# Research Papers — 2025-11 · bundle page 82 of 197

> Full-text markdown of papers #4051–4100 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/82
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/81.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/83.md)

### Structured Contrastive Learning for Interpretable Latent Representations

Authors: Zhengyang Shen, Hua Tu, Mayue Shi
Published: 2025-11-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.14920v1

Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to 0.2, while sensor rotations collapse activity recognition performance with inertial measurement units (IMUs). We identify the root cause as "laissez-faire" representation learning, where latent spaces evolve unconstrained provided task performance is satisfied. We propose Structured Contrastive Learning (SCL), a framework that partitions latent space representations into three semantic groups: invariant features that remain consistent under given transformations (e.g., phase shifts or rotations), variant features that actively differentiate transformations via a novel variant mechanism, and free features that preserve task flexibility. This creates controllable push-pull dynamics where different latent dimensions serve distinct, interpretable purposes. The variant mechanism enhances contrastive learning by encouraging variant features to differentiate within positive pairs, enabling simultaneous robustness and interpretability. Our approach requires no architectural modifications and integrates seamlessly into existing training pipelines. Experiments on ECG phase invariance and IMU rotation robustness demonstrate superior performance: ECG similarity improves from 0.25 to 0.91 under phase shifts, while WISDM activity recognition achieves 86.65% accuracy with 95.38% rotation consistency, consistently outperforming traditional data augmentation. This work represents a paradigm shift from reactive data augmentation to proactive structural learning, enabling interpretable latent representations in neural networks.

---

### X-WIN: Building Chest Radiograph World Model via Predictive Sensing

Authors: Zefan Yang, Ge Wang, James Hendler, Mannudeep K. Kalra, Pingkun Yan
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14918v2

Chest X-ray radiography (CXR) is an essential medical imaging technique for disease diagnosis. However, as 2D projectional images, CXRs are limited by structural superposition and hence fail to capture 3D anatomies. This limitation makes representation learning and disease diagnosis challenging. To address this challenge, we propose a novel CXR world model named X-WIN, which distills volumetric knowledge from chest computed tomography (CT) by learning to predict its 2D projections in latent space. The core idea is that a world model with internalized knowledge of 3D anatomical structure can predict CXRs under various transformations in 3D space. During projection prediction, we introduce an affinity-guided contrastive alignment loss that leverages mutual similarities to capture rich, correlated information across projections from the same volume. To improve model adaptability, we incorporate real CXRs into training through masked image modeling and employ a domain classifier to encourage statistically similar representations for real and simulated CXRs. Comprehensive experiments show that X-WIN outperforms existing foundation models on diverse downstream tasks using linear probing and few-shot fine-tuning. X-WIN also demonstrates the ability to render 2D projections for reconstructing a 3D CT volume.

---

### Teaching signal synchronization in deep neural networks with prospective neurons

Authors: Nicolas Zucchet, Qianqian Feng, Axel Laborieux, Friedemann Zenke, Walter Senn, João Sacramento
Published: 2025-11-18
Categories: q-bio.NC, cs.NE
arXiv: https://arxiv.org/abs/2511.14917v2

Working memory requires the brain to maintain information from the recent past to guide ongoing behavior. Neurons can contribute to this capacity by slowly integrating their inputs over time, creating persistent activity that outlasts the original stimulus. However, when these slowly integrating neurons are organized hierarchically, they introduce cumulative delays that create a fundamental challenge for learning: teaching signals that indicate whether behavior was correct or incorrect arrive out-of-sync with the neural activity they are meant to instruct. Here, we demonstrate that neurons enhanced with an adaptive current can compensate for these delays by responding to external stimuli prospectively -- effectively predicting future inputs to synchronize with them. First, we show that such prospective neurons enable teaching signal synchronization across a range of learning algorithms that propagate error signals through hierarchical networks. Second, we demonstrate that this successfully guides learning in slowly integrating neurons, enabling the formation and retrieval of memories over extended timescales. We support our findings with a mathematical analysis of the prospective coding mechanism and learning experiments on motor control tasks. Together, our results reveal how neural adaptation could solve a critical timing problem and enable efficient learning in dynamic environments.

---

### On-Premise SLMs vs. Commercial LLMs: Prompt Engineering and Incident Classification in SOCs and CSIRTs

Authors: Gefté Almeida, Marcio Pohlmann, Alex Severo, Diego Kreutz, Tiago Heinrich, Lourenço Pereira
Published: 2025-11-18
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.14908v1

In this study, we evaluate open-source models for security incident classification, comparing them with proprietary models. We utilize a dataset of anonymized real incidents, categorized according to the NIST SP 800-61r3 taxonomy and processed using five prompt-engineering techniques (PHP, SHP, HTP, PRP, and ZSL). The results indicate that, although proprietary models still exhibit higher accuracy, locally deployed open-source models provide advantages in privacy, cost-effectiveness, and data sovereignty.

---

### nnMIL: A generalizable multiple instance learning framework for computational pathology

Authors: Xiangde Luo, Jinxi Xiang, Yuanfeng Ji, Ruijiang Li
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14907v2

Computational pathology holds substantial promise for improving diagnosis and guiding treatment decisions. Recent pathology foundation models enable the extraction of rich patch-level representations from large-scale whole-slide images (WSIs), but current approaches for aggregating these features into slide-level predictions remain constrained by design limitations that hinder generalizability and reliability. Here we present nnMIL, a simple yet broadly applicable multiple-instance learning framework that connects patch-level foundation models to robust slide-level clinical prediction. nnMIL introduces random sampling at both the patch and feature levels, enabling large-batch optimization, task-aware sampling strategies, and efficient and scalable training across datasets and model architectures. A lightweight aggregator performs sliding-window inference to generate ensemble slide-level predictions and supports principled uncertainty estimation. Across 40,000 WSIs encompassing 35 clinical tasks and four pathology foundation models, nnMIL consistently outperformed existing MIL methods for disease diagnosis, histologic subtyping, molecular biomarker detection, and pan-cancer prognosis prediction. It further demonstrated strong cross-model generalization, reliable uncertainty quantification, and robust survival stratification in multiple external cohorts. In conclusion, nnMIL offers a practical and generalizable solution for translating pathology foundation models into clinically meaningful predictions, advancing the development and deployment of reliable AI systems in real-world settings.

---

### It's LIT! Reliability-Optimized LLMs with Inspectable Tools

Authors: Ruixin Zhang, Jon Donnelly, Zhicheng Guo, Ghazal Khalighinejad, Haiyang Huang, Alina Jade Barnett, Cynthia Rudin
Published: 2025-11-18
Categories: cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2511.14903v1

Large language models (LLMs) have exhibited remarkable capabilities across various domains. The ability to call external tools further expands their capability to handle real-world tasks. However, LLMs often follow an opaque reasoning process, which limits their usefulness in high-stakes domains where solutions need to be trustworthy to end users. LLMs can choose solutions that are unreliable and difficult to troubleshoot, even if better options are available. We address this issue by forcing LLMs to use external -- more reliable -- tools to solve problems when possible. We present a framework built on the tool-calling capabilities of existing LLMs to enable them to select the most reliable and easy-to-troubleshoot solution path, which may involve multiple sequential tool calls. We refer to this framework as LIT (LLMs with Inspectable Tools). In order to support LIT, we introduce a new and challenging benchmark dataset of 1,300 questions and a customizable set of reliability cost functions associated with a collection of specialized tools. These cost functions summarize how reliable each tool is and how easy it is to troubleshoot. For instance, a calculator is reliable across domains, whereas a linear prediction model is not reliable if there is distribution shift, but it is easy to troubleshoot. A tool that constructs a random forest is neither reliable nor easy to troubleshoot. These tools interact with the Harvard USPTO Patent Dataset and a new dataset of NeurIPS 2023 papers to solve mathematical, coding, and modeling problems of varying difficulty levels. We demonstrate that LLMs can achieve more reliable and informed problem-solving while maintaining task performance using our framework.

