# Research Papers — 2025-11 · bundle page 193 of 197

> Full-text markdown of papers #9601–9650 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/193
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/192.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/194.md)

### GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networks

Authors: Heng Zheng, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Hao Zhang, Wenjun Huang, Jin Huang
Published: 2025-11-02
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2511.00908v2

Visual geo-localization requires extensive geographic knowledge and sophisticated reasoning to determine image locations without GPS metadata. Traditional retrieval methods are constrained by database coverage and quality. Recent Large Vision-Language Models (LVLMs) enable direct location reasoning from image content, yet individual models struggle with diverse geographic regions and complex scenes. Existing multi-agent systems improve performance through model collaboration but treat all agent interactions uniformly. They lack mechanisms to handle conflicting predictions effectively. We propose \textbf{GraphGeo}, a multi-agent debate framework using heterogeneous graph neural networks for visual geo-localization. Our approach models diverse debate relationships through typed edges, distinguishing supportive collaboration, competitive argumentation, and knowledge transfer. We introduce a dual-level debate mechanism combining node-level refinement and edge-level argumentation modeling. A cross-level topology refinement strategy enables co-evolution between graph structure and agent representations. Experiments on multiple benchmarks demonstrate GraphGeo significantly outperforms state-of-the-art methods. Our framework transforms cognitive conflicts between agents into enhanced geo-localization accuracy through structured debate.

---

### Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle

Authors: Ruifeng Ren, Sheng Ouyang, Huayi Tang, Yong Liu
Published: 2025-11-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00907v2

Attention-based Transformers have demonstrated strong adaptability across a wide range of tasks and have become the backbone of modern Large Language Models (LLMs). However, their underlying mechanisms remain open for further exploration. The energy-based perspective has long provided a valuable principle for understanding neural computation. In this paper, we revisit the principle of energy as a lens to understand attention-based Transformer models. We present a unified energy-based framework which is composed of three key components: the local energy $E_i$, the global energy $F$, and the employed optimization algorithms. We show that different attention forms including unnormalized linear attention, gated linear attention and standard softmax attention can be induced by choosing their corresponding recipes within this framework. Building on this framework, we propose energy-based modifications of attention structures. Inspired by classical gradient descent (GD) algorithms, we extend the original attention formulation based on standard GD to the momentum-based GD, Nesterov Accelerated Gradient (NAG), and Newton's method, each inducing a corresponding new attention structure. Our experiments provide preliminary support for the potential of the energy-based framework for designing attention mechanisms.

---

### Random Spiking Neural Networks are Stable and Spectrally Simple

Authors: Ernesto Araya, Massimiliano Datres, Gitta Kutyniok
Published: 2025-11-02
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.00904v2

Spiking neural networks (SNNs) are a promising paradigm for energy-efficient computation, yet their theoretical foundations-especially regarding stability and robustness-remain limited compared to artificial neural networks. In this work, we study discrete-time leaky integrate-and-fire (LIF) SNNs through the lens of Boolean function analysis. We focus on noise sensitivity and stability in classification tasks, quantifying how input perturbations affect outputs. Our main result shows that wide LIF-SNN classifiers are stable on average, a property explained by the concentration of their Fourier spectrum on low-frequency components. Motivated by this, we introduce the notion of spectral simplicity, which formalizes simplicity in terms of Fourier spectrum concentration and connects our analysis to the simplicity bias observed in deep networks. Within this framework, we show that random LIF-SNNs are biased toward simple functions. Experiments on trained networks confirm that these stability properties persist in practice. Together, these results provide new insights into the stability and robustness properties of SNNs.

---

### ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval

Authors: Ahmed Masry, Megh Thakkar, Patrice Bechard, Sathwik Tejaswi Madhusudhan, Rabiul Awal, Shambhavi Mishra, Akshay Kalkunte Suresh, Srivatsava Daruru, Enamul Hoque, Spandana Gella, Torsten Scholak, Sai Rajeswar
Published: 2025-11-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.00903v1

Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, existing methods for multimodal document retrieval often replicate techniques developed for text-only retrieval, whether in how they encode documents, define training objectives, or compute similarity scores. To address these limitations, we present ColMate, a document retrieval model that bridges the gap between multimodal representation learning and document retrieval. ColMate utilizes a novel OCR-based pretraining objective, a self-supervised masked contrastive learning objective, and a late interaction scoring mechanism more relevant to multimodal document structures and visual characteristics. ColMate obtains 3.61% improvements over existing retrieval models on the ViDoRe V2 benchmark, demonstrating stronger generalization to out-of-domain benchmarks.

---

### Learning with Category-Equivariant Representations for Human Activity Recognition

Authors: Yoshihiro Maruyama
Published: 2025-11-02
Categories: cs.LG, cs.AI, cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2511.00900v1

Human activity recognition is challenging because sensor signals shift with context, motion, and environment; effective models must therefore remain stable as the world around them changes. We introduce a categorical symmetry-aware learning framework that captures how signals vary over time, scale, and sensor hierarchy. We build these factors into the structure of feature representations, yielding models that automatically preserve the relationships between sensors and remain stable under realistic distortions such as time shifts, amplitude drift, and device orientation changes. On the UCI Human Activity Recognition benchmark, this categorical symmetry-driven design improves out-of-distribution accuracy by approx. 46 percentage points (approx. 3.6x over the baseline), demonstrating that abstract symmetry principles can translate into concrete performance gains in everyday sensing tasks via category-equivariant representation theory.

---

### Dynamic Logic of Trust-Based Beliefs

Authors: Junli Jiang, Pavel Naumov, Wenxuan Zhang
Published: 2025-11-02
Categories: cs.LO, cs.AI, math.LO
arXiv: https://arxiv.org/abs/2511.00899v1

Traditionally, an agent's beliefs would come from what the agent can see, hear, or sense. In the modern world, beliefs are often based on the data available to the agents. In this work, we investigate a dynamic logic of such beliefs that incorporates public announcements of data. The main technical contribution is a sound and complete axiomatisation of the interplay between data-informed beliefs and data announcement modalities. We also describe a non-trivial polynomial model checking algorithm for this logical system.

---

### Android Malware Detection: A Machine Leaning Approach

Authors: Hasan Abdulla
Published: 2025-11-02
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.00894v1

This study examines machine learning techniques like Decision Trees, Support Vector Machines, Logistic Regression, Neural Networks, and ensemble methods to detect Android malware. The study evaluates these models on a dataset of Android applications and analyzes their accuracy, efficiency, and real-world applicability. Key findings show that ensemble methods demonstrate superior performance, but there are trade-offs between model interpretability, efficiency, and accuracy. Given its increasing threat, the insights guide future research and practical use of ML to combat Android malware.

---

### HEATNETs: Explainable Random Feature Neural Networks for High-Dimensional Parabolic PDEs

Authors: Kyriakos Georgiou, Gianluca Fabiani, Constantinos Siettos, Athanasios N. Yannacopoulos
Published: 2025-11-02
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2511.00886v1

We deal with the solution of the forward problem for high-dimensional parabolic PDEs with random feature (projection) neural networks (RFNNs). We first prove that there exists a single-hidden layer neural network with randomized heat-kernels arising from the fundamental solution (Green's functions) of the heat operator, that we call HEATNET, that provides an unbiased universal approximator to the solution of parabolic PDEs in arbitrary (high) dimensions, with the rate of convergence being analogous to the ${O}(N^{-1/2})$, where $N$ is the size of HEATNET. Thus, HEATNETs are explainable schemes, based on the analytical framework of parabolic PDEs, exploiting insights from physics-informed neural networks aided by numerical and functional analysis, and the structure of the corresponding solution operators. Importantly, we show how HEATNETs can be scaled up for the efficient numerical solution of arbitrary high-dimensional parabolic PDEs using suitable transformations and importance Monte Carlo sampling of the integral representation of the solution, in order to deal with the singularities of the heat kernel around the collocation points. We evaluate the performance of HEATNETs through benchmark linear parabolic problems up to 2,000 dimensions. We show that HEATNETs result in remarkable accuracy with the order of the approximation error ranging from $1.0E-05$ to $1.0E-07$ for problems up to 500 dimensions, and of the order of $1.0E-04$ to $1.0E-03$ for 1,000 to 2,000 dimensions, with a relatively low number (up to 15,000) of features.

