# Research Papers — 2025-11 · bundle page 80 of 197

> Full-text markdown of papers #3951–4000 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/80
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/79.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/81.md)

### MAIF: Enforcing AI Trust and Provenance with an Artifact-Centric Agentic Paradigm

Authors: Vineeth Sai Narajala, Manish Bhatt, Idan Habler, Ronald F. Del Rosario, Ads Dawson
Published: 2025-11-19
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.15097v2

The AI trustworthiness crisis threatens to derail the artificial intelligence revolution, with regulatory barriers, security vulnerabilities, and accountability gaps preventing deployment in critical domains. Current AI systems operate on opaque data structures that lack the audit trails, provenance tracking, or explainability required by emerging regulations like the EU AI Act. We propose an artifact-centric AI agent paradigm where behavior is driven by persistent, verifiable data artifacts rather than ephemeral tasks, solving the trustworthiness problem at the data architecture level. Central to this approach is the Multimodal Artifact File Format (MAIF), an AI-native container embedding semantic representations, cryptographic provenance, and granular access controls. MAIF transforms data from passive storage into active trust enforcement, making every AI operation inherently auditable. Our production-ready implementation demonstrates ultra-high-speed streaming (2,720.7 MB/s), optimized video processing (1,342 MB/s), and enterprise-grade security. Novel algorithms for cross-modal attention, semantic compression, and cryptographic binding achieve up to 225 compression while maintaining semantic fidelity. Advanced security features include stream-level access control, real-time tamper detection, and behavioral anomaly analysis with minimal overhead. This approach directly addresses the regulatory, security, and accountability challenges preventing AI deployment in sensitive domains, offering a viable path toward trustworthy AI systems at scale.

---

### Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesis

Authors: Chengyu Xie, Zhi Gong, Junchi Ren, Linkun Yu, Si Shen, Fei Shen, Xiaoyu Du
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15092v1

Pose-guided human image generation is limited by incomplete textures from single reference views and the absence of explicit cross-view interaction. We present jointly conditioned diffusion model (JCDM), a jointly conditioned diffusion framework that exploits multi-view priors. The appearance prior module (APM) infers a holistic identity preserving prior from incomplete references, and the joint conditional injection (JCI) mechanism fuses multi-view cues and injects shared conditioning into the denoising backbone to align identity, color, and texture across poses. JCDM supports a variable number of reference views and integrates with standard diffusion backbones with minimal and targeted architectural modifications. Experiments demonstrate state of the art fidelity and cross-view consistency.

---

### SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning

Authors: Wenhan Yu, Zhaoxi Zhang, Wang Chen, Guanqiang Qi, Weikang Li, Lei Sha, Deguo Xia, Jizhou Huang
Published: 2025-11-19
Categories: cs.DB, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.15090v2

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at the page level without explicitly annotating the evidence regions that support the answer, which limits both interpretability and the reliability of evaluation. To address this limitation, we introduce SciEGQA, a scientific document question answering and reasoning dataset with semantic evidence grounding, where supporting evidence is represented as semantically coherent document regions annotated with bounding boxes. SciEGQA consists of two components: a **human-annotated fine-grained benchmark** containing 1,623 high-quality question--answer pairs, and a **large-scale automatically constructed training set** with over 30K QA pairs generated through an automated data construction pipeline. Extensive experiments on a wide range of Vision-Language Models (VLMs) show that existing models still struggle with evidence localization and evidence-based question answering in scientific documents. Training on the proposed dataset significantly improves the scientific reasoning capabilities of VLMs. The project page is available at https://yuwenhan07.github.io/SciEGQA-project/.

---

### TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition

Authors: Wen Yin, Siyu Zhan, Cencen Liu, Xin Hu, Guiduo Duan, Xiurui Xie, Yuan-Fang Li, Tao He
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15085v1

Multimodal Emotion Recognition (MER) aims to accurately identify human emotional states by integrating heterogeneous modalities such as visual, auditory, and textual data. Existing approaches predominantly rely on unified emotion labels to supervise model training, often overlooking a critical challenge: inter-modal emotion conflicts, wherein different modalities within the same sample may express divergent emotional tendencies. In this work, we address this overlooked issue by proposing a novel framework, Typicality-based Consistent-aware Multimodal Emotion Recognition (TiCAL), inspired by the stage-wise nature of human emotion perception. TiCAL dynamically assesses the consistency of each training sample by leveraging pseudo unimodal emotion labels alongside a typicality estimation. To further enhance emotion representation, we embed features in a hyperbolic space, enabling the capture of fine-grained distinctions among emotional categories. By incorporating consistency estimates into the learning process, our method improves model performance, particularly on samples exhibiting high modality inconsistency. Extensive experiments on benchmark datasets, e.g, CMU-MOSEI and MER2023, validate the effectiveness of TiCAL in mitigating inter-modal emotional conflicts and enhancing overall recognition accuracy, e.g., with about 2.6% improvements over the state-of-the-art DMD.

---

### Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection

Authors: Xiancheng Wang, Lin Wang, Rui Wang, Zhibo Zhang, Minghang Zhao
Published: 2025-11-19
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2511.15083v2

Time-series anomaly detection plays a critical role in numerous real-world applications, including industrial monitoring and fault diagnosis. Recently, Mamba-based state-space models have shown remarkable efficiency in long-sequence modeling. However, directly applying Mamba to anomaly detection tasks still faces challenges in capturing complex temporal patterns and nonlinear dynamics. In this paper, we propose Fourier-KAN-Mamba, a novel hybrid architecture that integrates Fourier layer, Kolmogorov-Arnold Networks (KAN), and Mamba selective state-space model. The Fourier layer extracts multi-scale frequency features, KAN enhances nonlinear representation capability, and a temporal gating control mechanism further improves the model's ability to distinguish normal and anomalous patterns. Extensive experiments on MSL, SMAP, and SWaT datasets demonstrate that our method significantly outperforms existing state-of-the-art approaches. Keywords: time-series anomaly detection, state-space model, Mamba, Fourier transform, Kolmogorov-Arnold Network

---

### MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal Variation

Authors: Shengjing Tian, Yinan Han, Xiantong Zhao, Xuehu Liu, Qi Lang
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15077v1

Dynamic outdoor environments with high temporal variation (HTV) pose significant challenges for 3D single object tracking in LiDAR point clouds. Existing memory-based trackers often suffer from quadratic computational complexity, temporal redundancy, and insufficient exploitation of geometric priors. To address these issues, we propose MambaTrack3D, a novel HTV-oriented tracking framework built upon the state space model Mamba. Specifically, we design a Mamba-based Inter-frame Propagation (MIP) module that replaces conventional single-frame feature extraction with efficient inter-frame propagation, achieving near-linear complexity while explicitly modeling spatial relations across historical frames. Furthermore, a Grouped Feature Enhancement Module (GFEM) is introduced to separate foreground and background semantics at the channel level, thereby mitigating temporal redundancy in the memory bank. Extensive experiments on KITTI-HTV and nuScenes-HTV benchmarks demonstrate that MambaTrack3D consistently outperforms both HTV-oriented and normal-scenario trackers, achieving improvements of up to 6.5 success and 9.5 precision over HVTrack under moderate temporal gaps. On the standard KITTI dataset, MambaTrack3D remains highly competitive with state-of-the-art normal-scenario trackers, confirming its strong generalization ability. Overall, MambaTrack3D achieves a superior accuracy-efficiency trade-off, delivering robust performance across both specialized HTV and conventional tracking scenarios.

