# Research Papers — 2025-11 · bundle page 70 of 197

> Full-text markdown of papers #3451–3500 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/70
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/69.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/71.md)

### NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening

Authors: Misaal Khan, Mayank Vatsa, Kuldeep Singh, Richa Singh
Published: 2025-11-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.16566v1

Child malnutrition remains a global crisis, yet existing screening methods are laborious and poorly scalable, hindering early intervention. In this work, we present NutriScreener, a retrieval-augmented, multi-pose graph attention network that combines CLIP-based visual embeddings, class-boosted knowledge retrieval, and context awareness to enable robust malnutrition detection and anthropometric prediction from children's images, simultaneously addressing generalizability and class imbalance. In a clinical study, doctors rated it 4.3/5 for accuracy and 4.6/5 for efficiency, confirming its deployment readiness in low-resource settings. Trained and tested on 2,141 children from AnthroVision and additionally evaluated on diverse cross-continent populations, including ARAN and an in-house collected CampusPose dataset, it achieves 0.79 recall, 0.82 AUC, and significantly lower anthropometric RMSEs, demonstrating reliable measurement in unconstrained pediatric settings. Cross-dataset results show up to 25% recall gain and up to 3.5 cm RMSE reduction using demographically matched knowledge bases. NutriScreener offers a scalable and accurate solution for early malnutrition detection in low-resource environments.

---

### Interfacial and bulk switching MoS2 memristors for an all-2D reservoir computing framework

Authors: Asmita S. Thool, Sourodeep Roy, Prahalad Kanti Barman, Kartick Biswas, Pavan Nukala, Abhishek Misra, Saptarshi Das, and Bhaswar Chakrabarti
Published: 2025-11-20
Categories: cs.ET, cs.AI
arXiv: https://arxiv.org/abs/2511.16557v1

In this study, we design a reservoir computing (RC) network by exploiting short- and long-term memory dynamics in Au/Ti/MoS$_2$/Au memristive devices. The temporal dynamics is engineered by controlling the thickness of the Chemical Vapor Deposited (CVD) MoS$_2$ films. Devices with a monolayer (1L)-MoS$_2$ film exhibit volatile (short-term memory) switching dynamics. We also report non-volatile resistance switching with excellent uniformity and analog behavior in conductance tuning for the multilayer (ML) MoS$_2$ memristive devices. We correlate this performance with trap-assisted space-charge limited conduction (SCLC) mechanism, leading to a bulk-limited resistance switching behavior. Four-bit reservoir states are generated using volatile memristors. The readout layer is implemented with an array of nonvolatile synapses. This small RC network achieves 89.56\% precision in a spoken-digit recognition task and is also used to analyze a nonlinear time series equation.

---

### Lite Any Stereo: Efficient Zero-Shot Stereo Matching

Authors: Junpeng Jing, Weixun Luo, Ye Mao, Krystian Mikolajczyk
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16555v3

Recent advances in stereo matching have focused on accuracy, often at the cost of significantly increased model size. Traditionally, the community has regarded efficient models as incapable of zero-shot ability due to their limited capacity. In this paper, we introduce Lite Any Stereo, a stereo depth estimation framework that achieves strong zero-shot generalization while remaining highly efficient. To this end, we design a compact yet expressive backbone to ensure scalability, along with a carefully crafted hybrid cost aggregation module. We further propose a three-stage training strategy on million-scale data to effectively bridge the sim-to-real gap. Together, these components demonstrate that an ultra-light model can deliver strong generalization, ranking 1st across four widely used real-world benchmarks. Remarkably, our model attains accuracy comparable to or exceeding state-of-the-art non-prior-based accurate methods while requiring less than 1% computational cost, setting a new standard for efficient stereo matching.

---

### Lite Any Stereo: Efficient Zero-Shot Stereo Matching

Authors: Junpeng Jing, Weixun Luo, Ye Mao, Krystian Mikolajczyk
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16555v1

Recent advances in stereo matching have focused on accuracy, often at the cost of significantly increased model size. Traditionally, the community has regarded efficient models as incapable of zero-shot ability due to their limited capacity. In this paper, we introduce Lite Any Stereo, a stereo depth estimation framework that achieves strong zero-shot generalization while remaining highly efficient. To this end, we design a compact yet expressive backbone to ensure scalability, along with a carefully crafted hybrid cost aggregation module. We further propose a three-stage training strategy on million-scale data to effectively bridge the sim-to-real gap. Together, these components demonstrate that an ultra-light model can deliver strong generalization, ranking 1st across four widely used real-world benchmarks. Remarkably, our model attains accuracy comparable to or exceeding state-of-the-art non-prior-based accurate methods while requiring less than 1% computational cost, setting a new standard for efficient stereo matching.

---

### Toward Valid Generative Clinical Trial Data with Survival Endpoints

Authors: Perrine Chassat, Van Tuan Nguyen, Lucas Ducrot, Emilie Lanoy, Agathe Guilloux
Published: 2025-11-20
Categories: cs.LG, stat.AP, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2511.16551v1

Clinical trials face mounting challenges: fragmented patient populations, slow enrollment, and unsustainable costs, particularly for late phase trials in oncology and rare diseases. While external control arms built from real-world data have been explored, a promising alternative is the generation of synthetic control arms using generative AI. A central challenge is the generation of time-to-event outcomes, which constitute primary endpoints in oncology and rare disease trials, but are difficult to model under censoring and small sample sizes. Existing generative approaches, largely GAN-based, are data-hungry, unstable, and rely on strong assumptions such as independent censoring. We introduce a variational autoencoder (VAE) that jointly generates mixed-type covariates and survival outcomes within a unified latent variable framework, without assuming independent censoring. Across synthetic and real trial datasets, we evaluate our model in two realistic scenarios: (i) data sharing under privacy constraints, where synthetic controls substitute for original data, and (ii) control-arm augmentation, where synthetic patients mitigate imbalances between treated and control groups. Our method outperforms GAN baselines on fidelity, utility, and privacy metrics, while revealing systematic miscalibration of type I error and power. We propose a post-generation selection procedure that improves calibration, highlighting both progress and open challenges for generative survival modeling.

---

### Broad stochastic configuration residual learning system for norm-convergent universal approximation

Authors: Han Su, Zhongyan Li, Wanquan Liu
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16550v1

Universal approximation serves as the foundation of neural network learning algorithms. However, some networks establish their universal approximation property by demonstrating that the iterative errors converge in probability measure rather than the more rigorous norm convergence, which makes the universal approximation property of randomized learning networks highly sensitive to random parameter selection, Broad residual learning system (BRLS), as a member of randomized learning models, also encounters this issue. We theoretically demonstrate the limitation of its universal approximation property, that is, the iterative errors do not satisfy norm convergence if the selection of random parameters is inappropriate and the convergence rate meets certain conditions. To address this issue, we propose the broad stochastic configuration residual learning system (BSCRLS) algorithm, which features a novel supervisory mechanism adaptively constraining the range settings of random parameters on the basis of BRLS framework, Furthermore, we prove the universal approximation theorem of BSCRLS based on the more stringent norm convergence. Three versions of incremental BSCRLS algorithms are presented to satisfy the application requirements of various network updates. Solar panels dust detection experiments are performed on publicly available dataset and compared with 13 deep and broad learning algorithms. Experimental results reveal the effectiveness and superiority of BSCRLS algorithms.

