# Research Papers — 2025-11 · bundle page 50 of 197 > Full-text markdown of papers #2451–2500 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/50 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/49.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/51.md) ### Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion Authors: Keyang Lu, Sifan Zhou, Hongbin Xu, Gang Xu, Zhifei Yang, Yikai Wang, Zhen Xiao, Jieyi Long, Ming Li Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18734v3 Realistic 3D city generation is fundamental to a wide range of applications, including virtual reality and digital twins. However, most existing methods rely on training a single diffusion model, which limits their ability to generate personalized and boundless city-scale scenes. In this paper, we present Yo'City, a novel agentic framework that enables user-customized and infinitely expandable 3D city generation by leveraging the reasoning and compositional capabilities of off-the-shelf large models. Specifically, Yo'City first conceptualizes the city through a top-down planning strategy that defines a hierarchical "City-District-Grid" structure. The Global Planner determines the overall layout and potential functional districts, while the Local Designer further refines each district with detailed grid-level descriptions. Subsequently, the grid-level 3D generation is achieved through a "produce-refine-evaluate" isometric image synthesis loop, followed by image-to-3D generation. To simulate continuous city evolution, Yo'City further introduces a user-interactive, relationship-guided expansion mechanism, which performs scene graph-based distance- and semantics-aware layout optimization, ensuring spatially coherent city growth. To comprehensively evaluate our method, we construct a diverse benchmark dataset and design six multi-dimensional metrics that assess generation quality from the perspectives of semantics, geometry, texture, and layout. Extensive experiments demonstrate that Yo'City consistently outperforms existing state-of-the-art methods across all evaluation aspects. --- ### OceanForecastBench: A Benchmark Dataset for Data-Driven Global Ocean Forecasting Authors: Haoming Jia, Yi Han, Xiang Wang, Huizan Wang, Wei Wu, Jianming Zheng, Peikun Xiao Published: 2025-11-24 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.18732v2 Global ocean forecasting aims to predict key ocean variables such as temperature, salinity, and currents, which is essential for understanding and describing oceanic phenomena. In recent years, data-driven deep learning-based ocean forecast models, such as XiHe, WenHai, LangYa and AI-GOMS, have demonstrated significant potential in capturing complex ocean dynamics and improving forecasting efficiency. Despite these advancements, the absence of open-source, standardized benchmarks has led to inconsistent data usage and evaluation methods. This gap hinders efficient model development, impedes fair performance comparison, and constrains interdisciplinary collaboration. To address this challenge, we propose OceanForecastBench, a benchmark offering three core contributions: (1) A high-quality global ocean reanalysis data over 28 years for model training, including 4 ocean variables across 23 depth levels and 4 sea surface variables. (2) A high-reliability satellite and in-situ observations for model evaluation, covering approximately 100 million locations in the global ocean. (3) An evaluation pipeline and a comprehensive benchmark with 6 typical baseline models, leveraging observations to evaluate model performance from multiple perspectives. OceanForecastBench represents the most comprehensive benchmarking framework currently available for data-driven ocean forecasting, offering an open-source platform for model development, evaluation, and comparison. The dataset and code are publicly available at: https://github.com/Ocean-Intelligent-Forecasting/OceanForecastBench. --- ### Large-Scale In-Game Outcome Forecasting for Match, Team and Players in Football using an Axial Transformer Neural Network Authors: Michael Horton, Patrick Lucey Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18730v1 Football (soccer) is a sport that is characterised by complex game play, where players perform a variety of actions, such as passes, shots, tackles, fouls, in order to score goals, and ultimately win matches. Accurately forecasting the total number of each action that each player will complete during a match is desirable for a variety of applications, including tactical decision-making, sports betting, and for television broadcast commentary and analysis. Such predictions must consider the game state, the ability and skill of the players in both teams, the interactions between the players, and the temporal dynamics of the game as it develops. In this paper, we present a transformer-based neural network that jointly and recurrently predicts the expected totals for thirteen individual actions at multiple time-steps during the match, and where predictions are made for each individual player, each team and at the game-level. The neural network is based on an \emph{axial transformer} that efficiently captures the temporal dynamics as the game progresses, and the interactions between the players at each time-step. We present a novel axial transformer design that we show is equivalent to a regular sequential transformer, and the design performs well experimentally. We show empirically that the model can make consistent and reliable predictions, and efficiently makes $\sim$75,000 live predictions at low latency for each game. --- ### GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving Authors: Lin Liu, Caiyan Jia, Guanyi Yu, Ziying Song, JunQiao Li, Feiyang Jia, Peiliang Wu, Xiaoshuai Hao, Yadan Luo Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18729v3 Driving planning is a critical component of end-to-end (E2E) autonomous driving. However, prevailing Imitative E2E Planners often suffer from multimodal trajectory mode collapse, failing to produce diverse trajectory proposals. Meanwhile, Generative E2E Planners struggle to incorporate crucial safety and physical constraints directly into the generative process, necessitating an additional optimization stage to refine their outputs. In this paper, we propose \textit{\textbf{GuideFlow}}, a novel planning framework that leverages Constrained Flow Matching. Concretely, \textit{\textbf{GuideFlow}} explicitly models the flow matching process, which inherently mitigates mode collapse and allows for flexible guidance from various conditioning signals. Our core contribution lies in directly enforcing explicit constraints within the flow matching generation process, rather than relying on implicit constraint encoding. Crucially, \textit{\textbf{GuideFlow}} unifies the training of the flow matching with the Energy-Based Model (EBM) to enhance the model's autonomous optimization capability to robustly satisfy physical constraints. Secondly, \textit{\textbf{GuideFlow}} parameterizes driving aggressiveness as a control signal during generation, enabling precise manipulation of trajectory style. Extensive evaluations on major driving benchmarks (Bench2Drive, NuScenes, NavSim and ADV-NuScenes) validate the effectiveness of \textit{\textbf{GuideFlow}}. Notably, on the NavSim test hard split (Navhard), \textit{\textbf{GuideFlow}} achieved SOTA with an EPDMS score of 43.0. The code will be in https://github.com/liulin815/GuideFlow. --- ### Reinforcement Learning for Self-Healing Material Systems Authors: Maitreyi Chatterjee, Devansh Agarwal, Biplab Chatterjee Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18728v1 The transition to autonomous material systems necessitates adaptive control methodologies to maximize structural longevity. This study frames the self-healing process as a Reinforcement Learning (RL) problem within a Markov Decision Process (MDP), enabling agents to autonomously derive optimal policies that efficiently balance structural integrity maintenance against finite resource consumption. A comparative evaluation of discrete-action (Q-learning, DQN) and continuous-action (TD3) agents in a stochastic simulation environment revealed that RL controllers significantly outperform heuristic baselines, achieving near-complete material recovery. Crucially, the TD3 agent utilizing continuous dosage control demonstrated superior convergence speed and stability, underscoring the necessity of fine-grained, proportional actuation in dynamic self-healing applications. --- ### LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs Authors: Devansh Agarwal, Maitreyi Chatterjee, Biplab Chatterjee Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18727v2 Aircraft maintenance logs hold valuable safety data but remain underused due to their unstructured text format. This paper introduces LogSyn, a framework that uses Large Language Models (LLMs) to convert these logs into structured, machine-readable