# Research Papers — 2025-11 · bundle page 90 of 197

> Full-text markdown of papers #4451–4500 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/90
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/89.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/91.md)

### Hint-Augmented Re-ranking: Efficient Product Search using LLM-Based Query Decomposition

Authors: Yilun Zhu, Nikhita Vedula, Shervin Malmasi
Published: 2025-11-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.13994v1

Search queries with superlatives (e.g., best, most popular) require comparing candidates across multiple dimensions, demanding linguistic understanding and domain knowledge. We show that LLMs can uncover latent intent behind these expressions in e-commerce queries through a framework that extracts structured interpretations or hints. Our approach decomposes queries into attribute-value hints generated concurrently with retrieval, enabling efficient integration into the ranking pipeline. Our method improves search performanc eby 10.9 points in MAP and ranking by 5.9 points in MRR over baselines. Since direct LLM-based reranking faces prohibitive latency, we develop an efficient approach transferring superlative interpretations to lightweight models. Our findings provide insights into how superlative semantics can be represented and transferred between models, advancing linguistic interpretation in retrieval systems while addressing practical deployment constraints.

---

### Learning Skill-Attributes for Transferable Assessment in Video

Authors: Kumar Ashutosh, Kristen Grauman
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13993v1

Skill assessment from video entails rating the quality of a person's physical performance and explaining what could be done better. Today's models specialize for an individual sport, and suffer from the high cost and scarcity of expert-level supervision across the long tail of sports. Towards closing that gap, we explore transferable video representations for skill assessment. Our CrossTrainer approach discovers skill-attributes, such as balance, control, and hand positioning -- whose meaning transcends the boundaries of any given sport, then trains a multimodal language model to generate actionable feedback for a novel video, e.g., "lift hands more to generate more power" as well as its proficiency level, e.g., early expert. We validate the new model on multiple datasets for both cross-sport (transfer) and intra-sport (in-domain) settings, where it achieves gains up to 60% relative to the state of the art. By abstracting out the shared behaviors indicative of human skill, the proposed video representation generalizes substantially better than an array of existing techniques, enriching today's multimodal large language models.

---

### Artificial Intelligence Agents in Music Analysis: An Integrative Perspective Based on Two Use Cases

Authors: Antonio Manuel Martínez-Heredia, Dolores Godrid Rodríguez, Andrés Ortiz García
Published: 2025-11-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.13987v1

This paper presents an integrative review and experimental validation of artificial intelligence (AI) agents applied to music analysis and education. We synthesize the historical evolution from rule-based models to contemporary approaches involving deep learning, multi-agent architectures, and retrieval-augmented generation (RAG) frameworks. The pedagogical implications are evaluated through a dual-case methodology: (1) the use of generative AI platforms in secondary education to foster analytical and creative skills; (2) the design of a multiagent system for symbolic music analysis, enabling modular, scalable, and explainable workflows. Experimental results demonstrate that AI agents effectively enhance musical pattern recognition, compositional parameterization, and educational feedback, outperforming traditional automated methods in terms of interpretability and adaptability. The findings highlight key challenges concerning transparency, cultural bias, and the definition of hybrid evaluation metrics, emphasizing the need for responsible deployment of AI in educational environments. This research contributes to a unified framework that bridges technical, pedagogical, and ethical considerations, offering evidence-based guidance for the design and application of intelligent agents in computational musicology and music education.

---

### Node-Level Uncertainty Estimation in LLM-Generated SQL

Authors: Hilaf Hasson, Ruocheng Guo
Published: 2025-11-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.13984v2

We present a practical framework for detecting errors in LLM-generated SQL by estimating uncertainty at the level of individual nodes in the query's abstract syntax tree (AST). Our approach proceeds in two stages. First, we introduce a semantically aware labeling algorithm that, given a generated SQL and a gold reference, assigns node-level correctness without over-penalizing structural containers or alias variation. Second, we represent each node with a rich set of schema-aware and lexical features - capturing identifier validity, alias resolution, type compatibility, ambiguity in scope, and typo signals - and train a supervised classifier to predict per-node error probabilities. We interpret these probabilities as calibrated uncertainty, enabling fine-grained diagnostics that pinpoint exactly where a query is likely to be wrong. Across multiple databases and datasets, our method substantially outperforms token log-probabilities: average AUC improves by +27.44% while maintaining robustness under cross-database evaluation. Beyond serving as an accuracy signal, node-level uncertainty supports targeted repair, human-in-the-loop review, and downstream selective execution. Together, these results establish node-centric, semantically grounded uncertainty estimation as a strong and interpretable alternative to aggregate sequence level confidence measures.

---

### Data Whitening Improves Sparse Autoencoder Learning

Authors: Ashwin Saraswatula, David Klindt
Published: 2025-11-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.13981v1

Sparse autoencoders (SAEs) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE training can be challenging due to correlations in the input data. We demonstrate that applying PCA Whitening to input activations -- a standard preprocessing technique in classical sparse coding -- improves SAE performance across multiple metrics. Through theoretical analysis and simulation, we show that whitening transforms the optimization landscape, making it more convex and easier to navigate. We evaluate both ReLU and Top-K SAEs across diverse model architectures, widths, and sparsity regimes. Empirical evaluation on SAEBench, a comprehensive benchmark for sparse autoencoders, reveals that whitening consistently improves interpretability metrics, including sparse probing accuracy and feature disentanglement, despite minor drops in reconstruction quality. Our results challenge the assumption that interpretability aligns with an optimal sparsity--fidelity trade-off and suggest that whitening should be considered as a default preprocessing step for SAE training, particularly when interpretability is prioritized over perfect reconstruction.

---

### Efficient reconstruction of multidimensional random field models with heterogeneous data using stochastic neural networks

Authors: Mingtao Xia, Qijing Shen
Published: 2025-11-17
Categories: cs.LG, math.NA, math.PR
arXiv: https://arxiv.org/abs/2511.13977v1

In this paper, we analyze the scalability of a recent Wasserstein-distance approach for training stochastic neural networks (SNNs) to reconstruct multidimensional random field models. We prove a generalization error bound for reconstructing multidimensional random field models on training stochastic neural networks with a limited number of training data. Our results indicate that when noise is heterogeneous across dimensions, the convergence rate of the generalization error may not depend explicitly on the model's dimensionality, partially alleviating the "curse of dimensionality" for learning multidimensional random field models from a finite number of data points. Additionally, we improve the previous Wasserstein-distance SNN training approach and showcase the robustness of the SNN. Through numerical experiments on different multidimensional uncertainty quantification tasks, we show that our Wasserstein-distance approach can successfully train stochastic neural networks to learn multidimensional uncertainty models.

---

### Show and Tell: Prompt Strategies for Style Control in Multi-Turn LLM Code Generation

Authors: Jeremiah Bohr
Published: 2025-11-17
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2511.13972v1

Language models generate functionally correct code that tends toward excessive verbosity, with elaborate documentation and defensive patterns that diverge from human baselines. Two prompting mechanisms have emerged for stylistic control: instruction based prompts that articulate abstract directives, and example based prompts that provide concrete code demonstrations. The core problem is whether stylistic constraints persist when models enhance initial implementations with additional features while maintaining high functional accuracy. Here we show that instruction-based, example-based, and combined prompts produce distinct patterns of initial control and expansion discipline over one enhancement turn. We manipulated system prompts across four conditions in a paired two-turn protocol where models first generated solutions to an intermediate Python task, then revised their code under general improvement directives, holding the user task fixed (N = 160 paired programs). Combined prompts produced the strongest initial compression and greatest expansion discipline. Instructions showed large initial effects and moderate expansion discipline. Examples showed modest initial effects with no expansion discipline. These results show that initial prompt effectiveness and expansion discipline are separate aspects of prompt design, and that combined approaches provide the most stable stylistic control in this two-turn workflow.