---

### FairLRF: Achieving Fairness through Sparse Low Rank Factorization

Authors: Yuanbo Guo, Jun Xia, Yiyu Shi
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16549v2

As deep learning (DL) techniques become integral to various applications, ensuring model fairness while maintaining high performance has become increasingly critical, particularly in sensitive fields such as medical diagnosis. Although a variety of bias-mitigation methods have been proposed, many rely on computationally expensive debiasing strategies or suffer substantial drops in model accuracy, which limits their practicality in real-world, resource-constrained settings. To address this issue, we propose a fairness-oriented low rank factorization (LRF) framework that leverages singular value decomposition (SVD) to improve DL model fairness. Unlike traditional SVD, which is mainly used for model compression by decomposing and reducing weight matrices, our work shows that SVD can also serve as an effective tool for fairness enhancement. Specifically, we observed that elements in the unitary matrices obtained from SVD contribute unequally to model bias across groups defined by sensitive attributes. Motivated by this observation, we propose a method, named FairLRF, that selectively removes bias-inducing elements from unitary matrices to reduce group disparities, thus enhancing model fairness. Extensive experiments show that our method outperforms conventional LRF methods as well as state-of-the-art fairness-enhancing techniques in terms of improving fairness while maintaining accuracy. Additionally, an ablation study examines how major hyper-parameters may influence the performance of processed models. To the best of our knowledge, this is the first work utilizing SVD not primarily for compression but for fairness enhancement of DL classifications.

---

### FairLRF: Achieving Fairness through Sparse Low Rank Factorization

Authors: Yuanbo Guo, Jun Xia, Yiyu Shi
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16549v1

As deep learning (DL) techniques become integral to various applications, ensuring model fairness while maintaining high performance has become increasingly critical, particularly in sensitive fields such as medical diagnosis. Although a variety of bias-mitigation methods have been proposed, many rely on computationally expensive debiasing strategies or suffer substantial drops in model accuracy, which limits their practicality in real-world, resource-constrained settings. To address this issue, we propose a fairness-oriented low rank factorization (LRF) framework that leverages singular value decomposition (SVD) to improve DL model fairness. Unlike traditional SVD, which is mainly used for model compression by decomposing and reducing weight matrices, our work shows that SVD can also serve as an effective tool for fairness enhancement. Specifically, we observed that elements in the unitary matrices obtained from SVD contribute unequally to model bias across groups defined by sensitive attributes. Motivated by this observation, we propose a method, named FairLRF, that selectively removes bias-inducing elements from unitary matrices to reduce group disparities, thus enhancing model fairness. Extensive experiments show that our method outperforms conventional LRF methods as well as state-of-the-art fairness-enhancing techniques. Additionally, an ablation study examines how major hyper-parameters may influence the performance of processed models. To the best of our knowledge, this is the first work utilizing SVD not primarily for compression but for fairness enhancement.

---

### Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes

Authors: Guanchen Wu, Yuzhang Xie, Huanwei Wu, Zhe He, Hui Shao, Xiao Hu, Carl Yang
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16548v1

Integrating novel medical concepts and relationships into existing ontologies can significantly enhance their coverage and utility for both biomedical research and clinical applications. Clinical notes, as unstructured documents rich with detailed patient observations, offer valuable context-specific insights and represent a promising yet underutilized source for ontology extension. Despite this potential, directly leveraging clinical notes for ontology extension remains largely unexplored. To address this gap, we propose CLOZE, a novel framework that uses large language models (LLMs) to automatically extract medical entities from clinical notes and integrate them into hierarchical medical ontologies. By capitalizing on the strong language understanding and extensive biomedical knowledge of pre-trained LLMs, CLOZE effectively identifies disease-related concepts and captures complex hierarchical relationships. The zero-shot framework requires no additional training or labeled data, making it a cost-efficient solution. Furthermore, CLOZE ensures patient privacy through automated removal of protected health information (PHI). Experimental results demonstrate that CLOZE provides an accurate, scalable, and privacy-preserving ontology extension framework, with strong potential to support a wide range of downstream applications in biomedical research and clinical informatics.

---

### Progressive Supernet Training for Efficient Visual Autoregressive Modeling

Authors: Xiaoyue Chen, Yuling Shi, Kaiyuan Li, Huandong Wang, Yong Li, Xiaodong Gu, Xinlei Chen, Mingbao Lin
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16546v1

Visual Auto-Regressive (VAR) models significantly reduce inference steps through the "next-scale" prediction paradigm. However, progressive multi-scale generation incurs substantial memory overhead due to cumulative KV caching, limiting practical deployment. We observe a scale-depth asymmetric dependency in VAR: early scales exhibit extreme sensitivity to network depth, while later scales remain robust to depth reduction. Inspired by this, we propose VARiant: by equidistant sampling, we select multiple subnets ranging from 16 to 2 layers from the original 30-layer VAR-d30 network. Early scales are processed by the full network, while later scales utilize subnet. Subnet and the full network share weights, enabling flexible depth adjustment within a single model. However, weight sharing between subnet and the entire network can lead to optimization conflicts. To address this, we propose a progressive training strategy that breaks through the Pareto frontier of generation quality for both subnets and the full network under fixed-ratio training, achieving joint optimality. Experiments on ImageNet demonstrate that, compared to the pretrained VAR-d30 (FID 1.95), VARiant-d16 and VARiant-d8 achieve nearly equivalent quality (FID 2.05/2.12) while reducing memory consumption by 40-65%. VARiant-d2 achieves 3.5 times speedup and 80% memory reduction at moderate quality cost (FID 2.97). In terms of deployment, VARiant's single-model architecture supports zero-cost runtime depth switching and provides flexible deployment options from high quality to extreme efficiency, catering to diverse application scenarios.

---

### WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue

Authors: Zachary Ellis, Jared Joselowitz, Yash Deo, Yajie He, Anna Kalygina, Aisling Higham, Mana Rahimzadeh, Yan Jia, Ibrahim Habli, Ernest Lim
Published: 2025-11-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.16544v3

As Automatic Speech Recognition (ASR) is increasingly deployed in clinical dialogue, standard evaluations still rely heavily on Word Error Rate (WER). This paper challenges that standard, investigating whether WER or other common metrics correlate with the clinical impact of transcription errors. We establish a gold-standard benchmark by having expert clinicians compare ground-truth utterances to their ASR-generated counterparts, labeling the clinical impact of any discrepancies found in two distinct doctor-patient dialogue datasets. Our analysis reveals that WER and a comprehensive suite of existing metrics correlate poorly with the clinician-assigned risk labels (No, Minimal, or Significant Impact). To bridge this evaluation gap, we introduce an LLM-as-a-Judge, programmatically optimized using GEPA through DSPy to replicate expert clinical assessment. The optimized judge (Gemini-2.5-Pro) achieves human-comparable performance, obtaining 90% accuracy and a strong Cohen's kappa of 0.816. This work provides a validated, automated framework for moving ASR evaluation beyond simple textual fidelity to a necessary, scalable assessment of safety in clinical dialogue.