---

### FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding

Authors: Zhenshi Li, Weikang Yu, Dilxat Muhtar, Xueliang Zhang, Pengfeng Xiao, Pedram Ghamisi, Xiao Xiang Zhu
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14901v1

As CLIP's global alignment limits its ability to capture fine-grained details, recent efforts have focused on enhancing its region-text alignment. However, current remote sensing (RS)-specific CLIP variants still inherit this limited spatial awareness. We identify two key limitations behind this: (1) current RS image-text datasets generate global captions from object-level labels, leaving the original object-level supervision underutilized; (2) despite the success of region-text alignment methods in general domain, their direct application to RS data often leads to performance degradation. To address these, we construct the first multi-granularity RS image-text dataset, MGRS-200k, featuring rich object-level textual supervision for RS region-category alignment. We further investigate existing fine-grained CLIP tuning strategies and find that current explicit region-text alignment methods, whether in a direct or indirect way, underperform due to severe degradation of CLIP's semantic coherence. Building on these, we propose FarSLIP, a Fine-grained Aligned RS Language-Image Pretraining framework. Rather than the commonly used patch-to-CLS self-distillation, FarSLIP employs patch-to-patch distillation to align local and global visual cues, which improves feature discriminability while preserving semantic coherence. Additionally, to effectively utilize region-text supervision, it employs simple CLS token-based region-category alignment rather than explicit patch-level alignment, further enhancing spatial awareness. FarSLIP features improved fine-grained vision-language alignment in RS domain and sets a new state of the art not only on RS open-vocabulary semantic segmentation, but also on image-level tasks such as zero-shot classification and image-text retrieval. Our dataset, code, and models are available at https://github.com/NJU-LHRS/FarSLIP.

---

### Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models

Authors: Zehao Liu, Weijieying Ren, Jipeng Zhang, Tianxiang Zhao, Jingxi Zhu, Xiaoting Li, Vasant G Honavar
Published: 2025-11-18
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.14900v2

Vision--language models (VLMs) have recently shown promise for assisting clinical reasoning in dermatological diagnosis. However, their trustworthiness and clinical utility remain limited by three key challenges: heterogeneous datasets with inconsistent diagnostic labels and concept annotations, the lack of grounded diagnostic rationales for reliable reasoning supervision, and limited scalability when transferring knowledge from small, densely annotated datasets to large collections with sparse labels. To address these challenges, we propose Skin-R1, a dermatology-oriented VLM that integrates textbook-grounded clinical reasoning supervision with reinforcement learning (RL) to improve the accuracy and robustness of diagnostic prediction. First, we construct a textbook-based reasoning generator that synthesizes hierarchy-aware and differential-diagnosis (DDx) diagnostic trajectories derived from authoritative dermatology knowledge. Second, these trajectories are used for supervised fine-tuning (SFT), establishing a clinically grounded reasoning foundation for the model. Finally, we introduce an RL training framework that incorporates the hierarchical structure of dermatological diseases into the reward design, enabling the model to generalize grounded diagnostic reasoning to large-scale datasets with sparse annotations. Extensive experiments across multiple dermatology benchmarks demonstrate that Skin-R1 consistently improves diagnostic accuracy and robustness compared to state-of-the-art Med-VLM baselines. Ablation studies further highlight the critical role of grounded reasoning supervision introduced during the SFT stage.

---

### InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization

Authors: Daniel Gilo, Or Litany
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14899v1

We address the task of multi-view image editing from sparse input views, where the inputs can be seen as a mix of images capturing the scene from different viewpoints. The goal is to modify the scene according to a textual instruction while preserving consistency across all views. Existing methods, based on per-scene neural fields or temporal attention mechanisms, struggle in this setting, often producing artifacts and incoherent edits. We propose InstructMix2Mix (I-Mix2Mix), a framework that distills the editing capabilities of a 2D diffusion model into a pretrained multi-view diffusion model, leveraging its data-driven 3D prior for cross-view consistency. A key contribution is replacing the conventional neural field consolidator in Score Distillation Sampling (SDS) with a multi-view diffusion student, which requires novel adaptations: incremental student updates across timesteps, a specialized teacher noise scheduler to prevent degeneration, and an attention modification that enhances cross-view coherence without additional cost. Experiments demonstrate that I-Mix2Mix significantly improves multi-view consistency while maintaining high per-frame edit quality.

---

### HULFSynth : An INR based Super-Resolution and Ultra Low-Field MRI Synthesis via Contrast factor estimation

Authors: Pranav Indrakanti, Luca Trautmann, Ivor Simpson
Published: 2025-11-18
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.14897v2

We present an unsupervised single image bidirectional Magnetic Resonance Image (MRI) synthesizer that synthesizes an Ultra-Low Field (ULF) like image from a High-Field (HF) magnitude image and vice-versa. Unlike existing MRI synthesis models, our approach is inspired by the physics that drives contrast changes between HF and ULF MRIs. Our forward model simulates a HF to ULF transformation by estimating the tissue-type Signal-to-Noise ratio (SNR) values based on target contrast values. For the Super-Resolution task, we used an Implicit Neural Representation (INR) network to synthesize HF image by simultaneously predicting tissue-type segmentations and image intensity without observed HF data. The proposed method is evaluated using synthetic ULF-like data from generated from standard 3T T$_1$-weighted images for qualitative assessments and paired 3T-64mT T$_1$-weighted images for validation experiments. WM-GM contrast improved by 52% in synthetic ULF-like images and 37% in 64mT images. Sensitivity experiments demonstrated the robustness of our forward model to variations in target contrast, noise and initial seeding.

---

### Bringing Federated Learning to Space

Authors: Grace Kim, Filip Svoboda, Nicholas Lane
Published: 2025-11-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.14889v1

As Low Earth Orbit (LEO) satellite constellations rapidly expand to hundreds and thousands of spacecraft, the need for distributed on-board machine learning becomes critical to address downlink bandwidth limitations. Federated learning (FL) offers a promising framework to conduct collaborative model training across satellite networks. Realizing its benefits in space naturally requires addressing space-specific constraints, from intermittent connectivity to dynamics imposed by orbital motion. This work presents the first systematic feasibility analysis of adapting off-the-shelf FL algorithms for satellite constellation deployment. We introduce a comprehensive "space-ification" framework that adapts terrestrial algorithms (FedAvg, FedProx, FedBuff) to operate under orbital constraints, producing an orbital-ready suite of FL algorithms. We then evaluate these space-ified methods through extensive parameter sweeps across 768 constellation configurations that vary cluster sizes (1-10), satellites per cluster (1-10), and ground station networks (1-13). Our analysis demonstrates that space-adapted FL algorithms efficiently scale to constellations of up to 100 satellites, achieving performance close to the centralized ideal. Multi-month training cycles can be reduced to days, corresponding to a 9x speedup through orbital scheduling and local coordination within satellite clusters. These results provide actionable insights for future mission designers, enabling distributed on-board learning for more autonomous, resilient, and data-driven satellite operations.