data. Using few-shot in-context learning on 6,169 records, LogSyn performs Controlled Abstraction Generation (CAG) to summarize problem-resolution narratives and classify events within a detailed hierarchical ontology. The framework identifies key failure patterns, offering a scalable method for semantic structuring and actionable insight extraction from maintenance logs. This work provides a practical path to improve maintenance workflows and predictive analytics in aviation and related industries. --- ### Neural B-Frame Coding: Tackling Domain Shift Issues with Lightweight Online Motion Resolution Adaptation Authors: Sang NguyenQuang, Xiem HoangVan, Wen-Hsiao Peng Published: 2025-11-24 Categories: eess.IV, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2511.18724v1 Learned B-frame codecs with hierarchical temporal prediction often encounter the domain-shift issue due to mismatches between the Group-of-Pictures (GOP) sizes for training and testing, leading to inaccurate motion estimates, particularly for large motion. A common solution is to turn large motion into small motion by downsampling video frames during motion estimation. However, determining the optimal downsampling factor typically requires costly rate-distortion optimization. This work introduces lightweight classifiers to predict downsampling factors. These classifiers leverage simple state signals from current and reference frames to balance rate-distortion performance with computational cost. Three variants are proposed: (1) a binary classifier (Bi-Class) trained with Focal Loss to choose between high and low resolutions, (2) a multi-class classifier (Mu-Class) trained with novel soft labels based on rate-distortion costs, and (3) a co-class approach (Co-Class) that combines the predictive capability of the multi-class classifier with the selective search of the binary classifier. All classifier methods can work seamlessly with existing B-frame codecs without requiring codec retraining. Experimental results show that they achieve coding performance comparable to exhaustive search methods while significantly reducing computational complexity. The code is available at: https://github.com/NYCU-MAPL/Fast-OMRA.git. --- ### N2N: A Parallel Framework for Large-Scale MILP under Distributed Memory Authors: Longfei Wang, Junyan Liu, Fan Zhang, Jiangwen Wei, Yuanhua Tang, Jie Sun, Xiaodong Luo Published: 2025-11-24 Categories: cs.AI, cs.DC, math.OC arXiv: https://arxiv.org/abs/2511.18723v4 Parallelization has emerged as a promising approach for accelerating MILP solving. However, the complexity of the branch-and-bound (B&B) framework and the numerous effective algorithm components in MILP solvers make it difficult to parallelize. In this study, a scalable parallel framework, N2N (a node-to-node framework that maps the B&B nodes to distributed computing nodes), was proposed to solve large-scale problems in a distributed memory computing environment. Both deterministic and nondeterministic modes are supported, and the framework is designed to be easily integrated with existing solvers. Regarding the deterministic mode, a novel sliding-window-based algorithm was designed and implemented to ensure that tasks are generated and solved in a deterministic order. Moreover, several advanced techniques, such as the utilization of CP search and general primal heuristics, have been developed to fully utilize distributed computing resources and capabilities of base solvers. Adaptive solving and data communication optimization were also investigated. A popular open-source MILP solver, SCIP, was integrated into N2N as the base solver, yielding N2N-SCIP. Extensive computational experiments were conducted to evaluate the performance of N2N-SCIP compared to ParaSCIP, which is a state-of-the-art distributed parallel MILP solver under the UG framework. The nondeterministic N2N-SCIP achieves speedups of 22.52 and 12.71 with 1,000 MPI processes on the Kunpeng and x86 computing clusters, which is 1.98 and 2.08 times faster than ParaSCIP, respectively. In the deterministic mode, N2N-SCIP also shows significant performance improvements over ParaSCIP across different process numbers and computing clusters. To validate the generality of N2N, HiGHS, another open-source solver, was integrated into N2N. The related results are analyzed, and the requirements of N2N on base solvers are also concluded. --- ### Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM Authors: Adarsh Kumarappan, Ayushi Mehrotra Published: 2025-11-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.18721v4 The SmoothLLM defense provides a certification guarantee against jailbreaking attacks, but it relies on a strict "k-unstable" assumption that rarely holds in practice. This strong assumption can limit the trustworthiness of the provided safety certificate. In this work, we address this limitation by introducing a more realistic probabilistic framework, "(k, $\varepsilon$)-unstable," to certify defenses against diverse jailbreaking attacks, from gradient-based (GCG) to semantic (PAIR). We derive a new, data-informed lower bound on SmoothLLM's defense probability by incorporating empirical models of attack success, providing a more trustworthy and practical safety certificate. By introducing the notion of (k, $\varepsilon$)-unstable, our framework provides practitioners with actionable safety guarantees, enabling them to set certification thresholds that better reflect the real-world behavior of LLMs. Ultimately, this work contributes a practical and theoretically-grounded mechanism to make LLMs more resistant to the exploitation of their safety alignments, a critical challenge in secure AI deployment. --- ### Seeing What Matters: Visual Preference Policy Optimization for Visual Generation Authors: Ziqi Ni, Yuanzhi Liang, Rui Li, Yi Zhou, Haibin Huang, Chi Zhang, Xuelong Li Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18719v4 Reinforcement learning (RL) has become a powerful tool for post-training visual generative models, with Group Relative Policy Optimization (GRPO) increasingly used to align generators with human preferences. However, existing GRPO pipelines rely on a single scalar reward per sample, treating each image or video as a holistic entity and ignoring the rich spatial and temporal structure of visual content. This coarse supervision hinders the correction of localized artifacts and the modeling of fine-grained perceptual cues. We introduce Visual Preference Policy Optimization (ViPO), a GRPO variant that lifts scalar feedback into structured, pixel-level advantages. ViPO employs a Perceptual Structuring Module that uses pretrained vision backbones to construct spatially and temporally aware advantage maps, redistributing optimization pressure toward perceptually important regions while preserving the stability of standard GRPO. Across both image and video benchmarks, ViPO consistently outperforms vanilla GRPO, improving in-domain alignment with human-preference rewards and enhancing generalization on out-of-domain evaluations. The method is architecture-agnostic, lightweight, and fully compatible with existing GRPO training pipelines, providing a more expressive and informative learning signal for visual generation. --- ### AIRHILT: A Human-in-the-Loop Testbed for Multimodal Conflict Detection in Aviation Authors: Omar Garib, Jayaprakash D. Kambhampaty, Olivia J. Pinon Fischer, Dimitri N. Mavris Published: 2025-11-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.18718v1 We introduce AIRHILT (Aviation Integrated Reasoning, Human-in-the-Loop Testbed), a modular and lightweight simulation environment designed to evaluate multimodal pilot and air traffic control (ATC) assistance systems for aviation conflict detection. Built on the open-source Godot engine, AIRHILT synchronizes pilot and ATC radio communications, visual scene understanding from camera streams, and ADS-B surveillance data within a unified, scalable platform. The environment supports pilot- and controller-in-the-loop interactions, providing a comprehensive scenario suite covering both terminal area and en route operational conflicts, including communication errors and procedural mistakes. AIRHILT offers standardized JSON-based interfaces that enable researchers to easily integrate, swap, and evaluate automatic speech recognition (ASR), visual detection, decision-making, and text-to-speech (TTS) models. We demonstrate AIRHILT through a reference pipeline incorporating fine-tuned Whisper ASR, YOLO-based visual detection, ADS-B-based conflict logic, and GPT-OSS-20B structured reasoning, and present preliminary results from representative runway-overlap scenarios, where the assistant achieves an average time-to-first-warning of approximately 7.7 s, with average ASR and vision latencies of approximately 5.9 s and 0.4 s, respectively. The AIRHILT environment and scenario suite are openly available, supporting reproducible research on multimodal