---

### GPU-Initiated Networking for NCCL

Authors: Khaled Hamidouche, John Bachan, Pak Markthub, Peter-Jan Gootzen, Elena Agostini, Sylvain Jeaugey, Aamir Shafi, Georgios Theodorakis, Manjunath Gorentla Venkata
Published: 2025-11-19
Categories: cs.DC, cs.AI, cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2511.15076v2

Modern AI workloads, especially Mixture-of-Experts (MoE) architectures, increasingly demand low-latency, fine-grained GPU-to-GPU communication with device-side control. Traditional GPU communication follows a host-initiated model, where the CPU orchestrates all communication operations - a characteristic of the CUDA runtime. Although robust for collective operations, applications requiring tight integration of computation and communication can benefit from device-initiated communication that eliminates CPU coordination overhead. NCCL 2.28 introduces the Device API with three operation modes: Load/Store Accessible (LSA) for NVLink/PCIe, Multimem for NVLink SHARP, and GPU-Initiated Networking (GIN) for network RDMA. This paper presents the GIN architecture, design, semantics, and highlights its impact on MoE communication. GIN builds on a three-layer architecture: i) NCCL Core host-side APIs for device communicator setup and collective memory window registration; ii) Device-side APIs for remote memory operations callable from CUDA kernels; and iii) A network plugin architecture with dual semantics (GPUDirect Async Kernel-Initiated and Proxy) for broad hardware support. The GPUDirect Async Kernel-Initiated backend leverages DOCA GPUNetIO for direct GPU-to-NIC communication, while the Proxy backend provides equivalent functionality via lock-free GPU-to-CPU queues over standard RDMA networks. We demonstrate GIN's practicality through integration with DeepEP, an MoE communication library. Comprehensive benchmarking shows that GIN provides device-initiated communication within NCCL's unified runtime, combining low-latency operations with NCCL's collective algorithms and production infrastructure.

---

### Knowledge-Informed Automatic Feature Extraction via Collaborative Large Language Model Agents

Authors: Henrik Bradland, Morten Goodwin, Vladimir I. Zadorozhny, Per-Arne Andersen
Published: 2025-11-19
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.15074v1

The performance of machine learning models on tabular data is critically dependent on high-quality feature engineering. While Large Language Models (LLMs) have shown promise in automating feature extraction (AutoFE), existing methods are often limited by monolithic LLM architectures, simplistic quantitative feedback, and a failure to systematically integrate external domain knowledge. This paper introduces Rogue One, a novel, LLM-based multi-agent framework for knowledge-informed automatic feature extraction. Rogue One operationalizes a decentralized system of three specialized agents-Scientist, Extractor, and Tester-that collaborate iteratively to discover, generate, and validate predictive features. Crucially, the framework moves beyond primitive accuracy scores by introducing a rich, qualitative feedback mechanism and a "flooding-pruning" strategy, allowing it to dynamically balance feature exploration and exploitation. By actively incorporating external knowledge via an integrated retrieval-augmented (RAG) system, Rogue One generates features that are not only statistically powerful but also semantically meaningful and interpretable. We demonstrate that Rogue One significantly outperforms state-of-the-art methods on a comprehensive suite of 19 classification and 9 regression datasets. Furthermore, we show qualitatively that the system surfaces novel, testable hypotheses, such as identifying a new potential biomarker in the myocardial dataset, underscoring its utility as a tool for scientific discovery.

---

### ProRAC: A Neuro-symbolic Method for Reasoning about Actions with LLM-based Progression

Authors: Haoyong Wu, Yongmei Liu
Published: 2025-11-19
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.15069v1

In this paper, we propose ProRAC (Progression-based Reasoning about Actions and Change), a neuro-symbolic framework that leverages LLMs to tackle RAC problems. ProRAC extracts fundamental RAC elements including actions and questions from the problem, progressively executes each action to derive the final state, and then evaluates the query against the progressed state to arrive at an answer. We evaluate ProRAC on several RAC benchmarks, and the results demonstrate that our approach achieves strong performance across different benchmarks, domains, LLM backbones, and types of RAC tasks.

---

### Classification Trees with Valid Inference via the Exponential Mechanism

Authors: Soham Bakshi, Snigdha Panigrahi
Published: 2025-11-19
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2511.15068v3

Decision trees are widely used for non-linear modeling, as they capture interactions between predictors while producing inherently interpretable models. Despite their popularity, performing inference on the non-linear fit remains largely unaddressed. This paper focuses on classification trees and makes two key contributions. First, we introduce a novel tree-fitting method that replaces the greedy splitting of the predictor space in standard tree algorithms with a probabilistic approach. Each split in our approach is selected according to sampling probabilities defined by an exponential mechanism, with a temperature parameter controlling its deviation from the deterministic choice given data. Second, while our approach can fit a tree that with high probability coincides with the fit produced by standard tree algorithms at low temperatures, it is not merely predictive; unlike standard algorithms, it enables inference by taking into account the highly adaptive tree structure. Our method produces pivots directly from the sampling probabilities in the exponential mechanism. In theory, our pivots allow asymptotically valid inference on the parameters in the predictive fit, and in practice, our method delivers powerful inference without sacrificing predictive accuracy, in contrast to data splitting methods.

---

### Deep Pathomic Learning Defines Prognostic Subtypes and Molecular Drivers in Colorectal Cancer

Authors: Zisong Wang, Xuanyu Wang, Hang Chen, Haizhou Wang, Yuxin Chen, Yihang Xu, Yunhe Yuan, Lihuan Luo, Xitong Ling, Xiaoping Liu
Published: 2025-11-19
Categories: cs.LG, cs.AI, cs.CV, q-bio.GN
arXiv: https://arxiv.org/abs/2511.15067v1

Precise prognostic stratification of colorectal cancer (CRC) remains a major clinical challenge due to its high heterogeneity. The conventional TNM staging system is inadequate for personalized medicine. We aimed to develop and validate a novel multiple instance learning model TDAM-CRC using histopathological whole-slide images for accurate prognostic prediction and to uncover its underlying molecular mechanisms. We trained the model on the TCGA discovery cohort (n=581), validated it in an independent external cohort (n=1031), and further we integrated multi-omics data to improve model interpretability and identify novel prognostic biomarkers. The results demonstrated that the TDAM-CRC achieved robust risk stratification in both cohorts. Its predictive performance significantly outperformed the conventional clinical staging system and multiple state-of-the-art models. The TDAM-CRC risk score was confirmed as an independent prognostic factor in multivariable analysis. Multi-omics analysis revealed that the high-risk subtype is closely associated with metabolic reprogramming and an immunosuppressive tumor microenvironment. Through interaction network analysis, we identified and validated Mitochondrial Ribosomal Protein L37 (MRPL37) as a key hub gene linking deep pathomic features to clinical prognosis. We found that high expression of MRPL37, driven by promoter hypomethylation, serves as an independent biomarker of favorable prognosis. Finally, we constructed a nomogram incorporating the TDAM-CRC risk score and clinical factors to provide a precise and interpretable clinical decision-making tool for CRC patients. Our AI-driven pathological model TDAM-CRC provides a robust tool for improved CRC risk stratification, reveals new molecular targets, and facilitates personalized clinical decision-making.

---

### BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching

Authors: Yachuan Huang, Xianrui Luo, Qiwen Wang, Liao Shen, Jiaqi Li, Huiqiang Sun, Zihao Huang, Wei Jiang, Zhiguo Cao
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15066v1

Bokeh rendering simulates the shallow depth-of-field effect in photography, enhancing visual aesthetics and guiding viewer attention to regions of interest. Although recent approaches perform well, rendering controllable bokeh without additional depth inputs remains a significant challenge. Existing classical and neural controllable methods rely on accurate depth maps, while generative approaches often struggle with limited controllability and efficiency. In this paper, we propose BokehFlow, a depth-free framework for controllable bokeh rendering based on flow matching. BokehFlow directly synthesizes photorealistic bokeh effects from all-in-focus images, eliminating the need for depth inputs. It employs a cross-attention mechanism to enable semantic control over both focus regions and blur intensity via text prompts. To support training and evaluation, we collect and synthesize four datasets. Extensive experiments demonstrate that BokehFlow achieves visually compelling bokeh effects and offers precise control, outperforming existing depth-dependent and generative methods in both rendering quality and efficiency.