---

### SpEx: A Spectral Approach to Explainable Clustering

Authors: Tal Argov, Tal Wagner
Published: 2025-11-02
Categories: cs.LG, cs.DS
arXiv: https://arxiv.org/abs/2511.00885v1

Explainable clustering by axis-aligned decision trees was introduced by Moshkovitz et al. (2020) and has gained considerable interest. Prior work has focused on minimizing the price of explainability for specific clustering objectives, lacking a general method to fit an explanation tree to any given clustering, without restrictions. In this work, we propose a new and generic approach to explainable clustering, based on spectral graph partitioning. With it, we design an explainable clustering algorithm that can fit an explanation tree to any given non-explainable clustering, or directly to the dataset itself. Moreover, we show that prior algorithms can also be interpreted as graph partitioning, through a generalized framework due to Trevisan (2013) wherein cuts are optimized in two graphs simultaneously. Our experiments show the favorable performance of our method compared to baselines on a range of datasets.

---

### Deep Generative Models for Enhanced Vitreous OCT Imaging

Authors: Simone Sarrocco, Philippe C. Cattin, Peter M. Maloca, Paul Friedrich, Philippe Valmaggia
Published: 2025-11-02
Categories: eess.IV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.00881v2

Purpose: To evaluate deep learning (DL) models for enhancing vitreous optical coherence tomography (OCT) image quality and reducing acquisition time. Methods: Conditional Denoising Diffusion Probabilistic Models (cDDPMs), Brownian Bridge Diffusion Models (BBDMs), U-Net, Pix2Pix, and Vector-Quantised Generative Adversarial Network (VQ-GAN) were used to generate high-quality spectral-domain (SD) vitreous OCT images. Inputs were SD ART10 images, and outputs were compared to pseudoART100 images obtained by averaging ten ART10 images per eye location. Model performance was assessed using image quality metrics and Visual Turing Tests, where ophthalmologists ranked generated images and evaluated anatomical fidelity. The best model's performance was further tested within the manually segmented vitreous on newly acquired data. Results: U-Net achieved the highest Peak Signal-to-Noise Ratio (PSNR: 30.230) and Structural Similarity Index Measure (SSIM: 0.820), followed by cDDPM. For Learned Perceptual Image Patch Similarity (LPIPS), Pix2Pix (0.697) and cDDPM (0.753) performed best. In the first Visual Turing Test, cDDPM ranked highest (3.07); in the second (best model only), cDDPM achieved a 32.9% fool rate and 85.7% anatomical preservation. On newly acquired data, cDDPM generated vitreous regions more similar in PSNR to the ART100 reference than true ART1 or ART10 B-scans and achieved higher PSNR on whole images when conditioned on ART1 than ART10. Conclusions: Results reveal discrepancies between quantitative metrics and clinical evaluation, highlighting the need for combined assessment. cDDPM showed strong potential for generating clinically meaningful vitreous OCT images while reducing acquisition time fourfold. Translational Relevance: cDDPMs show promise for clinical integration, supporting faster, higher-quality vitreous imaging. Dataset and code will be made publicly available.

---

### KFCPO: Kronecker-Factored Approximated Constrained Policy Optimization

Authors: Joonyoung Lim, Younghwan Yoo
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00880v1

We propose KFCPO, a novel Safe Reinforcement Learning (Safe RL) algorithm that combines scalable Kronecker-Factored Approximate Curvature (K-FAC) based second-order policy optimization with safety-aware gradient manipulation. KFCPO leverages K-FAC to perform efficient and stable natural gradient updates by approximating the Fisher Information Matrix (FIM) in a layerwise, closed form manner, avoiding iterative approximation overheads. To address the tradeoff between reward maximization and constraint satisfaction, we introduce a margin aware gradient manipulation mechanism that adaptively adjusts the influence of reward and cost gradients based on the agent's proximity to safety boundaries. This method blends gradients using a direction sensitive projection, eliminating harmful interference and avoiding abrupt changes caused by fixed hard thresholds. Additionally, a minibatch level KL rollback strategy is adopted to ensure trust region compliance and to prevent destabilizing policy shifts. Experiments on Safety Gymnasium using OmniSafe show that KFCPO achieves 10.3% to 50.2% higher average return across environments compared to the best baseline that respected the safety constraint, demonstrating superior balance of safety and performance.

---

### Assessing LLM Reasoning Steps via Principal Knowledge Grounding

Authors: Hyeon Hwang, Yewon Cho, Chanwoong Yoon, Yein Park, Minju Song, Kyungjae Lee, Gangwoo Kim, Jaewoo Kang
Published: 2025-11-02
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.00879v1

Step-by-step reasoning has become a standard approach for large language models (LLMs) to tackle complex tasks. While this paradigm has proven effective, it raises a fundamental question: How can we verify that an LLM's reasoning is accurately grounded in knowledge? To address this question, we introduce a novel evaluation suite that systematically assesses the knowledge grounding of intermediate reasoning. Our framework comprises three key components. (1) Principal Knowledge Collection, a large-scale repository of atomic knowledge essential for reasoning. Based on the collection, we propose (2) knowledge-grounded evaluation metrics designed to measure how well models recall and apply prerequisite knowledge in reasoning. These metrics are computed by our (3) evaluator LLM, a lightweight model optimized for cost-effective and reliable metric computation. Our evaluation suite demonstrates remarkable effectiveness in identifying missing or misapplied knowledge elements, providing crucial insights for uncovering fundamental reasoning deficiencies in LLMs. Beyond evaluation, we demonstrate how these metrics can be integrated into preference optimization, showcasing further applications of knowledge-grounded evaluation.

---

### Controlling Gender Bias in Retrieval via a Backpack Architecture

Authors: Amirabbas Afzali, Amirreza Velae, Iman Ahmadi, Mohammad Aliannejadi
Published: 2025-11-02
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2511.00875v1

The presence of social biases in large language models (LLMs) has become a significant concern in AI research. These biases, often embedded in training data, can perpetuate harmful stereotypes and distort decision-making processes. When LLMs are integrated into ranking systems, they can propagate these biases, leading to unfair outcomes in critical applications such as search engines and recommendation systems. Backpack Language Models, unlike traditional transformer-based models that treat text sequences as monolithic structures, generate outputs as weighted combinations of non-contextual, learned word aspects, also known as senses. Leveraging this architecture, we propose a framework for debiasing ranking tasks. Our experimental results show that this framework effectively mitigates gender bias in text retrieval and ranking with minimal degradation in performance.

---

### Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding

Authors: Taowen Liu, Marta Andronic, Deniz Gündüz, George A. Constantinides
Published: 2025-11-02
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2511.00874v1

LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade model accuracy. Stochastic Rounding (SR) has emerged as a theoretically attractive alternative to deterministic rounding, offering unbiased gradient estimates. However, its interaction with other training factors -- especially batch size -- remains under explored. In this paper, we present a theoretical and empirical study of mini-batch stochastic gradient descent (SGD) with SR, showing that increased batch sizes can compensate for reduced precision during back-propagation. Furthermore, we show that quantizing weights and activations impacts gradient variance in distinct ways. Our experiments validate these theoretical insights.