---

### WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue

Authors: Zachary Ellis, Jared Joselowitz, Yash Deo, Yajie He, Anna Kalygina, Aisling Higham, Mana Rahimzadeh, Yan Jia, Ibrahim Habli, Ernest Lim
Published: 2025-11-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.16544v1

As Automatic Speech Recognition (ASR) is increasingly deployed in clinical dialogue, standard evaluations still rely heavily on Word Error Rate (WER). This paper challenges that standard, investigating whether WER or other common metrics correlate with the clinical impact of transcription errors. We establish a gold-standard benchmark by having expert clinicians compare ground-truth utterances to their ASR-generated counterparts, labeling the clinical impact of any discrepancies found in two distinct doctor-patient dialogue datasets. Our analysis reveals that WER and a comprehensive suite of existing metrics correlate poorly with the clinician-assigned risk labels (No, Minimal, or Significant Impact). To bridge this evaluation gap, we introduce an LLM-as-a-Judge, programmatically optimized using GEPA to replicate expert clinical assessment. The optimized judge (Gemini-2.5-Pro) achieves human-comparable performance, obtaining 90% accuracy and a strong Cohen's $κ$ of 0.816. This work provides a validated, automated framework for moving ASR evaluation beyond simple textual fidelity to a necessary, scalable assessment of safety in clinical dialogue.

---

### The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation

Authors: Jiaheng Zhang, Daqiang Zhang
Published: 2025-11-20
Categories: cs.IR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.16543v2

The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. Inspired by knowledge distillation, Prism leverages a powerful, instruction-following teacher LLM (FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. Our extensive experiments on benchmark datasets reveal a key finding: the distillation process not only transfers knowledge but also acts as a noise filter. Our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, demonstrating an emergent ability to correct hallucinations present in the teacher's outputs. While achieving a 24x speedup and a 10x reduction in memory consumption, our analysis validates that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality, and perhaps more importantly, trustworthy explainable recommendation.

---

### The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation

Authors: Jiaheng Zhang, Daqiang Zhang
Published: 2025-11-20
Categories: cs.IR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.16543v1

The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. Inspired by knowledge distillation, Prism leverages a powerful teacher LLM (e.g., FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (e.g., BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. Extensive experiments on benchmark datasets demonstrate that our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, while achieving a 24 times speedup and a 10 times reduction in memory consumption during inference. These results validate that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality explainable recommendation.

---

### EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering

Authors: Pierrick Bournez, Luca Savant Aira, Thibaud Ehret, Gabriele Facciolo
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16542v2

Recently, 3D Gaussian Splatting has been introduced as a compelling alternative to NeRF for Earth observation, offering competitive reconstruction quality with significantly reduced training times. In this work, we extend the Earth Observation Gaussian Splatting (EOGS) framework to propose EOGS++, a novel method tailored for satellite imagery that directly operates on raw high-resolution panchromatic data without requiring external preprocessing. Furthermore, leveraging optical flow techniques we embed bundle adjustment directly within the training process, avoiding reliance on external optimization tools while improving camera pose estimation. We also introduce several improvements to the original implementation, including early stopping and TSDF post-processing, all contributing to sharper reconstructions and better geometric accuracy. Experiments on the IARPA 2016 and DFC2019 datasets demonstrate that EOGS++ achieves state-of-the-art performance in terms of reconstruction quality and efficiency, outperforming the original EOGS method and other NeRF-based methods while maintaining the computational advantages of Gaussian Splatting. Our model demonstrates an improvement from 1.33 to 1.19 mean MAE errors on buildings compared to the original EOGS models

---

### EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering

Authors: Pierrick Bournez, Luca Savant Aira, Thibaud Ehret, Gabriele Facciolo
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16542v1

Recently, 3D Gaussian Splatting has been introduced as a compelling alternative to NeRF for Earth observation, offering com- petitive reconstruction quality with significantly reduced training times. In this work, we extend the Earth Observation Gaussian Splatting (EOGS) framework to propose EOGS++, a novel method tailored for satellite imagery that directly operates on raw high-resolution panchromatic data without requiring external preprocessing. Furthermore, leveraging optical flow techniques we embed bundle adjustment directly within the training process, avoiding reliance on external optimization tools while improving camera pose estimation. We also introduce several improvements to the original implementation, including early stopping and TSDF post-processing, all contributing to sharper reconstructions and better geometric accuracy. Experiments on the IARPA 2016 and DFC2019 datasets demonstrate that EOGS++ achieves state-of-the-art performance in terms of reconstruction quality and effi- ciency, outperforming the original EOGS method and other NeRF-based methods while maintaining the computational advantages of Gaussian Splatting. Our model demonstrates an improvement from 1.33 to 1.19 mean MAE errors on buildings compared to the original EOGS models

---

### Supervised Contrastive Learning for Few-Shot AI-Generated Image Detection and Attribution

Authors: Jaime Álvarez Urueña, David Camacho, Javier Huertas Tato
Published: 2025-11-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.16541v2

The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem is compounded by the accelerated release cycle of novel generative models, which renders traditional detection approaches (reliant on periodic retraining) computationally infeasible and operationally impractical. This work proposes a novel two-stage detection framework designed to address the generalization challenge inherent in synthetic image detection. The first stage employs a vision deep learning model trained via supervised contrastive learning to extract discriminative embeddings from input imagery. Critically, this model was trained on a strategically partitioned subset of available generators, with specific architectures withheld from training to rigorously ablate cross-generator generalization capabilities. The second stage utilizes a k-nearest neighbors (k-NN) classifier operating on the learned embedding space, trained in a few-shot learning paradigm incorporating limited samples from previously unseen test generators. With merely 150 images per class in the few-shot learning regime, which are easily obtainable from current generation models, the proposed framework achieves an average detection accuracy of 91.3%, representing a 5.2 percentage point improvement over existing approaches . For the source attribution task, the proposed approach obtains improvements of of 14.70% and 4.27% in AUC and OSCR respectively on an open set classification context, marking a significant advancement toward robust, scalable forensic attribution systems capable of adapting to the evolving generative AI landscape without requiring exhaustive retraining protocols.

---

### Supervised Contrastive Learning for Few-Shot AI-Generated Image Detection and Attribution

Authors: Jaime Álvarez Urueña, David Camacho, Javier Huertas Tato
Published: 2025-11-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.16541v1

The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem is compounded by the accelerated release cycle of novel generative models, which renders traditional detection approaches (reliant on periodic retraining) computationally infeasible and operationally impractical. This work proposes a novel two-stage detection framework designed to address the generalization challenge inherent in synthetic image detection. The first stage employs a vision deep learning model trained via supervised contrastive learning to extract discriminative embeddings from input imagery. Critically, this model was trained on a strategically partitioned subset of available generators, with specific architectures withheld from training to rigorously ablate cross-generator generalization capabilities. The second stage utilizes a k-nearest neighbors (k-NN) classifier operating on the learned embedding space, trained in a few-shot learning paradigm incorporating limited samples from previously unseen test generators. With merely 150 images per class in the few-shot learning regime, which are easily obtainable from current generation models, the proposed framework achieves an average detection accuracy of 91.3\%, representing a 5.2 percentage point improvement over existing approaches . For the source attribution task, the proposed approach obtains improvements of of 14.70\% and 4.27\% in AUC and OSCR respectively on an open set classification context, marking a significant advancement toward robust, scalable forensic attribution systems capable of adapting to the evolving generative AI landscape without requiring exhaustive retraining protocols.