situational awareness and conflict detection in aviation; code and scenarios are available at https://github.com/ogarib3/airhilt. --- ### When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential Recommendation Authors: Jin Chai, Xiaoxiao Ma, Jian Yang, Jia Wu Published: 2025-11-24 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2511.18717v1 Sequential recommendation models user preferences to predict the next target item. Most existing work is passive, where the system responds only when users open the application, missing chances after closure. We investigate active recommendation, which predicts the next interaction time and actively delivers items. Two challenges: accurately estimating the Time of Interest (ToI) and generating Item of Interest (IoI) conditioned on the predicted ToI. We propose PASRec, a diffusion-based framework that aligns ToI and IoI via a joint objective. Experiments on five benchmarks show superiority over eight state-of-the-art baselines under leave-one-out and temporal splits. --- ### GRIT-LP: Graph Transformer with Long-Range Skip Connection and Partitioned Spatial Graphs for Accurate Ice Layer Thickness Prediction Authors: Zesheng Liu, Maryam Rahnemoonfar Published: 2025-11-24 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.18716v1 Graph transformers have demonstrated remarkable capability on complex spatio-temporal tasks, yet their depth is often limited by oversmoothing and weak long-range dependency modeling. To address these challenges, we introduce GRIT-LP, a graph transformer explicitly designed for polar ice-layer thickness estimation from polar radar imagery. Accurately estimating ice layer thickness is critical for understanding snow accumulation, reconstructing past climate patterns and reducing uncertainties in projections of future ice sheet evolution and sea level rise. GRIT-LP combines an inductive geometric graph learning framework with self-attention mechanism, and introduces two major innovations that jointly address challenges in modeling the spatio-temporal patterns of ice layers: a partitioned spatial graph construction strategy that forms overlapping, fully connected local neighborhoods to preserve spatial coherence and suppress noise from irrelevant long-range links, and a long-range skip connection mechanism within the transformer that improves information flow and mitigates oversmoothing in deeper attention layers. We conducted extensive experiments, demonstrating that GRIT-LP outperforms current state-of-the-art methods with a 24.92\% improvement in root mean squared error. These results highlight the effectiveness of graph transformers in modeling spatiotemporal patterns by capturing both localized structural features and long-range dependencies across internal ice layers, and demonstrate their potential to advance data-driven understanding of cryospheric processes. --- ### HuggingR$^{4}$: A Progressive Reasoning Framework for Discovering Optimal Model Companions Authors: Shaoyin Ma, Chenggong Hu, Huiqiong Wang, Li Sun, Mingli Song, Jie Song Published: 2025-11-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.18715v2 Building effective LLM agents increasingly requires selecting appropriate AI models as tools from large open repositories (e.g., HuggingFace with > 2M models) based on natural language requests. Unlike invoking a fixed set of API tools, repository-scale model selection must handle massive, evolving candidates with incomplete metadata. Existing approaches incorporate full model descriptions into prompts, resulting in prompt bloat, excessive token costs, and limited scalability. To address these issues, we propose HuggingR$^4$, the first framework to recast model selection as an iterative reasoning process rather than one-shot retrieval. By synergistically integrating Reasoning, Retrieval, Refinement, and Reflection, HuggingR$^4$ progressively decomposes user intent, retrieves candidates through multi-round deliberation, refines selections via fine-grained analysis, and validates results through reflection. To facilitate rigorous evaluation, we introduce a large-scale benchmark comprising 14,399 diverse user requests across 37 task categories. Experiments demonstrate that HuggingR$^4$ achieves 92.03% workability and 82.46% reasonability-outperforming current state-of-the-art baselines by 26.51% and 33.25%, respectively, while reducing token consumption by $6.9 \times$. --- ### MAGMA-Edu: Multi-Agent Generative Multimodal Framework for Text-Diagram Educational Question Generation Authors: Zhenyu Wu, Jian Li, Hua Huang Published: 2025-11-24 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2511.18714v1 Educational illustrations play a central role in communicating abstract concepts, yet current multimodal large language models (MLLMs) remain limited in producing pedagogically coherent and semantically consistent educational visuals. We introduce MAGMA-Edu, a self-reflective multi-agent framework that unifies textual reasoning and diagrammatic synthesis for structured educational problem generation. Unlike existing methods that treat text and image generation independently, MAGMA-Edu employs a two-stage co-evolutionary pipeline: (1) a generation-verification-reflection loop that iteratively refines question statements and solutions for mathematical accuracy, and (2) a code-based intermediate representation that enforces geometric fidelity and semantic alignment during image rendering. Both stages are guided by internal self-reflection modules that evaluate and revise outputs until domain-specific pedagogical constraints are met. Extensive experiments on multimodal educational benchmarks demonstrate the superiority of MAGMA-Edu over state-of-the-art MLLMs. Compared to GPT-4o, MAGMA-Edu improves the average textual metric from 57.01 to 92.31 (+35.3 pp) and boosts image-text consistency (ITC) from 13.20 to 85.24 (+72 pp). Across all model backbones, MAGMA-Edu achieves the highest scores (Avg-Text 96.20, ITC 99.12), establishing a new state of the art for multimodal educational content generation and demonstrating the effectiveness of self-reflective multi-agent collaboration in pedagogically aligned vision-language reasoning. --- ### DriveFlow: Rectified Flow Adaptation for Robust 3D Object Detection in Autonomous Driving Authors: Hongbin Lin, Yiming Yang, Chaoda Zheng, Yifan Zhang, Shuaicheng Niu, Zilu Guo, Yafeng Li, Gui Gui, Shuguang Cui, Zhen Li Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18713v1 In autonomous driving, vision-centric 3D object detection recognizes and localizes 3D objects from RGB images. However, due to high annotation costs and diverse outdoor scenes, training data often fails to cover all possible test scenarios, known as the out-of-distribution (OOD) issue. Training-free image editing offers a promising solution for improving model robustness by training data enhancement without any modifications to pre-trained diffusion models. Nevertheless, inversion-based methods often suffer from limited effectiveness and inherent inaccuracies, while recent rectified-flow-based approaches struggle to preserve objects with accurate 3D geometry. In this paper, we propose DriveFlow, a Rectified Flow Adaptation method for training data enhancement in autonomous driving based on pre-trained Text-to-Image flow models. Based on frequency decomposition, DriveFlow introduces two strategies to adapt noise-free editing paths derived from text-conditioned velocities. 1) High-Frequency Foreground Preservation: DriveFlow incorporates a high-frequency alignment loss for foreground to maintain precise 3D object geometry. 2) Dual-Frequency Background Optimization: DriveFlow also conducts dual-frequency optimization for background, balancing editing flexibility and semantic consistency. Comprehensive experiments validate the effectiveness and efficiency of DriveFlow, demonstrating comprehensive performance improvements on all categories across OOD scenarios. Code is available at https://github.com/Hongbin98/DriveFlow. --- ### Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation Authors: Yuyang Wanyan, Xiaoshan Yang, Weiming Dong, Changsheng Xu Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18711v1 In this paper, we study the challenging task of Few-Shot Video Domain Adaptation (FSVDA). The multimodal nature of videos introduces unique challenges, necessitating the simultaneous consideration of both domain alignment and modality collaboration in a few-shot scenario, which is ignored in previous literature. We observe that, under the influence of domain shift, the generalization performance on the target domain of each individual modality, as well as that of fused multimodal features, is constrained. Because each modality is comprised of coupled features with multiple components that exhibit different domain shifts. This variability increases the complexity of domain adaptation, thereby reducing the effectiveness of multimodal feature integration. To