---

### Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

Authors: Cheng Yang, Haiyuan Wan, Yiran Peng, Xin Cheng, Zhaoyang Yu, Jiayi Zhang, Junchi Yu, Xinlei Yu, Xiawu Zheng, Dongzhan Zhou, Chenglin Wu
Published: 2025-11-19
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.15065v2

Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reasoning in language modeling, the development of video models motivates us to ask: Can video models reason via video generation? Compared with the discrete text corpus, video grounds reasoning in explicit spatial layouts and temporal continuity, which serves as an ideal substrate for spatial reasoning. In this work, we explore the reasoning via video paradigm and introduce VR-Bench -- a comprehensive benchmark designed to systematically evaluate video models' reasoning capabilities. Grounded in maze-solving tasks that inherently require spatial planning and multi-step reasoning, VR-Bench contains 7,920 procedurally generated videos across five maze types and diverse visual styles. Our empirical analysis demonstrates that SFT can efficiently elicit the reasoning ability of video model. Video models exhibit stronger spatial perception during reasoning, outperforming leading VLMs and generalizing well across diverse scenarios, tasks, and levels of complexity. We further discover a test-time scaling effect, where diverse sampling during inference improves reasoning reliability by 10--20%. These findings highlight the unique potential and scalability of reasoning via video for spatial reasoning tasks.

---

### Interpretable temporal fusion network of multi- and multi-class arrhythmia classification

Authors: Yun Kwan Kim
Published: 2025-11-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.15062v1

Clinical decision support systems (CDSSs) have been widely utilized to support the decisions made by cardiologists when detecting and classifying arrhythmia from electrocardiograms. However, forming a CDSS for the arrhythmia classification task is challenging due to the varying lengths of arrhythmias. Although the onset time of arrhythmia varies, previously developed methods have not considered such conditions. Thus, we propose a framework that consists of (i) local and global extraction and (ii) local-global information fusion with attention to enable arrhythmia detection and classification within a constrained input length. The framework's performance was evaluated in terms of 10-class and 4-class arrhythmia detection, focusing on identifying the onset and ending point of arrhythmia episodes and their duration using the MIT-BIH arrhythmia database (MITDB) and the MIT-BIH atrial fibrillation database (AFDB). Duration, episode, and Dice score performances resulted in overall F1-scores of 96.45%, 82.05%, and 96.31% on the MITDB and 97.57%, 98.31%, and 97.45% on the AFDB, respectively. The results demonstrated statistically superior performance compared to those of the benchmark models. To assess the generalization capability of the proposed method, an MITDB-trained model and MIT-BIH malignant ventricular arrhythmia database-trained model were tested AFDB and MITDB, respectively. Superior performance was attained compared with that of a state-of-the-art model. The proposed method effectively captures both local and global information and dynamics without significant information loss. Consequently, arrhythmias can be detected with greater accuracy, and their occurrence times can be precisely determined, enabling the clinical field to develop more accurate treatment plans based on the proposed method.

---

### Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answering

Authors: Haodong Chen, Guido Zuccon, Teerapong Leelanupab
Published: 2025-11-19
Categories: cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2511.15061v1

Genomic question answering often requires complex reasoning and integration across diverse biomedical sources. GeneGPT addressed this challenge by combining domain-specific APIs with OpenAI's code-davinci-002 large language model to enable natural language interaction with genomic databases. However, its reliance on a proprietary model limits scalability, increases operational costs, and raises concerns about data privacy and generalization. In this work, we revisit and reproduce GeneGPT in a pilot study using open source models, including Llama 3.1, Qwen2.5, and Qwen2.5 Coder, within a monolithic architecture; this allows us to identify the limitations of this approach. Building on this foundation, we then develop OpenBioLLM, a modular multi-agent framework that extends GeneGPT by introducing agent specialization for tool routing, query generation, and response validation. This enables coordinated reasoning and role-based task execution. OpenBioLLM matches or outperforms GeneGPT on over 90% of the benchmark tasks, achieving average scores of 0.849 on Gene-Turing and 0.830 on GeneHop, while using smaller open-source models without additional fine-tuning or tool-specific pretraining. OpenBioLLM's modular multi-agent design reduces latency by 40-50% across benchmark tasks, significantly improving efficiency without compromising model capability. The results of our comprehensive evaluation highlight the potential of open-source multi-agent systems for genomic question answering. Code and resources are available at https://github.com/ielab/OpenBioLLM.

---

### Transformed $\ell_1$ Gradient Regularization for Image Denoising

Authors: Nabiha Choudhury, Jianqing Jia, Yifei Lou
Published: 2025-11-19
Categories: eess.IV, cs.CV, math.OC
arXiv: https://arxiv.org/abs/2511.15060v2

Total variation (TV) regularization is a classical edge-preserving technique widely used across image recovery and reconstruction problems; however, its convex $\ell_1$ gradient penalty tends to over-shrink large gradients, producing staircase artifacts and contrast loss. We propose a gradient-based regularization using the Transformed $\ell_1$ (TL1) penalty and apply it to image denoising. The TL1 penalty asymptotically interpolates between $\ell_1$ and the $\ell_0$ pseudo-norm, offering a principled alternative to TV that better preserves sharp edges and piecewise-smooth regions. Moreover, TL1 admits a tractable proximal operator, enabling an efficient algorithm based on a proximal splitting scheme with subproblems solved by the Alternating Direction Method of Multipliers (ADMM). The weak convexity of TL1 guarantees global convergence of the proximal iterates to a stationary point under mild conditions. Numerical experiments on image denoising demonstrate that the proposed method effectively preserves sharp edges, local contrast, and piecewise-smooth structures, outperforming other gradient-based approaches.

---

### Evaluating Multimodal Large Language Models on Vertically Written Japanese Text

Authors: Keito Sasagawa, Shuhei Kurita, Daisuke Kawahara
Published: 2025-11-19
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2511.15059v1

Multimodal Large Language Models (MLLMs) have seen rapid advances in recent years and are now being applied to visual document understanding tasks. They are expected to process a wide range of document images across languages, including Japanese. Understanding documents from images requires models to read what are written in them. Since some Japanese documents are written vertically, support for vertical writing is essential. However, research specifically focused on vertically written Japanese text remains limited. In this study, we evaluate the reading capability of existing MLLMs on vertically written Japanese text. First, we generate a synthetic Japanese OCR dataset by rendering Japanese texts into images, and use it for both model fine-tuning and evaluation. This dataset includes Japanese text in both horizontal and vertical writing. We also create an evaluation dataset sourced from the real-world document images containing vertically written Japanese text. Using these datasets, we demonstrate that the existing MLLMs perform worse on vertically written Japanese text than on horizontally written Japanese text. Furthermore, we show that training MLLMs on our synthesized Japanese OCR dataset results in improving the performance of models that previously could not handle vertical writing. The datasets and code are publicly available https://github.com/llm-jp/eval_vertical_ja.

---

### ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling

Authors: Yaxiong Chen, Qicong Wang, Chunlei Li, Jingliang Hu, Yilei Shi, Shengwu Xiong, Xiao Xiang Zhu, Lichao Mou
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15057v1

Existing approaches for the problem of ultrasound image segmentation, whether supervised or semi-supervised, are typically specialized for specific anatomical structures or tasks, limiting their practical utility in clinical settings. In this paper, we pioneer the task of universal semi-supervised ultrasound image segmentation and propose ProPL, a framework that can handle multiple organs and segmentation tasks while leveraging both labeled and unlabeled data. At its core, ProPL employs a shared vision encoder coupled with prompt-guided dual decoders, enabling flexible task adaptation through a prompting-upon-decoding mechanism and reliable self-training via an uncertainty-driven pseudo-label calibration (UPLC) module. To facilitate research in this direction, we introduce a comprehensive ultrasound dataset spanning 5 organs and 8 segmentation tasks. Extensive experiments demonstrate that ProPL outperforms state-of-the-art methods across various metrics, establishing a new benchmark for universal ultrasound image segmentation.