---

### Fast Stochastic Greedy Algorithm for $k$-Submodular Cover Problem

Authors: Hue T. Nguyen, Tan D. Tran, Nguyen Long Giang, Canh V. Pham
Published: 2025-11-02
Categories: cs.DS, cs.AI
arXiv: https://arxiv.org/abs/2511.00869v1

We study the $k$-Submodular Cover ($kSC$) problem, a natural generalization of the classical Submodular Cover problem that arises in artificial intelligence and combinatorial optimization tasks such as influence maximization, resource allocation, and sensor placement. Existing algorithms for $\kSC$ often provide weak approximation guarantees or incur prohibitively high query complexity. To overcome these limitations, we propose a \textit{Fast Stochastic Greedy} algorithm that achieves strong bicriteria approximation while substantially lowering query complexity compared to state-of-the-art methods. Our approach dramatically reduces the number of function evaluations, making it highly scalable and practical for large-scale real-world AI applications where efficiency is essential.

---

### FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management

Authors: Nazmul Takbir, Hamidreza Alikhani, Nikil Dutt, Sangeetha Abdu Jyothi
Published: 2025-11-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00868v2

Large Language Model (LLM) serving is increasingly constrained by the growing size of the key-value (KV) cache, which scales with both context length and generation length. Prior work shows that attention is dominated by a small subset of critical tokens, yet existing systems struggle to exploit this efficiently without degrading accuracy, especially in long generation. We make a key observation: the temporal stability of these critical tokens varies significantly across KV heads: some heads consistently focus on the same tokens, while others shift frequently. Building on this insight, we introduce FlexiCache, a hierarchical KV-cache management system that leverages the temporal stability of KV heads to reduce GPU memory usage and computation overhead, while preserving model accuracy. FlexiCache classifies KV heads as stable or unstable: it retains all KV-cache pages from unstable heads in GPU memory, whereas for stable heads, it keeps only the top-K pages on the GPU and offloads the rest to host memory. By exploiting temporal stability, FlexiCache performs periodic reranking for stable heads to fetch newly promoted top pages. Implemented atop vLLM, FlexiCache reduces GPU memory footprint for long-context requests by up to 70%, improves offline serving throughput by 1.38-1.55x, and lowers online token latency by 1.6-2.1x, all while maintaining accuracy in long-context, long-generation scenarios.

---

### Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion

Authors: Jaehyun Park, Konyul Park, Daehun Kim, Junseo Park, Jun Won Choi
Published: 2025-11-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00859v1

In autonomous driving, transparency in the decision-making of perception models is critical, as even a single misperception can be catastrophic. Yet with multi-sensor inputs, it is difficult to determine how each modality contributes to a prediction because sensor information becomes entangled within the fusion network. We introduce Layer-Wise Modality Decomposition (LMD), a post-hoc, model-agnostic interpretability method that disentangles modality-specific information across all layers of a pretrained fusion model. To our knowledge, LMD is the first approach to attribute the predictions of a perception model to individual input modalities in a sensor-fusion system for autonomous driving. We evaluate LMD on pretrained fusion models under camera-radar, camera-LiDAR, and camera-radar-LiDAR settings for autonomous driving. Its effectiveness is validated using structured perturbation-based metrics and modality-wise visual decompositions, demonstrating practical applicability to interpreting high-capacity multimodal architectures. Code is available at https://github.com/detxter-jvb/Layer-Wise-Modality-Decomposition.

---

### Occlusion-Aware Diffusion Model for Pedestrian Intention Prediction

Authors: Yu Liu, Zhijie Liu, Zedong Yang, You-Fu Li, He Kong
Published: 2025-11-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.00858v1

Predicting pedestrian crossing intentions is crucial for the navigation of mobile robots and intelligent vehicles. Although recent deep learning-based models have shown significant success in forecasting intentions, few consider incomplete observation under occlusion scenarios. To tackle this challenge, we propose an Occlusion-Aware Diffusion Model (ODM) that reconstructs occluded motion patterns and leverages them to guide future intention prediction. During the denoising stage, we introduce an occlusion-aware diffusion transformer architecture to estimate noise features associated with occluded patterns, thereby enhancing the model's ability to capture contextual relationships in occluded semantic scenarios. Furthermore, an occlusion mask-guided reverse process is introduced to effectively utilize observation information, reducing the accumulation of prediction errors and enhancing the accuracy of reconstructed motion features. The performance of the proposed method under various occlusion scenarios is comprehensively evaluated and compared with existing methods on popular benchmarks, namely PIE and JAAD. Extensive experimental results demonstrate that the proposed method achieves more robust performance than existing methods in the literature.

---

### TriCon-Fair: Triplet Contrastive Learning for Mitigating Social Bias in Pre-trained Language Models

Authors: Chong Lyu, Lin Li, Shiqing Wu, Jingling Yuan
Published: 2025-11-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.00854v1

The increasing utilization of large language models raises significant concerns about the propagation of social biases, which may result in harmful and unfair outcomes. However, existing debiasing methods treat the biased and unbiased samples independently, thus ignoring their mutual relationship. This oversight enables a hidden negative-positive coupling, where improvements for one group inadvertently compromise the other, allowing residual social bias to persist. In this paper, we introduce TriCon-Fair, a contrastive learning framework that employs a decoupled loss that combines triplet and language modeling terms to eliminate positive-negative coupling. Our TriCon-Fair assigns each anchor an explicitly biased negative and an unbiased positive, decoupling the push-pull dynamics and avoiding positive-negative coupling, and jointly optimizes a language modeling (LM) objective to preserve general capability. Experimental results demonstrate that TriCon-Fair reduces discriminatory output beyond existing debiasing baselines while maintaining strong downstream performance. This suggests that our proposed TriCon-Fair offers a practical and ethical solution for sensitive NLP applications.

---

### Identifying Slug Formation in Oil Well Pipelines: A Use Case from Industrial Analytics

Authors: Abhishek Patange, Sharat Chidambaran, Prabhat Shankar, Manjunath G. B., Anindya Chatterjee
Published: 2025-11-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00851v1

Slug formation in oil and gas pipelines poses significant challenges to operational safety and efficiency, yet existing detection approaches are often offline, require domain expertise, and lack real-time interpretability. We present an interactive application that enables end-to-end data-driven slug detection through a compact and user-friendly interface. The system integrates data exploration and labeling, configurable model training and evaluation with multiple classifiers, visualization of classification results with time-series overlays, and a real-time inference module that generates persistence-based alerts when slug events are detected. The demo supports seamless workflows from labeled CSV uploads to live inference on unseen datasets, making it lightweight, portable, and easily deployable. By combining domain-relevant analytics with novel UI/UX features such as snapshot persistence, visual labeling, and real-time alerting, our tool adds significant dissemination value as both a research prototype and a practical industrial application. The demo showcases how interactive human-in-the-loop ML systems can bridge the gap between data science methods and real-world decision-making in critical process industries, with broader applicability to time-series fault diagnosis tasks beyond oil and gas.

---

### MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models

Authors: Yayue Deng, Guoqiang Hu, Haiyang Sun, Xiangyu Zhang, Haoyang Zhang, Fei Tian, Xuerui Yang, Gang Yu, Eng Siong Chng
Published: 2025-11-02
Categories: eess.AS, cs.AI, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2511.00850v1

Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on single-turn exchanges. We introduce Multi-Bench, the first benchmark explicitly designed to evaluate SDMs in multi-turn interactive dialogue with an emphasis on emotional intelligence. Multi-Bench employs a hierarchical structure with a basic track for emotion understanding and reasoning and an advanced track for emotion support and application. It comprises five carefully designed tasks and about 3.2K samples, ranging from emotion recognition to complex reasoning and interactive dialogue, supported by a reproducible evaluation framework. We evaluate six representative SDMs on eight subsets of Multi-Bench. Results show that while current SDMs achieve good performance on basic understanding tasks, they still have room for improvement in advanced multi-turn interactive dialogue and reasoning-related tasks, particularly in emotion awareness and application.