address these challenges, we introduce a novel framework of Modality-Collaborative LowRank Decomposers (MC-LRD) to decompose modality-unique and modality-shared features with different domain shift levels from each modality that are more friendly for domain alignment. The MC-LRD comprises multiple decomposers for each modality and Multimodal Decomposition Routers (MDR). Each decomposer has progressively shared parameters across different modalities. The MDR is leveraged to selectively activate the decomposers to produce modality-unique and modality-shared features. To ensure efficient decomposition, we apply orthogonal decorrelation constraints separately to decomposers and subrouters, enhancing their diversity. Furthermore, we propose a cross-domain activation consistency loss to guarantee that target and source samples of the same category exhibit consistent activation preferences of the decomposers, thereby facilitating domain alignment. Extensive experimental results on three public benchmarks demonstrate that our model achieves significant improvements over existing methods. --- ### CoD: A Diffusion Foundation Model for Image Compression Authors: Zhaoyang Jia, Zihan Zheng, Naifu Xue, Jiahao Li, Bin Li, Zongyu Guo, Xiaoyi Zhang, Houqiang Li, Yan Lu Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18706v3 Existing diffusion codecs typically build on text-to-image diffusion foundation models like Stable Diffusion. However, text conditioning is suboptimal from a compression perspective, hindering the potential of downstream diffusion codecs, particularly at ultra-low bitrates. To address it, we introduce \textbf{CoD}, the first \textbf{Co}mpression-oriented \textbf{D}iffusion foundation model, trained from scratch to enable end-to-end optimization of both compression and generation. CoD is not a fixed codec but a general foundation model designed for various diffusion-based codecs. It offers several advantages: \textbf{High compression efficiency}, replacing Stable Diffusion with CoD in downstream codecs like DiffC achieves SOTA results, especially at ultra-low bitrates (e.g., 0.0039 bpp); \textbf{Low-cost and reproducible training}, 300$\times$ faster training than Stable Diffusion ($\sim$ 20 vs. $\sim$ 6,250 A100 GPU days) on entirely open image-only datasets; \textbf{Providing new insights}, e.g., We find pixel-space diffusion can achieve VTM-level PSNR with high perceptual quality and can outperform GAN-based codecs using fewer parameters. We hope CoD lays the foundation for future diffusion codec research. Codes are released at https://github.com/microsoft/GenCodec/tree/main/CoD. --- ### CNN-Based Camera Pose Estimation and Localisation of Scan Images for Aircraft Visual Inspection Authors: Xueyan Oh, Leonard Loh, Shaohui Foong, Zhong Bao Andy Koh, Kow Leong Ng, Poh Kang Tan, Pei Lin Pearlin Toh, U-Xuan Tan Published: 2025-11-24 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.18702v1 General Visual Inspection is a manual inspection process regularly used to detect and localise obvious damage on the exterior of commercial aircraft. There has been increasing demand to perform this process at the boarding gate to minimise the downtime of the aircraft and automating this process is desired to reduce the reliance on human labour. Automating this typically requires estimating a camera's pose with respect to the aircraft for initialisation but most existing localisation methods require infrastructure, which is very challenging in uncontrolled outdoor environments and within the limited turnover time (approximately 2 hours) on an airport tarmac. Additionally, many airlines and airports do not allow contact with the aircraft's surface or using UAVs for inspection between flights, and restrict access to commercial aircraft. Hence, this paper proposes an on-site method that is infrastructure-free and easy to deploy for estimating a pan-tilt-zoom camera's pose and localising scan images. This method initialises using the same pan-tilt-zoom camera used for the inspection task by utilising a Deep Convolutional Neural Network fine-tuned on only synthetic images to predict its own pose. We apply domain randomisation to generate the dataset for fine-tuning the network and modify its loss function by leveraging aircraft geometry to improve accuracy. We also propose a workflow for initialisation, scan path planning, and precise localisation of images captured from a pan-tilt-zoom camera. We evaluate and demonstrate our approach through experiments with real aircraft, achieving root-mean-square camera pose estimation errors of less than 0.24 m and 2 degrees for all real scenes. --- ### ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction Authors: Mustafa Munir, Harsh Goel, Xiwen Wei, Minkyu Choi, Sahil Shah, Kartikeya Bhardwaj, Paul Whatmough, Sandeep Chinchali, Radu Marculescu Published: 2025-11-24 Categories: cs.CV, cs.AI, cs.FL, cs.LG arXiv: https://arxiv.org/abs/2511.18701v1 Video editing and synthesis often introduce object inconsistencies, such as frame flicker and identity drift that degrade perceptual quality. To address these issues, we introduce ObjectAlign, a novel framework that seamlessly blends perceptual metrics with symbolic reasoning to detect, verify, and correct object-level and temporal inconsistencies in edited video sequences. The novel contributions of ObjectAlign are as follows: First, we propose learnable thresholds for metrics characterizing object consistency (i.e. CLIP-based semantic similarity, LPIPS perceptual distance, histogram correlation, and SAM-derived object-mask IoU). Second, we introduce a neuro-symbolic verifier that combines two components: (a) a formal, SMT-based check that operates on masked object embeddings to provably guarantee that object identity does not drift, and (b) a temporal fidelity check that uses a probabilistic model checker to verify the video's formal representation against a temporal logic specification. A frame transition is subsequently deemed "consistent" based on a single logical assertion that requires satisfying both the learned metric thresholds and this unified neuro-symbolic constraint, ensuring both low-level stability and high-level temporal correctness. Finally, for each contiguous block of flagged frames, we propose a neural network based interpolation for adaptive frame repair, dynamically choosing the interpolation depth based on the number of frames to be corrected. This enables reconstruction of the corrupted frames from the last valid and next valid keyframes. Our results show up to 1.4 point improvement in CLIP Score and up to 6.1 point improvement in warp error compared to SOTA baselines on the DAVIS and Pexels video datasets. --- ### Dendritic Convolution for Noise Image Recognition Authors: Jiarui Xue, Dongjian Yang, Ye Sun, Gang Liu Published: 2025-11-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.18699v1 In real-world scenarios of image recognition, there exists substantial noise interference. Existing works primarily focus on methods such as adjusting networks or training strategies to address noisy image recognition, and the anti-noise performance has reached a bottleneck. However, little is known about the exploration of anti-interference solutions from a neuronal perspective.This paper proposes an anti-noise neuronal convolution. This convolution mimics the dendritic structure of neurons, integrates the neighborhood interaction computation logic of dendrites into the underlying design of convolutional operations, and simulates the XOR logic preprocessing function of biological dendrites through nonlinear interactions between input features, thereby fundamentally reconstructing the mathematical paradigm of feature extraction. Unlike traditional convolution where noise directly interferes with feature extraction and exerts a significant impact, DDC mitigates the influence of noise by focusing on the interaction of neighborhood information. Experimental results demonstrate that in image classification tasks (using YOLOv11-cls, VGG16, and EfficientNet-B0) and object detection tasks (using YOLOv11, YOLOv8, and YOLOv5), after replacing traditional convolution with the dendritic convolution, the accuracy of the EfficientNet-B0 model on noisy datasets is relatively improved by 11.23%, and the mean Average Precision (mAP) of YOLOv8 is increased by 19.80%. The consistency between the computation method of this convolution and the dendrites of biological neurons enables it to perform significantly better than traditional convolution in complex noisy environments. --- ### Multimodal Real-Time Anomaly Detection and Industrial Applications Authors: Aman Verma, Keshav Samdani, Mohd. Samiuddin Shafi Published: 2025-11-24 Categories: cs.SD, cs.AI, cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2511.18698v1 This paper presents the design, implementation, and evolution of a comprehensive multimodal room-monitoring system that integrates synchronized video and