---

### Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization

Authors: Jian-Ting Guo, Yu-Cheng Chen, Ping-Chun Hsieh, Kuo-Hao Ho, Po-Wei Huang, Ti-Rong Wu, I-Chen Wu
Published: 2025-11-19
Categories: cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2511.15055v1

Human-like agents have long been one of the goals in pursuing artificial intelligence. Although reinforcement learning (RL) has achieved superhuman performance in many domains, relatively little attention has been focused on designing human-like RL agents. As a result, many reward-driven RL agents often exhibit unnatural behaviors compared to humans, raising concerns for both interpretability and trustworthiness. To achieve human-like behavior in RL, this paper first formulates human-likeness as trajectory optimization, where the objective is to find an action sequence that closely aligns with human behavior while also maximizing rewards, and adapts the classic receding-horizon control to human-like learning as a tractable and efficient implementation. To achieve this, we introduce Macro Action Quantization (MAQ), a human-like RL framework that distills human demonstrations into macro actions via Vector-Quantized VAE. Experiments on D4RL Adroit benchmarks show that MAQ significantly improves human-likeness, increasing trajectory similarity scores, and achieving the highest human-likeness rankings among all RL agents in the human evaluation study. Our results also demonstrate that MAQ can be easily integrated into various off-the-shelf RL algorithms, opening a promising direction for learning human-like RL agents. Our code is available at https://rlg.iis.sinica.edu.tw/papers/MAQ.

---

### CellGenNet: A Knowledge-Distilled Framework for Robust Cell Segmentation in Cancer Tissues

Authors: Srijan Ray, Bikesh K. Nirala, Jason T. Yustein, Sundaresh Ram
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15054v1

Accurate nuclei segmentation in microscopy whole slide images (WSIs) remains challenging due to variability in staining, imaging conditions, and tissue morphology. We propose CellGenNet, a knowledge distillation framework for robust cross-tissue cell segmentation under limited supervision. CellGenNet adopts a student-teacher architecture, where a capacity teacher is trained on sparse annotations and generates soft pseudo-labels for unlabeled regions. The student is optimized using a joint objective that integrates ground-truth labels, teacher-derived probabilistic targets, and a hybrid loss function combining binary cross-entropy and Tversky loss, enabling asymmetric penalties to mitigate class imbalance and better preserve minority nuclear structures. Consistency regularization and layerwise dropout further stabilize feature representations and promote reliable feature transfer. Experiments across diverse cancer tissue WSIs show that CellGenNet improves segmentation accuracy and generalization over supervised and semi-supervised baselines, supporting scalable and reproducible histopathology analysis.

---

### Hyperspectral Super-Resolution with Inter-Image Variability via Degradation-based Low-Rank and Residual Fusion Method

Authors: Yue Wen, Kunjing Yang, Minru Bai
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15052v1

The fusion of hyperspectral image (HSI) with multispectral image (MSI) provides an effective way to enhance the spatial resolution of HSI. However, due to different acquisition conditions, there may exist spectral variability and spatially localized changes between HSI and MSI, referred to as inter-image variability, which can significantly affect the fusion performance. Existing methods typically handle inter-image variability by applying direct transformations to the images themselves, which can exacerbate the ill-posedness of the fusion model. To address this challenge, we propose a Degradation-based Low-Rank and Residual Fusion (DLRRF) model. First, we model the spectral variability as change in the spectral degradation operator. Second, to recover the lost spatial details caused by spatially localized changes, we decompose the target HSI into low rank and residual components, where the latter is used to capture the lost details. By exploiting the spectral correlation within the images, we perform dimensionality reduction on both components. Additionally, we introduce an implicit regularizer to utilize the spatial prior information from the images. The proposed DLRRF model is solved using the Proximal Alternating Optimization (PAO) algorithm within a Plug-and-Play (PnP) framework, where the subproblem regarding implicit regularizer is addressed by an external denoiser. We further provide a comprehensive convergence analysis of the algorithm. Finally, extensive numerical experiments demonstrate that DLRRF achieves superior performance in fusing HSI and MSI with inter-image variability.

---

### Oversampling techniques for predicting COVID-19 patient length of stay

Authors: Zachariah Farahany, Jiawei Wu, K M Sajjadul Islam, Praveen Madiraju
Published: 2025-11-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.15048v1

COVID-19 is a respiratory disease that caused a global pandemic in 2019. It is highly infectious and has the following symptoms: fever or chills, cough, shortness of breath, fatigue, muscle or body aches, headache, the new loss of taste or smell, sore throat, congestion or runny nose, nausea or vomiting, and diarrhea. These symptoms vary in severity; some people with many risk factors have been known to have lengthy hospital stays or die from the disease. In this paper, we analyze patients' electronic health records (EHR) to predict the severity of their COVID-19 infection using the length of stay (LOS) as our measurement of severity. This is an imbalanced classification problem, as many people have a shorter LOS rather than a longer one. To combat this problem, we synthetically create alternate oversampled training data sets. Once we have this oversampled data, we run it through an Artificial Neural Network (ANN), which during training has its hyperparameters tuned using Bayesian optimization. We select the model with the best F1 score and then evaluate it and discuss it.

---

### UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space

Authors: Panqi Yang, Haodong Jing, Nanning Zheng, Yongqiang Ma
Published: 2025-11-19
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.15046v1

In the field of human-object interaction (HOI), detection and generation are two dual tasks that have traditionally been addressed separately, hindering the development of comprehensive interaction understanding. To address this, we propose UniHOI, which jointly models HOI detection and generation via a unified token space, thereby effectively promoting knowledge sharing and enhancing generalization. Specifically, we introduce a symmetric interaction-aware attention module and a unified semi-supervised learning paradigm, enabling effective bidirectional mapping between images and interaction semantics even under limited annotations. Extensive experiments demonstrate that UniHOI achieves state-of-the-art performance in both HOI detection and generation. Specifically, UniHOI improves accuracy by 4.9% on long-tailed HOI detection and boosts interaction metrics by 42.0% on open-vocabulary generation tasks.

---

### Aligning Generative Music AI with Human Preferences: Methods and Challenges

Authors: Dorien Herremans, Abhinaba Roy
Published: 2025-11-19
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2511.15038v1

Recent advances in generative AI for music have achieved remarkable fidelity and stylistic diversity, yet these systems often fail to align with nuanced human preferences due to the specific loss functions they use. This paper advocates for the systematic application of preference alignment techniques to music generation, addressing the fundamental gap between computational optimization and human musical appreciation. Drawing on recent breakthroughs including MusicRL's large-scale preference learning, multi-preference alignment frameworks like diffusion-based preference optimization in DiffRhythm+, and inference-time optimization techniques like Text2midi-InferAlign, we discuss how these techniques can address music's unique challenges: temporal coherence, harmonic consistency, and subjective quality assessment. We identify key research challenges including scalability to long-form compositions, reliability amongst others in preference modelling. Looking forward, we envision preference-aligned music generation enabling transformative applications in interactive composition tools and personalized music services. This work calls for sustained interdisciplinary research combining advances in machine learning, music-theory to create music AI systems that truly serve human creative and experiential needs.

---

### Simulated Human Learning in a Dynamic, Partially-Observed, Time-Series Environment

Authors: Jeffrey Jiang, Kevin Hong, Emily Kuczynski, Gregory Pottie
Published: 2025-11-19
Categories: cs.LG, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2511.15032v1

While intelligent tutoring systems (ITSs) can use information from past students to personalize instruction, each new student is unique. Moreover, the education problem is inherently difficult because the learning process is only partially observable. We therefore develop a dynamic, time-series environment to simulate a classroom setting, with student-teacher interventions - including tutoring sessions, lectures, and exams. In particular, we design the simulated environment to allow for varying levels of probing interventions that can gather more information. Then, we develop reinforcement learning ITSs that combine learning the individual state of students while pulling from population information through the use of probing interventions. These interventions can reduce the difficulty of student estimation, but also introduce a cost-benefit decision to find a balance between probing enough to get accurate estimates and probing so often that it becomes disruptive to the student. We compare the efficacy of standard RL algorithms with several greedy rules-based heuristic approaches to find that they provide different solutions, but with similar results. We also highlight the difficulty of the problem with increasing levels of hidden information, and the boost that we get if we allow for probing interventions. We show the flexibility of both heuristic and RL policies with regards to changing student population distributions, finding that both are flexible, but RL policies struggle to help harder classes. Finally, we test different course structures with non-probing policies and we find that our policies are able to boost the performance of quiz and midterm structures more than we can in a finals-only structure, highlighting the benefit of having additional information.

