent non-determinism of LLMs and found its performance to be broadly consistent across runs, within the variability range typically observed for traditional ML approaches. These results demonstrate that LLM-AL can serve as a generalizable alternative to conventional AL pipelines for more efficient and interpretable experiment selection and potential LLM-driven autonomous discovery.

---

### Maritime Small Object Detection from UAVs using Deep Learning with Altitude-Aware Dynamic Tiling

Authors: Sakib Ahmed, Oscar Pizarro
Published: 2025-11-24
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.19728v1

Unmanned Aerial Vehicles (UAVs) are crucial in Search and Rescue (SAR) missions due to their ability to monitor vast maritime areas. However, small objects often remain difficult to detect from high altitudes due to low object-to-background pixel ratios. We propose an altitude-aware dynamic tiling method that scales and adaptively subdivides the image into tiles for enhanced small object detection. By integrating altitude-dependent scaling with an adaptive tiling factor, we reduce unnecessary computation while maintaining detection performance. Tested on the SeaDronesSee dataset (1) with YOLOv5 (2) and Slicing Aided Hyper Inference (SAHI) framework (3), our approach improves Mean Average Precision (mAP) for small objects by 38% compared to a baseline and achieves more than double the inference speed compared to static tiling. This approach enables more efficient and accurate UAV-based SAR operations under diverse conditions.

---

### Prompt Fencing: A Cryptographic Approach to Establishing Security Boundaries in Large Language Model Prompts

Authors: Steven Peh
Published: 2025-11-24
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.19727v1

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic authentication and data architecture principles to establish explicit security boundaries within LLM prompts. Our approach decorates prompt segments with cryptographically signed metadata including trust ratings and content types, enabling LLMs to distinguish between trusted instructions and untrusted content. While current LLMs lack native fence awareness, we demonstrate that simulated awareness through prompt instructions achieved complete prevention of injection attacks in our experiments, reducing success rates from 86.7% (260/300 successful attacks) to 0% (0/300 successful attacks) across 300 test cases with two leading LLM providers. We implement a proof-of-concept fence generation and verification pipeline with a total overhead of 0.224 seconds (0.130s for fence generation, 0.094s for validation) across 100 samples. Our approach is platform-agnostic and can be incrementally deployed as a security layer above existing LLM infrastructure, with the expectation that future models will be trained with native fence awareness for optimal security.

---

### An Adaptive, Data-Integrated Agent-Based Modeling Framework for Explainable and Contestable Policy Design

Authors: Roberto Garrone
Published: 2025-11-24
Categories: cs.MA, cs.AI, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2511.19726v1

Multi-agent systems often operate under feedback, adaptation, and non-stationarity, yet many simulation studies retain static decision rules and fixed control parameters. This paper introduces a general adaptive multi-agent learning framework that integrates: (i) four dynamic regimes distinguishing static versus adaptive agents and fixed versus adaptive system parameters; (ii) information-theoretic diagnostics (entropy rate, statistical complexity, and predictive information) to assess predictability and structure; (iii) structural causal models for explicit intervention semantics; (iv) procedures for generating agent-level priors from aggregate or sample data; and (v) unsupervised methods for identifying emergent behavioral regimes. The framework offers a domain-neutral architecture for analyzing how learning agents and adaptive controls jointly shape system trajectories, enabling systematic comparison of stability, performance, and interpretability across non-equilibrium, oscillatory, or drifting dynamics. Mathematical definitions, computational operators, and an experimental design template are provided, yielding a structured methodology for developing explainable and contestable multi-agent decision processes.