---

### Beyond Tokens in Language Models: Interpreting Activations through Text Genre Chunks

Authors: Éloïse Benito-Rodriguez, Einar Urdshals, Jasmina Nasufi, Nicky Pochinkov
Published: 2025-11-20
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.16540v1

Understanding Large Language Models (LLMs) is key to ensure their safe and beneficial deployment. This task is complicated by the difficulty of interpretability of LLM structures, and the inability to have all their outputs human-evaluated. In this paper, we present the first step towards a predictive framework, where the genre of a text used to prompt an LLM, is predicted based on its activations. Using Mistral-7B and two datasets, we show that genre can be extracted with F1-scores of up to 98% and 71% using scikit-learn classifiers. Across both datasets, results consistently outperform the control task, providing a proof of concept that text genres can be inferred from LLMs with shallow learning models.

---

### Investigating Optical Flow Computation: From Local Methods to a Multiresolution Horn-Schunck Implementation with Bilinear Interpolation

Authors: Haytham Ziani
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16535v1

This paper presents an applied analysis of local and global methods, with a focus on the Horn-Schunck algorithm for optical flow computation. We explore the theoretical and practical aspects of local approaches, such as the Lucas-Kanade method, and global techniques such as Horn-Schunck. Additionally, we implement a multiresolution version of the Horn-Schunck algorithm, using bilinear interpolation and prolongation to improve accuracy and convergence. The study investigates the effectiveness of these combined strategies in estimating motion between frames, particularly under varying image conditions.

---

### Enhancing Multi-Camera Gymnast Tracking Through Domain Knowledge Integration

Authors: Fan Yang, Shigeyuki Odashima, Shoichi Masui, Ikuo Kusajima, Sosuke Yamao, Shan Jiang
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16532v1

We present a robust multi-camera gymnast tracking, which has been applied at international gymnastics championships for gymnastics judging. Despite considerable progress in multi-camera tracking algorithms, tracking gymnasts presents unique challenges: (i) due to space restrictions, only a limited number of cameras can be installed in the gymnastics stadium; and (ii) due to variations in lighting, background, uniforms, and occlusions, multi-camera gymnast detection may fail in certain views and only provide valid detections from two opposing views. These factors complicate the accurate determination of a gymnast's 3D trajectory using conventional multi-camera triangulation. To alleviate this issue, we incorporate gymnastics domain knowledge into our tracking solution. Given that a gymnast's 3D center typically lies within a predefined vertical plane during \revised{much of their} performance, we can apply a ray-plane intersection to generate coplanar 3D trajectory candidates for opposing-view detections. More specifically, we propose a novel cascaded data association (DA) paradigm that employs triangulation to generate 3D trajectory candidates when cross-view detections are sufficient, and resort to the ray-plane intersection when they are insufficient. Consequently, coplanar candidates are used to compensate for uncertain trajectories, thereby minimizing tracking failures. The robustness of our method is validated through extensive experimentation, demonstrating its superiority over existing methods in challenging scenarios. Furthermore, our gymnastics judging system, equipped with this tracking method, has been successfully applied to recent Gymnastics World Championships, earning significant recognition from the International Gymnastics Federation.

---

### TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval

Authors: Özay Ezerceli, Mahmoud El Hussieni, Selva Taş, Reyhan Bayraktar, Fatma Betül Terzioğlu, Yusuf Çelebi, Yağız Asker
Published: 2025-11-20
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2511.16528v1

Neural information retrieval systems excel in high-resource languages but remain underexplored for morphologically rich, lower-resource languages such as Turkish. Dense bi-encoders currently dominate Turkish IR, yet late-interaction models -- which retain token-level representations for fine-grained matching -- have not been systematically evaluated. We introduce TurkColBERT, the first comprehensive benchmark comparing dense encoders and late-interaction models for Turkish retrieval. Our two-stage adaptation pipeline fine-tunes English and multilingual encoders on Turkish NLI/STS tasks, then converts them into ColBERT-style retrievers using PyLate trained on MS MARCO-TR. We evaluate 10 models across five Turkish BEIR datasets covering scientific, financial, and argumentative domains. Results show strong parameter efficiency: the 1.0M-parameter colbert-hash-nano-tr is 600$\times$ smaller than the 600M turkish-e5-large dense encoder while preserving over 71\% of its average mAP. Late-interaction models that are 3--5$\times$ smaller than dense encoders significantly outperform them; ColmmBERT-base-TR yields up to +13.8\% mAP on domain-specific tasks. For production-readiness, we compare indexing algorithms: MUVERA+Rerank is 3.33$\times$ faster than PLAID and offers +1.7\% relative mAP gain. This enables low-latency retrieval, with ColmmBERT-base-TR achieving 0.54 ms query times under MUVERA. We release all checkpoints, configs, and evaluation scripts. Limitations include reliance on moderately sized datasets ($\leq$50K documents) and translated benchmarks, which may not fully reflect real-world Turkish retrieval conditions; larger-scale MUVERA evaluations remain necessary.

---

### Contrastive vision-language learning with paraphrasing and negation

Authors: Kwun Ho Ngan, Saman Sadeghi Afgeh, Joe Townsend, Artur d'Avila Garcez
Published: 2025-11-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.16527v2

Contrastive vision-language models continue to be the dominant approach for image-text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks to align their image and text embeddings in a shared latent space. As a challenging case-study for neurosymbolic AI, recent results evaluating CLIP on negated or paraphrased text have shown mixed performance as these are difficult to define formally for text data. Negation produces the opposite meaning using various possible but small lexical changes. Paraphrasing may use very different textual expressions to denote essentially the same thing. As a result, learning of paraphrasing and negation together poses a significant challenge because of the above mismatch between changes in syntax and intended meaning expected to be captured by distances in embedding space. This paper proposes a new CLIP contrastive loss function capable of balancing the requirements of having both paraphrasing and negation. It applies training triplets consisting of original, paraphrased and negated text generated by multiple large language models to the evaluation of CLIP models. The approach, called SemCLIP, aims to learn semantically-relevant and simple embeddings, placing paraphrased captions nearer to the original image embeddings while at the same time pushing negated captions farther away. Empirically, SemCLIP is shown to be capable of preserving roughly the same performance as CLIP augmented with either negation or paraphrasing. Although direct comparisons are difficult to make because the problem of learning with both negation and paraphrasing is different, an expected benefit of SemCLIP should be robustness when applied zero-shot to downstream image classification tasks. Our experiments confirm such robustness as measured by difference in accuracy (mean-accuracy delta) between original and negated captions on five downstream datasets.

---

### Contrastive vision-language learning with paraphrasing and negation

Authors: Kwun Ho Ngan, Saman Sadeghi Afgeh, Joe Townsend, Artur d'Avila Garcez
Published: 2025-11-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.16527v1

Contrastive vision-language models continue to be the dominant approach for image and text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks in contrastive manner to align their image and text embeddings in a shared latent space. Recent results evaluating CLIP on negated or paraphrased text have shown mixed performance because negation changes meaning radically with minimal lexical changes, while paraphrasing can create very different textual expressions with the same intended meaning. This poses a significant challenge for improving the evaluation results and alignment of vision-language models. To address this challenge, this paper evaluates the combination of paraphrasing and negation, proposes a new CLIP contrastive loss function accounting for both paraphrasing and negation, and applies LLM-generated training triples consisting of original, paraphrased and negated textual captions to CLIP-like training models. The approach, called SemCLIP, is shown to move paraphrased captions towards the original image embeddings while pushing negated captions further away in embedding space. Empirically, SemCLIP is shown to be capable of preserving CLIP's performance while increasing considerably the distances to negated captions. On the CC-Neg benchmark using an original over negation image-retrieval accuracy metric, SemCLIP improves accuracy from 68.1% to 78.1%. Although results are mixed when compared with CLIP on the Sugarcrepe++ benchmark, SemCLIP's performance is generally better than the models trained with negated captions. This robustness to negation extends to downstream zero-shot classification tasks where SemCLIP pre-trained on Sugarcrepe++ performs better than CLIP on all tested downstream tasks. These results indicate that SemCLIP can achieve significant robustness to semantic transformations.