---

### Scene Graph-Guided Generative AI Framework for Synthesizing and Evaluating Industrial Hazard Scenarios

Authors: Sanjay Acharjee, Abir Khan Ratul, Diego Patino, Md Nazmus Sakib
Published: 2025-11-17
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.13970v1

Training vision models to detect workplace hazards accurately requires realistic images of unsafe conditions that could lead to accidents. However, acquiring such datasets is difficult because capturing accident-triggering scenarios as they occur is nearly impossible. To overcome this limitation, this study presents a novel scene graph-guided generative AI framework that synthesizes photorealistic images of hazardous scenarios grounded in historical Occupational Safety and Health Administration (OSHA) accident reports. OSHA narratives are analyzed using GPT-4o to extract structured hazard reasoning, which is converted into object-level scene graphs capturing spatial and contextual relationships essential for understanding risk. These graphs guide a text-to-image diffusion model to generate compositionally accurate hazard scenes. To evaluate the realism and semantic fidelity of the generated data, a visual question answering (VQA) framework is introduced. Across four state-of-the-art generative models, the proposed VQA Graph Score outperforms CLIP and BLIP metrics based on entropy-based validation, confirming its higher discriminative sensitivity.

---

### PoCGM: Poisson-Conditioned Generative Model for Sparse-View CT Reconstruction

Authors: Changsheng Fang, Yongtong Liu, Bahareh Morovati, Shuo Han, Li Zhou, Hengyong Yu
Published: 2025-11-17
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2511.13967v1

In computed tomography (CT), reducing the number of projection views is an effective strategy to lower radiation exposure and/or improve temporal resolution. However, this often results in severe aliasing artifacts and loss of structural details in reconstructed images, posing significant challenges for clinical applications. Inspired by the success of the Poisson Flow Generative Model (PFGM++) in natural image generation, we propose a PoCGM (Poisson-Conditioned Generative Model) to address the challenges of sparse-view CT reconstruction. Since PFGM++ was originally designed for unconditional generation, it lacks direct applicability to medical imaging tasks that require integrating conditional inputs. To overcome this limitation, the PoCGM reformulates PFGM++ into a conditional generative framework by incorporating sparse-view data as guidance during both training and sampling phases. By modeling the posterior distribution of full-view reconstructions conditioned on sparse observations, PoCGM effectively suppresses artifacts while preserving fine structural details. Qualitative and quantitative evaluations demonstrate that PoCGM outperforms the baselines, achieving improved artifact suppression, enhanced detail preservation, and reliable performance in dose-sensitive and time-critical imaging scenarios.

---

### A Brain Wave Encodes a Thousand Tokens: Modeling Inter-Cortical Neural Interactions for Effective EEG-based Emotion Recognition

Authors: Nilay Kumar, Priyansh Bhandari, G. Maragatham
Published: 2025-11-17
Categories: q-bio.NC, cs.LG
arXiv: https://arxiv.org/abs/2511.13954v1

Human emotions are difficult to convey through words and are often abstracted in the process; however, electroencephalogram (EEG) signals can offer a more direct lens into emotional brain activity. Recent studies show that deep learning models can process these signals to perform emotion recognition with high accuracy. However, many existing approaches overlook the dynamic interplay between distinct brain regions, which can be crucial to understanding how emotions unfold and evolve over time, potentially aiding in more accurate emotion recognition. To address this, we propose RBTransformer, a Transformer-based neural network architecture that models inter-cortical neural dynamics of the brain in latent space to better capture structured neural interactions for effective EEG-based emotion recognition. First, the EEG signals are converted into Band Differential Entropy (BDE) tokens, which are then passed through Electrode Identity embeddings to retain spatial provenance. These tokens are processed through successive inter-cortical multi-head attention blocks that construct an electrode x electrode attention matrix, allowing the model to learn the inter-cortical neural dependencies. The resulting features are then passed through a classification head to obtain the final prediction. We conducted extensive experiments, specifically under subject-dependent settings, on the SEED, DEAP, and DREAMER datasets, over all three dimensions, Valence, Arousal, and Dominance (for DEAP and DREAMER), under both binary and multi-class classification settings. The results demonstrate that the proposed RBTransformer outperforms all previous state-of-the-art methods across all three datasets, over all three dimensions under both classification settings. The source code is available at: https://github.com/nnilayy/RBTransformer.

---

### The Impact of Bootstrap Sampling Rate on Random Forest Performance in Regression Tasks

Authors: Michał Iwaniuk, Mateusz Jarosz, Bartłomiej Borycki, Bartosz Jezierski, Jan Cwalina, Stanisław Kaźmierczak, Jacek Mańdziuk
Published: 2025-11-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.13952v1

Random Forests (RFs) typically train each tree on a bootstrap sample of the same size as the training set, i.e., bootstrap rate (BR) equals 1.0. We systematically examine how varying BR from 0.2 to 5.0 affects RF performance across 39 heterogeneous regression datasets and 16 RF configurations, evaluating with repeated two-fold cross-validation and mean squared error. Our results demonstrate that tuning the BR can yield significant improvements over the default: the best setup relied on BR \leq 1.0 for 24 datasets, BR > 1.0 for 15, and BR = 1.0 was optimal in 4 cases only. We establish a link between dataset characteristics and the preferred BR: datasets with strong global feature-target relationships favor higher BRs, while those with higher local target variance benefit from lower BRs. To further investigate this relationship, we conducted experiments on synthetic datasets with controlled noise levels. These experiments reproduce the observed bias-variance trade-off: in low-noise scenarios, higher BRs effectively reduce model bias, whereas in high-noise settings, lower BRs help reduce model variance. Overall, BR is an influential hyperparameter that should be tuned to optimize RF regression models.

---

### EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation

Authors: Matin Daghyani, Lyuyang Wang, Nima Hashemi, Bassant Medhat, Baraa Abdelsamad, Eros Rojas Velez, XiaoXiao Li, Michael Y. C. Tsang, Christina Luong, Teresa S. M. Tsang, Purang Abolmaesumi
Published: 2025-11-17
Categories: cs.CV, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.13948v1

Purpose: Echocardiographic interpretation requires video-level reasoning and guideline-based measurement analysis, which current deep learning models for cardiac ultrasound do not support. We present EchoAgent, a framework that enables structured, interpretable automation for this domain. Methods: EchoAgent orchestrates specialized vision tools under Large Language Model (LLM) control to perform temporal localization, spatial measurement, and clinical interpretation. A key contribution is a measurement-feasibility prediction model that determines whether anatomical structures are reliably measurable in each frame, enabling autonomous tool selection. We curated a benchmark of diverse, clinically validated video-query pairs for evaluation. Results: EchoAgent achieves accurate, interpretable results despite added complexity of spatiotemporal video analysis. Outputs are grounded in visual evidence and clinical guidelines, supporting transparency and traceability. Conclusion: This work demonstrates the feasibility of agentic, guideline-aligned reasoning for echocardiographic video analysis, enabled by task-specific tools and full video-level automation. EchoAgent sets a new direction for trustworthy AI in cardiac ultrasound.

---

### Single Tensor Cell Segmentation using Scalar Field Representations

Authors: Kevin I. Ruiz Vargas, Gabriel G. Galdino, Tsang Ing Ren, Alexandre L. Cunha
Published: 2025-11-17
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.13947v1

We investigate image segmentation of cells under the lens of scalar fields. Our goal is to learn a continuous scalar field on image domains such that its segmentation produces robust instances for cells present in images. This field is a function parameterized by the trained network, and its segmentation is realized by the watershed method. The fields we experiment with are solutions to the Poisson partial differential equation and a diffusion mimicking the steady-state solution of the heat equation. These solutions are obtained by minimizing just the field residuals, no regularization is needed, providing a robust regression capable of diminishing the adverse impacts of outliers in the training data and allowing for sharp cell boundaries. A single tensor is all that is needed to train a \unet\ thus simplifying implementation, lowering training and inference times, hence reducing energy consumption, and requiring a small memory footprint, all attractive features in edge computing. We present competitive results on public datasets from the literature and show that our novel, simple yet geometrically insightful approach can achieve excellent cell segmentation results.