---

### Perturbations in the Orthogonal Complement Subspace for Efficient Out-of-Distribution Detection

Authors: Zhexiao Huang, Weihao He, Shutao Deng, Junzhe Chen, Chao Yuan, Hongxin Wang, Changsheng Zhou
Published: 2025-11-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.00849v1

Out-of-distribution (OOD) detection is essential for deploying deep learning models in open-world environments. Existing approaches, such as energy-based scoring and gradient-projection methods, typically rely on high-dimensional representations to separate in-distribution (ID) and OOD samples. We introduce P-OCS (Perturbations in the Orthogonal Complement Subspace), a lightweight and theoretically grounded method that operates in the orthogonal complement of the principal subspace defined by ID features. P-OCS applies a single projected perturbation restricted to this complementary subspace, enhancing subtle ID-OOD distinctions while preserving the geometry of ID representations. We show that a one-step update is sufficient in the small-perturbation regime and provide convergence guarantees for the resulting detection score. Experiments across multiple architectures and datasets demonstrate that P-OCS achieves state-of-the-art OOD detection with negligible computational cost and without requiring model retraining, access to OOD data, or changes to model architecture.

---

### Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers

Authors: Yuhan Cao, Yu Wang, Sitong Liu, Miao Li, Yixin Tao, Tianxing He
Published: 2025-11-02
Categories: cs.GT, cs.AI
arXiv: https://arxiv.org/abs/2511.00847v5

The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: the potential for dishonest manipulation by service providers. This manipulation can manifest in various forms, such as secretly substituting a proclaimed high-performance model with a low-cost alternative, or inflating responses with meaningless tokens to increase billing. This work tackles the issue through the lens of algorithmic game theory and mechanism design. We are the first to propose a formal economic model for a realistic user-provider ecosystem, where a user can iteratively delegate $T$ queries to multiple model providers, and providers can engage in a range of strategic behaviors. As our central contribution, we prove that for a continuous strategy space and any $ε\in(0,\frac12)$, there exists an approximate incentive-compatible mechanism with an additive approximation ratio of $O(T^{1-ε}\log T)$, and a guaranteed quasi-linear second-best user utility. We also prove an impossibility result, stating that no mechanism can guarantee an expected user utility that is asymptotically better than our mechanism. Furthermore, we demonstrate the effectiveness of our mechanism in simulation experiments with real-world API settings.

---

### OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks

Authors: Zhihao Peng, Cheng Wang, Shengyuan Liu, Zhiying Liang, Zanting Ye, Minjie Ju, PeterYM Woo, Yixuan Yuan
Published: 2025-11-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.00846v2

Brain imaging analysis is crucial for diagnosing and treating brain disorders, and multimodal large language models (MLLMs) are increasingly supporting it. However, current brain imaging visual question-answering (VQA) benchmarks either cover a limited number of imaging modalities or are restricted to coarse-grained pathological descriptions, hindering a comprehensive assessment of MLLMs across the full clinical continuum. To address these, we introduce OmniBrainBench, the first comprehensive multimodal VQA benchmark specifically designed to assess the multimodal comprehension capabilities of MLLMs in brain imaging analysis with closed- and open-ended evaluations. OmniBrainBench comprises 15 distinct brain imaging modalities collected from 30 verified medical sources, yielding 9,527 validated VQA pairs and 31,706 images. It simulates clinical workflows and encompasses 15 multi-stage clinical tasks rigorously validated by a professional radiologist. Evaluations of 24 state-of-the-art models, including open-source general-purpose, medical, and proprietary MLLMs, highlight the substantial challenges posed by OmniBrainBench. Experiments reveal that proprietary MLLMs like GPT-5 (63.37%) outperform others yet lag far behind physicians (91.35%), while medical ones show wide variance in closed- and open-ended VQA. Open-source general-purpose MLLMs generally trail but excel in specific tasks, and all ones fall short in complex preoperative reasoning, revealing a critical visual-to-clinical gap. OmniBrainBench establishes a new standard to assess MLLMs in brain imaging analysis, highlighting the gaps against physicians. We publicly release our benchmark at link.

---

### CodeClash: Benchmarking Goal-Oriented Software Engineering

Authors: John Yang, Kilian Lieret, Joyce Yang, Carlos E. Jimenez, Muhtasham Oblokulov, Aryan Siddiqui, Ofir Press, Ludwig Schmidt, Diyi Yang
Published: 2025-11-02
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.00839v2

Current benchmarks for coding evaluate language models (LMs) on concrete, well-specified tasks such as fixing specific bugs or writing targeted tests. However, human programmers do not spend all day incessantly addressing isolated tasks. Instead, real-world software development is grounded in the pursuit of high-level goals, like improving user retention or reducing costs. Evaluating whether LMs can also iteratively develop code to better accomplish open-ended objectives without any explicit guidance remains an open challenge. To address this, we introduce CodeClash, a benchmark where LMs compete in multi-round tournaments to build the best codebase for achieving a competitive objective. Each round proceeds in two phases: agents edit their code, then their codebases compete head-to-head in a code arena that determines winners based on objectives like score maximization, resource acquisition, or survival. Whether it's writing notes, scrutinizing documentation, analyzing competition logs, or creating test suites, models must decide for themselves how to improve their codebases both absolutely and against their opponents. We run 1680 tournaments (25,200 rounds total) to evaluate 8 LMs across 6 arenas. Our results reveal that while models exhibit diverse development styles, they share fundamental limitations in strategic reasoning. Models also struggle with long-term codebase maintenance, as repositories become progressively messy and redundant. These limitations are stark: top models lose every round against expert human programmers. We open-source CodeClash to advance the study of autonomous, goal-oriented code development.

---

### Parameter Interpolation Adversarial Training for Robust Image Classification

Authors: Xin Liu, Yichen Yang, Kun He, John E. Hopcroft
Published: 2025-11-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.00836v1

Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks. However, existing adversarial training methods show that the model robustness has apparent oscillations and overfitting issues in the training process, degrading the defense efficacy. To address these issues, we propose a novel framework called Parameter Interpolation Adversarial Training (PIAT). PIAT tunes the model parameters between each epoch by interpolating the parameters of the previous and current epochs. It makes the decision boundary of model change more moderate and alleviates the overfitting issue, helping the model converge better and achieving higher model robustness. In addition, we suggest using the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the relative magnitude of logits between clean and adversarial examples rather than the absolute magnitude. Extensive experiments conducted on several benchmark datasets demonstrate that our framework could prominently improve the robustness of both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs).

---

### Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials

Authors: Yifan Pu, Jixuan Ying, Qixiu Li, Tianzhu Ye, Dongchen Han, Xiaochen Wang, Ziyi Wang, Xinyu Shao, Gao Huang, Xiu Li
Published: 2025-11-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.00833v1

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending the bulk of computation on visually weak or redundant correlations. We introduce Visual-Contrast Attention (VCA), a drop-in replacement for MHSA that injects an explicit notion of discrimination while reducing the theoretical complexity from O(N N C) to O(N n C) with n << N. VCA first distils each head's dense query field into a handful of spatially pooled visual-contrast tokens, then splits them into a learnable positive and negative stream whose differential interaction highlights what truly separates one region from another. The module adds fewer than 0.3M parameters to a DeiT-Tiny backbone, requires no extra FLOPs, and is wholly architecture-agnostic. Empirically, VCA lifts DeiT-Tiny top-1 accuracy on ImageNet-1K from 72.2% to 75.6% (+3.4) and improves three strong hierarchical ViTs by up to 3.1%, while in class-conditional ImageNet generation it lowers FID-50K by 2.1 to 5.2 points across both diffusion (DiT) and flow (SiT) models. Extensive ablations confirm that (i) spatial pooling supplies low-variance global cues, (ii) dual positional embeddings are indispensable for contrastive reasoning, and (iii) combining the two in both stages yields the strongest synergy. VCA therefore offers a simple path towards faster and sharper Vision Transformers. The source code is available at https://github.com/LeapLabTHU/LinearDiff.