audio processing for real-time activity recognition and anomaly detection. We describe two iterations of the system: an initial lightweight implementation using YOLOv8, ByteTrack, and the Audio Spectrogram Transformer (AST), and an advanced version that incorporates multi-model audio ensembles, hybrid object detection, bidirectional cross-modal attention, and multi-method anomaly detection. The evolution demonstrates significant improvements in accuracy, robustness, and industrial applicability. The advanced system combines three audio models (AST, Wav2Vec2, and HuBERT) for comprehensive audio understanding, dual object detectors (YOLO and DETR) for improved accuracy, and sophisticated fusion mechanisms for enhanced cross-modal learning. Experimental evaluation shows the system's effectiveness in general monitoring scenarios as well as specialized industrial safety applications, achieving real-time performance on standard hardware while maintaining high accuracy. --- ### Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models Authors: Wangjiaxuan Xin Published: 2025-11-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.18696v2 This report presents the Empathetic Cascading Networks (ECN) framework, a multi-stage prompting method designed to enhance the empathetic and inclusive capabilities of large language models. ECN employs four stages: Perspective Adoption, Emotional Resonance, Reflective Understanding, and Integrative Synthesis, to guide models toward generating emotionally resonant and contextually aware responses. Experimental results demonstrate that ECN achieves the highest Empathy Quotient (EQ) scores across GPT-3.5-turbo and GPT-4, while maintaining competitive Regard and Perplexity metrics. These findings emphasize ECN's potential for applications requiring empathy and inclusivity in conversational AI. --- ### Exploring Surround-View Fisheye Camera 3D Object Detection Authors: Changcai Li, Wenwei Lin, Zuoxun Hou, Gang Chen, Wei Zhang, Huihui Zhou, Weishi Zheng Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18695v1 In this work, we explore the technical feasibility of implementing end-to-end 3D object detection (3DOD) with surround-view fisheye camera system. Specifically, we first investigate the performance drop incurred when transferring classic pinhole-based 3D object detectors to fisheye imagery. To mitigate this, we then develop two methods that incorporate the unique geometry of fisheye images into mainstream detection frameworks: one based on the bird's-eye-view (BEV) paradigm, named FisheyeBEVDet, and the other on the query-based paradigm, named FisheyePETR. Both methods adopt spherical spatial representations to effectively capture fisheye geometry. In light of the lack of dedicated evaluation benchmarks, we release Fisheye3DOD, a new open dataset synthesized using CARLA and featuring both standard pinhole and fisheye camera arrays. Experiments on Fisheye3DOD show that our fisheye-compatible modeling improves accuracy by up to 6.2% over baseline methods. --- ### Stable Multi-Drone GNSS Tracking System for Marine Robots Authors: Shuo Wen, Edwin Meriaux, Mariana Sosa Guzmán, Zhizun Wang, Junming Shi, Gregory Dudek Published: 2025-11-24 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.18694v2 Stable and accurate tracking is essential for marine robotics, yet Global Navigation Satellite System (GNSS) signals vanish immediately below the sea surface. Traditional alternatives suffer from error accumulation, high computational demands, or infrastructure dependence. In this work, we present a multi-drone GNSS-based tracking system for surface and near-surface marine robots. Our approach combines efficient visual detection, lightweight multi-object tracking, GNSS-based triangulation, and a confidence-weighted Extended Kalman Filter (EKF) to provide stable GNSS estimation in real time. We further introduce a cross-drone tracking ID alignment algorithm that enforces global consistency across views, enabling robust multi-robot tracking with cooperative aerial coverage. We validate our system in diversified complex settings to show the accuracy and robustness of the proposed algorithm. --- ### VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking Authors: Kichang Yang, Seonjun Kim, Minjae Kim, Nairan Zhang, Chi Zhang, Youngki Lee Published: 2025-11-24 Categories: cs.LG, cs.AI, cs.CV, cs.PF arXiv: https://arxiv.org/abs/2511.18692v1 Edge deployment of large Vision-Language Models (VLMs) increasingly relies on flash-based weight offloading, where activation sparsification is used to reduce I/O overhead. However, conventional sparsification remains model-centric, selecting neurons solely by activation magnitude and neglecting how access patterns influence flash performance. We present Neuron Chunking, an I/O-efficient sparsification strategy that operates on chunks (i.e., groups of contiguous neurons in memory) and couples neuron importance with storage access cost. The method models I/O latency through a lightweight abstraction of access contiguity and selects chunks with high utility, defined as neuron importance normalized by estimated latency. By aligning sparsification decisions with the underlying storage behavior, Neuron Chunking improves I/O efficiency by up to 4.65x and 5.76x on Jetson Orin Nano and Jetson AGX Orin, respectively. --- ### EVCC: Enhanced Vision Transformer-ConvNeXt-CoAtNet Fusion for Classification Authors: Kazi Reyazul Hasan, Md Nafiu Rahman, Wasif Jalal, Sadif Ahmed, Shahriar Raj, Mubasshira Musarrat, Muhammad Abdullah Adnan Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18691v1 Hybrid vision architectures combining Transformers and CNNs have significantly advanced image classification, but they usually do so at significant computational cost. We introduce EVCC (Enhanced Vision Transformer-ConvNeXt-CoAtNet), a novel multi-branch architecture integrating the Vision Transformer, lightweight ConvNeXt, and CoAtNet through key innovations: (1) adaptive token pruning with information preservation, (2) gated bidirectional cross-attention for enhanced feature refinement, (3) auxiliary classification heads for multi-task learning, and (4) a dynamic router gate employing context-aware confidence-driven weighting. Experiments across the CIFAR-100, Tobacco3482, CelebA, and Brain Cancer datasets demonstrate EVCC's superiority over powerful models like DeiT-Base, MaxViT-Base, and CrossViT-Base by consistently achieving state-of-the-art accuracy with improvements of up to 2 percentage points, while reducing FLOPs by 25 to 35%. Our adaptive architecture adjusts computational demands to deployment needs by dynamically reducing token count, efficiently balancing the accuracy-efficiency trade-off while combining global context, local details, and hierarchical features for real-world applications. The source code of our implementation is available at https://anonymous.4open.science/r/EVCC. --- ### QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks Authors: Kazi Ahmed Asif Fuad, Lizhong Chen Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18689v4 Kolmogorov--Arnold Networks (KANs) replace linear weights with spline-based functions, offering strong expressivity but posing challenges for low-precision deployment due to heterogeneous parameter distributions. We introduce QuantKAN, the first unified framework for quantization-aware training (QAT) and post-training quantization (PTQ) of KANs. The framework employs branch-aware quantizers for base and spline parameters and extends modern QAT and PTQ methods to spline-based layers across EfficientKAN, FastKAN, PyKAN, and KAGN. Experiments on MNIST, CIFAR-10/100, TinyImageNet, and ImageNet provide the first unified QAT/PTQ KAN benchmarks and show that DSQ is the most robust QAT method at aggressive low-bit settings, while GPTQ is the strongest PTQ method at moderate precision. Sensitivity analyses reveal architecture-specific failure modes: spline/basis parameters dominate in FastKAN, while base or scaling parameters dominate in EfficientKAN, GRAM, and PyKAN. Vivado HLS estimates on a Xilinx UltraScale+ device further suggest up to 3.32$\times$ throughput and 7.7$\times$ lower estimated dynamic energy per inference under W4A4, exposing a residual \emph{basis-evaluation tax} that motivates basis-aware microarchitecture. QuantKAN is available at https://github.com/OSU-STARLAB/QuantKAN/. --- ### Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents Authors: Dayong Liu, Chao Xu, Weihong Chen, Suyu Zhang, Juncheng Wang, Jiankang Deng, Baigui Sun, Yang Liu Published: 2025-11-24 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.18685v4 Multimodal Large Language Models (MLLMs) show promising results as decision-making engines for embodied agents operating in complex, physical environments. However, existing benchmarks often prioritize high-level planning or spatial reasoning, leaving the fine-grained action intelligence required for embodied physical