---

### Individual and group fairness in geographical partitioning

Authors: Ilya O. Ryzhov, John Gunnar Carlsson, Yinchu Zhu
Published: 2025-11-24
Categories: econ.EM, cs.LG
arXiv: https://arxiv.org/abs/2511.19722v1

Socioeconomic segregation often arises in school districting and other contexts, causing some groups to be over- or under-represented within a particular district. This phenomenon is closely linked with disparities in opportunities and outcomes. We formulate a new class of geographical partitioning problems in which the population is heterogeneous, and it is necessary to ensure fair representation for each group at each facility. We prove that the optimal solution is a novel generalization of the additively weighted Voronoi diagram, and we propose a simple and efficient algorithm to compute it, thus resolving an open question dating back to Dvoretzky et al. (1951). The efficacy and potential for practical insight of the approach are demonstrated in a realistic case study involving seven demographic groups and $78$ district offices.

---

### Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian

Authors: Mobina Mehrazar, Mohammad Amin Yousefi, Parisa Abolfath Beygi, Behnam Bahrak
Published: 2025-11-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.19719v1

Large language models (LLMs) are increasingly used to generate self-explanations alongside their predictions, a practice that raises concerns about the faithfulness of these explanations, especially in low-resource languages. This study evaluates the faithfulness of LLM-generated explanations in the context of emotion classification in Persian, a low-resource language, by comparing the influential words identified by the model against those identified by human annotators. We assess faithfulness using confidence scores derived from token-level log-probabilities. Two prompting strategies, differing in the order of explanation and prediction (Predict-then-Explain and Explain-then-Predict), are tested for their impact on explanation faithfulness. Our results reveal that while LLMs achieve strong classification performance, their generated explanations often diverge from faithful reasoning, showing greater agreement with each other than with human judgments. These results highlight the limitations of current explanation methods and metrics, emphasizing the need for more robust approaches to ensure LLM reliability in multilingual and low-resource contexts.

---

### Rethinking Vision Transformer Depth via Structural Reparameterization

Authors: Chengwei Zhou, Vipin Chaudhary, Gourav Datta
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19718v1

The computational overhead of Vision Transformers in practice stems fundamentally from their deep architectures, yet existing acceleration strategies have primarily targeted algorithmic-level optimizations such as token pruning and attention speedup. This leaves an underexplored research question: can we reduce the number of stacked transformer layers while maintaining comparable representational capacity? To answer this, we propose a branch-based structural reparameterization technique that operates during the training phase. Our approach leverages parallel branches within transformer blocks that can be systematically consolidated into streamlined single-path models suitable for inference deployment. The consolidation mechanism works by gradually merging branches at the entry points of nonlinear components, enabling both feed-forward networks (FFN) and multi-head self-attention (MHSA) modules to undergo exact mathematical reparameterization without inducing approximation errors at test time. When applied to ViT-Tiny, the framework successfully reduces the original 12-layer architecture to 6, 4, or as few as 3 layers while maintaining classification accuracy on ImageNet-1K. The resulting compressed models achieve inference speedups of up to 37% on mobile CPU platforms. Our findings suggest that the conventional wisdom favoring extremely deep transformer stacks may be unnecessarily restrictive, and point toward new opportunities for constructing efficient vision transformers.

---

### Large Scale Community-Aware Network Generation

Authors: Vikram Ramavarapu, João Alfredo Cardoso Lamy, Mohammad Dindoost, David A. Bader
Published: 2025-11-24
Categories: cs.SI, cs.LG
arXiv: https://arxiv.org/abs/2511.19717v1

Community detection, or network clustering, is used to identify latent community structure in networks. Due to the scarcity of labeled ground truth in real-world networks, evaluating these algorithms poses significant challenges. To address this, researchers use synthetic network generators that produce networks with ground-truth community labels. RECCS is one such algorithm that takes a network and its clustering as input and generates a synthetic network through a modular pipeline. Each generated ground truth cluster preserves key characteristics of the corresponding input cluster, including connectivity, minimum degree, and degree sequence distribution. The output consists of a synthetically generated network, and disjoint ground truth cluster labels for all nodes. In this paper, we present two enhanced versions: RECCS+ and RECCS++. RECCS+ maintains algorithmic fidelity to the original RECCS while introducing parallelization through an orchestrator that coordinates algorithmic components across multiple processes and employs multithreading. RECCS++ builds upon this foundation with additional algorithmic optimizations to achieve further speedup. Our experimental results demonstrate that RECCS+ and RECCS++ achieve speedups of up to 49x and 139x respectively on our benchmark datasets, with RECCS++'s additional performance gains involving a modest accuracy tradeoff. With this newfound performance, RECCS++ can now scale to networks with over 100 million nodes and nearly 2 billion edges.