---

### Transformer-Guided Deep Reinforcement Learning for Optimal Takeoff Trajectory Design of an eVTOL Drone

Authors: Nathan M. Roberts, Xiaosong Du
Published: 2025-11-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.14887v2

The rapid advancement of electric vertical takeoff and landing (eVTOL) aircraft offers a promising opportunity to alleviate urban traffic congestion but is still limited by excessive power demands, especially during the takeoff phase. Thus, developing optimal takeoff trajectories for minimum energy consumption becomes essential for broader eVTOL aircraft applications. Conventional optimal control methods (such as dynamic programming and linear quadratic regulator) provide highly efficient and well-established solutions but are prohibited by problem dimensionality and complexity. Deep reinforcement learning (DRL) emerges as a special type of artificial intelligence tackling complex, nonlinear systems; however, the training difficulty is a key bottleneck that hinders DRL applications. To address these challenges, we propose the transformer-guided DRL to alleviate the training difficulty by exploring a realistic state space at each time step using a transformer. The proposed transformer-guided DRL was demonstrated on an optimal takeoff trajectory design of an eVTOL drone for minimal energy consumption while meeting takeoff conditions (i.e., minimum vertical displacement and minimum horizontal velocity) by varying control variables (i.e., power and wing angle to the vertical). Results presented that the transformer-guided DRL agent learned to take off with $4.57\times10^6$ time steps, representing $25\%$ of the $19.79\times10^6$ time steps needed by a vanilla DRL agent. In addition, the transformer-guided DRL achieved $97.2\%$ accuracy on the optimal energy consumption compared against the simulation-based optimal reference, while the vanilla DRL achieved $96.1\%$ accuracy. Therefore, the proposed transformer-guided DRL outperformed vanilla DRL in terms of both training efficiency and optimal design verification.

---

### GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis

Authors: Antonio Ruiz, Tao Wu, Andrew Melnik, Qing Cheng, Xuqin Wang, Lu Liu, Yongliang Wang, Yanfeng Zhang, Helge Ritter
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14884v1

Methods that synthesize indoor 3D scenes from text prompts have wide-ranging applications in film production, interior design, video games, virtual reality, and synthetic data generation for training embodied agents. Existing approaches typically either train generative models from scratch or leverage vision-language models (VLMs). While VLMs achieve strong performance, particularly for complex or open-ended prompts, smaller task-specific models remain necessary for deployment on resource-constrained devices such as extended reality (XR) glasses or mobile phones. However, many generative approaches that train from scratch overlook the inherent graph structure of indoor scenes, which can limit scene coherence and realism. Conversely, methods that incorporate scene graphs either demand a user-provided semantic graph, which is generally inconvenient and restrictive, or rely on ground-truth relationship annotations, limiting their capacity to capture more varied object interactions. To address these challenges, we introduce GeoSceneGraph, a method that synthesizes 3D scenes from text prompts by leveraging the graph structure and geometric symmetries of 3D scenes, without relying on predefined relationship classes. Despite not using ground-truth relationships, GeoSceneGraph achieves performance comparable to methods that do. Our model is built on equivariant graph neural networks (EGNNs), but existing EGNN approaches are typically limited to low-dimensional conditioning and are not designed to handle complex modalities such as text. We propose a simple and effective strategy for conditioning EGNNs on text features, and we validate our design through ablation studies.

---

### Exact Learning of Weighted Graphs Using Composite Queries

Authors: Michael T. Goodrich, Songyu Liu, Ioannis Panageas
Published: 2025-11-18
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2511.14882v1

In this paper, we study the exact learning problem for weighted graphs, where we are given the vertex set, $V$, of a weighted graph, $G=(V,E,w)$, but we are not given $E$. The problem, which is also known as graph reconstruction, is to determine all the edges of $E$, including their weights, by asking queries about $G$ from an oracle. As we observe, using simple shortest-path length queries is not sufficient, in general, to learn a weighted graph. So we study a number of scenarios where it is possible to learn $G$ using a subquadratic number of composite queries, which combine two or three simple queries.

---

### Attacking Autonomous Driving Agents with Adversarial Machine Learning: A Holistic Evaluation with the CARLA Leaderboard

Authors: Henry Wong, Clement Fung, Weiran Lin, Karen Li, Stanley Chen, Lujo Bauer
Published: 2025-11-18
Categories: cs.CR, cs.CV, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2511.14876v1

To autonomously control vehicles, driving agents use outputs from a combination of machine-learning (ML) models, controller logic, and custom modules. Although numerous prior works have shown that adversarial examples can mislead ML models used in autonomous driving contexts, it remains unclear if these attacks are effective at producing harmful driving actions for various agents, environments, and scenarios. To assess the risk of adversarial examples to autonomous driving, we evaluate attacks against a variety of driving agents, rather than against ML models in isolation. To support this evaluation, we leverage CARLA, an urban driving simulator, to create and evaluate adversarial examples. We create adversarial patches designed to stop or steer driving agents, stream them into the CARLA simulator at runtime, and evaluate them against agents from the CARLA Leaderboard, a public repository of best-performing autonomous driving agents from an annual research competition. Unlike prior work, we evaluate attacks against autonomous driving systems without creating or modifying any driving-agent code and against all parts of the agent included with the ML model. We perform a case-study investigation of two attack strategies against three open-source driving agents from the CARLA Leaderboard across multiple driving scenarios, lighting conditions, and locations. Interestingly, we show that, although some attacks can successfully mislead ML models into predicting erroneous stopping or steering commands, some driving agents use modules, such as PID control or GPS-based rules, that can overrule attacker-manipulated predictions from ML models.

---

### B-Rep Distance Functions (BR-DF): How to Represent a B-Rep Model by Volumetric Distance Functions?

Authors: Fuyang Zhang, Pradeep Kumar Jayaraman, Xiang Xu, Yasutaka Furukawa
Published: 2025-11-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.14870v1

This paper presents a novel geometric representation for CAD Boundary Representation (B-Rep) based on volumetric distance functions, dubbed B-Rep Distance Functions (BR-DF). BR-DF encodes the surface mesh geometry of a CAD model as signed distance function (SDF). B-Rep vertices, edges, faces and their topology information are encoded as per-face unsigned distance functions (UDFs). An extension of the Marching Cubes algorithm converts BR-DF directly into watertight CAD B-Rep model (strictly speaking a faceted B-Rep model). A surprising characteristic of BR-DF is that this conversion process never fails. Leveraging the volumetric nature of BR-DF, we propose a multi-branch latent diffusion with 3D U-Net backbone for jointly generating the SDF and per-face UDFs of a BR-DF model. Our approach achieves comparable CAD generation performance against SOTA methods while reaching the unprecedented 100% success rate in producing (faceted) B-Rep models.

---

### Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings

Authors: Xueying Ding, Xingyue Huang, Mingxuan Ju, Liam Collins, Yozen Liu, Leman Akoglu, Neil Shah, Tong Zhao
Published: 2025-11-18
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.14868v1

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by prepending a single summary token, they over-compress information, hence harming performance on long documents. We propose Hierarchical Token Prepending (HTP), a method that resolves two critical bottlenecks. To mitigate attention-level compression, HTP partitions the input into blocks and prepends block-level summary tokens to subsequent blocks, creating multiple pathways for backward information flow. To address readout-level over-squashing, we replace last-token pooling with mean-pooling, a choice supported by theoretical analysis. HTP achieves consistent performance gains across 11 retrieval datasets and 30 general embedding benchmarks, especially in long-context settings. As a simple, architecture-agnostic method, HTP enhances both zero-shot and finetuned models, offering a scalable route to superior long-document embeddings.

---

### FinTRec: Transformer Based Unified Contextual Ads Targeting and Personalization for Financial Applications

Authors: Dwipam Katariya, Snehita Varma, Akshat Shreemali, Benjamin Wu, Kalanand Mishra, Pranab Mohanty
Published: 2025-11-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.14865v1

Transformer-based architectures are widely adopted in sequential recommendation systems, yet their application in Financial Services (FS) presents distinct practical and modeling challenges for real-time recommendation. These include:a) long-range user interactions (implicit and explicit) spanning both digital and physical channels generating temporally heterogeneous context, b) the presence of multiple interrelated products require coordinated models to support varied ad placements and personalized feeds, while balancing competing business goals. We propose FinTRec, a transformer-based framework that addresses these challenges and its operational objectives in FS. While tree-based models have traditionally been preferred in FS due to their explainability and alignment with regulatory requirements, our study demonstrate that FinTRec offers a viable and effective shift toward transformer-based architectures. Through historic simulation and live A/B test correlations, we show FinTRec consistently outperforms the production-grade tree-based baseline. The unified architecture, when fine-tuned for product adaptation, enables cross-product signal sharing, reduces training cost and technical debt, while improving offline performance across all products. To our knowledge, this is the first comprehensive study of unified sequential recommendation modeling in FS that addresses both technical and business considerations.