---

### Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers

Authors: Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran, Damien Teney, Anton van den Hengel
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13945v2

Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases in vision transformers (ViTs) through pretraining on procedurally generated data devoid of visual or semantic content. We generate this data with simple algorithms such as formal grammars, so the results bear no relationship to either natural or synthetic images. We use this procedurally generated data to pretrain ViTs in a warm-up phase that bypasses their visual patch embedding mechanisms, thus encouraging the models to internalise abstract computational priors. When followed by standard image-based training, this warm-up significantly improves data efficiency, convergence speed, and downstream performance. On ImageNet-1K, for example, allocating just 1% of the training budget to procedural data improves final accuracy by over 1.7%. In terms of its effect on performance, 1% procedurally generated data is thus equivalent to 28% of the ImageNet-1K data. These findings suggest a promising path toward new data-efficient and domain-agnostic pretraining strategies.

---

### Find the Leak, Fix the Split: Cluster-Based Method to Prevent Leakage in Video-Derived Datasets

Authors: Noam Glazner, Noam Tsfaty, Sharon Shalev, Avishai Weizman
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13944v2

We propose a cluster-based frame selection strategy to mitigate information leakage in video-derived frames datasets. By grouping visually similar frames before splitting into training, validation, and test sets, the method produces more representative, balanced, and reliable dataset partitions.

---

### CORGI: Efficient Pattern Matching With Quadratic Guarantees

Authors: Daniel Weitekamp
Published: 2025-11-17
Categories: cs.AI, cs.DS, cs.IR
arXiv: https://arxiv.org/abs/2511.13942v1

Rule-based systems must solve complex matching problems within tight time constraints to be effective in real-time applications, such as planning and reactive control for AI agents, as well as low-latency relational database querying. Pattern-matching systems can encounter issues where exponential time and space are required to find matches for rules with many underconstrained variables, or which produce combinatorial intermediate partial matches (but are otherwise well-constrained). When online AI systems automatically generate rules from example-driven induction or code synthesis, they can easily produce worst-case matching patterns that slow or halt program execution by exceeding available memory. In our own work with cognitive systems that learn from example, we've found that aggressive forms of anti-unification-based generalization can easily produce these circumstances. To make these systems practical without hand-engineering constraints or succumbing to unpredictable failure modes, we introduce a new matching algorithm called CORGI (Collection-Oriented Relational Graph Iteration). Unlike RETE-based approaches, CORGI offers quadratic time and space guarantees for finding single satisficing matches, and the ability to iteratively stream subsequent matches without committing entire conflict sets to memory. CORGI differs from RETE in that it does not have a traditional $β$-memory for collecting partial matches. Instead, CORGI takes a two-step approach: a graph of grounded relations is built/maintained in a forward pass, and an iterator generates matches as needed by working backward through the graph. This approach eliminates the high-latency delays and memory overflows that can result from populating full conflict sets. In a performance evaluation, we demonstrate that CORGI significantly outperforms RETE implementations from SOAR and OPS5 on a simple combinatorial matching task.

---

### ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels

Authors: Stuart H. Sul, Simran Arora, Benjamin F. Spector, Christopher Ré
Published: 2025-11-17
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2511.13940v1

Inter-GPU communication has become a major bottleneck for modern AI workloads as models scale and improvements in hardware compute throughput outpace improvements in interconnect bandwidth. Existing systems mitigate this through compute-communication overlap but often fail to meet theoretical peak performance across heterogeneous workloads and new accelerators. Instead of operator-specific techniques, we ask whether a small set of simple, reusable principles can systematically guide the design of optimal multi-GPU kernels. We present ParallelKittens (PK), a minimal CUDA framework that drastically simplifies the development of overlapped multi-GPU kernels. PK extends the ThunderKittens framework and embodies the principles of multi-GPU kernel design through eight core primitives and a unified programming template, derived from a comprehensive analysis of the factors that govern multi-GPU performance$\unicode{x2014}$data-transfer mechanisms, resource scheduling, and design overheads. We validate PK on both Hopper and Blackwell architectures. With fewer than 50 lines of device code, PK achieves up to $2.33 \times$ speedup for data- and tensor-parallel workloads, $4.08 \times$ for sequence-parallel workloads, and $1.22 \times$ for expert-parallel workloads.

---

### Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion

Authors: Cristina López Amado, Tassilo Schwarz, Yu Tian, Renaud Lambiotte
Published: 2025-11-17
Categories: cs.LG, cs.SI, math.DS, physics.soc-ph
arXiv: https://arxiv.org/abs/2511.13937v1

Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain limited by oversmoothing and poor performance on heterophilic graphs. To address these challenges, we introduce a novel framework that equips graphs with a complex-weighted structure, assigning each edge a complex number to drive a diffusion process that extends random walks into the complex domain. We prove that this diffusion is highly expressive: with appropriately chosen complex weights, any node-classification task can be solved in the steady state of a complex random walk. Building on this insight, we propose the Complex-Weighted Convolutional Network (CWCN), which learns suitable complex-weighted structures directly from data while enriching diffusion with learnable matrices and nonlinear activations. CWCN is simple to implement, requires no additional hyperparameters beyond those of standard GNNs, and achieves competitive performance on benchmark datasets. Our results demonstrate that complex-weighted diffusion provides a principled and general mechanism for enhancing GNN expressiveness, opening new avenues for models that are both theoretically grounded and practically effective.

---

### Preference-Based Learning in Audio Applications: A Systematic Analysis

Authors: Aaron Broukhim, Yiran Shen, Prithviraj Ammanabrolu, Nadir Weibel
Published: 2025-11-17
Categories: cs.SD, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.13936v1

Despite the parallel challenges that audio and text domains face in evaluating generative model outputs, preference learning remains remarkably underexplored in audio applications. Through a PRISMA-guided systematic review of approximately 500 papers, we find that only 30 (6%) apply preference learning to audio tasks. Our analysis reveals a field in transition: pre-2021 works focused on emotion recognition using traditional ranking methods (rankSVM), while post-2021 studies have pivoted toward generation tasks employing modern RLHF frameworks. We identify three critical patterns: (1) the emergence of multi-dimensional evaluation strategies combining synthetic, automated, and human preferences; (2) inconsistent alignment between traditional metrics (WER, PESQ) and human judgments across different contexts; and (3) convergence on multi-stage training pipelines that combine reward signals. Our findings suggest that while preference learning shows promise for audio, particularly in capturing subjective qualities like naturalness and musicality, the field requires standardized benchmarks, higher-quality datasets, and systematic investigation of how temporal factors unique to audio impact preference learning frameworks.

---

### Weather Maps as Tokens: Transformers for Renewable Energy Forecasting

Authors: Federico Battini
Published: 2025-11-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.13935v2

Accurate renewable energy forecasting is essential to reduce dependence on fossil fuels and enabling grid decarbonization. However, current approaches fail to effectively integrate the rich spatial context of weather patterns with their temporal evolution. This work introduces a novel approach that treats weather maps as tokens in transformer sequences to predict renewable energy. Hourly weather maps are encoded as spatial tokens using a lightweight convolutional neural network, and then processed by a transformer to capture temporal dynamics across a 45-hour forecast horizon. Despite disadvantages in input initialization, evaluation against ENTSO-E operational forecasts shows a reduction in RMSE of about 60% and 20% for wind and solar respectively. A live dashboard showing daily forecasts is available at: https://www.sardiniaforecast.ifabfoundation.it.