---

### BoxingVI: A Multi-Modal Benchmark for Boxing Action Recognition and Localization

Authors: Rahul Kumar, Vipul Baghel, Sudhanshu Singh, Bikash Kumar Badatya, Shivam Yadav, Babji Srinivasan, Ravi Hegde
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16524v1

Accurate analysis of combat sports using computer vision has gained traction in recent years, yet the development of robust datasets remains a major bottleneck due to the dynamic, unstructured nature of actions and variations in recording environments. In this work, we present a comprehensive, well-annotated video dataset tailored for punch detection and classification in boxing. The dataset comprises 6,915 high-quality punch clips categorized into six distinct punch types, extracted from 20 publicly available YouTube sparring sessions and involving 18 different athletes. Each clip is manually segmented and labeled to ensure precise temporal boundaries and class consistency, capturing a wide range of motion styles, camera angles, and athlete physiques. This dataset is specifically curated to support research in real-time vision-based action recognition, especially in low-resource and unconstrained environments. By providing a rich benchmark with diverse punch examples, this contribution aims to accelerate progress in movement analysis, automated coaching, and performance assessment within boxing and related domains.

---

### Dynamic Participation in Federated Learning: Benchmarks and a Knowledge Pool Plugin

Authors: Ming-Lun Lee, Fu-Shiang Yang, Cheng-Kuan Lin, Yan-Ann Chen, Chih-Yu Lin, Yu-Chee Tseng
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16523v1

Federated learning (FL) enables clients to collaboratively train a shared model in a distributed manner, setting it apart from traditional deep learning paradigms. However, most existing FL research assumes consistent client participation, overlooking the practical scenario of dynamic participation (DPFL), where clients may intermittently join or leave during training. Moreover, no existing benchmarking framework systematically supports the study of DPFL-specific challenges. In this work, we present the first open-source framework explicitly designed for benchmarking FL models under dynamic client participation. Our framework provides configurable data distributions, participation patterns, and evaluation metrics tailored to DPFL scenarios. Using this platform, we benchmark four major categories of widely adopted FL models and uncover substantial performance degradation under dynamic participation. To address these challenges, we further propose Knowledge-Pool Federated Learning (KPFL), a generic plugin that maintains a shared knowledge pool across both active and idle clients. KPFL leverages dual-age and data-bias weighting, combined with generative knowledge distillation, to mitigate instability and prevent knowledge loss. Extensive experiments demonstrate the significant impact of dynamic participation on FL performance and the effectiveness of KPFL in improving model robustness and generalization.

---

### YOWO: You Only Walk Once to Jointly Map An Indoor Scene and Register Ceiling-mounted Cameras

Authors: Fan Yang, Sosuke Yamao, Ikuo Kusajima, Atsunori Moteki, Shoichi Masui, Shan Jiang
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16521v1

Using ceiling-mounted cameras (CMCs) for indoor visual capturing opens up a wide range of applications. However, registering CMCs to the target scene layout presents a challenging task. While manual registration with specialized tools is inefficient and costly, automatic registration with visual localization may yield poor results when visual ambiguity exists. To alleviate these issues, we propose a novel solution for jointly mapping an indoor scene and registering CMCs to the scene layout. Our approach involves equipping a mobile agent with a head-mounted RGB-D camera to traverse the entire scene once and synchronize CMCs to capture this mobile agent. The egocentric videos generate world-coordinate agent trajectories and the scene layout, while the videos of CMCs provide pseudo-scale agent trajectories and CMC relative poses. By correlating all the trajectories with their corresponding timestamps, the CMC relative poses can be aligned to the world-coordinate scene layout. Based on this initialization, a factor graph is customized to enable the joint optimization of ego-camera poses, scene layout, and CMC poses. We also develop a new dataset, setting the first benchmark for collaborative scene mapping and CMC registration (https://sites.google.com/view/yowo/home). Experimental results indicate that our method not only effectively accomplishes two tasks within a unified framework, but also jointly enhances their performance. We thus provide a reliable tool to facilitate downstream position-aware applications.

---

### Saving Foundation Flow-Matching Priors for Inverse Problems

Authors: Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun
Published: 2025-11-20
Categories: cs.LG, cs.CV, eess.IV, eess.SP
arXiv: https://arxiv.org/abs/2511.16520v3

Foundation flow-matching (FM) models promise universal priors for solving inverse problems (IPs); yet today, they trail behind domain-specific and even untrained priors. \emph{How can we unlock their potential?} We introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. For evaluation, we consider both simple image restoration tasks and scientific IPs with a few similar samples -- where the prohibitive cost of data collection and model training hinders the development of domain-specific generative models. Our superior experimental results confirm the effectiveness of FMPlug. Overall, FMPlug paves the way for making foundation FM models practical, reusable priors for IPs, especially scientific ones with few similar samples. More details are available at https://sun-umn.github.io/xm-plug/ .

---

### Saving Foundation Flow-Matching Priors for Inverse Problems

Authors: Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun
Published: 2025-11-20
Categories: cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2511.16520v1

Foundation flow-matching (FM) models promise a universal prior for solving inverse problems (IPs), yet today they trail behind domain-specific or even untrained priors. How can we unlock their potential? We introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with a sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. This leads to a significant performance boost across image restoration and scientific IPs. Our results point to a path for making foundation FM models practical, reusable priors for IP solving.

---

### MiMo-Embodied: X-Embodied Foundation Model Technical Report

Authors: Xiaoshuai Hao, Lei Zhou, Zhijian Huang, Zhiwen Hou, Yingbo Tang, Lingfeng Zhang, Guang Li, Zheng Lu, Shuhuai Ren, Xianhui Meng, Yuchen Zhang, Jing Wu et al.
Published: 2025-11-20
Categories: cs.RO, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2511.16518v2

We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.

---

### MiMo-Embodied: X-Embodied Foundation Model Technical Report

Authors: Xiaoshuai Hao, Lei Zhou, Zhijian Huang, Zhiwen Hou, Yingbo Tang, Lingfeng Zhang, Guang Li, Zheng Lu, Shuhuai Ren, Xianhui Meng, Yuchen Zhang, Jing Wu et al.
Published: 2025-11-20
Categories: cs.RO, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2511.16518v1

We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.

---

### Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off

Authors: Nicholas Pellegrino, David Szczecina, Paul Fieguth
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16512v2

Incorrectly labelled training data are frustratingly ubiquitous in both benchmark and specially curated datasets. Such mislabelling clearly adversely affects the performance and generalizability of models trained through supervised learning on the associated datasets. Frameworks for detecting label errors typically require well-trained / well-generalized models; however, at the same time most frameworks rely on training these models on corrupt data, which clearly has the effect of reducing model generalizability and subsequent effectiveness in error detection -- unless a training scheme robust to label errors is employed. We evaluate two novel loss functions, Blurry Loss and Piecewise-zero Loss, that enhance robustness to label errors by de-weighting or disregarding difficult-to-classify samples, which are likely to be erroneous. These loss functions leverage the idea that mislabelled examples are typically more difficult to classify and should contribute less to the learning signal. Comprehensive experiments on a variety of artificially corrupted datasets demonstrate that the proposed loss functions outperform state-of-the-art robust loss functions in nearly all cases, achieving superior F1 scores for error detection. Further analyses through ablation studies offer insights to confirm these loss functions' broad applicability to cases of both uniform and non-uniform corruption, and with different label error detection frameworks. By using these robust loss functions, machine learning practitioners can more effectively identify, prune, or correct errors in their training data.