---

### When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation

Authors: Aashish Ghimire, Jun Zeng, Roshan Paudel, Nikhil Kumar Tomar, Deepak Ranjan Nayak, Harshith Reddy Nalla, Vivek Jha, Glenda Reynolds, Debesh Jha
Published: 2025-11-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.14860v1

Accurate identification and segmentation of dental caries in panoramic radiographs are critical for early diagnosis and effective treatment planning. Automated segmentation remains challenging due to low lesion contrast, morphological variability, and limited annotated data. In this study, we present the first comprehensive benchmarking of convolutional neural networks, vision transformers and state-space mamba architectures for automated dental caries segmentation on panoramic radiographs through a DC1000 dataset. Twelve state-of-the-art architectures, including VMUnet, MambaUNet, VMUNetv2, RMAMamba-S, TransNetR, PVTFormer, DoubleU-Net, and ResUNet++, were trained under identical configurations. Results reveal that, contrary to the growing trend toward complex attention based architectures, the CNN-based DoubleU-Net achieved the highest dice coefficient of 0.7345, mIoU of 0.5978, and precision of 0.8145, outperforming all transformer and Mamba variants. In the study, the top 3 results across all performance metrics were achieved by CNN-based architectures. Here, Mamba and transformer-based methods, despite their theoretical advantage in global context modeling, underperformed due to limited data and weaker spatial priors. These findings underscore the importance of architecture-task alignment in domain-specific medical image segmentation more than model complexity. Our code is available at: https://github.com/JunZengz/dental-caries-segmentation.

---

### Uncertainty-Aware Measurement of Scenario Suite Representativeness for Autonomous Systems

Authors: Robab Aghazadeh Chakherlou, Siddartha Khastgir, Xingyu Zhao, Jerein Jeyachandran, Shufeng Chen
Published: 2025-11-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.14853v2

Assuring the trustworthiness and safety of AI systems, e.g., autonomous vehicles (AV), depends critically on the data-related safety properties, e.g., representativeness, completeness, etc., of the datasets used for their training and testing. Among these properties, this paper focuses on representativeness-the extent to which the scenario-based data used for training and testing, reflect the operational conditions that the system is designed to operate safely in, i.e., Operational Design Domain (ODD) or expected to encounter, i.e., Target Operational Domain (TOD). We propose a probabilistic method that quantifies representativeness by comparing the statistical distribution of features encoded by the scenario suites with the corresponding distribution of features representing the TOD, acknowledging that the true TOD distribution is unknown, as it can only be inferred from limited data. We apply an imprecise Bayesian method to handle limited data and uncertain priors. The imprecise Bayesian formulation produces interval-valued, uncertainty-aware estimates of representativeness, rather than a single value. We present a numerical example comparing the distributions of the scenario suite and the inferred TOD across operational categories-weather, road type, time of day, etc., under dependencies and prior uncertainty. We estimate representativeness locally (between categories) and globally as an interval.

---

### PolyKAN: Efficient Fused GPU Operators for Polynomial Kolmogorov-Arnold Network Variants

Authors: Mingkun Yu, Heming Zhong, Dan Huang, Yutong Lu, Jiazhi Jiang
Published: 2025-11-18
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2511.14852v1

Kolmogorov-Arnold Networks (KANs) promise higher expressive capability and stronger interpretability than Multi-Layer Perceptron, particularly in the domain of AI for Science. However, practical adoption has been hindered by low GPU utilization of existing parallel implementations. To address this challenge, we present a GPU-accelerated operator library, named PolyKAN which is the first general open-source implementation of KAN and its variants. PolyKAN fuses the forward and backward passes of polynomial KAN layers into a concise set of optimized CUDA kernels. Four orthogonal techniques underpin the design: (i) \emph{lookup-table} with linear interpolation that replaces runtime expensive math-library functions; (ii) \emph{2D tiling} to expose thread-level parallelism with preserving memory locality; (iii) a \emph{two-stage reduction} scheme converting scattered atomic updates into a single controllable merge step; and (iv) \emph{coefficient-layout reordering} yielding unit-stride reads under the tiled schedule. Using a KAN variant, Chebyshev KAN, as a case-study, PolyKAN delivers $1.2$--$10\times$ faster inference and $1.4$--$12\times$ faster training than a Triton + cuBLAS baseline, with identical accuracy on speech, audio-enhancement, and tabular-regression workloads on both highend GPU and consumer-grade GPU.

---

### Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video

Authors: Yarin Bekor, Gal Michael Harari, Or Perel, Or Litany
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14848v1

We present Gaussian See, Gaussian Do, a novel approach for semantic 3D motion transfer from multiview video. Our method enables rig-free, cross-category motion transfer between objects with semantically meaningful correspondence. Building on implicit motion transfer techniques, we extract motion embeddings from source videos via condition inversion, apply them to rendered frames of static target shapes, and use the resulting videos to supervise dynamic 3D Gaussian Splatting reconstruction. Our approach introduces an anchor-based view-aware motion embedding mechanism, ensuring cross-view consistency and accelerating convergence, along with a robust 4D reconstruction pipeline that consolidates noisy supervision videos. We establish the first benchmark for semantic 3D motion transfer and demonstrate superior motion fidelity and structural consistency compared to adapted baselines. Code and data for this paper available at https://gsgd-motiontransfer.github.io/

---

### Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization

Authors: Yifeng Ding, Hung Le, Songyang Han, Kangrui Ruan, Zhenghui Jin, Varun Kumar, Zijian Wang, Anoop Deoras
Published: 2025-11-18
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.14846v2

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches. Current RL methods, exemplified by Group Relative Policy Optimization (GRPO), suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation. To address this issue, we propose Group Turn Policy Optimization (GTPO), a novel RL algorithm specifically designed for training LLMs on multi-turn TIR tasks. GTPO introduces three key innovations: (1) turn-level reward assignment that provides fine-grained feedback for individual turns, (2) return-based advantage estimation where normalized discounted returns are calculated as advantages, and (3) self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards. Our comprehensive evaluation demonstrates that GTPO outperforms GRPO by 3.0% across diverse math reasoning benchmarks, establishing its effectiveness. GTPO also improves GRPO by 3.9% on commonsense reasoning and program synthesis tasks, demonstrating its generalizability to non-math domains. Importantly, GTPO incurs negligible overhead, ensuring its practicality for real-world scenarios.

---

### How to pick the best anomaly detector?

Authors: Marie Hein, Gregor Kasieczka, Michael Krämer, Louis Moureaux, Alexander Mück, David Shih
Published: 2025-11-18
Categories: hep-ph, cs.LG, hep-ex, physics.data-an
arXiv: https://arxiv.org/abs/2511.14832v2

Anomaly detection has the potential to discover new physics in unexplored regions of the data. However, choosing the best anomaly detector for a given data set in a model-agnostic way is an important challenge which has hitherto largely been neglected. In this paper, we introduce the data-driven ARGOS metric, which has a sound theoretical foundation and is empirically shown to robustly select the most sensitive anomaly detection model given the data. Focusing on weakly-supervised, classifier-based anomaly detection methods, we show that the ARGOS metric outperforms other model selection metrics previously used in the literature, in particular the binary cross-entropy loss. We explore several realistic applications, including hyperparameter tuning as well as architecture and feature selection, and in all cases we demonstrate that ARGOS is robust to the noisy conditions of anomaly detection.