---

### Empirical Likelihood for Random Forests and Ensembles

Authors: Harold D. Chiang, Yukitoshi Matsushita, Taisuke Otsu
Published: 2025-11-17
Categories: stat.ML, cs.LG, econ.EM, math.ST
arXiv: https://arxiv.org/abs/2511.13934v1

We develop an empirical likelihood (EL) framework for random forests and related ensemble methods, providing a likelihood-based approach to quantify their statistical uncertainty. Exploiting the incomplete $U$-statistic structure inherent in ensemble predictions, we construct an EL statistic that is asymptotically chi-squared when subsampling induced by incompleteness is not overly sparse. Under sparser subsampling regimes, the EL statistic tends to over-cover due to loss of pivotality; we therefore propose a modified EL that restores pivotality through a simple adjustment. Our method retains key properties of EL while remaining computationally efficient. Theory for honest random forests and simulations demonstrate that modified EL achieves accurate coverage and practical reliability relative to existing inference methods.

---

### Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding

Authors: Qingyang Yan, Guangyao Chen, Yixiong Zou
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13924v1

Chain-of-Thought (CoT) prompting has recently shown significant promise across various NLP and computer vision tasks by explicitly generating intermediate reasoning steps. However, we find that reinforcement learning (RL)-based fine-tuned CoT reasoning can paradoxically degrade performance in Visual Grounding tasks, particularly as CoT outputs become lengthy or complex. Additionally, our analysis reveals that increased dataset size does not always enhance performance due to varying data complexities. Motivated by these findings, we propose Curriculum-based Relative Policy Optimization (CuRPO), a novel training strategy that leverages CoT length and generalized Intersection over Union (gIoU) rewards as complexity indicators to progressively structure training data from simpler to more challenging examples. Extensive experiments on RefCOCO, RefCOCO+, RefCOCOg, and LISA datasets demonstrate the effectiveness of our approach. CuRPO consistently outperforms existing methods, including Visual-RFT, with notable improvements of up to +12.52 mAP on RefCOCO. Moreover, CuRPO exhibits exceptional efficiency and robustness, delivering strong localization performance even in few-shot learning scenarios, particularly benefiting tasks characterized by ambiguous and intricate textual descriptions.The code is released on https://github.com/qyoung-yan/CuRPO.

---

### Self-Supervised Compression and Artifact Correction for Streaming Underwater Imaging Sonar

Authors: Rongsheng Qian, Chi Xu, Xiaoqiang Ma, Hao Fang, Yili Jin, William I. Atlas, Jiangchuan Liu
Published: 2025-11-17
Categories: eess.IV, cs.CV, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2511.13922v2

Real-time imaging sonar is crucial for underwater monitoring where optical sensing fails, but its use is limited by low uplink bandwidth and severe sonar-specific artifacts (speckle, motion blur, reverberation, acoustic shadows) affecting up to 98% of frames. We present SCOPE, a self-supervised framework that jointly performs compression and artifact correction without clean-noise pairs or synthetic assumptions. SCOPE combines (i) Adaptive Codebook Compression (ACC), which learns frequency-encoded latent representations tailored to sonar, with (ii) Frequency-Aware Multiscale Segmentation (FAMS), which decomposes frames into low-frequency structure and sparse high-frequency dynamics while suppressing rapidly fluctuating artifacts. A hedging training strategy further guides frequency-aware learning using low-pass proxy pairs generated without labels. Evaluated on months of in-situ ARIS sonar data, SCOPE achieves a structural similarity index (SSIM) of 0.77, representing a 40% improvement over prior self-supervised denoising baselines, at bitrates down to <= 0.0118 bpp. It reduces uplink bandwidth by more than 80% while improving downstream detection. The system runs in real time, with 3.1 ms encoding on an embedded GPU and 97 ms full multi-layer decoding on the server end. SCOPE has been deployed for months in three Pacific Northwest rivers to support real-time salmon enumeration and environmental monitoring in the wild. Results demonstrate that learning frequency-structured latents enables practical, low-bitrate sonar streaming with preserved signal details under real-world deployment conditions.

---

### Compute-in-Memory Implementation of State Space Models for Event Sequence Processing

Authors: Xiaoyu Zhang, Mingtao Hu, Sen Lu, Soohyeon Kim, Eric Yeu-Jer Lee, Yuyang Liu, Wei D. Lu
Published: 2025-11-17
Categories: eess.SP, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.13912v2

State space models (SSMs) have recently emerged as a powerful framework for long sequence processing, outperforming traditional methods on diverse benchmarks. Fundamentally, SSMs can generalize both recurrent and convolutional networks and have been shown to even capture key functions of biological systems. Here we report an approach to implement SSMs in energy-efficient compute-in-memory (CIM) hardware to achieve real-time, event-driven processing. Our work re-parameterizes the model to function with real-valued coefficients and shared decay constants, reducing the complexity of model mapping onto practical hardware systems. By leveraging device dynamics and diagonalized state transition parameters, the state evolution can be natively implemented in crossbar-based CIM systems combined with memristors exhibiting short-term memory effects. Through this algorithm and hardware co-design, we show the proposed system offers both high accuracy and high energy efficiency while supporting fully asynchronous processing for event-based vision and audio tasks.

---

### Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands

Authors: Vasiliki Tassopoulou, Charis Stamouli, Haochang Shou, George J. Pappas, Christos Davatzikos
Published: 2025-11-17
Categories: stat.ML, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2511.13911v1

Despite recent progress in predicting biomarker trajectories from real clinical data, uncertainty in the predictions poses high-stakes risks (e.g., misdiagnosis) that limit their clinical deployment. To enable safe and reliable use of such predictions in healthcare, we introduce a conformal method for uncertainty-calibrated prediction of biomarker trajectories resulting from randomly-timed clinical visits of patients. Our approach extends conformal prediction to the setting of randomly-timed trajectories via a novel nonconformity score that produces prediction bands guaranteed to cover the unknown biomarker trajectories with a user-prescribed probability. We apply our method across a wide range of standard and state-of-the-art predictors for two well-established brain biomarkers of Alzheimer's disease, using neuroimaging data from real clinical studies. We observe that our conformal prediction bands consistently achieve the desired coverage, while also being tighter than baseline prediction bands. To further account for population heterogeneity, we develop group-conditional conformal bands and test their coverage guarantees across various demographic and clinically relevant subpopulations. Moreover, we demonstrate the clinical utility of our conformal bands in identifying subjects at high risk of progression to Alzheimer's disease. Specifically, we introduce an uncertainty-calibrated risk score that enables the identification of 17.5% more high-risk subjects compared to standard risk scores, highlighting the value of uncertainty calibration in real-world clinical decision making. Our code is available at github.com/vatass/ConformalBiomarkerTrajectories.

---

### Mind the Gap: Evaluating LLM Understanding of Human-Taught Road Safety Principles

Authors: Chalamalasetti Kranti
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13909v1

Following road safety norms is non-negotiable not only for humans but also for the AI systems that govern autonomous vehicles. In this work, we evaluate how well multi-modal large language models (LLMs) understand road safety concepts, specifically through schematic and illustrative representations. We curate a pilot dataset of images depicting traffic signs and road-safety norms sourced from school text books and use it to evaluate models capabilities in a zero-shot setting. Our preliminary results show that these models struggle with safety reasoning and reveal gaps between human learning and model interpretation. We further provide an analysis of these performance gaps for future research.