---

### Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack

Authors: Xin Liu, Aoyang Zhou, Aoyang Zhou
Published: 2025-11-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.00831v1

Visual-Language Pre-training (VLP) models have achieved significant performance across various downstream tasks. However, they remain vulnerable to adversarial examples. While prior efforts focus on improving the adversarial transferability of multimodal adversarial examples through cross-modal interactions, these approaches suffer from overfitting issues, due to a lack of input diversity by relying excessively on information from adversarial examples in one modality when crafting attacks in another. To address this issue, we draw inspiration from strategies in some adversarial training methods and propose a novel attack called Local Shuffle and Sample-based Attack (LSSA). LSSA randomly shuffles one of the local image blocks, thus expanding the original image-text pairs, generating adversarial images, and sampling around them. Then, it utilizes both the original and sampled images to generate the adversarial texts. Extensive experiments on multiple models and datasets demonstrate that LSSA significantly enhances the transferability of multimodal adversarial examples across diverse VLP models and downstream tasks. Moreover, LSSA outperforms other advanced attacks on Large Vision-Language Models.

---

### Towards Ultra-Low Latency: Binarized Neural Network Architectures for In-Vehicle Network Intrusion Detection

Authors: Huiyao Dong, Igor Kotenko
Published: 2025-11-02
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.00828v1

The Control Area Network (CAN) protocol is essential for in-vehicle communication, facilitating high-speed data exchange among Electronic Control Units (ECUs). However, its inherent design lacks robust security features, rendering vehicles susceptible to cyberattacks. While recent research has investigated machine learning and deep learning techniques to enhance network security, their practical applicability remains uncertain. This paper presents a lightweight intrusion detection technique based on Binarized Neural Networks (BNNs), which utilizes payload data, message IDs, and CAN message frequencies for effective intrusion detection. Additionally, we develop hybrid binary encoding techniques to integrate non-binary features, such as message IDs and frequencies. The proposed method, namely the BNN framework specifically optimized for in-vehicle intrusion detection combined with hybrid binary quantization techniques for non-payload attributes, demonstrates efficacy in both anomaly detection and multi-class network traffic classification. The system is well-suited for deployment on micro-controllers and Gateway ECUs, aligning with the real-time requirements of CAN bus safety applications.

---

### OMEGA: Optimized Multimodal Position Encoding Index Derivation with Global Adaptive Scaling for Vision-Language Models

Authors: Ruoxiang Huang, Xindian Ma, Rundong Kong, Zhen Yuan, Peng Zhang
Published: 2025-11-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00821v1

Vision-Language Models (VLMs) have demonstrated strong performance across various multimodal tasks, where position encoding plays a vital role in modeling both the sequential structure of textual information and the spatial structure of visual information. However, current VLMs commonly adopt modality-unified 1D or 2D positional indexing strategies, which treat textual and visual tokens uniformly without accounting for their distinct structural properties and sequential continuity for text and spatial coherence for vision. To address this limitation, we propose OMEGA, a novel position encoding framework that employs Modality-Specific Position Encoding (MSPE) to assign positional indices while preserving the inherent structures of each modality across separate coordinate dimensions. Additionally, to align the information density of multimodal data in the positional index space, OMEGA introduces Global Adaptive Encoding Step Scaling (GAESS), which adaptively adjusts the position encoding step size of visual tokens based on the embedding entropy of both modalities. Experimental results demonstrate that OMEGA consistently enhances VLM performance across diverse architectures and VQA benchmarks. On visual-intensive tasks, OMEGA achieves up to 3.43% improvement over baseline position encoding strategies on Qwen2.5-VL-3B, with consistent gains observed across larger models including Qwen2.5-VL-7B and LLaVA-v1.5-7B.

---

### Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies

Authors: Yuxuan Hu, Jianchao Tan, Jiaqi Zhang, Wen Zan, Pingwei Sun, Yifan Lu, Yerui Sun, Yuchen Xie, Xunliang Cai, Jing Zhang
Published: 2025-11-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.00819v1

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression, selective) attention across layers, rather than using fixed patterns, enables more effective propagation of long-range dependencies and substantially boosts performance on long-sequence tasks. Meanwhile, we further refine NSA's branches with Latent Attention that the sliding-window branch is enhanced with Multi-head Latent Attention (MLA) while compression and selective branches adopt Group-head Latent Attention (GLA). These changes reduce KV-cache memory by 50\% versus NSA while improving the model's common-sense reasoning and long-text understanding capabilities. Experiments on models from 340M to 1.3B parameters (trained on 15B and 100B tokens) show our method matches or exceeds full attention and native sparse attention in both common-sense reasoning and long-context understanding tasks.

---

### TA-LSDiff:Topology-Aware Diffusion Guided by a Level Set Energy for Pancreas Segmentation

Authors: Yue Gou, Fanghui Song, Yuming Xing, Shengzhu Shi, Zhichang Guo, Boying Wu
Published: 2025-11-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00815v1

Pancreas segmentation in medical image processing is a persistent challenge due to its small size, low contrast against adjacent tissues, and significant topological variations. Traditional level set methods drive boundary evolution using gradient flows, often ignoring pointwise topological effects. Conversely, deep learning-based segmentation networks extract rich semantic features but frequently sacrifice structural details. To bridge this gap, we propose a novel model named TA-LSDiff, which combined topology-aware diffusion probabilistic model and level set energy, achieving segmentation without explicit geometric evolution. This energy function guides implicit curve evolution by integrating the input image and deep features through four complementary terms. To further enhance boundary precision, we introduce a pixel-adaptive refinement module that locally modulates the energy function using affinity weighting from neighboring evidence. Ablation studies systematically quantify the contribution of each proposed component. Evaluations on four public pancreas datasets demonstrate that TA-LSDiff achieves state-of-the-art accuracy, outperforming existing methods. These results establish TA-LSDiff as a practical and accurate solution for pancreas segmentation.

---

### Real-Time Learning of Predictive Dynamic Obstacle Models for Robotic Motion Planning

Authors: Stella Kombo, Masih Haseli, Skylar X. Wei, Joel W. Burdick
Published: 2025-11-02
Categories: cs.RO, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2511.00814v2

Autonomous systems often must predict the motions of nearby agents from partial and noisy data. This paper asks and answers the question: "can we learn, in real-time, a nonlinear predictive model of another agent's motions?" Our online framework denoises and forecasts such dynamics using a modified sliding-window Hankel Dynamic Mode Decomposition (Hankel-DMD). Partial noisy measurements are embedded into a Hankel matrix, while an associated Page matrix enables singular-value hard thresholding (SVHT) to estimate the effective rank. A Cadzow projection enforces structured low-rank consistency, yielding a denoised trajectory and local noise variance estimates. From this representation, a time-varying Hankel-DMD lifted linear predictor is constructed for multi-step forecasts. The residual analysis provides variance-tracking signals that can support downstream estimators and risk-aware planning. We validate the approach in simulation under Gaussian and heavy-tailed noise, and experimentally on a dynamic crane testbed. Results show that the method achieves stable variance-aware denoising and short-horizon prediction suitable for integration into real-time control frameworks.