---

### Loss Functions Robust to the Presence of Label Errors

Authors: Nicholas Pellegrino, David Szczecina, Paul Fieguth
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16512v1

Methods for detecting label errors in training data require models that are robust to label errors (i.e., not fit to erroneously labelled data points). However, acquiring such models often involves training on corrupted data, which presents a challenge. Adjustments to the loss function present an opportunity for improvement. Motivated by Focal Loss (which emphasizes difficult-to-classify samples), two novel, yet simple, loss functions are proposed that de-weight or ignore these difficult samples (i.e., those likely to have label errors). Results on artificially corrupted data show promise, such that F1 scores for detecting errors are improved from the baselines of conventional categorical Cross Entropy and Focal Loss.

---

### ODE-ViT: Plug & Play Attention Layer from the Generalization of the ViT as an Ordinary Differential Equation

Authors: Carlos Boned Riera, David Romero Sanchez, Oriol Ramos Terrades
Published: 2025-11-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.16501v1

In recent years, increasingly large models have achieved outstanding performance across CV tasks. However, these models demand substantial computational resources and storage, and their growing complexity limits our understanding of how they make decisions. Most of these architectures rely on the attention mechanism within Transformer-based designs. Building upon the connection between residual neural networks and ordinary differential equations (ODEs), we introduce ODE-ViT, a Vision Transformer reformulated as an ODE system that satisfies the conditions for well-posed and stable dynamics. Experiments on CIFAR-10 and CIFAR-100 demonstrate that ODE-ViT achieves stable, interpretable, and competitive performance with up to one order of magnitude fewer parameters, surpassing prior ODE-based Transformer approaches in classification tasks. We further propose a plug-and-play teacher-student framework in which a discrete ViT guides the continuous trajectory of ODE-ViT by treating the intermediate representations of the teacher as solutions of the ODE. This strategy improves performance by more than 10% compared to training a free ODE-ViT from scratch.

---

### Acquisition Time-Informed Breast Tumor Segmentation from Dynamic Contrast-Enhanced MRI

Authors: Rui Wang, Yuexi Du, John Lewin, R. Todd Constable, Nicha C. Dvornek
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16498v1

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays an important role in breast cancer screening, tumor assessment, and treatment planning and monitoring. The dynamic changes in contrast in different tissues help to highlight the tumor in post-contrast images. However, varying acquisition protocols and individual factors result in large variation in the appearance of tissues, even for images acquired in the same phase (e.g., first post-contrast phase), making automated tumor segmentation challenging. Here, we propose a tumor segmentation method that leverages knowledge of the image acquisition time to modulate model features according to the specific acquisition sequence. We incorporate the acquisition times using feature-wise linear modulation (FiLM) layers, a lightweight method for incorporating temporal information that also allows for capitalizing on the full, variables number of images acquired per imaging study. We trained baseline and different configurations for the time-modulated models with varying backbone architectures on a large public multisite breast DCE-MRI dataset. Evaluation on in-domain images and a public out-of-domain dataset showed that incorporating knowledge of phase acquisition time improved tumor segmentation performance and model generalization.

---

### Physics-Informed Machine Learning for Efficient Sim-to-Real Data Augmentation in Micro-Object Pose Estimation

Authors: Zongcai Tan, Lan Wei, Dandan Zhang
Published: 2025-11-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.16494v1

Precise pose estimation of optical microrobots is essential for enabling high-precision object tracking and autonomous biological studies. However, current methods rely heavily on large, high-quality microscope image datasets, which are difficult and costly to acquire due to the complexity of microrobot fabrication and the labour-intensive labelling. Digital twin systems offer a promising path for sim-to-real data augmentation, yet existing techniques struggle to replicate complex optical microscopy phenomena, such as diffraction artifacts and depth-dependent imaging.This work proposes a novel physics-informed deep generative learning framework that, for the first time, integrates wave optics-based physical rendering and depth alignment into a generative adversarial network (GAN), to synthesise high-fidelity microscope images for microrobot pose estimation efficiently. Our method improves the structural similarity index (SSIM) by 35.6% compared to purely AI-driven methods, while maintaining real-time rendering speeds (0.022 s/frame).The pose estimator (CNN backbone) trained on our synthetic data achieves 93.9%/91.9% (pitch/roll) accuracy, just 5.0%/5.4% (pitch/roll) below that of an estimator trained exclusively on real data. Furthermore, our framework generalises to unseen poses, enabling data augmentation and robust pose estimation for novel microrobot configurations without additional training data.

---

### Online Operator Design in Evolutionary Optimization for Flexible Job Shop Scheduling via Large Language Models

Authors: Rongjie Liao, Junhao Qiu, Xin Chen, Xiaoping Li
Published: 2025-11-20
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2511.16485v3

Customized static operator design has enabled widespread application of Evolutionary Algorithms (EAs), but their search effectiveness often deteriorates as evolutionary progresses. Dynamic operator configuration approaches attempt to alleviate this issue, but they typically rely on predefined operator structures and localized parameter control, lacking sustained adaptive optimization throughout evolution. To overcome these limitations, this work leverages Large Language Models (LLMs) to perceive evolutionary dynamics and enable operator-level meta-evolution. The proposed framework, LLMs for online operator design in Evolutionary Optimization, named LLM4EO, comprises three components: knowledge-transfer-based operator design, evolution perception and analysis, and adaptive operator evolution. Firstly, operators are initialized by leveraging LLMs to distill and transfer knowledge from well-established operators. Then, search behaviors and potential limitations of operators are analyzed by integrating fitness performance with evolutionary features, accompanied by suggestions for improvement. Upon stagnation of population evolution, an LLM-driven meta-operator dynamically optimizes gene selection of operators by prompt-guided improvement strategies. This approach achieves co-evolution of solutions and operators within a unified optimization framework, introducing a novel paradigm for enhancing the efficiency and adaptability of EAs. Finally, extensive experiments on multiple benchmarks of flexible job shop scheduling problem demonstrate that LLM4EO accelerates population evolution and outperforms tailored EAs.

---

### LLM4EO: Large Language Model for Evolutionary Optimization in Flexible Job Shop Scheduling

Authors: Rongjie Liao, Junhao Qiu, Xin Chen, Xiaoping Li
Published: 2025-11-20
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2511.16485v1

Customized static operator design has enabled widespread application of Evolutionary Algorithms (EAs), but their search performance is transient during iterations and prone to degradation. Dynamic operators aim to address this but typically rely on predefined designs and localized parameter control during the search process, lacking adaptive optimization throughout evolution. To overcome these limitations, this work leverages Large Language Models (LLMs) to perceive evolutionary dynamics and enable operator-level meta-evolution. The proposed framework, LLMs for Evolutionary Optimization (LLM4EO), comprises three components: knowledge-transfer-based operator design, evolution perception and analysis, and adaptive operator evolution. Firstly, initialization of operators is performed by transferring the strengths of classical operators via LLMs. Then, search preferences and potential limitations of operators are analyzed by integrating fitness performance and evolutionary features, accompanied by corresponding suggestions for improvement. Upon stagnation of population evolution, gene selection priorities of operators are dynamically optimized via improvement prompting strategies. This approach achieves co-evolution of populations and operators in the search, introducing a novel paradigm for enhancing the efficiency and adaptability of EAs. Finally, a series of validations on multiple benchmark datasets of the flexible job shop scheduling problem demonstrate that LLM4EO accelerates population evolution and outperforms both mainstream evolutionary programming and traditional EAs.