---

### Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability

Authors: Mitchell Scott, Tianshi Xu, Ziyuan Tang, Alexandra Pichette-Emmons, Qiang Ye, Yousef Saad, Yuanzhe Xi
Published: 2025-11-24
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2511.19716v3

Stochastic Gradient Descent (SGD) often slows in the late stage of training due to anisotropic curvature and gradient noise. We analyze preconditioned SGD in the geometry induced by a symmetric positive definite matrix $\mathbf{M}$, deriving bounds in which both the convergence rate and the stochastic noise floor are governed by $\mathbf{M}$-dependent quantities: the rate through an effective condition number in the $\mathbf{M}$-metric, and the floor through the product of that condition number and the preconditioned noise level. For nonconvex objectives, we establish a preconditioner-dependent basin-stability guarantee: when smoothness and basin size are measured in the $\mathbf{M}$-norm, the probability that the iterates remain in a well-behaved local region admits an explicit lower bound. This perspective is particularly relevant in Scientific Machine Learning (SciML), where achieving small training loss under stochastic updates is closely tied to physical fidelity, numerical stability, and constraint satisfaction. The framework applies to both diagonal/adaptive and curvature-aware preconditioners and yields a simple design principle: choose $\mathbf{M}$ to improve local conditioning while attenuating noise. Experiments on a quadratic diagnostic and three SciML benchmarks validate the predicted rate-floor behavior.

---

### CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation

Authors: Jinyu Liu, Gang Tan, Kiwan Maeng
Published: 2025-11-24
Categories: cs.CR, cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2511.19711v2

MPC-based ML uses multi-party computation (MPC) to run machine learning (ML) workloads across multiple parties without each having to share their private data or model parameters. However, existing frameworks frequently degrade accuracy and performance due to a series of MPC-specific transformations that add errors and overheads. These transformations are mostly opaque to users, making it hard to find and/or optimize problematic transformations. We propose CrypTorch, a modular, extensible, and iteratively-testable compiler framework for MPC-based ML. CrypTorch splits MPC-specific transformations into modular compilation stages, allowing users to easily inspect and optimize them. CrypTorch emits an executable graph after each transformation, allowing iterative testing to pinpoint any problematic transformations. Building on these features, CrypTorch automatically chooses a set of transformations from a pool of choices to balance performance and accuracy during the operator approximation stage, which we identified as the biggest contributor to accuracy/performance degradation. CrypTorch's auto-tuning alone provides 1.21-1.5x speedup without accuracy loss, and 1.33-1.74x speedup when some accuracy degradation is allowed. Combined with better engineering and adoption of state-of-the-art practices (made easier due to CrypTorch's modular design), CrypTorch brings 3.74-8.32x end-to-end speedup compared to the popular CrypTen. CrypTorch is built as an extension to PyTorch 2's compiler.

---

### Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor

Authors: Adele Myers Lantow, Nina Miolane
Published: 2025-11-24
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2511.19706v2

Rotation invariance is a fundamental requirement across many computer vision tasks. Historically, this inductive bias has been encoded through hand-crafted rotation-invariant representations. These are compact, interpretable, and fast to compute, but they come at the cost of descriptive power. More recently, architectures achieve inductive bias through learned representations. These are highly descriptive and achieve strong empirical performance, at the cost of efficiency and interpretability. In this work, we propose an alternative at the intersection of both paradigms. We introduce the selective disk bispectrum (SDB), a complex-valued rotation-invariant vector that preserves all information about the image except its orientation. Our key theoretical contributions are the selective disk bispectrum, its inversion, its (reduced) spatial and computational complexities (compared to the full disk bispectrum), and its expectation and variance under noise. Furthermore, we propose a numerical SDB approximation and provide theoretical guarantees for its accuracy and rotation invariance. Empirically, we validate SDB's invariance and robustness to noise classification tasks. We test our reconstruction algorithm on multi-reference alignment of rotated images.