---

### LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons

Authors: Shashank Nag, Alan T. L. Bacellar, Zachary Susskind, Anshul Jha, Logan Liberty, Aishwarya Sivakumar, Eugene B. John, Krishnan Kailas, Priscila M. V. Lima, Neeraja J. Yadwadkar, Felipe M. G. Franca, Lizy K. John
Published: 2025-11-02
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.00812v1

Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on FPGAs -- a field that has seen a recent surge in demand. We recognize the benefits of recent works on logic and Look Up Table (LUT) based networks, such as LogicNets, NeuraLUT, DWN, among others, in offering models that simultaneously reduce both the memory and compute footprints. However, these models natively do not perform well on common vision tasks, such as CIFAR-10/100. In this work, we propose LL-ViT, a novel edge optimized vision transformer design that integrates layers of LUT neurons within the transformer architecture. Based on our characterization that reveals that a majority of model weights and computations are from the channel mixer (MLP layer), we design an alternate LUT-based channel mixer, and simultaneously develop an FPGA-based accelerator for LL-ViT. Contrary to some attempts to replace each multiplication with a table lookup, our architecture utilizes a neural learning approach which natively learns the LUT functions. This approach allows for reduced model sizes, and a computational and energy-efficient inference solution for vision transformer models. Evaluating on edge-suitable workloads, we achieve accuracies of 95.5% on CIFAR-10, 78.8% on CIFAR-100, and 60.9% on Tiny-ImageNet datasets, comparable to the baseline transformer. LL-ViT eliminates over 60% of the model weights and 50% of the multiplications in the model, and achieves 1.9x energy efficiency and 1.3x lower latency over an integer quantized ViT accelerator, while also offering superior throughput against prior works at a 10.9W power budget.

---

### Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games

Authors: Runyu Lu, Peng Zhang, Ruochuan Shi, Yuanheng Zhu, Dongbin Zhao, Yang Liu, Dong Wang, Cesare Alippi
Published: 2025-11-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00811v2

Equilibrium learning in adversarial games is an important topic widely examined in the fields of game theory and reinforcement learning (RL). Pursuit-evasion game (PEG), as an important class of real-world games from the fields of robotics and security, requires exponential time to be accurately solved. When the underlying graph structure varies, even the state-of-the-art RL methods require recomputation or at least fine-tuning, which can be time-consuming and impair real-time applicability. This paper proposes an Equilibrium Policy Generalization (EPG) framework to effectively learn a generalized policy with robust cross-graph zero-shot performance. In the context of PEGs, our framework is generally applicable to both pursuer and evader sides in both no-exit and multi-exit scenarios. These two generalizability properties, to our knowledge, are the first to appear in this domain. The core idea of the EPG framework is to train an RL policy across different graph structures against the equilibrium policy for each single graph. To construct an equilibrium oracle for single-graph policies, we present a dynamic programming (DP) algorithm that provably generates pure-strategy Nash equilibrium with near-optimal time complexity. To guarantee scalability with respect to pursuer number, we further extend DP and RL by designing a grouping mechanism and a sequence model for joint policy decomposition, respectively. Experimental results show that, using equilibrium guidance and a distance feature proposed for cross-graph PEG training, the EPG framework guarantees desirable zero-shot performance in various unseen real-world graphs. Besides, when trained under an equilibrium heuristic proposed for the graphs with exits, our generalized pursuer policy can even match the performance of the fine-tuned policies from the state-of-the-art PEG methods.

---

### GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding

Authors: Shijie Zhou, Viet Dac Lai, Hao Tan, Jihyung Kil, Wanrong Zhu, Changyou Chen, Ruiyi Zhang
Published: 2025-11-02
Categories: cs.CV, cs.AI, cs.CL, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2511.00810v4

Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal Large Language Model (MLLM) approaches typically formulate GUI grounding as a text-based coordinate generation task. However, directly generating precise coordinates from visual inputs is challenging and often data-intensive. A more intuitive strategy is to first identify instruction-relevant visual patches and then determine the exact click location within them. Motivated by recent observations that general MLLMs exhibit native grounding ability embedded in their attention maps, we propose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the intrinsic multimodal attention of MLLMs with patch-wise grounding signals. These signals are calculated adaptively for diverse user instructions by multi-head aggregation on simplified query-visual attention matrices. Besides, its coordinate-free manner can easily integrate a plug-and-play zoom-in stage. GUI-AIMA-3B was trained with only 509k samples (around 101k screenshots), demonstrating exceptional data efficiency and verifying that light training can trigger the native grounding capability of MLLMs. It achieves state-of-the-art performance among 3B models, attaining an average accuracy of 61.5% on ScreenSpot-Pro, 92.1% on ScreenSpot-v2, 68.1% on OSWorld-G, 79.1% on MMBench-GUI-L2, and 60.0% on UI-Vision. Project page: https://github.com/sjz5202/GUI-AIMA .

---

### Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?

Authors: Bowen Fang, Ruijian Zha, Xuan Di
Published: 2025-11-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.00808v1

Predicting public transit incident duration from unstructured text alerts is a critical but challenging task. Addressing the domain sparsity of transit operations with standard Supervised Fine-Tuning (SFT) is difficult, as the task involves noisy, continuous labels and lacks reliable expert demonstrations for reasoning. While Reinforcement Learning from Verifiable Rewards (RLVR) excels at tasks with binary correctness, like mathematics, its applicability to noisy, continuous forecasting is an open question. This work, to our knowledge, is the first to bridge the gap between RLVR LLM training with the critical, real-world forecasting challenges in public transit operations. We adapt RLVR to this task by introducing a tolerance-based, shaped reward function that grants partial credit within a continuous error margin, rather than demanding a single correct answer. We systematically evaluate this framework on a curated dataset of NYC MTA service alerts. Our findings show that general-purpose, instruction-tuned LLMs significantly outperform specialized math-reasoning models, which struggle with the ambiguous, real-world text. We empirically demonstrate that the binary reward is unstable and degrades performance, whereas our shaped reward design is critical and allows our model to dominate on the most challenging metrics. While classical regressors are superior at minimizing overall MAE or MSE, our RLVR approach achieved a 35\% relative improvement in 5-minute accuracy (Acc@5) over the strongest baseline. This demonstrates that RLVR can be successfully adapted to real-world, noisy forecasting, but requires a verifier design that reflects the continuous nature of the problem.

---

### Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems

Authors: Guangxi Wan, Peng Zeng, Xiaoting Dong, Chunhe Song, Shijie Cui, Dong Li, Qingwei Dong, Yiyang Liu, Hongfei Bai
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00806v1

Cyber-physical systems (CPS) require the joint optimization of discrete cyber actions and continuous physical parameters under stringent safety logic constraints. However, existing hierarchical approaches often compromise global optimality, whereas reinforcement learning (RL) in hybrid action spaces often relies on brittle reward penalties, masking, or shielding and struggles to guarantee constraint satisfaction. We present logic-informed reinforcement learning (LIRL), which equips standard policy-gradient algorithms with projection that maps a low-dimensional latent action onto the admissible hybrid manifold defined on-the-fly by first-order logic. This guarantees feasibility of every exploratory step without penalty tuning. Experimental evaluations have been conducted across multiple scenarios, including industrial manufacturing, electric vehicle charging stations, and traffic signal control, in all of which the proposed method outperforms existing hierarchical optimization approaches. Taking a robotic reducer assembly system in industrial manufacturing as an example, LIRL achieves a 36.47\% to 44.33\% reduction at most in the combined makespan-energy objective compared to conventional industrial hierarchical scheduling methods. Meanwhile, it consistently maintains zero constraint violations and significantly surpasses state-of-the-art hybrid-action reinforcement learning baselines. Thanks to its declarative logic-based constraint formulation, the framework can be seamlessly transferred to other domains such as smart transportation and smart grid, thereby paving the way for safe and real-time optimization in large-scale CPS.