---

### Flow and Depth Assisted Video Prediction with Latent Transformer

Authors: Eliyas Suleyman, Paul Henderson, Eksan Firkat, Nicolas Pugeault
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16484v1

Video prediction is a fundamental task for various downstream applications, including robotics and world modeling. Although general video prediction models have achieved remarkable performance in standard scenarios, occlusion is still an inherent challenge in video prediction. We hypothesize that providing explicit information about motion (via point-flow) and geometric structure (via depth-maps) will enable video prediction models to perform better in situations with occlusion and the background motion. To investigate this, we present the first systematic study dedicated to occluded video prediction. We use a standard multi-object latent transformer architecture to predict future frames, but modify this to incorporate information from depth and point-flow. We evaluate this model in a controlled setting on both synthetic and real-world datasets with not only appearance-based metrics but also Wasserstein distances on object masks, which can effectively measure the motion distribution of the prediction. We find that when the prediction model is assisted with point flow and depth, it performs better in occluded scenarios and predicts more accurate background motion compared to models without the help of these modalities.

---

### Large Language Model-Based Reward Design for Deep Reinforcement Learning-Driven Autonomous Cyber Defense

Authors: Sayak Mukherjee, Samrat Chatterjee, Emilie Purvine, Ted Fujimoto, Tegan Emerson
Published: 2025-11-20
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2511.16483v1

Designing rewards for autonomous cyber attack and defense learning agents in a complex, dynamic environment is a challenging task for subject matter experts. We propose a large language model (LLM)-based reward design approach to generate autonomous cyber defense policies in a deep reinforcement learning (DRL)-driven experimental simulation environment. Multiple attack and defense agent personas were crafted, reflecting heterogeneity in agent actions, to generate LLM-guided reward designs where the LLM was first provided with contextual cyber simulation environment information. These reward structures were then utilized within a DRL-driven attack-defense simulation environment to learn an ensemble of cyber defense policies. Our results suggest that LLM-guided reward designs can lead to effective defense strategies against diverse adversarial behaviors.

---

### Correlation-Aware Feature Attribution Based Explainable AI

Authors: Poushali Sengupta, Yan Zhang, Frank Eliassen, Sabita Maharjan
Published: 2025-11-20
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2511.16482v1

Explainable AI (XAI) is increasingly essential as modern models become more complex and high-stakes applications demand transparency, trust, and regulatory compliance. Existing global attribution methods often incur high computational costs, lack stability under correlated inputs, and fail to scale efficiently to large or heterogeneous datasets. We address these gaps with \emph{ExCIR} (Explainability through Correlation Impact Ratio), a correlation-aware attribution score equipped with a lightweight transfer protocol that reproduces full-model rankings using only a fraction of the data. ExCIR quantifies sign-aligned co-movement between features and model outputs after \emph{robust centering} (subtracting a robust location estimate, e.g., median or mid-mean, from features and outputs). We further introduce \textsc{BlockCIR}, a \emph{groupwise} extension of ExCIR that scores \emph{sets} of correlated features as a single unit. By aggregating the same signed-co-movement numerators and magnitudes over predefined or data-driven groups, \textsc{BlockCIR} mitigates double-counting in collinear clusters (e.g., synonyms or duplicated sensors) and yields smoother, more stable rankings when strong dependencies are present. Across diverse text, tabular, signal, and image datasets, ExCIR shows trustworthy agreement with established global baselines and the full model, delivers consistent top-$k$ rankings across settings, and reduces runtime via lightweight evaluation on a subset of rows. Overall, ExCIR provides \emph{computationally efficient}, \emph{consistent}, and \emph{scalable} explainability for real-world deployment.

---

### Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluation

Authors: Elena V. Epure, Yashar Deldjoo, Bruno Sguerra, Markus Schedl, Manuel Moussallam
Published: 2025-11-20
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2511.16478v3

Music Recommender Systems (MRSs) have long relied on an information retrieval framing, where progress is measured mainly through accuracy on retrieval-oriented subtasks. While effective, this reductionist paradigm struggles to address the deeper question of what makes a good recommendation. Attempts to broaden evaluation, through user studies or fairness analyses, have had limited impact. The emergence of Large Language Models (LLMs) disrupts this framework: LLMs are generative rather than ranking-based, making standard accuracy metrics questionable. They also introduce challenges such as hallucinations, knowledge cutoffs, non-determinism, and opaque training data, rendering traditional train/test protocols difficult to interpret. At the same time, LLMs create new opportunities, enabling natural language (NL) interaction and even allowing models to act as evaluators. This work argues that the shift toward LLM-driven MRSs requires rethinking evaluation. We first review how LLMs have impacted user modeling, item modeling, and NL-based recommendation in music. We then analyze evaluation practices from NLP, highlighting methodologies and open challenges relevant to MRSs. Finally, we synthesize insights, focusing on how LLM prompting applies to MRSs, to outline a structured set of success and risk dimensions. Our goal is to provide the MRSs community with an updated, pedagogical, and cross-disciplinary perspective on evaluation.

---

### Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluation

Authors: Elena V. Epure, Yashar Deldjoo, Bruno Sguerra, Markus Schedl, Manuel Moussallam
Published: 2025-11-20
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2511.16478v1

Music Recommender Systems (MRS) have long relied on an information-retrieval framing, where progress is measured mainly through accuracy on retrieval-oriented subtasks. While effective, this reductionist paradigm struggles to address the deeper question of what makes a good recommendation, and attempts to broaden evaluation, through user studies or fairness analyses, have had limited impact. The emergence of Large Language Models (LLMs) disrupts this framework: LLMs are generative rather than ranking-based, making standard accuracy metrics questionable. They also introduce challenges such as hallucinations, knowledge cutoffs, non-determinism, and opaque training data, rendering traditional train/test protocols difficult to interpret. At the same time, LLMs create new opportunities, enabling natural-language interaction and even allowing models to act as evaluators. This work argues that the shift toward LLM-driven MRS requires rethinking evaluation. We first review how LLMs reshape user modeling, item modeling, and natural-language recommendation in music. We then examine evaluation practices from NLP, highlighting methodologies and open challenges relevant to MRS. Finally, we synthesize insights-focusing on how LLM prompting applies to MRS, to outline a structured set of success and risk dimensions. Our goal is to provide the MRS community with an updated, pedagogical, and cross-disciplinary perspective on evaluation.