---

### Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans

Authors: Zekun Wang, Sashank Varma
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15029v1

Mathematical thinking is a fundamental aspect of human cognition. Cognitive scientists have investigated the mechanisms that underlie our ability to thinking geometrically and numerically, to take two prominent examples, and developmental scientists have documented the trajectories of these abilities over the lifespan. Prior research has shown that computer vision (CV) models trained on the unrelated task of image classification nevertheless learn latent representations of geometric and numerical concepts similar to those of adults. Building on this demonstrated cognitive alignment, the current study investigates whether CV models also show developmental alignment: whether their performance improvements across training to match the developmental progressions observed in children. In a detailed case study of the ResNet-50 model, we show that this is the case. For the case of geometry and topology, we find developmental alignment for some classes of concepts (Euclidean Geometry, Geometrical Figures, Metric Properties, Topology) but not others (Chiral Figures, Geometric Transformations, Symmetrical Figures). For the case of number, we find developmental alignment in the emergence of a human-like ``mental number line'' representation with experience. These findings show the promise of computer vision models for understanding the development of mathematical understanding in humans. They point the way to future research exploring additional model architectures and building larger benchmarks.

---

### Complex-Valued 2D Gaussian Representation for Computer-Generated Holography

Authors: Yicheng Zhan, Xiangjun Gao, Long Quan, Kaan Akşit
Published: 2025-11-19
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2511.15022v2

Complex-valued Gaussian primitives have recently been explored for representing holographic radiance fields in 3D novel view synthesis. In this work, we extend this line of research to the hologram optimization domain and propose a structured representation based on complex-valued 2D Gaussian primitives. Inspired by Gabor's theory, we show that our primitive attains the minimum space-frequency uncertainty and reduces the parameter search space by 5:1 compared to per-pixel parameterization. To enable end-to-end training, we develop a differentiable rasterizer for our representation, integrated with a GPU-optimized light propagation kernel in free space. Extensive experiments show that our method reduces VRAM usage by up to 30% and accelerates optimization by 50% over standard autodiff-based implementations, delivers up to 13 dB higher PSNR than prior Gaussian-based methods, and achieves up to 3200x faster rendering while maintaining reconstruction quality on par with existing CGH approaches. For evaluation, we introduce a conversion procedure that adapts our representation to practical hologram formats, including smooth and random phase-only holograms. By reducing the hologram parameter search space, our representation enables a more scalable hologram estimation in the next-generation computer-generated holography systems.

---

### CKDA: Cross-modality Knowledge Disentanglement and Alignment for Visible-Infrared Lifelong Person Re-identification

Authors: Zhenyu Cui, Jiahuan Zhou, Yuxin Peng
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.15016v1

Lifelong person Re-IDentification (LReID) aims to match the same person employing continuously collected individual data from different scenarios. To achieve continuous all-day person matching across day and night, Visible-Infrared Lifelong person Re-IDentification (VI-LReID) focuses on sequential training on data from visible and infrared modalities and pursues average performance over all data. To this end, existing methods typically exploit cross-modal knowledge distillation to alleviate the catastrophic forgetting of old knowledge. However, these methods ignore the mutual interference of modality-specific knowledge acquisition and modality-common knowledge anti-forgetting, where conflicting knowledge leads to collaborative forgetting. To address the above problems, this paper proposes a Cross-modality Knowledge Disentanglement and Alignment method, called CKDA, which explicitly separates and preserves modality-specific knowledge and modality-common knowledge in a balanced way. Specifically, a Modality-Common Prompting (MCP) module and a Modality-Specific Prompting (MSP) module are proposed to explicitly disentangle and purify discriminative information that coexists and is specific to different modalities, avoiding the mutual interference between both knowledge. In addition, a Cross-modal Knowledge Alignment (CKA) module is designed to further align the disentangled new knowledge with the old one in two mutually independent inter- and intra-modality feature spaces based on dual-modality prototypes in a balanced manner. Extensive experiments on four benchmark datasets verify the effectiveness and superiority of our CKDA against state-of-the-art methods. The source code of this paper is available at https://github.com/PKU-ICST-MIPL/CKDA-AAAI2026.

---

### Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference

Authors: Kexin Chu, Dawei Xiang, Zixu Shen, Yiwei Yang, Zecheng Liu, Wei Zhang
Published: 2025-11-19
Categories: cs.PF, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.15015v4

Mixture-of-Experts (MoE) has become a practical architecture for scaling LLM capacity while keeping per-token compute modest, but deploying MoE models on a single, memory-limited GPU remains difficult because expert weights dominate the HBM footprint. Existing expert offloading and prefetching systems reduce the resident set, yet they often pay expert-loading costs on the critical path when activation becomes dense. Post-training quantization (PTQ) lowers the footprint without transfers, but prevailing pipelines fix expert bit-widths offline and assume routing remains stable, even though MoE expert utilization is heavy-tailed and the hot set can shift across workloads. We present DynaExq, a runtime-aware mixed-precision serving system that treats single-GPU MoE inference under a hard HBM envelope as an online, budget-constrained precision allocation problem. The key insight is to keep the experts that dominate runtime traffic resident at higher precision, while maintaining a low-precision fallback for the remaining experts, so the system can reduce transfer volume and avoid the waiting latency that limits offloading and prefetching under dense activation. DynaExq estimates long-horizon expert hotness from router traces, selects a per-layer high-precision resident set via a budget-feasible top-$n$ rule, and applies promotions and demotions asynchronously through stable expert handles so the forward pass always executes on a fully materialized expert version. Across Qwen3-MoE-30B/80B and six benchmarks, DynaExq improves accuracy over static PTQ on Qwen3-80B (73.09% to 77.57%) under comparable device-memory budgets and achieves up to 2.73x higher throughput than offloading/prefetch baselines at batch size 32.

---

### Latent space analysis and generalization to out-of-distribution data

Authors: Katie Rainey, Erin Hausmann, Donald Waagen, David Gray, Donald Hulsey
Published: 2025-11-19
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.15010v1

Understanding the relationships between data points in the latent decision space derived by the deep learning system is critical to evaluating and interpreting the performance of the system on real world data. Detecting \textit{out-of-distribution} (OOD) data for deep learning systems continues to be an active research topic. We investigate the connection between latent space OOD detection and classification accuracy of the model. Using open source simulated and measured Synthetic Aperture RADAR (SAR) datasets, we empirically demonstrate that the OOD detection cannot be used as a proxy measure for model performance. We hope to inspire additional research into the geometric properties of the latent space that may yield future insights into deep learning robustness and generalizability.

---

### Mathematical Analysis of Hallucination Dynamics in Large Language Models: Uncertainty Quantification, Advanced Decoding, and Principled Mitigation

Authors: Moses Kiprono
Published: 2025-11-19
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.15005v1

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to understand, measure, and mitigate these hallucinations. Drawing on probabilistic modeling, information theory, trigonometric signal analysis, and Bayesian uncertainty estimation, we analyze how errors compound autoregressively, propose refined uncertainty metrics, including semantic and phase-aware variants, and develop principled mitigation strategies such as contrastive decoding, retrieval-augmented grounding, factual alignment, and abstention. This unified lens connects recent advances in calibration, retrieval, and alignment to support safer and more reliable LLMs.