---

### CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding

Authors: Ziteng Sun, Adrian Benton, Samuel Kushnir, Asher Trockman, Vikas Singh, Suhas Diggavi, Ananda Theertha Suresh
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19705v1

Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization level scheme. However, this often introduces large errors due to outliers in the weights. Proposed mitigation mechanisms include applying adaptive rounding, random rotation transformations or committing to a post-training target using calibration data. Unfortunately, this reliance on calibration data can be severely limiting in some real-world scenarios as such data may be unavailable or subject to privacy regulations. In this paper, we propose algorithms to optimize transformations and adaptive rounding without access to any calibration data. The optimization is achieved by designing a suitable proxy function for the quantization loss without calibration data. To maintain inference efficiency, we perform structured matrix transformations for single matrices. For paired weights that interact directly in the computation graph, we use dual matrix transformations and adaptive rounding methods. We conduct experiments on Gemma 2 models, and observe consistent improvement over the baselines. For Gemma 2 9B quantization, our method improves the average benchmark score from 61.9 to 62.4 for 4-bit quantization and from 52.0 to 60.6 for 3-bit quantization, while adding less than 3% of computation overhead. Furthermore, our method achieves performance comparable to the commonly used GPTQ method, which requires calibration data.

---

### RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models

Authors: Omar Alama, Darshil Jariwala, Avigyan Bhattacharya, Seungchan Kim, Wenshan Wang, Sebastian Scherer
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19704v2

Open-vocabulary semantic segmentation (OVSS) underpins many vision and robotics tasks that require generalizable semantic understanding. Existing approaches either rely on limited segmentation training data, which hinders generalization, or apply zero-shot heuristics to vision-language models (e.g CLIP), while the most competitive approaches combine multiple models to improve performance at the cost of high computational and memory demands. In this work, we leverage an overlooked agglomerative vision foundation model, RADIO, to improve zero-shot OVSS along three key axes simultaneously: mIoU, latency, and parameter efficiency. We present the first comprehensive study of RADIO for zero-shot OVSS and enhance its performance through self-correlating recursive attention, self-correlating global aggregation, and computationally efficient RADIO SAM mask refinement. Our approach, RADSeg, achieves 6-30% mIoU improvement in the base ViT class while being 3.95x faster and using 2.5x fewer parameters. Surprisingly, RADSeg-base (106M) outperforms previous combinations of huge vision models (850-1350M) in mIoU, achieving state-of-the-art accuracy with substantially lower computational and memory cost.

---

### The Alexander-Hirschowitz theorem for neurovarieties

Authors: A. Massarenti, M. Mella
Published: 2025-11-24
Categories: math.AG, cs.AI, cs.LG, math.AC
arXiv: https://arxiv.org/abs/2511.19703v2

We study the dimension and identifiability of neurovarieties associated to polynomial neural networks. We give an independent geometric proof that the linear bounds $d_i\geq 2n_i-1$ on the activation degrees imply non defectiveness for any number of outputs, a dimension statement previously obtained from finite identifiability. The proof is based on a direct analysis of the differential of the parameterization. We also investigate secant and Grassmann-secant obstructions outside this range and prove global identifiability for multi-output architectures under the same degree bounds.