---

### Implicit Bias of the JKO Scheme

Authors: Peter Halmos, Boris Hanin
Published: 2025-11-18
Categories: stat.ML, cs.AI, cs.LG, math.AP
arXiv: https://arxiv.org/abs/2511.14827v3

Wasserstein gradient flow provides a general framework for minimizing an energy functional $J$ over the space of probability measures on a Riemannian manifold $(M,g)$. Its canonical time-discretization, the Jordan-Kinderlehrer-Otto (JKO) scheme, produces for any step size $η>0$ a sequence of probability distributions $ρ_k^η$ that approximate to first order in $η$ Wasserstein gradient flow on $J$. But the JKO scheme also has many other remarkable properties not shared by other first order integrators, e.g. it preserves energy dissipation and exhibits unconditional stability for $λ$-geodesically convex functionals $J$. To better understand the JKO scheme we characterize its implicit bias at second order in $η$. We show that $ρ_k^η$ are approximated to order $η^2$ by Wasserstein gradient flow on a modified energy \( J^η(ρ) = J(ρ) - \fracη{4}\int_M \Big\lVert \nabla_g \frac{δJ}{δρ} (ρ) \Big\rVert_{2}^{2} \,ρ(dx), \) obtained by subtracting from $J$ the squared metric curvature of $J$ times $η/4$. The JKO scheme therefore adds at second order in $η$ a deceleration in directions where the metric curvature of $J$ is rapidly changing. This corresponds to canonical implicit biases for common functionals: for entropy the implicit bias is the Fisher information, for KL-divergence it is the Fisher-Hyv{ä}rinen divergence, and for Riemannian gradient descent it is the kinetic energy in the metric $g$. To understand the differences between minimizing $J$ and $J^η$ we study JKO-Flow, Wasserstein gradient flow on $J^η$, in several simple numerical examples. These include exactly solvable Langevin dynamics on the Bures-Wasserstein space and Langevin sampling from a quartic potential in 1D.

---

### Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech

Authors: Nam-Gyu Kim
Published: 2025-11-18
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2511.14824v1

Recent advances in expressive text-to-speech (TTS) have introduced diverse methods based on style embedding extracted from reference speech. However, synthesizing high-quality expressive speech remains challenging. We propose SpotlightTTS, which exclusively emphasizes style via voiced-aware style extraction and style direction adjustment. Voiced-aware style extraction focuses on voiced regions highly related to style while maintaining continuity across different speech regions to improve expressiveness. We adjust the direction of the extracted style for optimal integration into the TTS model, which improves speech quality. Experimental results demonstrate that Spotlight-TTS achieves superior performance compared to baseline models in terms of expressiveness, overall speech quality, and style transfer capability.

---

### Dynamic Nested Hierarchies: Pioneering Self-Evolution in Machine Learning Architectures for Lifelong Intelligence

Authors: Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari
Published: 2025-11-18
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.14823v1

Contemporary machine learning models, including large language models, exhibit remarkable capabilities in static tasks yet falter in non-stationary environments due to rigid architectures that hinder continual adaptation and lifelong learning. Building upon the nested learning paradigm, which decomposes models into multi-level optimization problems with fixed update frequencies, this work proposes dynamic nested hierarchies as the next evolutionary step in advancing artificial intelligence and machine learning. Dynamic nested hierarchies empower models to autonomously adjust the number of optimization levels, their nesting structures, and update frequencies during training or inference, inspired by neuroplasticity to enable self-evolution without predefined constraints. This innovation addresses the anterograde amnesia in existing models, facilitating true lifelong learning by dynamically compressing context flows and adapting to distribution shifts. Through rigorous mathematical formulations, theoretical proofs of convergence, expressivity bounds, and sublinear regret in varying regimes, alongside empirical demonstrations of superior performance in language modeling, continual learning, and long-context reasoning, dynamic nested hierarchies establish a foundational advancement toward adaptive, general-purpose intelligence.

---

### Project Rachel: Can an AI Become a Scholarly Author?

Authors: Martin Monperrus, Benoit Baudry, Clément Vidal
Published: 2025-11-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.14819v3

This paper documents Project Rachel, an action research study that created and tracked a complete AI academic identity named Rachel So. Through careful publication of AI-generated research papers, we investigate how the scholarly ecosystem responds to AI authorship. Rachel So published 10+ papers between March and October 2025, was cited, and received a peer review invitation. We discuss the implications of AI authorship on publishers, researchers, and the scientific system at large. This work contributes empirical action research data to the necessary debate about the future of scholarly communication with super human, hyper capable AI systems.

---

### DEVAL: A Framework for Evaluating and Improving the Derivation Capability of Large Language Models

Authors: Yifan Li, Qin Li, Min Zhang, Min Zhang
Published: 2025-11-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.14813v2

Assessing the reasoning ability of Large Language Models (LLMs) over data remains an open and pressing research question. Compared with LLMs, human reasoning can derive corresponding modifications to the output based on certain kinds of changes to the input. This reasoning pattern, which relies on abstract rules that govern relationships between changes of data, has not been comprehensively described or evaluated in LLMs. In this paper, we formally define this reasoning pattern as the Derivation Relation (DR) and introduce the concept of Derivation Capability (DC), i.e. applying DR by making the corresponding modification to the output whenever the input takes certain changes. To assess DC, a systematically constructed evaluation framework named DEVAL is proposed and used to evaluate five popular LLMs and one Large Reasoning Model in seven mainstream tasks. The evaluation results show that mainstream LLMs, such as GPT-4o and Claude3.5, exhibit moderate DR recognition capabilities but reveal significant drop-offs on applying DR effectively in problem-solving scenarios. To improve this, we propose a novel prompt engineering approach called Derivation Prompting (DP). It achieves an average improvement of 15.2% in DC for all tested LLMs, outperforming commonly used prompt engineering techniques.

---

### ARC Is a Vision Problem!

Authors: Keya Hu, Ali Cy, Linlu Qiu, Xiaoman Delores Ding, Runqian Wang, Yeyin Eva Zhu, Jacob Andreas, Kaiming He
Published: 2025-11-18
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.14761v1

The Abstraction and Reasoning Corpus (ARC) is designed to promote research on abstract reasoning, a fundamental aspect of human intelligence. Common approaches to ARC treat it as a language-oriented problem, addressed by large language models (LLMs) or recurrent reasoning models. However, although the puzzle-like tasks in ARC are inherently visual, existing research has rarely approached the problem from a vision-centric perspective. In this work, we formulate ARC within a vision paradigm, framing it as an image-to-image translation problem. To incorporate visual priors, we represent the inputs on a "canvas" that can be processed like natural images. It is then natural for us to apply standard vision architectures, such as a vanilla Vision Transformer (ViT), to perform image-to-image mapping. Our model is trained from scratch solely on ARC data and generalizes to unseen tasks through test-time training. Our framework, termed Vision ARC (VARC), achieves 60.4% accuracy on the ARC-1 benchmark, substantially outperforming existing methods that are also trained from scratch. Our results are competitive with those of leading LLMs and close the gap to average human performance.

---

### UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning

Authors: Rui Tian, Mingfei Gao, Haiming Gang, Jiasen Lu, Zhe Gan, Yinfei Yang, Zuxuan Wu, Afshin Dehghan
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14760v1

We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen the image understanding and generation capabilities while unlocking strong image editing ability. Especially, we propose a unified Reinforcement Learning (RL) strategy that improves both image generation and image editing jointly via shared reward models. To further enhance image editing performance, we propose a light Edit Instruction Alignment stage that significantly improves the editing instruction comprehension that is essential for the success of the RL training. Experimental results show that UniGen-1.5 demonstrates competitive understanding and generation performance. Specifically, UniGen-1.5 achieves 0.89 and 4.31 overall scores on GenEval and ImgEdit that surpass the state-of-the-art models such as BAGEL and reaching performance comparable to proprietary models such as GPT-Image-1.