---

### IonCast: A Deep Learning Framework for Forecasting Ionospheric Dynamics

Authors: Halil S. Kelebek, Linnea M. Wolniewicz, Michael D. Vergalla, Simone Mestici, Giacomo Acciarini, Bala Poduval, Olga Verkhoglyadova, Madhulika Guhathakurta, Thomas E. Berger, Frank Soboczenski, Atılım Güneş Baydin
Published: 2025-11-19
Categories: cs.LG, astro-ph.EP
arXiv: https://arxiv.org/abs/2511.15004v1

The ionosphere is a critical component of near-Earth space, shaping GNSS accuracy, high-frequency communications, and aviation operations. For these reasons, accurate forecasting and modeling of ionospheric variability has become increasingly relevant. To address this gap, we present IonCast, a suite of deep learning models that include a GraphCast-inspired model tailored for ionospheric dynamics. IonCast leverages spatiotemporal learning to forecast global Total Electron Content (TEC), integrating diverse physical drivers and observational datasets. Validating on held-out storm-time and quiet conditions highlights improved skill compared to persistence. By unifying heterogeneous data with scalable graph-based spatiotemporal learning, IonCast demonstrates how machine learning can augment physical understanding of ionospheric variability and advance operational space weather resilience.

---

### Resource-Based Time and Cost Prediction in Project Networks: From Statistical Modeling to Graph Neural Networks

Authors: Reza Mirjalili, Behrad Braghi, Shahram Shadrokh Sikari
Published: 2025-11-19
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2511.15003v1

Accurate prediction of project duration and cost remains one of the most challenging aspects of project management, particularly in resource-constrained and interdependent task networks. Traditional analytical techniques such as the Critical Path Method (CPM) and Program Evaluation and Review Technique (PERT) rely on simplified and often static assumptions regarding task interdependencies and resource performance. This study proposes a novel resource-based predictive framework that integrates network representations of project activities with graph neural networks (GNNs) to capture structural and contextual relationships among tasks, resources, and time-cost dynamics. The model represents the project as a heterogeneous activity-resource graph in which nodes denote activities and resources, and edges encode temporal and resource dependencies. We evaluate multiple learning paradigms, including GraphSAGE and Temporal Graph Networks, on both synthetic and benchmark project datasets. Experimental results show that the proposed GNN framework achieves an average 23 to 31 percent reduction in mean absolute error compared to traditional regression and tree-based methods, while improving the coefficient of determination R2 from approximately 0.78 to 0.91 for large and complex project networks. Furthermore, the learned embeddings provide interpretable insights into resource bottlenecks and critical dependencies, enabling more explainable and adaptive scheduling decisions.

---

### Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning

Authors: Fatemeh Lotfi, Hossein Rajoli, Fatemeh Afghah
Published: 2025-11-19
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.15002v1

Next-generation networks utilize the Open Radio Access Network (O-RAN) architecture to enable dynamic resource management, facilitated by the RAN Intelligent Controller (RIC). While deep reinforcement learning (DRL) models show promise in optimizing network resources, they often struggle with robustness and generalizability in dynamic environments. This paper introduces a novel resource management approach that enhances the Soft Actor Critic (SAC) algorithm with Sharpness-Aware Minimization (SAM) in a distributed Multi-Agent RL (MARL) framework. Our method introduces an adaptive and selective SAM mechanism, where regularization is explicitly driven by temporal-difference (TD)-error variance, ensuring that only agents facing high environmental complexity are regularized. This targeted strategy reduces unnecessary overhead, improves training stability, and enhances generalization without sacrificing learning efficiency. We further incorporate a dynamic $ρ$ scheduling scheme to refine the exploration-exploitation trade-off across agents. Experimental results show our method significantly outperforms conventional DRL approaches, yielding up to a $22\%$ improvement in resource allocation efficiency and ensuring superior QoS satisfaction across diverse O-RAN slices.

---

### FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR

Authors: Yueru He, Xueqing Peng, Yupeng Cao, Yan Wang, Lingfei Qian, Haohang Li, Yi Han, Shuyao Wang, Ruoyu Xiang, Fan Zhang, Zhuohan Xie, Mingquan Lin et al.
Published: 2025-11-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14998v3

Recent progress in multimodal large language models (MLLMs) has substantially improved document understanding, yet strong optical character recognition (OCR) performance on surface metrics does not guarantee faithful preservation of decision-critical evidence. This limitation is especially consequential in financial documents, where small visual errors can induce discrete shifts in meaning. To study this gap, we introduce FinCriticalED (Financial Critical Error Detection), a fact-centric visual benchmark for evaluating whether OCR and vision-language systems preserve financially critical evidence beyond lexical similarity. FinCriticalED contains 859 real-world financial document pages with 9,481 expert-annotated facts spanning five critical field types: numeric, temporal, monetary unit, reporting entity, and financial concept. We formulate the task as structured OCR with fact-level verification, and develop a Deterministic-Rule-Guided LLM-as-Judge protocol to assess whether model outputs preserve annotated facts in context. We benchmark 13 systems spanning OCR pipelines, specialized OCR VLMs, open-source MLLMs, and proprietary MLLMs. Results reveal a clear gap between lexical accuracy and factual reliability, with numerical values and monetary units emerging as the most vulnerable fact types, and critical errors concentrating in visually complex, mixed-layout documents with distinct failure patterns across model families. Overall, FinCriticalED provides a rigorous benchmark for trustworthy financial OCR and a practical testbed for evidence fidelity in high-stakes multimodal document understanding. Benchmark and dataset details available at https://the-finai.github.io/FinCriticalED/

---

### Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Authors: Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko, Denis Parkhomenko, Viacheslav Vasilev, Alexey Letunovskiy, Nikolai Vaulin, Maria Kovaleva, Ivan Kirillov, Lev Novitskiy, Denis Koposov, Nikita Kiselev et al.
Published: 2025-11-19
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.14993v3

This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis. The framework comprises three core line-up of models: Kandinsky 5.0 Image Lite - a line-up of 6B parameter image generation models, Kandinsky 5.0 Video Lite - a fast and lightweight 2B parameter text-to-video and image-to-video models, and Kandinsky 5.0 Video Pro - 19B parameter models that achieves superior video generation quality. We provide a comprehensive review of the data curation lifecycle - including collection, processing, filtering and clustering - for the multi-stage training pipeline that involves extensive pre-training and incorporates quality-enhancement techniques such as self-supervised fine-tuning (SFT) and reinforcement learning (RL)-based post-training. We also present novel architectural, training, and inference optimizations that enable Kandinsky 5.0 to achieve high generation speeds and state-of-the-art performance across various tasks, as demonstrated by human evaluation. As a large-scale, publicly available generative framework, Kandinsky 5.0 leverages the full potential of its pre-training and subsequent stages to be adapted for a wide range of generative applications. We hope that this report, together with the release of our open-source code and training checkpoints, will substantially advance the development and accessibility of high-quality generative models for the research community.

---

### FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations

Authors: Yixing Peng, Licheng Zhang, Shancheng Fang, Yi Liu, Peijian Gu, Quan Wang
Published: 2025-11-18
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.18437v1

Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the user query, which degrades answer quality and robustness in real-world settings with noisy or irrelevant retrieved content. Moreover, the prevailing single-pass paradigm struggles to deliver optimal answers in long-form generation that requiring multiple citations. To address these limitations, we propose FineRef, a framework based on Fine-grained error Reflection, which explicitly teaches the model to self-identify and correct two key citation errors, mismatch and irrelevance, on a per-citation basis. FineRef follows a two-stage training strategy. The first stage instills an "attempt-reflect-correct" behavioral pattern via supervised fine-tuning, using fine-grained and controllable reflection data constructed by specialized lightweight models. An online self-reflective bootstrapping strategy is designed to improve generalization by iteratively enriching training data with verified, self-improving examples. To further enhance the self-reflection and correction capability, the second stage applies process-level reinforcement learning with a multi-dimensional reward scheme that promotes reflection accuracy, answer quality, and correction gain. Experiments on the ALCE benchmark demonstrate that FineRef significantly improves both citation performance and answer accuracy. Our 7B model outperforms GPT-4 by up to 18% in Citation F1 and 4% in EM Recall, while also surpassing the state-of-the-art model across key evaluation metrics. FineRef also exhibits strong generalization and robustness in domain transfer settings and noisy retrieval scenarios.