---

### EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment

Authors: Abhiram Kusumba, Maitreya Patel, Kyle Min, Changhoon Kim, Chitta Baral, Yezhou Yang
Published: 2025-11-02
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.00804v3

Erasing harmful or proprietary concepts from powerful text to image generators is an emerging safety requirement, yet current "concept erasure" techniques either collapse image quality, rely on brittle adversarial losses, or demand prohibitive retraining cycles. We trace these limitations to a myopic view of the denoising trajectories that govern diffusion based generation. We introduce EraseFlow, the first framework that casts concept unlearning as exploration in the space of denoising paths and optimizes it with GFlowNets equipped with the trajectory balance objective. By sampling entire trajectories rather than single end states, EraseFlow learns a stochastic policy that steers generation away from target concepts while preserving the model's prior. EraseFlow eliminates the need for carefully crafted reward models and by doing this, it generalizes effectively to unseen concepts and avoids hackable rewards while improving the performance. Extensive empirical results demonstrate that EraseFlow outperforms existing baselines and achieves an optimal trade off between performance and prior preservation.

---

### GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents

Authors: Jie JW Wu, Ayanda Patrick Herlihy, Ahmad Saleem Mirza, Ali Afoud, Fatemeh Fard
Published: 2025-11-02
Categories: cs.SE, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.00802v2

With data-driven development now widely adopted, online A/B testing is an established method for measuring the effects of new technologies. However, deploying online experiments demands resources for design, implementation, and deployment, and may negatively impact users (e.g., unsafe or unethical outcomes) while requiring weeks of data collection. To address this, the growing research area of off-policy evaluation (OPE), or offline A/B testing, assesses new technologies offline using previously collected logged data. OPE is also a fundamental problem in reinforcement learning and is important where online testing is expensive or risky, such as healthcare, recommender systems, education, and robotics. Despite advances in code-generation large language models (LLMs) and agentic workflows, little is known about whether and how LLMs and LLM-based agents can automatically optimize OPE implementations. We propose GrowthHacker, a benchmark that evaluates baseline LLMs and LLM-based agents on large-scale public datasets. GrowthHacker autonomously and iteratively modifies code, runs OPE, and uses the metrics to guide subsequent optimization. We evaluate methods on Open Bandit Pipeline (OBP) and Scope-RL, and develop a two_agent framework that addresses limitations of existing frameworks while reducing complexity. Across both libraries, two_agent shows the highest reliability (98.1%-100% success rate) and positive-outcome rate (78%), with a median improvement of 4.4% among positive outcomes; CrewAI achieves the highest average improvement (37.9%) and is the only framework with zero extreme-value failures. AutoGen and Default each reach 65% positive-outcome rates. These results establish the feasibility of using LLM-based agents as automated "growth hackers" to continuously improve OPE systems, with implications for scaling data-driven decision-making where manual optimization is expensive.

---

### Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories

Authors: Zhihui Chen, Qingyuan Lei, Kai He, Yanrui Du, Mengling Feng
Published: 2025-11-02
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2511.00801v4

Text-guided medical image editing must satisfy the requested pathology while preserving anatomy, modality-specific appearance, and clinical plausibility. However, existing datasets largely supervise editors with final accepted edits and discard the failed attempts produced during generation. We argue that these failures provide essential supervision for quality control: they specify what should be rejected, why an edit is medically or visually invalid, and how the instruction should be revised. We present Med-Banana, a trajectory-supervised framework for quality-controlled medical image editing. We introduce Med-Banana-80K, a large-scale resource of success-and-failure editing trajectories with candidate images, verification outcomes, rejection reasons, and prompt refinements. Building on it, Med-Banana jointly trains an editor, verifier, and refiner, enabling edit--verify--refine inference from accepted and rejected attempts. Experiments across MLLM judges, blind expert assessment, source-preservation and real--synthetic separability probes demonstrate consistent improvements over open medical image editors. Code and data are publicly available.

---

### Attention Saturation and Gradient Suppression at Inflection Layers: Diagnosing and Mitigating Bottlenecks in Transformer Adaptation

Authors: Wang Zixian
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00797v1

Pre-trained Transformers often exhibit over-confidence in source patterns and difficulty in forming new target-domain patterns during fine-tuning. We formalize the mechanism of output saturation leading to gradient suppression through standard cross-entropy and softmax analysis, showing that gradient suppression at inflection layers confines adaptation to high-level recombination of existing features while preventing low-level reconstruction. We introduce a set of layer-wise diagnostic metrics -- attention entropy (saturation proxy), activation gradient norm, parameter gradient norm, and Delta-CKA under a shared PCA basis -- to identify inflection layers characterized by both low attention entropy and steep gradient decay. Building on these findings, we propose a diagnose-first, inject-light fine-tuning strategy: selectively inserting LoRA adapters at inflection layers to restore suppressed backward signals with minimal parameter overhead. Experiments on BERT-base transfer from SST-2 to Rotten Tomatoes under under-trained and over-trained source regimes reveal that over-trained initialization benefits from inflection-layer LoRA injection, while under-trained initialization suffers performance degradation. When base features are strong, unblocking inflection layers facilitates high-level compositional adaptation; when base features are weak, full-pathway unblocking is required for low-level reconstruction, as supported by joint analysis of layer-wise activation gradients and Delta-CKA dynamics.

---

### AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs

Authors: Ran Yan, Youhe Jiang, Tianyuan Wu, Jiaxuan Gao, Zhiyu Mei, Wei Fu, Haohui Mai, Wei Wang, Yi Wu, Binhang Yuan
Published: 2025-11-02
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2511.00796v1

Maximizing training throughput and cost-efficiency of RL for LLMs is essential to democratize this advanced technique. One promising but challenging approach is to deploy such a computational workflow over heterogeneous GPUs. Unlike conventional large-scale LLM pretraining, RL training generally decomposes into three coupled stages, i.e., rollout generation, reward computation, and policy/value updates, which exhibit markedly different compute intensities, memory footprints, and communication patterns. Recent research shows that fully asynchronous RL training can disaggregate these stages across disjoint hardware pools without sacrificing training stability, creating a great opportunity for real-world heterogeneous deployment. To this end, we present AReaL-Hex, a heterogeneity-aware asynchronous RL training system that effectively schedules how to execute rollout generation and policy model training over heterogeneous GPUs while enforcing data staleness bounds. Concretely, we use a two-phase scheduler: (i) a constrained search with MILP to select per-stage parallelization strategies and workload assignments given a resource budget, and (ii) a graph-partitioning step that allocates heterogeneous GPUs and interconnects to maximize end-to-end throughput. Built atop a fully asynchronous RL architecture, AReaL-Hex maps HBM-I/O-bound generation and compute-bound optimization to more cost-efficient resources and balances their producer-consumer interactions to avoid both idleness and stale rollout trajectories. On the mathematical reasoning task with various model scales (1.5B, 7B, and 14B), compared to homogeneous deployments of state-of-the-art asynchronous RL systems: (i) When maintaining the same total budgets, AReaL-Hex delivers up to 1.50x higher training throughput; (ii) When achieving the same training throughput, AReaL-Hex results in up to 1.46x reduction in training cost.