---

### A Layered Protocol Architecture for the Internet of Agents

Authors: Charles Fleming, Luca Muscariello, Vijoy Pandey, Ramana Kompella
Published: 2025-11-24
Categories: cs.NI, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2511.19699v3

Large Language Models (LLMs) have demonstrated remarkable performance improvements and the ability to learn domain-specific languages (DSLs), including APIs and tool interfaces. This capability has enabled the creation of AI agents that can perform preliminary computations and act through tool calling, which is now being standardized via protocols like MCP. However, LLMs face fundamental limitations: their context windows cannot grow indefinitely, restricting their memory and computational capacity. Agent collaboration emerges as essential for solving increasingly complex problems, mirroring how computational systems rely on different types of memory to scale. The "Internet of Agents" (IoA) represents the communication stack that enables agents to scale by distributing computation across collaborating entities. Current network architectural stacks (OSI and TCP/IP) were designed for data delivery between hosts and processes, not for agent collaboration with semantic understanding. To address this gap, we propose two new layers: an Agent Communication Layer (L8) and an Agent Semantic Layer (L9). L8 formalizes the structure of communication, standardizing message envelopes, speech-act performatives (e.g., REQUEST, INFORM), and interaction patterns (e.g., request-reply, publish-subscribe), building on protocols like MCP. The proposed L9 layer: (1) formalizes semantic context discovery and negotiation, (2) provides semantic grounding by binding terms to semantic context, and (3) semantically validates incoming prompts and performs disambiguation as needed. Furthermore, L9 introduces primitives for coordination and consensus, allowing agents to achieve alignment on shared states, collective goals, and distributed beliefs. Together, these layers provide the foundation for scalable, distributed agent collaboration, enabling the next generation of multi-agentic systems.

---

### TiCT: A Synthetically Pre-Trained Foundation Model for Time Series Classification

Authors: Chin-Chia Michael Yeh, Uday Singh Saini, Junpeng Wang, Xin Dai, Xiran Fan, Jiarui Sun, Yujie Fan, Yan Zheng
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.19694v2

The ubiquity of time series data creates a strong demand for general-purpose foundation models, yet developing them for classification remains a significant challenge, largely due to the high cost of labeled data. Foundation models capable of in-context learning (ICL) offer a powerful solution, adapting to new tasks with minimal examples and reducing the need for extensive retraining. However, prior work on large-scale time series models has predominantly focused on forecasting, leaving a critical gap for versatile, fine-tuning-free classification. To address this, we introduce TiCT (Time-series in-Context Transformer), a transformer-based model pre-trained exclusively on synthetic data to perform in-context classification. We make two primary technical contributions: 1) a novel architecture featuring a scalable bit-based label encoding and a special output attention mechanism to handle an arbitrary number of classes; and 2) a synthetic pre-training framework that combines a Mixup-inspired process with data augmentation to foster generalization and noise invariance. Extensive evaluations on the UCR Archive show that TiCT achieves competitive performance against state-of-the-art supervised methods. Crucially, this is accomplished using only in-context examples at inference time, without updating a single model weight.

---

### TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding

Authors: Chin-Chia Michael Yeh, Uday Singh Saini, Xin Dai, Xiran Fan, Shubham Jain, Yujie Fan, Jiarui Sun, Junpeng Wang, Menghai Pan, Yingtong Dou, Yuzhong Chen, Vineeth Rakesh et al.
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.19693v3

Payment networks form the backbone of modern commerce, generating high volumes of transaction records from daily activities. Properly modeling this data can enable applications such as abnormal behavior detection and consumer-level insights for hyper-personalized experiences, ultimately improving people's lives. In this paper, we present TREASURE, TRansformer Engine As Scalable Universal transaction Representation Encoder, a multipurpose transformer-based foundation model specifically designed for transaction data. The model simultaneously captures both consumer behavior and payment network signals (such as response codes and system flags), providing comprehensive information necessary for applications like accurate recommendation systems and abnormal behavior detection. Verified with industry-grade datasets, TREASURE features three key capabilities: 1) an input module with dedicated sub-modules for static and dynamic attributes, enabling more efficient training and inference; 2) an efficient and effective training paradigm for predicting high-cardinality categorical attributes; and 3) demonstrated effectiveness as both a standalone model that increases abnormal behavior detection performance by 111% over production systems and an embedding provider that enhances recommendation models by 104%. We present key insights from extensive ablation studies, benchmarks against production models, and case studies, highlighting valuable knowledge gained from developing TREASURE.