---

### Edge Assisted Multi-Camera Vehicle Tracking Framework for Real-Time and Scalable Deployment

Authors: Yuqiang Lin, Sam Lockyer, Shucheng Zhang, Florian Stanek, Markus Zarbock, Adrian Evans, Wenbin Li, Yinhai Wang, Nic Zhang
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13904v2

Cameras are a core sensing modality in modern intelligent transportation systems (ITS), providing rich visual information on road-user activities. Multi-Camera Vehicle Tracking (MCVT) uses this data to reconstruct vehicle trajectories across camera networks, supporting applications such as traffic flow prediction and optimisation. However, most existing MCVT studies emphasise tracking accuracy while paying limited attention to real-time performance and scalability, both essential for real-world and city-scale deployment. To address this gap, we propose Edge-Assisted, Scalable and Efficient MCVT (EASE-MCVT), a distributed edge--server framework designed for real-time throughput and scalable operation. On the edge side, each camera stream is processed through object detection, single-camera tracking, geo-mapping and feature extraction, while only lightweight metadata, including vehicle locations and appearance features, is sent to the central server for cross-camera association. To improve both tracking accuracy and system efficiency, EASE-MCVT is optimised from algorithmic and system perspectives. Algorithmically, it introduces a dynamic workload scheme for tracklet-level feature extraction, a server-side re-match module to reconnect fragmented tracklets, and a self-supervised camera link model that learns spatio-temporal constraints to accelerate and stabilise cross-camera association. Systemically, it integrates production-oriented data engineering components to standardise deployment and data exchange for large-scale operation. To the best of our knowledge, EASE-MCVT is the first MCVT framework explicitly designed to address both real-time performance and scalability in a distributed edge--server setting. Experiments on the RoundaboutHD and CityFlow datasets demonstrate real-time throughput with competitive tracking accuracy, paving the way for city-wide real-time traffic management.

---

### What Works for 'Lost-in-the-Middle' in LLMs? A Study on GM-Extract and Mitigations

Authors: Mihir Gupte, Eshan Dixit, Muhammad Tayyab, Arun Adiththan
Published: 2025-11-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.13900v1

The diminishing ability of large language models (LLMs) to effectively utilize long-range context-the "lost-in-the-middle" phenomenon-poses a significant challenge in retrieval-based LLM applications. To study the impact of this phenomenon in a real-world application setting, we introduce GM-Extract, a novel benchmark dataset meticulously designed to evaluate LLM performance on retrieval of control variables. To accurately diagnose failure modes, we propose a simple yet elegant evaluation system using two distinct metrics: one for spatial retrieval capability (Document Metric) and the other for semantic retrieval capability (Variable Extraction Metric). We conduct a systematic evaluation of 7-8B parameter models on two multi-document tasks (key-value extraction and question-answering), demonstrating a significant change in retrieval performance simply by altering how the data is represented in the context window. While a distinct U-shaped curve was not consistently observed, our analysis reveals a clear pattern of performance across models, which we further correlate with perplexity scores. Furthermore, we perform a literature survey of mitigation methods, which we categorize into two distinct approaches: black-box and white-box methods. We then apply these techniques to our benchmark, finding that their efficacy is highly nuanced. Our evaluation highlights scenarios where these strategies successfully improve performance, as well as surprising cases where they lead to a negative impact, providing a comprehensive understanding of their utility in a practical context.

---

### A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity

Authors: Chengrui Li, Yunmiao Wang, Yule Wang, Weihan Li, Dieter Jaeger, Anqi Wu
Published: 2025-11-17
Categories: q-bio.NC, cs.CE, cs.LG
arXiv: https://arxiv.org/abs/2511.13899v2

Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks independence interpretations, making it difficult to assign distinct computational roles to different latent dimensions. To address this, we propose the Factored Recurrent Neural Network (FacRNN), a generative lrRNN framework that assumes group-wise independence among latent dynamics while allowing flexible within-group entanglement. These independent latent groups allow latent dynamics to evolve separately, but are internally rich for complex computation. We reformulate the lrRNN under a variational autoencoder (VAE) framework, enabling us to introduce a partial correlation penalty that encourages independence between groups of latent dimensions. Experiments on synthetic, monkey M1, and mouse voltage imaging data show that FacRNN consistently improves the disentanglement and interpretability of learned neural latent trajectories in low-dimensional space and low-rank connectivity over baseline lrRNNs that do not encourage group-wise independence.

---

### Temporal Realism Evaluation of Generated Videos Using Compressed-Domain Motion Vectors

Authors: Mert Onur Cakiroglu, Idil Bilge Altun, Zhihe Lu, Mehmet Dalkilic, Hasan Kurban
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13897v1

Temporal realism remains a central weakness of current generative video models, as most evaluation metrics prioritize spatial appearance and offer limited sensitivity to motion. We introduce a scalable, model-agnostic framework that assesses temporal behavior using motion vectors (MVs) extracted directly from compressed video streams. Codec-generated MVs from standards such as H.264 and HEVC provide lightweight, resolution-consistent descriptors of motion dynamics. We quantify realism by computing Kullback-Leibler, Jensen-Shannon, and Wasserstein divergences between MV statistics of real and generated videos. Experiments on the GenVidBench dataset containing videos from eight state-of-the-art generators reveal systematic discrepancies from real motion: entropy-based divergences rank Pika and SVD as closest to real videos, MV-sum statistics favor VC2 and Text2Video-Zero, and CogVideo shows the largest deviations across both measures. Visualizations of MV fields and class-conditional motion heatmaps further reveal center bias, sparse and piecewise constant flows, and grid-like artifacts that frame-level metrics do not capture. Beyond evaluation, we investigate MV-RGB fusion through channel concatenation, cross-attention, joint embedding, and a motion-aware fusion module. Incorporating MVs improves downstream classification across ResNet, I3D, and TSN backbones, with ResNet-18 and ResNet-34 reaching up to 97.4% accuracy and I3D achieving 99.0% accuracy on real-versus-generated discrimination. These findings demonstrate that compressed-domain MVs provide an effective temporal signal for diagnosing motion defects in generative videos and for strengthening temporal reasoning in discriminative models. The implementation is available at: https://github.com/KurbanIntelligenceLab/Motion-Vector-Learning

---

### Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis

Authors: Kai Chen, Chen Gong, Tianhao Wang
Published: 2025-11-17
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2511.13893v2

In differentially private (DP) tabular data synthesis, the consensus is that statistical models are better than neural network (NN)-based methods. However, we argue that this conclusion is incomplete and overlooks the challenge of densely correlated datasets, where intricate dependencies can overwhelm statistical models. In such complex scenarios, neural networks are more suitable due to their capacity to fit complex distributions by learning directly from samples. Despite this potential, existing NN-based algorithms still suffer from significant limitations. We therefore propose MargNet, incorporating successful algorithmic designs of statistical models into neural networks. MargNet applies an adaptive marginal selection strategy and trains the neural networks to generate data that conforms to the selected marginals. On sparsely correlated datasets, our approach achieves utility close to the best statistical method while offering an average 7$\times$ speedup over it. More importantly, on densely correlated datasets, MargNet establishes a new state-of-the-art, reducing fidelity error by up to 26\% compared to the previous best. We release our code on GitHub.\footnote{https://github.com/KaiChen9909/margnet}

---

### Jailbreaking Large Vision Language Models in Intelligent Transportation Systems

Authors: Badhan Chandra Das, Md Tasnim Jawad, Md Jueal Mia, M. Hadi Amini, Yanzhao Wu
Published: 2025-11-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.13892v1

Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper systematically analyzes the vulnerabilities of LVLMs integrated in Intelligent Transportation Systems (ITS) under carefully crafted jailbreaking attacks. First, we carefully construct a dataset with harmful queries relevant to transportation, following OpenAI's prohibited categories to which the LVLMs should not respond. Second, we introduce a novel jailbreaking attack that exploits the vulnerabilities of LVLMs through image typography manipulation and multi-turn prompting. Third, we propose a multi-layered response filtering defense technique to prevent the model from generating inappropriate responses. We perform extensive experiments with the proposed attack and defense on the state-of-the-art LVLMs (both open-source and closed-source). To evaluate the attack method and defense technique, we use GPT-4's judgment to determine the toxicity score of the generated responses, as well as manual verification. Further, we compare our proposed jailbreaking method with existing jailbreaking techniques and highlight severe security risks involved with jailbreaking attacks with image typography manipulation and multi-turn prompting in the LVLMs integrated in ITS.