interaction underexplored. To address this gap, we introduce CFG-Bench, a new benchmark designed to systematically evaluate this crucial capability. CFG-Bench consists of 1,368 curated videos paired with 19,562 question-answer pairs spanning three evaluation paradigms targeting four cognitive abilities: 1) Physical Interaction, 2) Temporal-Causal Relation, 3) Intentional Understanding, and 4) Evaluative Judgment. Together, these dimensions provide a systematic framework for assessing a model's ability to translate visual observations into actionable knowledge, moving beyond mere surface-level recognition. Our comprehensive evaluation on CFG-Bench reveals that leading MLLMs struggle to produce detailed instructions for physical interactions and exhibit profound limitations in the higher-order reasoning of intention and evaluation. Moreover, supervised fine-tuning (SFT) on our data demonstrates that teaching an MLLMs to articulate fine-grained actions directly translates to significant performance gains on established embodied benchmarks. Our analysis highlights these limitations and offers insights for developing more capable and grounded embodied agents. Project page: https://cfg-bench.github.io/ --- ### Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation Authors: Shristi Das Biswas, Arani Roy, Kaushik Roy Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18684v1 Robust concept removal for text-to-image (T2I) and text-to-video (T2V) models is essential for their safe deployment. Existing methods, however, suffer from costly retraining, inference overhead, or vulnerability to adversarial attacks. Crucially, they rarely model the latent semantic overlap between the target erase concept and surrounding content -- causing collateral damage post-erasure -- and even fewer methods work reliably across both T2I and T2V domains. We introduce Instant Concept Erasure (ICE), a training-free, modality-agnostic, one-shot weight modification approach that achieves precise, persistent unlearning with zero overhead. ICE defines erase and preserve subspaces using anisotropic energy-weighted scaling, then explicitly regularises against their intersection using a unique, closed-form overlap projector. We pose a convex and Lipschitz-bounded Spectral Unlearning Objective, balancing erasure fidelity and intersection preservation, that admits a stable and unique analytical solution. This solution defines a dissociation operator that is translated to the model's text-conditioning layers, making the edit permanent and runtime-free. Across targeted removals of artistic styles, objects, identities, and explicit content, ICE efficiently achieves strong erasure with improved robustness to red-teaming, all while causing only minimal degradation of original generative abilities in both T2I and T2V models. --- ### Hierarchical GraphCut Phase Unwrapping based on Invariance of Diffeomorphisms Framework Authors: Xiang Gao, Xinmu Wang, Zhou Zhao, Junqi Huang, Xianfeng David Gu Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18682v1 Recent years have witnessed rapid advancements in 3D scanning technologies, with applications spanning VR/AR, digital human creation, and medical imaging. Structured-light scanning with phase-shifting techniques is preferred for its use of low-intensity visible light and high accuracy, making it well suited for capturing 4D facial dynamics. A key step is phase unwrapping, which recovers continuous phase values from measurements wrapped modulo 2pi. The goal is to estimate the unwrapped phase count k in the equation Phi = phi + 2pi k, where phi is the wrapped phase and Phi is the true phase. Noise, occlusions, and complex 3D geometry make recovering the true phase challenging because phase unwrapping is ill-posed: measurements only provide modulo 2pi values, and estimating k requires assumptions about surface continuity. Existing methods trade speed for accuracy: fast approaches lack precision, while accurate algorithms are too slow for real-time use. To overcome these limitations, this work proposes a phase unwrapping framework that reformulates GraphCut-based unwrapping as a pixel-labeling problem. This framework improves the estimation of the unwrapped phase count k through the invariance property of diffeomorphisms applied in image space via conformal and optimal transport (OT) maps. An odd number of diffeomorphisms are precomputed from the input phase data, and a hierarchical GraphCut algorithm is applied in each domain. The resulting label maps are fused via majority voting to robustly estimate k at each pixel. Experimental results demonstrate a 45.5x speedup and lower L2 error in real experiments and simulations, showing potential for real-time applications. --- ### Inverse Rendering for High-Genus Surface Meshes from Multi-View Images Authors: Xiang Gao, Xinmu Wang, Xiaolong Wu, Jiazhi Li, Jingyu Shi, Yu Guo, Yuanpeng Liu, Xiyun Song, Heather Yu, Zongfang Lin, Xianfeng David Gu Published: 2025-11-24 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2511.18680v1 We present a topology-informed inverse rendering approach for reconstructing high-genus surface meshes from multi-view images. Compared to 3D representations like voxels and point clouds, mesh-based representations are preferred as they enable the application of differential geometry theory and are optimized for modern graphics pipelines. However, existing inverse rendering methods often fail catastrophically on high-genus surfaces, leading to the loss of key topological features, and tend to oversmooth low-genus surfaces, resulting in the loss of surface details. This failure stems from their overreliance on Adam-based optimizers, which can lead to vanishing and exploding gradients. To overcome these challenges, we introduce an adaptive V-cycle remeshing scheme in conjunction with a re-parametrized Adam optimizer to enhance topological and geometric awareness. By periodically coarsening and refining the deforming mesh, our method informs mesh vertices of their current topology and geometry before optimization, mitigating gradient issues while preserving essential topological features. Additionally, we enforce topological consistency by constructing topological primitives with genus numbers that match those of ground truth using Gauss-Bonnet theorem. Experimental results demonstrate that our inverse rendering approach outperforms the current state-of-the-art method, achieving significant improvements in Chamfer Distance and Volume IoU, particularly for high-genus surfaces, while also enhancing surface details for low-genus surfaces. --- ### Neural Geometry Image-Based Representations with Optimal Transport (OT) Authors: Xiang Gao, Yuanpeng Liu, Xinmu Wang, Jiazhi Li, Minghao Guo, Yu Guo, Xiyun Song, Heather Yu, Zhiqiang Lao, Xianfeng David Gu Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18679v1 Neural representations for 3D meshes are emerging as an effective solution for compact storage and efficient processing. Existing methods often rely on neural overfitting, where a coarse mesh is stored and progressively refined through multiple decoder networks. While this can restore high-quality surfaces, it is computationally expensive due to successive decoding passes and the irregular structure of mesh data. In contrast, images have a regular structure that enables powerful super-resolution and restoration frameworks, but applying these advantages to meshes is difficult because their irregular connectivity demands complex encoder-decoder architectures. Our key insight is that a geometry image-based representation transforms irregular meshes into a regular image grid, making efficient image-based neural processing directly applicable. Building on this idea, we introduce our neural geometry image-based representation, which is decoder-free, storage-efficient, and naturally suited for neural processing. It stores a low-resolution geometry-image mipmap of the surface, from which high-quality meshes are restored in a single forward pass. To construct geometry images, we leverage Optimal Transport (OT), which resolves oversampling in flat regions and undersampling in feature-rich regions, and enables continuous levels of detail (LoD) through geometry-image mipmapping. Experimental results demonstrate state-of-the-art storage efficiency and restoration accuracy, measured by compression ratio (CR), Chamfer distance (CD), and Hausdorff distance (HD). --- ### A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identification Authors: Yunpeng Gong, Yongjie Hou, Jiangming Shi, Kim Long Diep, Min Jiang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18677v1 Sketch based person re-identification aims to match hand-drawn sketches with RGB surveillance images, but remains challenging due to significant modality gaps and limited annotated data. To address this, we introduce KTCAA, a theoretically grounded framework for few-shot cross-modal generalization. Motivated by generalization