---

### Limitations of Scalarisation in MORL: A Comparative Study in Discrete Environments

Authors: Muhammad Sa'ood Shah, Asad Jeewa
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16476v1

Scalarisation functions are widely employed in MORL algorithms to enable intelligent decision-making. However, these functions often struggle to approximate the Pareto front accurately, rendering them unideal in complex, uncertain environments. This study examines selected Multi-Objective Reinforcement Learning (MORL) algorithms across MORL environments with discrete action and observation spaces. We aim to investigate further the limitations associated with scalarisation approaches for decision-making in multi-objective settings. Specifically, we use an outer-loop multi-policy methodology to assess the performance of a seminal single-policy MORL algorithm, MO Q-Learning implemented with linear scalarisation and Chebyshev scalarisation functions. In addition, we explore a pioneering inner-loop multi-policy algorithm, Pareto Q-Learning, which offers a more robust alternative. Our findings reveal that the performance of the scalarisation functions is highly dependent on the environment and the shape of the Pareto front. These functions often fail to retain the solutions uncovered during learning and favour finding solutions in certain regions of the solution space. Moreover, finding the appropriate weight configurations to sample the entire Pareto front is complex, limiting their applicability in uncertain settings. In contrast, inner-loop multi-policy algorithms may provide a more sustainable and generalizable approach and potentially facilitate intelligent decision-making in dynamic and uncertain environments.

---

### A Comparison Between Decision Transformers and Traditional Offline Reinforcement Learning Algorithms

Authors: Ali Murtaza Caunhye, Asad Jeewa
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16475v1

The field of Offline Reinforcement Learning (RL) aims to derive effective policies from pre-collected datasets without active environment interaction. While traditional offline RL algorithms like Conservative Q-Learning (CQL) and Implicit Q-Learning (IQL) have shown promise, they often face challenges in balancing exploration and exploitation, especially in environments with varying reward densities. The recently proposed Decision Transformer (DT) approach, which reframes offline RL as a sequence modelling problem, has demonstrated impressive results across various benchmarks. This paper presents a comparative study evaluating the performance of DT against traditional offline RL algorithms in dense and sparse reward settings for the ANT continous control environment. Our research investigates how these algorithms perform when faced with different reward structures, examining their ability to learn effective policies and generalize across varying levels of feedback. Through empirical analysis in the ANT environment, we found that DTs showed less sensitivity to varying reward density compared to other methods and particularly excelled with medium-expert datasets in sparse reward scenarios. In contrast, traditional value-based methods like IQL showed improved performance in dense reward settings with high-quality data, while CQL offered balanced performance across different data qualities. Additionally, DTs exhibited lower variance in performance but required significantly more computational resources compared to traditional approaches. These findings suggest that sequence modelling approaches may be more suitable for scenarios with uncertain reward structures or mixed-quality data, while value-based methods remain competitive in settings with dense rewards and high-quality demonstrations.

---

### FastSurfer-CC: A robust, accurate, and comprehensive framework for corpus callosum morphometry

Authors: Clemens Pollak, Kersten Diers, Santiago Estrada, David Kügler, Martin Reuter
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16471v2

The corpus callosum, the largest commissural structure in the human brain, is a central focus in research on aging and neurological diseases. It is also a critical target for interventions such as deep brain stimulation and serves as an important biomarker in clinical trials, including those investigating remyelination therapies. Despite extensive research on corpus callosum segmentation, few publicly available tools provide a comprehensive and automated analysis pipeline. To address this gap, we present FastSurfer-CC, an efficient and fully automated framework for corpus callosum morphometry. FastSurfer-CC automatically identifies mid-sagittal slices, segments the corpus callosum and fornix, localizes the anterior and posterior commissures to standardize head positioning, generates thickness profiles and subdivisions, and extracts eight shape metrics for statistical analysis. We demonstrate that FastSurfer-CC outperforms existing specialized tools across the individual tasks. Moreover, our method reveals statistically significant differences between Huntington's disease patients and healthy controls that are not detected by the current state-of-the-art.

---

### FastSurfer-CC: A robust, accurate, and comprehensive framework for corpus callosum morphometry

Authors: Clemens Pollak, Kersten Diers, Santiago Estrada, David Kügler, Martin Reuter
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16471v1

The corpus callosum, the largest commissural structure in the human brain, is a central focus in research on aging and neurological diseases. It is also a critical target for interventions such as deep brain stimulation and serves as an important biomarker in clinical trials, including those investigating remyelination therapies. Despite extensive research on corpus callosum segmentation, few publicly available tools provide a comprehensive and automated analysis pipeline. To address this gap, we present FastSurfer-CC, an efficient and fully automated framework for corpus callosum morphometry. FastSurfer-CC automatically identifies mid-sagittal slices, segments the corpus callosum and fornix, localizes the anterior and posterior commissures to standardize head positioning, generates thickness profiles and subdivisions, and extracts eight shape metrics for statistical analysis. We demonstrate that FastSurfer-CC outperforms existing specialized tools across the individual tasks. Moreover, our method reveals statistically significant differences between Huntington's disease patients and healthy controls that are not detected by the current state-of-the-art.

---

### Arctic-Extract Technical Report

Authors: Mateusz Chiliński, Julita Ołtusek, Wojciech Jaśkowski
Published: 2025-11-20
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2511.16470v1

Arctic-Extract is a state-of-the-art model designed for extracting structural data (question answering, entities and tables) from scanned or digital-born business documents. Despite its SoTA capabilities, the model is deployable on resource-constrained hardware, weighting only 6.6 GiB, making it suitable for deployment on devices with limited resources, such as A10 GPUs with 24 GB of memory. Arctic-Extract can process up to 125 A4 pages on those GPUs, making suitable for long document processing. This paper highlights Arctic-Extract's training protocols and evaluation results, demonstrating its strong performance in document understanding.

---

### Optimizing Quantum Key Distribution Network Performance using Graph Neural Networks

Authors: Akshit Pramod Anchan, Ameiy Acharya, Leki Chom Thungon
Published: 2025-11-20
Categories: quant-ph, cs.CR, cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2511.16468v1

This paper proposes an optimization of Quantum Key Distribution (QKD) Networks using Graph Neural Networks (GNN) framework. Today, the development of quantum computers threatens the security systems of classical cryptography. Moreover, as QKD networks are designed for protecting secret communication, they suffer from multiple operational difficulties: adaptive to dynamic conditions, optimization for multiple parameters and effective resource utilization. In order to overcome these obstacles, we propose a GNN-based framework which can model QKD networks as dynamic graphs and extracts exploitable characteristics from these networks' structure. The graph contains not only topological information but also specific characteristics associated with quantum communication (the number of edges between nodes, etc). Experimental results demonstrate that the GNN-optimized QKD network achieves a substantial increase in total key rate (from 27.1 Kbits/s to 470 Kbits/s), a reduced average QBER (from 6.6% to 6.0%), and maintains path integrity with a slight reduction in average transmission distance (from 7.13 km to 6.42 km). Furthermore, we analyze network performance across varying scales (10 to 250 nodes), showing improved link prediction accuracy and enhanced key generation rate in medium-sized networks. This work introduces a novel operation mode for QKD networks, shifting the paradigm of network optimization through adaptive and scalable quantum communication systems that enhance security and performance.

---

### Anatomy of an Idiom: Tracing Non-Compositionality in Language Models

Authors: Andrew Gomes
Published: 2025-11-20
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.16467v1

We investigate the processing of idiomatic expressions in transformer-based language models using a novel set of techniques for circuit discovery and analysis. First discovering circuits via a modified path patching algorithm, we find that idiom processing exhibits distinct computational patterns. We identify and investigate ``Idiom Heads,'' attention heads that frequently activate across different idioms, as well as enhanced attention between idiom tokens due to earlier processing, which we term ``augmented reception.'' We analyze these phenomena and the general features of the discovered circuits as mechanisms by which transformers balance computational efficiency and robustness. Finally, these findings provide insights into how transformers handle non-compositional language and suggest pathways for understanding the processing of more complex grammatical constructions.

---