---

### FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data

Authors: Viswa Chaitanya Marella, Suhasnadh Reddy Veluru, Sai Teja Erukude
Published: 2025-11-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.00795v1

Federated Learning (FL) allows multiple institutions to cooperatively train machine learning models while retaining sensitive data at the source, which has great utility in privacy-sensitive environments. However, FL systems remain vulnerable to membership-inference attacks and data heterogeneity. This paper presents FedOnco-Bench, a reproducible benchmark for privacy-aware FL using synthetic oncologic CT scans with tumor annotations. It evaluates segmentation performance and privacy leakage across FL methods: FedAvg, FedProx, FedBN, and FedAvg with DP-SGD. Results show a distinct trade-off between privacy and utility: FedAvg is high performance (Dice around 0.85) with more privacy leakage (attack AUC about 0.72), while DP-SGD provides a higher level of privacy (AUC around 0.25) at the cost of accuracy (Dice about 0.79). FedProx and FedBN offer balanced performance under heterogeneous data, especially with non-identical distributed client data. FedOnco-Bench serves as a standardized, open-source platform for benchmarking and developing privacy-preserving FL methods for medical image segmentation.

---

### Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration

Authors: Yan Sun, Jia Guo, Stanley Kok, Zihao Wang, Zujie Wen, Zhiqiang Zhang
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00794v3

Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning ability of large language models, yet training remains costly because many rollouts contribute little to optimization, considering the amount of computation required. This study investigates how simply leveraging intrinsic data properties, almost free benefit during training, can improve data efficiency for RLVR. We propose PREPO with two complementary components. First, we adopt prompt perplexity as an indicator of model adaptability in learning, enabling the model to progress from well-understood contexts to more challenging ones. Second, we amplify the discrepancy among the rollouts by differentiating their relative entropy, and prioritize sequences that exhibit a higher degree of exploration. Together, these mechanisms reduce rollout demand while preserving competitive performance. On the Qwen and Llama models, PREPO achieves effective results on mathematical reasoning benchmarks with up to 3 times fewer rollouts than the baselines. Beyond empirical gains, we provide theoretical and in-depth analyses explaining the underlying rationale of our method to improve the data efficiency of RLVR.

---

### Fast PINN Eigensolvers via Biconvex Reformulation

Authors: Akshay Sai Banderwaar, Abhishek Gupta
Published: 2025-11-02
Categories: cs.LG, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2511.00792v1

Eigenvalue problems have a distinctive forward-inverse structure and are fundamental to characterizing a system's thermal response, stability, and natural modes. Physics-Informed Neural Networks (PINNs) offer a mesh-free alternative for solving such problems but are often orders of magnitude slower than classical numerical schemes. In this paper, we introduce a reformulated PINN approach that casts the search for eigenpairs as a biconvex optimization problem, enabling fast and provably convergent alternating convex search (ACS) over eigenvalues and eigenfunctions using analytically optimal updates. Numerical experiments show that PINN-ACS attains high accuracy with convergence speeds up to 500$\times$ faster than gradient-based PINN training. We release our codes at https://github.com/NeurIPS-ML4PS-2025/PINN_ACS_CODES.

---

### Class-agnostic 3D Segmentation by Granularity-Consistent Automatic 2D Mask Tracking

Authors: Juan Wang, Yasutomo Kawanishi, Tomo Miyazaki, Zhijie Wang, Shinichiro Omachi
Published: 2025-11-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.00785v1

3D instance segmentation is an important task for real-world applications. To avoid costly manual annotations, existing methods have explored generating pseudo labels by transferring 2D masks from foundation models to 3D. However, this approach is often suboptimal since the video frames are processed independently. This causes inconsistent segmentation granularity and conflicting 3D pseudo labels, which degrades the accuracy of final segmentation. To address this, we introduce a Granularity-Consistent automatic 2D Mask Tracking approach that maintains temporal correspondences across frames, eliminating conflicting pseudo labels. Combined with a three-stage curriculum learning framework, our approach progressively trains from fragmented single-view data to unified multi-view annotations, ultimately globally coherent full-scene supervision. This structured learning pipeline enables the model to progressively expose to pseudo-labels of increasing consistency. Thus, we can robustly distill a consistent 3D representation from initially fragmented and contradictory 2D priors. Experimental results demonstrated that our method effectively generated consistent and accurate 3D segmentations. Furthermore, the proposed method achieved state-of-the-art results on standard benchmarks and open-vocabulary ability.

---

### Count-Based Approaches Remain Strong: A Benchmark Against Transformer and LLM Pipelines on Structured EHR

Authors: Jifan Gao, Michael Rosenthal, Brian Wolpin, Simona Cristea
Published: 2025-11-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.00782v1

Structured electronic health records (EHR) are essential for clinical prediction. While count-based learners continue to perform strongly on such data, no benchmarking has directly compared them against more recent mixture-of-agents LLM pipelines, which have been reported to outperform single LLMs in various NLP tasks. In this study, we evaluated three categories of methodologies for EHR prediction using the EHRSHOT dataset: count-based models built from ontology roll-ups with two time bins, based on LightGBM and the tabular foundation model TabPFN; a pretrained sequential transformer (CLMBR); and a mixture-of-agents pipeline that converts tabular histories to natural-language summaries followed by a text classifier. We assessed eight outcomes using the EHRSHOT dataset. Across the eight evaluation tasks, head-to-head wins were largely split between the count-based and the mixture-of-agents methods. Given their simplicity and interpretability, count-based models remain a strong candidate for structured EHR benchmarking. The source code is available at: https://github.com/cristea-lab/Structured_EHR_Benchmark.

---

### A Hybrid YOLOv5-SSD IoT-Based Animal Detection System for Durian Plantation Protection

Authors: Anis Suttan Shahrir, Zakiah Ayop, Syarulnaziah Anawar, Norulzahrah Mohd Zainudin
Published: 2025-11-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00777v1

Durian plantation suffers from animal intrusions that cause crop damage and financial loss. The traditional farming practices prove ineffective due to the unavailability of monitoring without human intervention. The fast growth of machine learning and Internet of Things (IoT) technology has led to new ways to detect animals. However, current systems are limited by dependence on single object detection algorithms, less accessible notification platforms, and limited deterrent mechanisms. This research suggests an IoT-enabled animal detection system for durian crops. The system integrates YOLOv5 and SSD object detection algorithms to improve detection accuracy. The system provides real-time monitoring, with detected intrusions automatically reported to farmers via Telegram notifications for rapid response. An automated sound mechanism (e.g., tiger roar) is triggered once the animal is detected. The YOLO+SSD model achieved accuracy rates of elephant, boar, and monkey at 90%, 85% and 70%, respectively. The system shows the highest accuracy in daytime and decreases at night, regardless of whether the image is still or a video. Overall, this study contributes a comprehensive and practical framework that combines detection, notification, and deterrence, paving the way for future innovations in automated farming solutions.

---

### Quantifying truth and authenticity in AI-assisted candidate evaluation: A multi-domain pilot analysis

Authors: Eldred Lee, Nicholas Worley, Koshu Takatsuji
Published: 2025-11-02
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.00774v2

This paper presents a retrospective analysis of anonymized candidate-evaluation data collected during pilot hiring campaigns conducted through AlteraSF, an AI-native resume-verification platform. The system evaluates resume claims, generates context-sensitive verification questions, and measures performance along quantitative axes of factual validity and job fit, complemented by qualitative integrity detection. Across six job families and 1,700 applications, the platform achieved a 90-95% reduction in screening time and detected measurable linguistic patterns consistent with AI-assisted or copied responses. The analysis demonstrates that candidate truthfulness can be assessed not only through factual accuracy but also through patterns of linguistic authenticity. The results suggest that a multi-dimensional verification framework can improve both hiring efficiency and trust in AI-mediated evaluation systems.

---