---

### Weakly Supervised Ephemeral Gully Detection In Remote Sensing Images Using Vision Language Models

Authors: Seyed Mohamad Ali Tousi, Ramy Farag, John A. Lory, G. N. DeSouza
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13891v2

Among soil erosion problems, Ephemeral Gullies are one of the most concerning phenomena occurring in agricultural fields. Their short temporal cycles increase the difficulty in automatically detecting them using classical computer vision approaches and remote sensing. Also, due to scarcity of and the difficulty in producing accurate labeled data, automatic detection of ephemeral gullies using Machine Learning is limited to zero-shot approaches which are hard to implement. To overcome these challenges, we present the first weakly supervised pipeline for detection of ephemeral gullies. Our method relies on remote sensing and uses Vision Language Models (VLMs) to drastically reduce the labor-intensive task of manual labeling. In order to achieve that, the method exploits: 1) the knowledge embedded in the VLM's pretraining; 2) a teacher-student model where the teacher learns from noisy labels coming from the VLMs, and the student learns by weak supervision using teacher-generate labels and a noise-aware loss function. We also make available the first-of-its-kind dataset for semi-supervised detection of ephemeral gully from remote-sensed images. The dataset consists of a number of locations labeled by a group of soil and plant scientists, as well as a large number of unlabeled locations. The dataset represent more than 18,000 high-resolution remote-sensing images obtained over the course of 13 years. Our experimental results demonstrate the validity of our approach by showing superior performances compared to VLMs and the label model itself when using weak supervision to train an student model. The code and dataset for this work are made publicly available.

---

### Uni-Hema: Unified Model for Digital Hematopathology

Authors: Abdul Rehman, Iqra Rasool, Ayisha Imran, Mohsen Ali, Waqas Sultani
Published: 2025-11-17
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.13889v2

Digital hematopathology requires cell-level analysis across diverse disease categories, including malignant disorders (e.g., leukemia), infectious conditions (e.g., malaria), and non-malignant red blood cell disorders (e.g., sickle cell disease). Whether single-task, vision-language, WSI-optimized, or single-cell hematology models, these approaches share a key limitation, they cannot provide unified, multi-task, multi-modal reasoning across the complexities of digital hematopathology. To overcome these limitations, we propose Uni-Hema, a multi-task, unified model for digital hematopathology integrating detection, classification, segmentation, morphology prediction, and reasoning across multiple diseases. Uni-Hema leverages 46 publicly available datasets, encompassing over 700K images and 21K question-answer pairs, and is built upon Hema-Former, a multimodal module that bridges visual and textual representations at the hierarchy level for the different tasks (detection, classification, segmentation, morphology, mask language modeling and visual question answer) at different granularity. Extensive experiments demonstrate that Uni-Hema achieves comparable or superior performance to train on a single-task and single dataset models, across diverse hematological tasks, while providing interpretable, morphologically relevant insights at the single-cell level. Our framework establishes a new standard for multi-task and multi-modal digital hematopathology. The code will be made publicly available.

---

### Tractable Probabilistic Models for Investment Planning

Authors: Nicolas M. Cuadrado A., Mohannad Takrouri, Jiří Němeček, Martin Takáč, Jakub Mareček
Published: 2025-11-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.13888v3

Investment planning in power utilities, such as generation and transmission expansion, requires decisions under substantial uncertainty over decade--long horizons for policies, demand, renewable availability, and outages, while maintaining reliability and computational tractability. Conventional approaches approximate uncertainty using finite scenario sets (modeled as a mixture of Diracs in statistical theory terms), which can become computationally intensive as scenario detail increases and provide limited probabilistic resolution for reliability assessment. We propose an alternative based on tractable probabilistic models, using sum--product networks (SPNs) to represent high--dimensional uncertainty in a compact, analytically tractable form that supports exact probabilistic queries (e.g., likelihoods, marginals, and conditionals). This framework enables the direct embedding of chance constraints into mixed--integer linear programming (MILP) models for investment planning to evaluate reliability events and enforce probabilistic feasibility requirements without enumerating large scenario trees. We demonstrate the approach on a representative planning case study and report reliability--cost trade--offs and computational behavior relative to standard scenario--based formulations.

---

### Can QE-informed (Re)Translation lead to Error Correction?

Authors: Govardhan Padmanabhan
Published: 2025-11-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.13884v1

The paper presents two approaches submitted to the WMT 2025 Automated Translation Quality Evaluation Systems Task 3 - Quality Estimation (QE)-informed Segment-level Error Correction. While jointly training QE systems with Automatic Post-Editing (APE) has shown improved performance for both tasks, APE systems are still known to overcorrect the output of Machine Translation (MT), leading to a degradation in performance. We investigate a simple training-free approach - QE-informed Retranslation, and compare it with another within the same training-free paradigm. Our winning approach selects the highest-quality translation from multiple candidates generated by different LLMs. The second approach, more akin to APE, instructs an LLM to replace error substrings as specified in the provided QE explanation(s). A conditional heuristic was employed to minimise the number of edits, with the aim of maximising the Gain-to-Edit ratio. The two proposed approaches achieved a Delta COMET score of 0.0201 and -0.0108, respectively, leading the first approach to achieve the winning position on the subtask leaderboard.

---

### Revisiting Data Scaling in Medical Image Segmentation via Topology-Aware Augmentation

Authors: Yuetan Chu, Zhongyi Han, Gongning Luo, Xin Gao
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13883v2

Understanding how segmentation performance scales with training data is fundamental for developing data-efficient medical AI systems. In this study, we systematically revisit data scaling behavior across 15 anatomical segmentation tasks spanning four imaging modalities. We observe that medical segmentation follows a structurally stable power-law-like relationship between predictive error and dataset size, characterized by rapid improvement in low-data regimes. However, unlike classical large-scale vision or language tasks, segmentation exhibits earlier and task-dependent performance saturation, with a persistent error floor emerging even as data increases. This behavior suggests that segmentation scaling is not purely data-constrained but is influenced by intrinsic geometric and anatomical structure. To further probe this geometry-constrained regime, we investigate whether topology-aware deformation-based augmentation can modify effective scaling dynamics. We compare random elastic deformation with registration-guided and generative deformation-field modeling strategies. While the overall functional form of the scaling law remains preserved, topology-aware augmentation systematically lowers the effective error scale and reshapes convergence behavior in a task-dependent manner, leading to improved sample efficiency without overturning the underlying scaling principle. These findings indicate that medical segmentation obeys a geometry-limited scaling law, and that anatomically grounded augmentation enhances data efficiency by expanding effective topological coverage rather than altering the fundamental scaling structure. Our results provide a principled empirical perspective on data-efficient learning in medical image segmentation. The code will be released after acceptance.

---

### VLMs Guided Interpretable Decision Making for Autonomous Driving

Authors: Xin Hu, Taotao Jing, Renran Tian, Zhengming Ding
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13881v1

Recent advancements in autonomous driving (AD) have explored the use of vision-language models (VLMs) within visual question answering (VQA) frameworks for direct driving decision-making. However, these approaches often depend on handcrafted prompts and suffer from inconsistent performance, limiting their robustness and generalization in real-world scenarios. In this work, we evaluate state-of-the-art open-source VLMs on high-level decision-making tasks using ego-view visual inputs and identify critical limitations in their ability to deliver reliable, context-aware decisions. Motivated by these observations, we propose a new approach that shifts the role of VLMs from direct decision generators to semantic enhancers. Specifically, we leverage their strong general scene understanding to enrich existing vision-based benchmarks with structured, linguistically rich scene descriptions. Building on this enriched representation, we introduce a multi-modal interactive architecture that fuses visual and linguistic features for more accurate decision-making and interpretable textual explanations. Furthermore, we design a post-hoc refinement module that utilizes VLMs to enhance prediction reliability. Extensive experiments on two autonomous driving benchmarks demonstrate that our approach achieves state-of-the-art performance, offering a promising direction for integrating VLMs into reliable and interpretable AD systems.