theory, we identify two key factors influencing target domain risk: (1) domain discrepancy, which quantifies the alignment difficulty between source and target distributions; and (2) perturbation invariance, which evaluates the model's robustness to modality shifts. Based on these insights, we propose two components: (1) Alignment Augmentation (AA), which applies localized sketch-style transformations to simulate target distributions and facilitate progressive alignment; and (2) Knowledge Transfer Catalyst (KTC), which enhances invariance by introducing worst-case perturbations and enforcing consistency. These modules are jointly optimized under a meta-learning paradigm that transfers alignment knowledge from data-rich RGB domains to sketch-based scenarios. Experiments on multiple benchmarks demonstrate that KTCAA achieves state-of-the-art performance, particularly in data-scarce conditions. --- ### MedVision: Benchmarking Quantitative Medical Image Analysis Authors: Yongcheng Yao, Yongshuo Zong, Raman Dutt, Yongxin Yang, Sotirios A Tsaftaris, Timothy Hospedales Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18676v3 Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., "Is this normal or abnormal?") or qualitative descriptive tasks. However, clinical decision-making often relies on quantitative assessments, such as measuring the size of a tumor or the angle of a joint, from which clinicians draw their own diagnostic conclusions. This quantitative reasoning capability remains underexplored and poorly supported in existing VLMs. In this work, we introduce MedVision, a large-scale dataset and benchmark specifically designed to evaluate and improve VLMs on quantitative medical image analysis. MedVision spans 22 public datasets covering diverse anatomies and modalities, with 29.0K 3D images, 11.2M annotated 2D slices, and 24.3M single-instance annotations. We focus on three representative quantitative tasks: (1) detection of anatomical structures and abnormalities, (2) tumor/lesion (T/L) size estimation, and (3) angle/distance (A/D) measurement. We show that current off-the-shelf VLMs perform poorly on these tasks. However, supervised and reinforcement fine-tuning (RFT) on MedVision significantly enhances performance across detection, T/L size estimation, and A/D measurement, yielding MedVision-V0 as a strong open baseline. In the RFT stage, we design and evaluate the efficacy of process rewards, multiplicative reward composition, and multi-task RFT with curriculum learning. MedVision provides a foundation for developing VLMs with robust quantitative reasoning capabilities in medical imaging. --- ### Low-Rank GEMM: Efficient Matrix Multiplication via Low-Rank Approximation with FP8 Acceleration Authors: Alfredo Metere Published: 2025-11-24 Categories: cs.PF, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2511.18674v1 Large matrix multiplication is a cornerstone of modern machine learning workloads, yet traditional approaches suffer from cubic computational complexity (e.g., $\mathcal{O}(n^3)$ for a matrix of size $n\times n$). We present Low-Rank GEMM, a novel approach that leverages low-rank matrix approximations to achieve sub-quadratic complexity while maintaining hardware-accelerated performance through FP8 precision and intelligent kernel selection. On a NVIDIA RTX 4090, our implementation achieves up to 378 TFLOPS on matrices up to $N=20480$, providing 75\% memory savings and $7.8\times$ speedup over PyTorch FP32 for large matrices. The system automatically adapts to hardware capabilities, selecting optimal decomposition methods (SVD, randomized SVD) and precision levels based on matrix characteristics and available accelerators. Comprehensive benchmarking on NVIDIA RTX 4090 demonstrates that Low-Rank GEMM becomes the fastest approach for matrices $N\geq10240$, surpassing traditional cuBLAS implementations through memory bandwidth optimization rather than computational shortcuts. --- ### Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers Authors: Yiqing Shi, Yiren Song, Mike Zheng Shou Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18673v1 Recent advances in diffusion transformers have shown remarkable generalization in visual synthesis, yet most dense perception methods still rely on text-to-image (T2I) generators designed for stochastic generation. We revisit this paradigm and show that image editing diffusion models are inherently image-to-image consistent, providing a more suitable foundation for dense perception task. We introduce Edit2Perceive, a unified diffusion framework that adapts editing models for depth, normal, and matting. Built upon the FLUX.1 Kontext architecture, our approach employs full-parameter fine-tuning and a pixel-space consistency loss to enforce structure-preserving refinement across intermediate denoising states. Moreover, our single-step deterministic inference yields up to faster runtime while training on relatively small datasets. Extensive experiments demonstrate comprehensive state-of-the-art results across all three tasks, revealing the strong potential of editing-oriented diffusion transformers for geometry-aware perception. --- ### Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement Authors: Yuchen Xia, Souvik Kundu, Mosharaf Chowdhury, Nishil Talati Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18672v1 Novel View Synthesis (NVS) is the task of generating new images of a scene from viewpoints that were not part of the original input. Diffusion-based NVS can generate high-quality, temporally consistent images, however, remains computationally prohibitive. Conversely, regression-based NVS offers suboptimal generation quality despite requiring significantly lower compute; leaving the design objective of a high-quality, inference-efficient NVS framework an open challenge. To close this critical gap, we present Sphinx, a training-free hybrid inference framework that achieves diffusion-level fidelity at a significantly lower compute. Sphinx proposes to use regression-based fast initialization to guide and reduce the denoising workload for the diffusion model. Additionally, it integrates selective refinement with adaptive noise scheduling, allowing more compute to uncertain regions and frames. This enables Sphinx to provide flexible navigation of the performance-quality trade-off, allowing adaptation to latency and fidelity requirements for dynamically changing inference scenarios. Our evaluation shows that Sphinx achieves an average 1.8x speedup over diffusion model inference with negligible perceptual degradation of less than 5%, establishing a new Pareto frontier between quality and latency in NVS serving. --- ### Multi-Agent Cross-Entropy Method with Monotonic Nonlinear Critic Decomposition Authors: Yan Wang, Ke Deng, Yongli Ren Published: 2025-11-24 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2511.18671v2 Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution (CTDE), where centralized critics leverage global information to guide decentralized actors. However, centralized-decentralized mismatch (CDM) arises when the suboptimal behavior of one agent degrades others' learning. Prior approaches mitigate CDM through value decomposition, but linear decompositions allow per-agent gradients at the cost of limited expressiveness, while nonlinear decompositions improve representation but require centralized gradients, reintroducing CDM. To overcome this trade-off, we propose the multi-agent cross-entropy method (MCEM), combined with monotonic nonlinear critic decomposition (NCD). MCEM updates policies by increasing the probability of high-value joint actions, thereby excluding suboptimal behaviors. For sample efficiency, we extend off-policy learning with a modified k-step return and Retrace. Analysis and experiments demonstrate that MCEM outperforms state-of-the-art methods across both continuous and discrete action benchmarks. --- ### Deterministic Continuous Replacement: Fast and Stable Module Replacement in Pretrained Transformers Authors: Rowan Bradbury, Aniket Srinivasan Ashok, Sai Ram Kasanagottu, Gunmay Jhingran, Shuai Meng Published: 2025-11-24 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.18670v1 Replacing modules in pretrained models, especially swapping quadratic self-attention for efficient attention alternatives, poses a hard optimization problem: cold-start reinitialization destabilizes frozen backbones. We isolate this core stability challenge in a controlled study. Deterministic Continuous Replacement (DCR) blends teacher and student outputs with a deterministic, annealed weight. Theoretically, DCR eliminates gate-induced gradient variance inherent to stochastic replacement. In a single-seed study, DCR attains faster convergence and stronger alignment than stochastic gating and distillation baselines on controlled attention replacement, establishing a foundation for heterogeneous operator swaps. --- ### Data Augmentation Strategies for Robust