---

### CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimation

Authors: Abdurahman Ali Mohammed, Wallapak Tavanapong, Catherine Fonder, Donald S. Sakaguchi
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19686v1

Cell counting in biomedical imaging is pivotal for various clinical applications, yet the interpretability of deep learning models in this domain remains a significant challenge. We propose a novel prototype-based method for interpretable cell counting via density map estimation. Our approach integrates a prototype layer into the density estimation network, enabling the model to learn representative visual patterns for both cells and background artifacts. The learned prototypes were evaluated through a survey of biologists, who confirmed the relevance of the visual patterns identified, further validating the interpretability of the model. By generating interpretations that highlight regions in the input image most similar to each prototype, our method offers a clear understanding of how the model identifies and counts cells. Extensive experiments on two public datasets demonstrate that our method achieves interpretability without compromising counting effectiveness. This work provides researchers and clinicians with a transparent and reliable tool for cell counting, potentially increasing trust and accelerating the adoption of deep learning in critical biomedical applications. Code is available at https://github.com/NRT-D4/CountXplain.

---

### IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants

Authors: Vivek Chavan, Yasmina Imgrund, Tung Dao, Sanwantri Bai, Bosong Wang, Ze Lu, Oliver Heimann, Jörg Krüger
Published: 2025-11-24
Categories: cs.CV, cs.AI, cs.HC, cs.RO
arXiv: https://arxiv.org/abs/2511.19684v1

We introduce IndEgo, a multimodal egocentric and exocentric dataset addressing common industrial tasks, including assembly/disassembly, logistics and organisation, inspection and repair, woodworking, and others. The dataset contains 3,460 egocentric recordings (approximately 197 hours), along with 1,092 exocentric recordings (approximately 97 hours). A key focus of the dataset is collaborative work, where two workers jointly perform cognitively and physically intensive tasks. The egocentric recordings include rich multimodal data and added context via eye gaze, narration, sound, motion, and others. We provide detailed annotations (actions, summaries, mistake annotations, narrations), metadata, processed outputs (eye gaze, hand pose, semi-dense point cloud), and benchmarks on procedural and non-procedural task understanding, Mistake Detection, and reasoning-based Question Answering. Baseline evaluations for Mistake Detection, Question Answering and collaborative task understanding show that the dataset presents a challenge for the state-of-the-art multimodal models. Our dataset is available at: https://huggingface.co/datasets/FraunhoferIPK/IndEgo

---

### INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models

Authors: Parsa Madinei, Ryan Solgi, Ziqi Wen, Jonathan Skaza, Miguel Eckstein, Ramtin Pedarsani
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19676v1

We introduce INTERLACE, a novel framework that prunes redundant layers in VLMs while maintaining performance through sample-efficient finetuning. Existing layer pruning methods lead to significant performance drop when applied to VLMs. Instead, we analyze triplets of consecutive layers to identify local redundancy, removing the most redundant of the first two layers, finetune the remaining layer to compensate for the lost capacity, and freeze the third layer to serve as a stable anchor during finetuning. We found that this interleaved finetune-freeze design enables rapid convergence with minimal data after pruning. By finetuning only a subset of layers on just 1% of the FineVision dataset for one epoch, Interlace achieves 88.9% average performance retention after dropping 25% of the network, achieving SOTA performance. Our code is available at: https://github.com/pmadinei/Interlace.git

---

### FISCAL: Financial Synthetic Claim-document Augmented Learning for Efficient Fact-Checking

Authors: Rishab Sharma, Iman Saberi, Elham Alipour, Jie JW Wu, Fatemeh Fard
Published: 2025-11-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.19671v1