---

### Orchestrating Heterogeneous Experts: A Scalable MoE Framework with Anisotropy-Preserving Fusion

Authors: Ye Liu, Xu Chen, Wuji Chen, Mang Li
Published: 2025-11-18
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.00003v2

In cross-border e-commerce, search relevance modeling faces the dual challenge of extreme linguistic diversity and fine-grained semantic nuances. Existing approaches typically rely on scaling up a single monolithic Large Language Model (LLM). However, our empirical analysis reveals that single models suffer from uneven capability distributions across regions. For example, excelling in English while underperforming in specific Southeast Asian languages. In this work, we shift the paradigm from scaling a single model to orchestrating heterogeneous experts. We propose a scalable Coarse-grained Mixture-of-Experts (MoE) framework that leverages the inherent complementarity of distinct open-source LLMs (e.g., Qwen, Gemma) without expensive pre-training. Unlike standard token-level MoE, our framework dynamically routes entire queries to specialized experts and, crucially, employs an Information-Preserving Concatenation Fusion strategy. We theoretically posit that preserving the distinct embedding manifolds of heterogeneous experts-rather than compressing them via weighted averaging-is essential for capturing complex relevance signals in a multi-model latent space. On datasets spanning six Southeast Asian markets, our MoE improves AUC by 0.72 percentage points over a dense baseline with the same active parameters. Meanwhile, the optimized pipeline achieves 13.72 queries per second (QPS), a 9% throughput improvement.

---

### AI for Proactive Mental Health: A Multi-Institutional, Longitudinal, Randomized Controlled Trial

Authors: Julie Y. A. Cachia, Xuan Zhao, John Hunter, Delancey Wu, Eta Lin, Julian De Freitas
Published: 2025-11-18
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.11530v1

Young adults today face unprecedented mental health challenges, yet many hesitate to seek support due to barriers such as accessibility, stigma, and time constraints. Bite-sized well-being interventions offer a promising solution to preventing mental distress before it escalates to clinical levels, but have not yet been delivered through personalized, interactive, and scalable technology. We conducted the first multi-institutional, longitudinal, preregistered randomized controlled trial of a generative AI-powered mobile app ("Flourish") designed to address this gap. Over six weeks in Fall 2024, 486 undergraduate students from three U.S. institutions were randomized to receive app access or waitlist control. Participants in the treatment condition reported significantly greater positive affect, resilience, and social well-being (i.e., increased belonging, closeness to community, and reduced loneliness) and were buffered against declines in mindfulness and flourishing. These findings suggest that, with purposeful and ethical design, generative AI can deliver proactive, population-level well-being interventions that produce measurable benefits.

---

### SNAP: A Plan-Driven Framework for Controllable Interactive Narrative Generation

Authors: Geonwoo Bang, DongMyung Kim, Hayoung Oh
Published: 2025-11-18
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.11529v1

Large Language Models (LLMs) hold great potential for web-based interactive applications, including browser games, online education, and digital storytelling platforms. However, LLM-based conversational agents suffer from spatiotemporal distortions when responding to variant user inputs, failing to maintain consistency with provided scenarios. We propose SNAP (Story and Narrative-based Agent with Planning), a framework that structures narratives into Cells with explicit Plans to prevent narrative drift in web environments. By confining context within each Cell and employing detailed plans that specify spatiotemporal settings, character actions, and plot developments, SNAP enables coherent and scenario-consistent dialogues while adapting to diverse user responses. Via automated and human evaluations, we validate SNAP's superiority in narrative controllability, demonstrating effective scenario consistency despite variant user inputs in web-based interactive storytelling.

---

### On the Difficulty of Token-Level Modeling of Dysfluency and Fluency Shaping Artifacts

Authors: Kashaf Gulzar, Dominik Wagner, Sebastian P. Bayerl, Florian Hönig, Tobias Bocklet, Korbinian Riedhammer
Published: 2025-11-18
Categories: eess.AS, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.02027v1

Automatic transcription of stuttered speech remains a challenge, even for modern end-to-end (E2E) automatic speech recognition (ASR) frameworks. Dysfluencies and fluency-shaping artifacts are often overlooked, resulting in non-verbatim transcriptions with limited clinical and research value. We propose a parameter-efficient adaptation method to decode dysfluencies and fluency modifications as special tokens within transcriptions, evaluated on simulated (LibriStutter, English) and natural (KSoF, German) stuttered speech datasets. To mitigate ASR performance disparities and bias towards English, we introduce a multi-step fine-tuning strategy with language-adaptive pretraining. Tokenization analysis further highlights the tokenizer's English-centric bias, which poses challenges for improving performance on German data. Our findings demonstrate the effectiveness of lightweight adaptation techniques for dysfluency-aware ASR while exposing key limitations in multilingual E2E systems.

---

### Towards Sustainable Precision: Machine Learning for Laser Micromachining Optimization

Authors: Luis Correas-Naranjo, Miguel Camacho-Sánchez, Laëtitia Launet, Milena Zuric, Valery Naranjo
Published: 2025-11-18
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2512.02026v1

In the pursuit of sustainable manufacturing, ultra-short pulse laser micromachining stands out as a promising solution while also offering high-precision and qualitative laser processing. However, unlocking the full potential of ultra-short pulse lasers requires an optimized monitoring system capable of early detection of defective workpieces, regardless of the preprocessing technique employed. While advances in machine learning can help predict process quality features, the complexity of monitoring data necessitates reducing both model size and data dimensionality to enable real-time analysis. To address these challenges, this paper introduces a machine learning framework designed to enhance surface quality assessment across diverse preprocessing techniques. To facilitate real-time laser processing monitoring, our solution aims to optimize the computational requirements of the machine learning model. Experimental results show that the proposed model not only outperforms the generalizability achieved by previous works across diverse preprocessing techniques but also significantly reduces the computational requirements for training. Through these advancements, we aim to establish the baseline for a more sustainable manufacturing process.

---

### DySTAN: Joint Modeling of Sedentary Activity and Social Context from Smartphone Sensors

Authors: Aditya Sneh, Nilesh Kumar Sahu, Snehil Gupta, Haroon R. Lone
Published: 2025-11-18
Categories: eess.SP, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2512.02025v1

Accurately recognizing human context from smartphone sensor data remains a significant challenge, especially in sedentary settings where activities such as studying, attending lectures, relaxing, and eating exhibit highly similar inertial patterns. Furthermore, social context plays a critical role in understanding user behavior, yet is often overlooked in mobile sensing research. To address these gaps, we introduce LogMe, a mobile sensing application that passively collects smartphone sensor data (accelerometer, gyroscope, magnetometer, and rotation vector) and prompts users for hourly self-reports capturing both sedentary activity and social context. Using this dual-label dataset, we propose DySTAN (Dynamic Cross-Stitch with Task Attention Network), a multi-task learning framework that jointly classifies both context dimensions from shared sensor inputs. It integrates task-specific layers with cross-task attention to model subtle distinctions effectively. DySTAN improves sedentary activity macro F1 scores by 21.8% over a single-task CNN-BiLSTM-GRU (CBG) model and by 8.2% over the strongest multi-task baseline, Sluice Network (SN). These results demonstrate the importance of modeling multiple, co-occurring context dimensions to improve the accuracy and robustness of mobile context recognition.

---

### Reinforcement Learning from Implicit Neural Feedback for Human-Aligned Robot Control

Authors: Suzie Kim
Published: 2025-11-18
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.00050v1

Conventional reinforcement learning (RL) approaches often struggle to learn effective policies under sparse reward conditions, necessitating the manual design of complex, task-specific reward functions. To address this limitation, reinforcement learning from human feedback (RLHF) has emerged as a promising strategy that complements hand-crafted rewards with human-derived evaluation signals. However, most existing RLHF methods depend on explicit feedback mechanisms such as button presses or preference labels, which disrupt the natural interaction process and impose a substantial cognitive load on the user. We propose a novel reinforcement learning from implicit human feedback (RLIHF) framework that utilizes non-invasive electroencephalography (EEG) signals, specifically error-related potentials (ErrPs), to provide continuous, implicit feedback without requiring explicit user intervention. The proposed method adopts a pre-trained decoder to transform raw EEG signals into probabilistic reward components, enabling effective policy learning even in the presence of sparse external rewards. We evaluate our approach in a simulation environment built on the MuJoCo physics engine, using a Kinova Gen2 robotic arm to perform a complex pick-and-place task that requires avoiding obstacles while manipulating target objects. The results show that agents trained with decoded EEG feedback achieve performance comparable to those trained with dense, manually designed rewards. These findings validate the potential of using implicit neural feedback for scalable and human-aligned reinforcement learning in interactive robotics.