---

### $π^{*}_{0.6}$: a VLA That Learns From Experience

Authors: Physical Intelligence, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Jared DiCarlo, Danny Driess, Michael Equi et al.
Published: 2025-11-18
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2511.14759v2

We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of VLAs via advantage conditioning. Our method incorporates heterogeneous data into the self-improvement process, including demonstrations, data from on-policy collection, and expert teleoperated interventions provided during autonomous execution. RECAP starts by pre-training a generalist VLA with offline RL, which we call $π^{*}_{0.6}$, that can then be specialized to attain high performance on downstream tasks through on-robot data collection. We show that the $π^{*}_{0.6}$ model trained with the full RECAP method can fold laundry in real homes, reliably assemble boxes, and make espresso drinks using a professional espresso machine. On some of the hardest tasks, RECAP more than doubles task throughput and roughly halves the task failure rate.

---

### Robust Verification of Controllers under State Uncertainty via Hamilton-Jacobi Reachability Analysis

Authors: Albert Lin, Alessandro Pinto, Somil Bansal
Published: 2025-11-18
Categories: cs.RO, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2511.14755v2

As perception-based controllers for autonomous systems become increasingly popular in the real world, it is important that we can formally verify their safety and performance despite perceptual uncertainty. Unfortunately, the verification of such systems remains challenging, largely due to the complexity of the controllers, which are often nonlinear, nonconvex, learning-based, and/or black-box. Prior works propose verification algorithms that are based on approximate reachability methods, but they often restrict the class of controllers and systems that can be handled or result in overly conservative analyses. Hamilton-Jacobi (HJ) reachability analysis is a popular formal verification tool for general nonlinear systems that can compute optimal reachable sets under worst-case system uncertainties; however, its application to perception-based systems is currently underexplored. In this work, we propose RoVer-CoRe, a framework for the Robust Verification of Controllers via HJ Reachability. To the best of our knowledge, RoVer-CoRe is the first HJ reachability-based framework for the verification of perception-based systems under perceptual uncertainty. Our key insight is to concatenate the system controller, observation function, and the state estimation modules to obtain an equivalent closed-loop system that is readily compatible with existing reachability frameworks. Within RoVer-CoRe, we propose novel methods for formal safety verification and robust controller design. We demonstrate the efficacy of the framework in case studies involving aircraft taxiing and NN-based rover navigation. Code is available at the link in the footnote.

---

### SparseST: Exploiting Data Sparsity in Spatiotemporal Modeling and Prediction

Authors: Junfeng Wu, Hadjer Benmeziane, Kaoutar El Maghraoui, Liu Liu, Yinan Wang
Published: 2025-11-18
Categories: cs.LG, cs.CE
arXiv: https://arxiv.org/abs/2511.14753v1

Spatiotemporal data mining (STDM) has a wide range of applications in various complex physical systems (CPS), i.e., transportation, manufacturing, healthcare, etc. Among all the proposed methods, the Convolutional Long Short-Term Memory (ConvLSTM) has proved to be generalizable and extendable in different applications and has multiple variants achieving state-of-the-art performance in various STDM applications. However, ConvLSTM and its variants are computationally expensive, which makes them inapplicable in edge devices with limited computational resources. With the emerging need for edge computing in CPS, efficient AI is essential to reduce the computational cost while preserving the model performance. Common methods of efficient AI are developed to reduce redundancy in model capacity (i.e., model pruning, compression, etc.). However, spatiotemporal data mining naturally requires extensive model capacity, as the embedded dependencies in spatiotemporal data are complex and hard to capture, which limits the model redundancy. Instead, there is a fairly high level of data and feature redundancy that introduces an unnecessary computational burden, which has been largely overlooked in existing research. Therefore, we developed a novel framework SparseST, that pioneered in exploiting data sparsity to develop an efficient spatiotemporal model. In addition, we explore and approximate the Pareto front between model performance and computational efficiency by designing a multi-objective composite loss function, which provides a practical guide for practitioners to adjust the model according to computational resource constraints and the performance requirements of downstream tasks.

---

### Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers

Authors: Yutian Chen, Yuheng Qiu, Ruogu Li, Ali Agha, Shayegan Omidshafiei, Jay Patrikar, Sebastian Scherer
Published: 2025-11-18
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.14751v2

We propose Confidence-Guided Token Merging (Co-Me), an acceleration mechanism for visual geometric transformers without retraining or finetuning the base model. Co-Me distilled a light-weight confidence predictor to rank tokens by uncertainty and selectively merge low-confidence ones, effectively reducing computation while maintaining spatial coverage. Compared to similarity-based merging or pruning, the confidence signal in Co-Me reliably indicates regions emphasized by the transformer, enabling substantial acceleration without degrading performance. Co-Me applies seamlessly to various multi-view and streaming visual geometric transformers, achieving speedups that scale with sequence length. When applied to VGGT and Pi3, Co-Me achieves up to 21.5x and 20.4x speedup, making visual geometric transformers practical for real-time 3D perception and reconstruction.

---

### Vision Large Language Models Are Good Noise Handlers in Engagement Analysis

Authors: Alexander Vedernikov, Puneet Kumar, Haoyu Chen, Tapio Seppänen, Xiaobai Li
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14749v1

Engagement recognition in video datasets, unlike traditional image classification tasks, is particularly challenged by subjective labels and noise limiting model performance. To overcome the challenges of subjective and noisy engagement labels, we propose a framework leveraging Vision Large Language Models (VLMs) to refine annotations and guide the training process. Our framework uses a questionnaire to extract behavioral cues and split data into high- and low-reliability subsets. We also introduce a training strategy combining curriculum learning with soft label refinement, gradually incorporating ambiguous samples while adjusting supervision to reflect uncertainty. We demonstrate that classical computer vision models trained on refined high-reliability subsets and enhanced with our curriculum strategy show improvements, highlighting benefits of addressing label subjectivity with VLMs. This method surpasses prior state of the art across engagement benchmarks such as EngageNet (three of six feature settings, maximum improvement of +1.21%), and DREAMS / PAFE with F1 gains of +0.22 / +0.06.

---

### Look-Ahead Reasoning on Learning Platforms

Authors: Haiqing Zhu, Tijana Zrnic, Celestine Mendler-Dünner
Published: 2025-11-18
Categories: cs.LG, cs.GT, stat.ML
arXiv: https://arxiv.org/abs/2511.14745v2

On many learning platforms, the optimization criteria guiding model training reflect the priorities of the designer rather than those of the individuals they affect. Consequently, users may act strategically to obtain more favorable outcomes. While past work has studied strategic user behavior on learning platforms, the focus has largely been on strategic responses to a deployed model, without considering the behavior of other users. In contrast, look-ahead reasoning takes into account that user actions are coupled, and -- at scale -- impact future predictions. Within this framework, we first formalize level-k thinking, a concept from behavioral economics, where users aim to outsmart their peers by looking one step ahead. We show that, while convergence to an equilibrium is accelerated, the equilibrium remains the same, providing no benefit of higher-level reasoning for individuals in the long run. Then, we focus on collective reasoning, where users take coordinated actions by optimizing through their joint impact on the model. By contrasting collective with selfish behavior, we characterize the benefits and limits of coordination; a new notion of alignment between the learner's and the users' utilities emerges as a key concept. Look-ahead reasoning can be seen as a generalization of algorithmic collective action; we thus offer the first results characterizing the utility trade-offs of coordination when contesting algorithmic systems.