Financial applications of large language models (LLMs) require factual reliability and computational efficiency, yet current systems often hallucinate details and depend on prohibitively large models. We propose FISCAL (Financial Synthetic Claim-Document Augmented Learning), a modular framework for generating synthetic data tailored to financial fact-checking. Using FISCAL, we generate a dataset called FISCAL-data and use it to train MiniCheck-FISCAL, a lightweight verifier for numerical financial claims. MiniCheck-FISCAL outperforms its baseline, surpasses GPT-3.5 Turbo and other open-source peers of similar size, and approaches the accuracy of much larger systems (20x), such as Mixtral-8x22B and Command R+. On external datasets FinDVer and Fin-Fact, it rivals GPT-4o and Claude-3.5 while outperforming Gemini-1.5 Flash. These results show that domain-specific synthetic data, combined with efficient fine-tuning, enables compact models to achieve state-of-the-art accuracy, robustness, and scalability for practical financial AI. The dataset and scripts are available in the project repository (link provided in the paper).

---

### HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimization

Authors: Souradip Poddar, Chia-Tung Ho, Ziming Wei, Weidong Cao, Haoxing Ren, David Z. Pan
Published: 2025-11-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.19669v2

Conventional AI-driven AMS design automation algorithms remain constrained by their reliance on high-quality datasets to capture underlying circuit behavior, coupled with poor transferability across architectures, and a lack of adaptive mechanisms. This work proposes HeaRT, a hierarchical circuit reasoning-based agentic framework for automation loops and a step toward adaptive, human-style design optimization. HeaRT consistently improves F1(subcircuits) by >= 13.5% and F1(loops) by >= 37.8% over few-shot prompting baselines across multiple LLM backbones on our 40-circuit AMS benchmark of flattened SPICE netlists, even as circuit complexity increases. Our experiments further show that HeaRT achieves >= 3x faster convergence in incremental design adaptation tasks under specification shifts across diverse optimization approaches, supporting both topology reconfiguration and sizing.

---

### OncoVision: Integrating Mammography and Clinical Data through Attention-Driven Multimodal AI for Enhanced Breast Cancer Diagnosis

Authors: Istiak Ahmed, Galib Ahmed, K. Shahriar Sanjid, Md. Tanzim Hossain, Md. Nishan Khan, Md. Misbah Khan, Md. Arifur Rahman, Sheikh Anisul Haque, Sharmin Akhtar Rupa, Mohammed Mejbahuddin Mia, Mahmud Hasan Mostofa Kamal, Md. Mostafa Kamal Sarker et al.
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19667v2

OncoVision is a privileged-information training framework that uses mammography images and clinical features during training and performs inference from mammographic images alone. Employing an attention-based encoder-decoder backbone, it jointly segments four regions of interest (masses, calcifications, axillary findings, and breast tissue) with accuracy exceeding the nnU-Net baseline and predicts ten structured clinical features, including BI-RADS category. We developed two late-fusion strategies, Independent and Dependent, that integrate imaging, radiomic, and clinical information during training to improve diagnostic precision and potentially reduce inter-observer variability. Radiomic features extracted from predicted masks provide shape, intensity, and texture descriptors that complement the learned CNN representations. We evaluated OncoVision in a retrospective multi-reader study with six board-certified radiologists, assessing diagnostic confidence, reading time, and segmentation accuracy with and without AI assistance. In a paired reader-assistance evaluation, OncoVision was associated with higher diagnostic confidence for junior and senior radiologists, reduced reading time by up to 61%, and achieved segmentation accuracy comparable to or exceeding that of radiologists for mass lesions. We operationalized OncoVision as a secure web application, now deployed at a partner hospital, that generates structured reports with dual-confidence scoring and attention-weighted visualizations for real-time diagnostic support. The platform is designed for integration into clinical workflows, with the goal of supporting screening access in underprivileged regions. By combining accurate segmentation with clinical intuition, OncoVision advances AI-assisted mammographic interpretation, offering a scalable and accessible approach to earlier and more consistent image interpretation.

---