---

### Socially aware navigation for mobile robots: a survey on deep reinforcement learning approaches

Authors: Ibrahim Khalil Kabir, Muhammad Faizan Mysorewala
Published: 2025-11-18
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.00049v1

Socially aware navigation is a fast-evolving research area in robotics that enables robots to move within human environments while adhering to the implicit human social norms. The advent of Deep Reinforcement Learning (DRL) has accelerated the development of navigation policies that enable robots to incorporate these social conventions while effectively reaching their objectives. This survey offers a comprehensive overview of DRL-based approaches to socially aware navigation, highlighting key aspects such as proxemics, human comfort, naturalness, trajectory and intention prediction, which enhance robot interaction in human environments. This work critically analyzes the integration of value-based, policy-based, and actor-critic reinforcement learning algorithms alongside neural network architectures, such as feedforward, recurrent, convolutional, graph, and transformer networks, for enhancing agent learning and representation in socially aware navigation. Furthermore, we examine crucial evaluation mechanisms, including metrics, benchmark datasets, simulation environments, and the persistent challenges of sim-to-real transfer. Our comparative analysis of the literature reveals that while DRL significantly improves safety, and human acceptance over traditional approaches, the field still faces setback due to non-uniform evaluation mechanisms, absence of standardized social metrics, computational burdens that limit scalability, and difficulty in transferring simulation to real robotic hardware applications. We assert that future progress will depend on hybrid approaches that leverage the strengths of multiple approaches and producing benchmarks that balance technical efficiency with human-centered evaluation.

---

### DNNs, Dataset Statistics, and Correlation Functions

Authors: Robert W. Batterman, James F. Woodward
Published: 2025-11-18
Categories: physics.hist-ph, cond-mat.stat-mech, cs.LG
arXiv: https://arxiv.org/abs/2511.21715v2

This paper argues that dataset structure is important in image recognition tasks (among other tasks). Specifically, we focus on the nature and genesis of correlational structure in the actual datasets upon which DNNs are trained. We argue that DNNs are implementing a widespread methodology in condensed matter physics and materials science that focuses on mesoscale correlation structures that live between fundamental atomic/molecular scales and continuum scales. Specifically, we argue that DNNs that are successful in image classification must be discovering high order correlation functions. It is well-known that DNNs successfully generalize in apparent contravention of standard statistical learning theory. We consider the implications of our discussion for this puzzle.

---

### GPS: General Per-Sample Prompter

Authors: Pawel Batorski, Paul Swoboda
Published: 2025-11-18
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.21714v1

LLMs are sensitive to prompting, with task performance often hinging on subtle, sometimes imperceptible variations in phrasing. As a result, crafting effective prompts manually remains challenging and time-consuming. Recent automatic prompting methods mitigate this difficulty but face three key limitations: (i) for each new task, they require large datasets to train good prompts;(ii) they rely on costly optimization loops that may take hours; (iii)they typically produce a single task-level prompt that does not adapt to the individual input problem to be solved. We propose GPS, the first general-purpose, per-sample prompting method. Without any task-specific tuning, GPS generates a tailored prompt for each unseen input, improving performance across diverse tasks. The prompter is trained with reinforcement learning on a suite of training tasks and includes a novel regularization for effectively adapting to per-sample prompting. Finally, we employ Minimum Bayes Risk decoding to stabilize inference. Empirically, GPS demonstrates competitive performance: we attain second best results among baselines on text simplification, third best results on summarization and on-par results on classification, while not training on any of these tasks, in contrast to the baselines. For in-domain prompting, we obtain sota on GSM8K. Our work shows the potential of a novel and effective paradigm for automatic prompting: generating adaptive, input-specific prompts without extensive optimization and without access to a task-specific training set. Our code is available at https://github.com/Batorskq/GPS.

---

### EulerESG: Automating ESG Disclosure Analysis with LLMs

Authors: Yi Ding, Xushuo Tang, Zhengyi Yang, Wenqian Zhang, Simin Wu, Yuxin Huang, Lingjing Lan, Weiyuan Li, Yin Chen, Mingchen Ju, Wenke Yang, Thong Hoang et al.
Published: 2025-11-18
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2511.21712v2

Environmental, Social, and Governance (ESG) reports have become central to how companies communicate climate risk, social impact, and governance practices, yet they are still published primarily as long, heterogeneous PDF documents. This makes it difficult to systematically answer seemingly simple questions. Existing tools either rely on brittle rule-based extraction or treat ESG reports as generic text, without explicitly modelling the underlying reporting standards. We present \textbf{EulerESG}, an LLM-powered system for automating ESG disclosure analysis with explicit awareness of ESG frameworks. EulerESG combines (i) dual-channel retrieval and LLM-driven disclosure analysis over ESG reports, and (ii) an interactive dashboard and chatbot for exploration, benchmarking, and explanation. Using four globally recognised companies and twelve SASB sub-industries, we show that EulerESG can automatically populate standard-aligned metric tables with high fidelity (up to 0.95 average accuracy) while remaining practical in end-to-end runtime, and we compare several recent LLM models in this setting. The full implementation, together with a demonstration video, is publicly available at https://github.com/UNSW-database/EulerESG.

---

### Addressing Stereotypes in Large Language Models: A Critical Examination and Mitigation

Authors: Fatima Kazi
Published: 2025-11-18
Categories: cs.CL, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2511.21711v1

Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and implicit biases from the datasets they were trained on; these biases can include social, ethical, cultural, religious, and other prejudices and stereotypes. It is important to comprehensively examine such shortcomings by identifying the existence and extent of such biases, recognizing the origin, and attempting to mitigate such biased outputs to ensure fair outputs to reduce harmful stereotypes and misinformation. This study inspects and highlights the need to address biases in LLMs amid growing generative Artificial Intelligence (AI). We utilize bias-specific benchmarks such StereoSet and CrowSPairs to evaluate the existence of various biases in many different generative models such as BERT, GPT 3.5, and ADA. To detect both explicit and implicit biases, we adopt a three-pronged approach for thorough and inclusive analysis. Results indicate fine-tuned models struggle with gender biases but excel at identifying and avoiding racial biases. Our findings also illustrated that despite some cases of success, LLMs often over-rely on keywords in prompts and its outputs. This demonstrates the incapability of LLMs to attempt to truly understand the accuracy and authenticity of its outputs. Finally, in an attempt to bolster model performance, we applied an enhancement learning strategy involving fine-tuning, models using different prompting techniques, and data augmentation of the bias benchmarks. We found fine-tuned models to exhibit promising adaptability during cross-dataset testing and significantly enhanced performance on implicit bias benchmarks, with performance gains of up to 20%.

---

### Dual-Domain Deep Learning Method to Accelerate Local Basis Functions Computation for Reservoir Simulation in High-Contrast Porous Media

Authors: Peiqi Li, Jie Chen
Published: 2025-11-18
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2511.20685v1

In energy science, Darcy flow in heterogeneous porous media is a central problem in reservoir sim-ulation. However, the pronounced multiscale characteristics of such media pose significant challenges to conventional numerical methods in terms of computational demand and efficiency. The Mixed Generalized Multiscale Finite Element Method (MGMsFEM) provides an effective framework for addressing these challenges, yet the construction of multiscale basis functions remains computationally expensive. In this work, we propose a dual-domain deep learning framework to accelerate the computation of multiscale basis functions within MGMsFEM for solving Darcy flow problems. By extracting and decoding permeability field features in both the frequency and spatial domains, the method enables rapid generation of numerical matrices of multiscale basis functions. Numerical experiments demonstrate that the proposed framework achieves significant computational acceleration while maintaining high approximation accuracy, thereby offering the potential for future applications in real-world reservoir engineering.

---