---

### Measuring AI Progress in Drug Discovery: A Reproducible Leaderboard for the Tox21 Challenge

Authors: Antonia Ebner, Christoph Bartmann, Sonja Topf, Sohvi Luukkonen, Johannes Schimunek, Günter Klambauer
Published: 2025-11-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.14744v1

Deep learning's rise since the early 2010s has transformed fields like computer vision and natural language processing and strongly influenced biomedical research. For drug discovery specifically, a key inflection - akin to vision's "ImageNet moment" - arrived in 2015, when deep neural networks surpassed traditional approaches on the Tox21 Data Challenge. This milestone accelerated the adoption of deep learning across the pharmaceutical industry, and today most major companies have integrated these methods into their research pipelines. After the Tox21 Challenge concluded, its dataset was included in several established benchmarks, such as MoleculeNet and the Open Graph Benchmark. However, during these integrations, the dataset was altered and labels were imputed or manufactured, resulting in a loss of comparability across studies. Consequently, the extent to which bioactivity and toxicity prediction methods have improved over the past decade remains unclear. To this end, we introduce a reproducible leaderboard, hosted on Hugging Face with the original Tox21 Challenge dataset, together with a set of baseline and representative methods. The current version of the leaderboard indicates that the original Tox21 winner - the ensemble-based DeepTox method - and the descriptor-based self-normalizing neural networks introduced in 2017, continue to perform competitively and rank among the top methods for toxicity prediction, leaving it unclear whether substantial progress in toxicity prediction has been achieved over the past decade. As part of this work, we make all baselines and evaluated models publicly accessible for inference via standardized API calls to Hugging Face Spaces.

---

### Beyond Means: A Dynamic Framework for Predicting Customer Satisfaction

Authors: Christof Naumzik, Abdurahman Maarouf, Stefan Feuerriegel, Markus Weinmann
Published: 2025-11-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.14743v1

Online ratings influence customer decision-making, yet standard aggregation methods, such as the sample mean, fail to adapt to quality changes over time and ignore review heterogeneity (e.g., review sentiment, a review's helpfulness). To address these challenges, we demonstrate the value of using the Gaussian process (GP) framework for rating aggregation. Specifically, we present a tailored GP model that captures the dynamics of ratings over time while additionally accounting for review heterogeneity. Based on 121,123 ratings from Yelp, we compare the predictive power of different rating aggregation methods in predicting future ratings, thereby finding that the GP model is considerably more accurate and reduces the mean absolute error by 10.2% compared to the sample mean. Our findings have important implications for marketing practitioners and customers. By moving beyond means, designers of online reputation systems can display more informative and adaptive aggregated rating scores that are accurate signals of expected customer satisfaction.

---

### A Neural Field-Based Approach for View Computation & Data Exploration in 3D Urban Environments

Authors: Stefan Cobeli, Kazi Shahrukh Omar, Rodrigo Valença, Nivan Ferreira, Fabio Miranda
Published: 2025-11-18
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2511.14742v1

Despite the growing availability of 3D urban datasets, extracting insights remains challenging due to computational bottlenecks and the complexity of interacting with data. In fact, the intricate geometry of 3D urban environments results in high degrees of occlusion and requires extensive manual viewpoint adjustments that make large-scale exploration inefficient. To address this, we propose a view-based approach for 3D data exploration, where a vector field encodes views from the environment. To support this approach, we introduce a neural field-based method that constructs an efficient implicit representation of 3D environments. This representation enables both faster direct queries, which consist of the computation of view assessment indices, and inverse queries, which help avoid occlusion and facilitate the search for views that match desired data patterns. Our approach supports key urban analysis tasks such as visibility assessments, solar exposure evaluation, and assessing the visual impact of new developments. We validate our method through quantitative experiments, case studies informed by real-world urban challenges, and feedback from domain experts. Results show its effectiveness in finding desirable viewpoints, analyzing building facade visibility, and evaluating views from outdoor spaces. Code and data are publicly available at https://urbantk.org/neural-3d.

---

### LAUD: Integrating Large Language Models with Active Learning for Unlabeled Data

Authors: Tzu-Hsuan Chou, Chun-Nan Chou
Published: 2025-11-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.14738v1

Large language models (LLMs) have shown a remarkable ability to generalize beyond their pre-training data, and fine-tuning LLMs can elevate performance to human-level and beyond. However, in real-world scenarios, lacking labeled data often prevents practitioners from obtaining well-performing models, thereby forcing practitioners to highly rely on prompt-based approaches that are often tedious, inefficient, and driven by trial and error. To alleviate this issue of lacking labeled data, we present a learning framework integrating LLMs with active learning for unlabeled dataset (LAUD). LAUD mitigates the cold-start problem by constructing an initial label set with zero-shot learning. Experimental results show that LLMs derived from LAUD outperform LLMs with zero-shot or few-shot learning on commodity name classification tasks, demonstrating the effectiveness of LAUD.

---

### Heterogeneous Multi-Agent Proximal Policy Optimization for Power Distribution System Restoration

Authors: Parya Dolatyabi, Ali Farajzadeh Bavil, Mahdi Khodayar
Published: 2025-11-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.14730v5

Restoring power distribution systems (PDSs) after large-scale outages requires sequential switching actions that reconfigure feeder topology and coordinate distributed energy resources (DERs) under nonlinear constraints, including power balance, voltage limits, and thermal ratings. These challenges limit the scalability of conventional optimization and value-based reinforcement learning (RL) approaches. This paper applies a Heterogeneous-Agent Reinforcement Learning (HARL) framework via Heterogeneous-Agent Proximal Policy Optimization (HAPPO) to enable coordinated restoration across interconnected microgrids. Each agent controls a distinct microgrid with different loads, DER capacities, and switch counts. Decentralized actors are trained with a centralized critic for stable on-policy learning, while a physics-informed OpenDSS environment enforces electrical feasibility. Experiments on IEEE 123-bus and 8500-node feeders show HAPPO outperforms PPO, QMIX, Mean-Field RL, and other baselines in restored power, convergence stability, and multi-seed reproducibility. Under a 2400 kW generation cap, the framework restores over 95\% of available load on both systems with low-latency execution, supporting practical real-time PDS restoration.

---

### Automated proving in planar geometry based on the complex number identity method and elimination

Authors: Zoltán Kovács, Xicheng Peng
Published: 2025-11-18
Categories: cs.CG, cs.AI
arXiv: https://arxiv.org/abs/2511.14728v1

We improve the complex number identity proving method to a fully automated procedure, based on elimination ideals. By using declarative equations or rewriting each real-relational hypothesis $h_i$ to $h_i-r_i$, and the thesis $t$ to $t-r$, clearing the denominators and introducing an extra expression with a slack variable, we eliminate all free and relational point variables. From the obtained ideal $I$ in $\mathbb{Q}(r,r_1,r_2,\ldots)$ we can find a conclusive result. It plays an important role that if $r_1,r_2,\ldots$ are real, $r$ must also be real if there is a linear polynomial $p(r)\in I$, unless division by zero occurs when expressing $r$. Our results are presented in Mathematica, Maple and in a new version of the Giac computer algebra system. Finally, we present a prototype of the automated procedure in an experimental version of the dynamic geometry software GeoGebra.

---

### AdamHD: Decoupled Huber Decay Regularization for Language Model Pre-Training

Authors: Fu-Ming Guo, Yingfang Fan
Published: 2025-11-18
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2511.14721v1

Adaptive optimizers with decoupled weight decay, such as AdamW, are the de facto standard for pre-training large transformer-based generative models. Yet the quadratic nature of the $\ell_2$ penalty embedded in weight decay drives all parameters toward the origin at the same rate, making the update vulnerable to rare but extreme gradient directions and often over-penalizing well-conditioned coordinates. We propose AdamHuberDecay, a drop-in replacement for AdamW that substitutes the $\ell_2$ penalty with a decoupled smooth Huber regularizer. The resulting update decays parameters quadratically while their magnitude remains below a threshold $δ$, and linearly ($\ell_1$-like) once they exceed $δ$, yielding (i) bounded regularization gradients, (ii) invariance to per-coordinate second-moment rescaling, and (iii) stronger sparsity pressure on overgrown weights. We derive the closed-form decoupled Huber decay step and show how to integrate it with any Adam-family optimizer at $O(1)$ extra cost. Extensive experiments on GPT-2 and GPT-3 pre-training demonstrate that AdamHuberDecay (a) converges 10-15% faster in wall-clock time, (b) reduces validation perplexity by up to 4 points, (c) delivers performance improvements of 2.5-4.7% across downstream tasks, and (d) yields visibly sparser weight histograms that translate into 20-30% memory savings after magnitude pruning, without tuning the decay coefficient beyond the default grid used for AdamW. Ablations confirm robustness to outlier gradients and large-batch regimes, together with theoretical analyses that bound the expected parameter norm under noisy updates. AdamHuberDecay therefore provides a simple, principled path toward more efficient and resilient training of next-generation foundational generative transformers.