---

### AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection

Authors: Saleh Momeni, Changnan Xiao, Bing Liu
Published: 2025-11-17
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.13880v1

This paper studies the problem of class-incremental learning (CIL), a core setting within continual learning where a model learns a sequence of tasks, each containing a distinct set of classes. Traditional CIL methods, which do not leverage pre-trained models (PTMs), suffer from catastrophic forgetting (CF) due to the need to incrementally learn both feature representations and the classifier. The integration of PTMs into CIL has recently led to efficient approaches that treat the PTM as a fixed feature extractor combined with analytic classifiers, achieving state-of-the-art performance. However, they still face a major limitation: the inability to continually adapt feature representations to best suit the CIL tasks, leading to suboptimal performance. To address this, we propose AnaCP (Analytic Contrastive Projection), a novel method that preserves the efficiency of analytic classifiers while enabling incremental feature adaptation without gradient-based training, thereby eliminating the CF caused by gradient updates. Our experiments show that AnaCP not only outperforms existing baselines but also achieves the accuracy level of joint training, which is regarded as the upper bound of CIL.

---

### Hybrid Convolution Neural Network Integrated with Pseudo-Newton Boosting for Lumbar Spine Degeneration Detection

Authors: Pandiyaraju V, Abishek Karthik, Jaspin K, Kannan A, Jaime Lloret
Published: 2025-11-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.13877v1

This paper proposes a new enhanced model architecture to perform classification of lumbar spine degeneration with DICOM images while using a hybrid approach, integrating EfficientNet and VGG19 together with custom-designed components. The proposed model is differentiated from traditional transfer learning methods as it incorporates a Pseudo-Newton Boosting layer along with a Sparsity-Induced Feature Reduction Layer that forms a multi-tiered framework, further improving feature selection and representation. The Pseudo-Newton Boosting layer makes smart variations of feature weights, with more detailed anatomical features, which are mostly left out in a transfer learning setup. In addition, the Sparsity-Induced Layer removes redundancy for learned features, producing lean yet robust representations for pathology in the lumbar spine. This architecture is novel as it overcomes the constraints in the traditional transfer learning approach, especially in the high-dimensional context of medical images, and achieves a significant performance boost, reaching a precision of 0.9, recall of 0.861, F1 score of 0.88, loss of 0.18, and an accuracy of 88.1%, compared to the baseline model, EfficientNet. This work will present the architectures, preprocessing pipeline, and experimental results. The results contribute to the development of automated diagnostic tools for medical images.

---

### QwenCLIP: Boosting Medical Vision-Language Pretraining via LLM Embeddings and Prompt tuning

Authors: Xiaoyang Wei, Camille Kurtz, Florence Cloppet
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13876v1

Contrastive Language-Image Pretraining (CLIP) has demonstrated strong generalization for vision-language tasks in computer vision and medical domains, yet its text encoder accepts only up to 77 tokens, which limits its ability to represent long and information-rich radiology reports. Recent adaptations using domain-specific encoders, such as PubMedBERT or ClinicalBERT, mitigate this issue by leveraging medical corpora, but remain constrained by their limited input length (typically 512 tokens) and relatively shallow semantic understanding. To address these limitations, we propose QwenCLIP, a vision-language framework that replaces CLIP's text encoder with a large language model (LLM)-based embedding module (e.g., Qwen3-Embedding) and introduces learnable prompts to enhance cross-modal alignment. By leveraging the extended context window and richer representations of LLMs, QwenCLIP captures comprehensive medical semantics from long-form clinical text, substantially improving medical image-text alignment and downstream performance on radiology benchmarks. Our code is publicly available at https://github.com/Wxy-24/QwenCLIP.

---

### H-CNN-ViT: A Hierarchical Gated Attention Multi-Branch Model for Bladder Cancer Recurrence Prediction

Authors: Xueyang Li, Zongren Wang, Yuliang Zhang, Zixuan Pan, Yu-Jen Chen, Nishchal Sapkota, Gelei Xu, Danny Z. Chen, Yiyu Shi
Published: 2025-11-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.13869v2

Bladder cancer is one of the most prevalent malignancies worldwide, with a recurrence rate of up to 78%, necessitating accurate post-operative monitoring for effective patient management. Multi-sequence contrast-enhanced MRI is commonly used for recurrence detection; however, interpreting these scans remains challenging, even for experienced radiologists, due to post-surgical alterations such as scarring, swelling, and tissue remodeling. AI-assisted diagnostic tools have shown promise in improving bladder cancer recurrence prediction, yet progress in this field is hindered by the lack of dedicated multi-sequence MRI datasets for recurrence assessment study. In this work, we first introduce a curated multi-sequence, multi-modal MRI dataset specifically designed for bladder cancer recurrence prediction, establishing a valuable benchmark for future research. We then propose H-CNN-ViT, a new Hierarchical Gated Attention Multi-Branch model that enables selective weighting of features from the global (ViT) and local (CNN) paths based on contextual demands, achieving a balanced and targeted feature fusion. Our multi-branch architecture processes each modality independently, ensuring that the unique properties of each imaging channel are optimally captured and integrated. Evaluated on our dataset, H-CNN-ViT achieves an AUC of 78.6%, surpassing state-of-the-art models. Our model is publicly available at https://github.com/XLIAaron/H-CNN-ViT.

---

### Randomized Controlled Trials for Conditional Access Optimization Agent

Authors: James Bono, Beibei Cheng, Joaquin Lozano
Published: 2025-11-17
Categories: econ.GN, cs.AI
arXiv: https://arxiv.org/abs/2511.13865v1

AI agents are increasingly deployed to automate complex enterprise workflows, yet evidence of their effectiveness in identity governance is limited. We report results from the first randomized controlled trial (RCT) evaluating an AI agent for Conditional Access (CA) policy management in Microsoft Entra. The agent assists with four high-value tasks: policy merging, Zero-Trust baseline gap detection, phased rollout planning, and user-policy alignment. In a production-grade environment, 162 identity administrators were randomly assigned to a control group (no agent) or treatment group (agent-assisted) and asked to perform these tasks. Agent access produced substantial gains: accuracy improved by 48% and task completion time decreased by 43% while holding accuracy constant. The largest benefits emerged on cognitively demanding tasks such as baseline gap detection. These findings demonstrate that purpose-built AI agents can significantly enhance both speed and accuracy in identity administration.

---

### GRLoc: Geometric Representation Regression for Visual Localization

Authors: Changyang Li, Xuejian Ma, Lixiang Liu, Zhan Li, Qingan Yan, Yi Xu
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13864v2

Absolute Pose Regression (APR) has emerged as a compelling paradigm for visual localization. However, APR models typically operate as black boxes, directly regressing a 6-DoF pose from a query image, which can lead to memorizing training views rather than understanding 3D scene geometry. In this work, we propose a geometrically-grounded alternative. Inspired by novel view synthesis, which renders images from intermediate geometric representations, we reformulate APR as its inverse that regresses the underlying 3D representations directly from the image, and we name this paradigm Geometric Representation Regression (GRR). Our model explicitly predicts two disentangled geometric representations in the world coordinate system: (1) a raymap's directions to estimate camera rotation, and (2) a corresponding pointmap to estimate camera translation. The final camera pose is then recovered from these geometric components using a differentiable deterministic solver. This disentangled approach, which separates the learned visual-to-geometry mapping from the final pose calculation, introduces a strong geometric prior into the network. We find that the explicit decoupling of rotation and translation predictions measurably boosts performance. We demonstrate state-of-the-art performance on 7-Scenes and Cambridge Landmarks datasets, validating that modeling the inverse rendering process is a more robust path toward generalizable absolute pose estimation.