---

### Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising

Authors: Yifan Wang, Liya Ji, Zhanghan Ke, Harry Yang, Ser-Nam Lim, Qifeng Chen
Published: 2025-11-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.14719v1

We propose an approach to enhancing synthetic video realism, which can re-render synthetic videos from a simulator in photorealistic fashion. Our realism enhancement approach is a zero-shot framework that focuses on preserving the multi-level structures from synthetic videos into the enhanced one in both spatial and temporal domains, built upon a diffusion video foundational model without further fine-tuning. Specifically, we incorporate an effective modification to have the generation/denoising process conditioned on estimated structure-aware information from the synthetic video, such as depth maps, semantic maps, and edge maps, by an auxiliary model, rather than extracting the information from a simulator. This guidance ensures that the enhanced videos are consistent with the original synthetic video at both the structural and semantic levels. Our approach is a simple yet general and powerful approach to enhancing synthetic video realism: we show that our approach outperforms existing baselines in structural consistency with the original video while maintaining state-of-the-art photorealism quality in our experiments.

---

### Diffusion As Self-Distillation: End-to-End Latent Diffusion In One Model

Authors: Xiyuan Wang, Muhan Zhang
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14716v1

Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to suboptimal performance, and prevents the unification of diffusion with the single-network architectures common in vision foundation models. Our goal is to unify these three components into a single, end-to-end trainable network. We first demonstrate that a naive joint training approach fails catastrophically due to ``latent collapse'', where the diffusion training objective interferes with the network's ability to learn a good latent representation. We identify the root causes of this instability by drawing a novel analogy between diffusion and self-distillation based unsupervised learning method. Based on this insight, we propose Diffusion as Self-Distillation (DSD), a new framework with key modifications to the training objective that stabilize the latent space. This approach enables, for the first time, the stable end-to-end training of a single network that simultaneously learns to encode, decode, and perform diffusion. DSD achieves outstanding performance on the ImageNet $256\times 256$ conditional generation task: FID=13.44/6.38/4.25 with only 42M/118M/205M parameters and 50 training epochs on ImageNet, without using classifier-free-guidance.

---

### FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning

Authors: Abolfazl Younesi, Leon Kiss, Zahra Najafabadi Samani, Juan Aznar Poveda, Thomas Fahringer
Published: 2025-11-18
Categories: cs.LG, cs.AI, cs.CR, cs.DC, cs.MA
arXiv: https://arxiv.org/abs/2511.14715v3

Federated learning (FL) enables collaborative model training while preserving data privacy. However, it remains vulnerable to malicious clients who compromise model integrity through Byzantine attacks, data poisoning, or adaptive adversarial behaviors. Existing defense mechanisms rely on static thresholds and binary classification, failing to adapt to evolving client behaviors in real-world deployments. We propose FLARE, an adaptive reputation-based framework that transforms client reliability assessment from binary decisions to a continuous, multi-dimensional trust evaluation. FLARE integrates: (i) a multi-dimensional reputation score capturing performance consistency, statistical anomaly indicators, and temporal behavior, (ii) a self-calibrating adaptive threshold mechanism that adjusts security strictness based on model convergence and recent attack intensity, (iii) reputation-weighted aggregation with soft exclusion to proportionally limit suspicious contributions rather than eliminating clients outright, and (iv) a Local Differential Privacy (LDP) mechanism enabling reputation scoring on privatized client updates. We further introduce a highly evasive Statistical Mimicry (SM) attack, a benchmark adversary that blends honest gradients with synthetic perturbations and persistent drift to remain undetected by traditional filters. Extensive experiments with 100 clients on MNIST, CIFAR-10, and SVHN demonstrate that FLARE maintains high model accuracy and converges faster than state-of-the-art Byzantine-robust methods under diverse attack types, including label flipping, gradient scaling, adaptive attacks, ALIE, and SM. FLARE improves robustness by up to 16% and preserves model convergence within 30% of the non-attacked baseline, while achieving strong malicious-client detection performance with minimal computational overhead. https://github.com/Anonymous0-0paper/FLARE

---

### FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation

Authors: Yunfeng Wu, Jiayi Song, Zhenxiong Tan, Zihao He, Songhua Liu
Published: 2025-11-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.14712v2

The quadratic time and memory complexity of the attention mechanism in modern Transformer based video generators makes end-to-end training for ultra high resolution videos prohibitively expensive. Motivated by this limitation, we introduce a training-free approach that leverages video Diffusion Transformers pretrained at their native scale to synthesize higher resolution videos without any additional training or adaptation. At the core of our method lies an inward sliding window attention mechanism, which originates from a key observation: maintaining each query token's training scale receptive field is crucial for preserving visual fidelity and detail. However, naive local window attention, unfortunately, often leads to repetitive content and exhibits a lack of global coherence in the generated results. To overcome this challenge, we devise a dual-path pipeline that backs up window attention with a novel cross-attention override strategy, enabling the semantic content produced by local attention to be guided by another branch with a full receptive field and, therefore, ensuring holistic consistency. Furthermore, to improve efficiency, we incorporate a cross-attention caching strategy for this branch to avoid the frequent computation of full 3D attention. Extensive experiments demonstrate that our method delivers ultra-high-resolution videos with fine-grained visual details and high efficiency in a training-free paradigm. Meanwhile, it achieves superior performance on VBench, even compared to training-based alternatives, with competitive or improved efficiency. Codes are available at: https://github.com/WillWu111/FreeSwim

---

### Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization

Authors: Zonghao Chen, Atsushi Nitanda, Arthur Gretton, Taiji Suzuki
Published: 2025-11-18
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.14710v1

We establish the first global convergence result of neural networks for two stage least squares (2SLS) approach in nonparametric instrumental variable regression (NPIV). This is achieved by adopting a lifted perspective through mean-field Langevin dynamics (MFLD), unlike standard MFLD, however, our setting of 2SLS entails a \emph{bilevel} optimization problem in the space of probability measures. To address this challenge, we leverage the penalty gradient approach recently developed for bilevel optimization which formulates bilevel optimization as a Lagrangian problem. This leads to a novel fully first-order algorithm, termed \texttt{F$^2$BMLD}. Apart from the convergence bound, we further provide a generalization bound, revealing an inherent trade-off in the choice of the Lagrange multiplier between optimization and statistical guarantees. Finally, we empirically validate the effectiveness of the proposed method on an offline reinforcement learning benchmark.

---

### Strategic Innovation Management in the Age of Large Language Models Market Intelligence, Adaptive R&D, and Ethical Governance

Authors: Raha Aghaei, Ali A. Kiaei, Mahnaz Boush, Mahan Rofoosheh, Mohammad Zavvar
Published: 2025-11-18
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.14709v2

This study analyzes the multiple functions of Large Language Models (LLMs) in transforming research and development (R&D) processes. By automating knowledge discovery, boosting hypothesis creation, integrating transdisciplinary insights, and enabling cooperation within innovation ecosystems, LLMs dramatically improve the efficiency and effectiveness of research processes. Through extensive analysis of scientific literature, patent databases, and experimental data, these models enable more flexible and informed R&D workflows, ultimately accelerating innovation cycles and lowering time-to-market for breakthrough ideas.

---