---

### Segmenting Collision Sound Sources in Egocentric Videos

Authors: Kranti Kumar Parida, Omar Emara, Hazel Doughty, Dima Damen
Published: 2025-11-17
Categories: cs.CV, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2511.13863v2

Humans excel at multisensory perception and can often recognise object properties from the sound of their interactions. Inspired by this, we propose the novel task of Collision Sound Source Segmentation (CS3), where we aim to segment the objects responsible for a collision sound in visual input (i.e. video frames from the collision clip), conditioned on the audio. This task presents unique challenges. Unlike isolated sound events, a collision sound arises from interactions between two objects, and the acoustic signature of the collision depends on both. We focus on egocentric video, where sounds are often clear, but the visual scene is cluttered, objects are small, and interactions are brief. To address these challenges, we propose a weakly-supervised method for audio-conditioned segmentation, utilising foundation models (CLIP and SAM2). We also incorporate egocentric cues, i.e. objects in hands, to find acting objects that can potentially be collision sound sources. Our approach outperforms competitive baselines by $3\times$ and $4.7\times$ in mIoU on two benchmarks we introduce for the CS3 task: EPIC-CS3 and Ego4D-CS3.

---

### Randomized Controlled Trials for Phishing Triage Agent

Authors: James Bono
Published: 2025-11-17
Categories: econ.GN, cs.AI
arXiv: https://arxiv.org/abs/2511.13860v1

Security operations centers (SOCs) face a persistent challenge: efficiently triaging a high volume of user-reported phishing emails while maintaining robust protection against threats. This paper presents the first randomized controlled trial (RCT) evaluating the impact of a domain-specific AI agent - the Microsoft Security Copilot Phishing Triage Agent - on analyst productivity and accuracy. Our results demonstrate that agent-augmented analysts achieved up to 6.5 times as many true positives per analyst minute and a 77% improvement in verdict accuracy compared to a control group. The agent's queue prioritization and verdict explanations were both significant drivers of efficiency. Behavioral analysis revealed that agent-augmented analysts reallocated their attention, spending 53% more time on malicious emails, and were not prone to rubber-stamping the agent's malicious verdicts. These findings offer actionable insights for SOC leaders considering AI adoption, including the potential for agents to fundamentally change the optimal allocation of SOC resources.

---

### RSPose: Ranking Based Losses for Human Pose Estimation

Authors: Muhammed Can Keles, Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13857v1

While heatmap-based human pose estimation methods have shown strong performance, they suffer from three main problems: (P1) "Commonly used Mean Squared Error (MSE)" Loss may not always improve joint localization because it penalizes all pixel deviations equally, without focusing explicitly on sharpening and correctly localizing the peak corresponding to the joint; (P2) heatmaps are spatially and class-wise imbalanced; and, (P3) there is a discrepancy between the evaluation metric (i.e., mAP) and the loss functions. We propose ranking-based losses to address these issues. Both theoretically and empirically, we show that our proposed losses are superior to commonly used heatmap losses (MSE, KL-Divergence). Our losses considerably increase the correlation between confidence scores and localization qualities, which is desirable because higher correlation leads to more accurate instance selection during Non-Maximum Suppression (NMS) and better Average Precision (mAP) performance. We refer to the models trained with our losses as RSPose. We show the effectiveness of RSPose across two different modes: one-dimensional and two-dimensional heatmaps, on three different datasets (COCO, CrowdPose, MPII). To the best of our knowledge, we are the first to propose losses that align with the evaluation metric (mAP) for human pose estimation. RSPose outperforms the previous state of the art on the COCO-val set and achieves an mAP score of 79.9 with ViTPose-H, a vision transformer model for human pose estimation. We also improve SimCC Resnet-50, a coordinate classification-based pose estimation method, by 1.5 AP on the COCO-val set, achieving 73.6 AP.

---

### Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark

Authors: Xinxin Liu, Zhaopan Xu, Ming Li, Kai Wang, Yong Jae Lee, Yuzhang Shang
Published: 2025-11-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.13853v3

While Chain-of-Thought (CoT) prompting enables sophisticated symbolic reasoning in LLMs, it remains confined to discrete text and cannot simulate the continuous, physics-governed dynamics of the real world. Recent video generation models have emerged as potential world simulators through Chain-of-Frames (CoF) reasoning -- materializing thought as frame-by-frame visual sequences, with each frame representing a physically-grounded reasoning step. Despite compelling demonstrations, a challenge persists: existing benchmarks, focusing on fidelity or alignment, do not assess CoF reasoning and thus cannot measure core cognitive abilities in multi-step planning, algorithmic logic, or abstract pattern extrapolation. This evaluation void prevents systematic understanding of model capabilities and principled guidance for improvement. We introduce Gen-ViRe (Generative Visual Reasoning Benchmark), a framework grounded in cognitive science and real-world AI applications, which decomposes CoF reasoning into six cognitive dimensions -- from perceptual logic to abstract planning -- and 24 subtasks. Through multi-source data curation, minimal prompting protocols, and hybrid VLM-assisted evaluation with detailed criteria, Gen-ViRe delivers the first quantitative assessment of video models as reasoners. Our experiments on SOTA systems reveal substantial discrepancies between impressive visual quality and actual reasoning depth, establishing baselines and diagnostic tools to advance genuine world simulators.

---

### Causal computations in Semi Markovian Structural Causal Models using divide and conquer

Authors: Anna Rodum Bjøru, Rafael Cabañas, Helge Langseth, Antonio Salmerón
Published: 2025-11-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.13852v1

Recently, Bjøru et al. proposed a novel divide-and-conquer algorithm for bounding counterfactual probabilities in structural causal models (SCMs). They assumed that the SCMs were learned from purely observational data, leading to an imprecise characterization of the marginal distributions of exogenous variables. Their method leveraged the canonical representation of structural equations to decompose a general SCM with high-cardinality exogenous variables into a set of sub-models with low-cardinality exogenous variables. These sub-models had precise marginals over the exogenous variables and therefore admitted efficient exact inference. The aggregated results were used to bound counterfactual probabilities in the original model. The approach was developed for Markovian models, where each exogenous variable affects only a single endogenous variable. In this paper, we investigate extending the methodology to \textit{semi-Markovian} SCMs, where exogenous variables may influence multiple endogenous variables. Such models are capable of representing confounding relationships that Markovian models cannot. We illustrate the challenges of this extension using a minimal example, which motivates a set of alternative solution strategies. These strategies are evaluated both theoretically and through a computational study.

---

### QUASAR: An Evolutionary Algorithm to Accelerate High-Dimensional Numerical Optimization

Authors: Julian G. Soltes
Published: 2025-11-17
Categories: math.OC, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2511.13843v4

High-dimensional numerical optimization presents a persistent challenge in computational science. This paper introduces Quasi-Adaptive Search with Asymptotic Reinitialization (QUASAR), an evolutionary algorithm to accelerate convergence in complex, non-differentiable problems afflicted by the curse of dimensionality. QUASAR expands upon the core principles of Differential Evolution (DE), introducing quasi-adaptive mechanisms to dynamically balance exploration and exploitation in its search. Inspired by the behavior of quantum particles, the algorithm utilizes three highly stochastic mechanisms that augment standard DE: 1) probabilistic mutation strategies and scaling factors; 2) rank-based crossover rates; 3) asymptotically decaying covariance reinitializations. Evaluated on the notoriously difficult CEC2017 benchmark suite of 29 test functions, QUASAR achieved the lowest overall rank sum (367) using the Friedman test, outperforming DE (735) and L-SHADE (452). Geometric mean comparisons show average final solution quality improvements of $3.85 \times$ and $2.07 \times$ compared to DE and L-SHADE, respectively ($p \ll 0.001$), with average optimization speed averaging $1.40 \times$ and $5.16 \times$ faster. QUASAR's performance establishes it as an effective, efficient, and user-friendly evolutionary algorithm for complex high-dimensional problems.

---