Lane Marking Detection Authors: Flora Lian, Dinh Quang Huynh, Hector Penades, J. Stephany Berrio Perez, Mao Shan, Stewart Worrall Published: 2025-11-24 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2511.18668v1 Robust lane detection is essential for advanced driver assistance and autonomous driving, yet models trained on public datasets such as CULane often fail to generalise across different camera viewpoints. This paper addresses the challenge of domain shift for side-mounted cameras used in lane-wheel monitoring by introducing a generative AI-based data enhancement pipeline. The approach combines geometric perspective transformation, AI-driven inpainting, and vehicle body overlays to simulate deployment-specific viewpoints while preserving lane continuity. We evaluated the effectiveness of the proposed augmentation in two state-of-the-art models, SCNN and UFLDv2. With the augmented data trained, both models show improved robustness to different conditions, including shadows. The experimental results demonstrate gains in precision, recall, and F1 score compared to the pre-trained model. By bridging the gap between widely available datasets and deployment-specific scenarios, our method provides a scalable and practical framework to improve the reliability of lane detection in a pilot deployment scenario. --- ### Equivariant Deep Equilibrium Models for Imaging Inverse Problems Authors: Alexander Mehta, Ruangrawee Kitichotkul, Vivek K Goyal, Julián Tachella Published: 2025-11-24 Categories: eess.IV, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.18667v1 Equivariant imaging (EI) enables training signal reconstruction models without requiring ground truth data by leveraging signal symmetries. Deep equilibrium models (DEQs) are a powerful class of neural networks where the output is a fixed point of a learned operator. However, training DEQs with complex EI losses requires implicit differentiation through fixed-point computations, whose implementation can be challenging. We show that backpropagation can be implemented modularly, simplifying training. Experiments demonstrate that DEQs trained with implicit differentiation outperform those trained with Jacobian-free backpropagation and other baseline methods. Additionally, we find evidence that EI-trained DEQs approximate the proximal map of an invariant prior. --- ### Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data Authors: Guillaume Braun, Bruno Loureiro, Ha Quang Minh, Masaaki Imaizumi Published: 2025-11-24 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.18661v1 Scaling laws describe how learning performance improves with data, compute, or training time, and have become a central theme in modern deep learning. We study this phenomenon in a canonical nonlinear model: phase retrieval with anisotropic Gaussian inputs whose covariance spectrum follows a power law. Unlike the isotropic case, where dynamics collapse to a two-dimensional system, anisotropy yields a qualitatively new regime in which an infinite hierarchy of coupled equations governs the evolution of the summary statistics. We develop a tractable reduction that reveals a three-phase trajectory: (i) fast escape from low alignment, (ii) slow convergence of the summary statistics, and (iii) spectral-tail learning in low-variance directions. From this decomposition, we derive explicit scaling laws for the mean-squared error, showing how spectral decay dictates convergence times and error curves. Experiments confirm the predicted phases and exponents. These results provide the first rigorous characterization of scaling laws in nonlinear regression with anisotropic data, highlighting how anisotropy reshapes learning dynamics. --- ### Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic Authors: Mostafa Mozafari, Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri Published: 2025-11-24 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.18660v2 Corrupted training data are ubiquitous. Corrective Machine Unlearning (CMU) seeks to remove the influence of such corruption post-training. Prior CMU typically assumes access to identified corrupted training samples (a "forget set"). However, in many real-world scenarios the training data are no longer accessible. We formalize source-free CMU, where the original training data are unavailable and, consequently, no forget set of identified corrupted training samples can be specified. Instead, we assume a small proxy (surrogate) set of corrupted samples that reflect the suspected corruption type without needing to be the original training samples. In this stricter setting, methods relying on forget set are ineffective or narrow in scope. We introduce Corrective Unlearning in Task Space (CUTS), a lightweight weight space correction method guided by the proxy set using task arithmetic principles. CUTS treats the clean and the corruption signal as distinct tasks. Specifically, we briefly fine-tune the corrupted model on the proxy to amplify the corruption mechanism in the weight space, compute the difference between the corrupted and fine-tuned weights as a proxy task vector, and subtract a calibrated multiple of this vector to cancel the corruption. Without access to clean data or a forget set, CUTS recovers a large fraction of the lost utility under label noise and, for backdoor triggers, nearly eliminates the attack with minimal damage to utility, outperforming state-of-the-art specialized CMU methods in source-free setting. --- ### CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning Authors: Jie He, Richard He Bai, Sinead Williamson, Jeff Z. Pan, Navdeep Jaitly, Yizhe Zhang Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18659v3 Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval-generation optimization. In this work, we propose CLaRa (Continuous Latent Reasoning), a unified framework that performs embedding-based compression and joint optimization in a shared continuous space. To obtain semantically rich and retrievable compressed vectors, thereby reducing the document length fed into the generator, we introduce SCP, a key-preserving data synthesis framework based on question answering and paraphrase supervision. CLaRa then trains the reranker and generator end-to-end via a single language modeling loss, with gradients flowing through both modules using a differentiable top-k estimator. Theoretically, this unified optimization aligns retrieval relevance with answer quality. Experiments across multiple QA benchmarks show that CLaRa achieves state-of-the-art compression and reranking performance, even at a text compression rate of 16, outperforming text-based fine-tuned baselines. --- ### BitRL-Light: 1-bit LLM Agents with Deep Reinforcement Learning for Energy-Efficient Smart Home Lighting Optimization Authors: Ravi Gupta, Shabista Haider Published: 2025-11-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20623v1 Smart home lighting systems consume 15-20% of residential energy but lack adaptive intelligence to optimize for user comfort and energy efficiency simultaneously. We present BitRL-Light, a novel framework combining 1-bit quantized Large Language Models (LLMs) with Deep Q-Network (DQN) reinforcement learning for real-time smart home lighting control on edge devices. Our approach deploys a 1-bit quantized Llama-3.2-1B model on Raspberry Pi hardware, achieving 71.4 times energy reduction compared to full-precision models while maintaining intelligent control capabilities. Through multi-objective reinforcement learning, BitRL-Light learns optimal lighting policies from user feedback, balancing energy consumption, comfort, and circadian alignment. Experimental results demonstrate 32% energy savings compared to rule-based systems, with inference latency under 200ms on Raspberry Pi 4 and 95% user satisfaction. The system processes natural language commands via Google Home/IFTTT integration and learns from implicit feedback through manual overrides. Our comparative analysis shows 1-bit models achieve 5.07 times speedup over 2-bit alternatives on ARM processors while maintaining 92% task accuracy. This work establishes a practical framework for deploying adaptive AI on resource-constrained IoT devices, enabling intelligent home automation without cloud dependencies. --- ### Physics-Guided Deep Learning for Heat Pump Stress Detection: A Comprehensive Analysis on When2Heat Dataset Authors: Md Shahabub Alam, Md Asifuzzaman Jishan, Ayan Kumar Ghosh Published: 2025-11-23 Categories: cs.LG, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2512.13696v1 Heat pump systems are critical components in modern energy-efficient buildings, yet their operational stress detection remains challenging due to complex thermodynamic interactions and limited real-world data. This paper presents a novel Physics-Guided Deep Neural Network (PG-DNN) approach for heat pump stress classification using the When2Heat dataset, containing 131,483 samples with 656 features across 26 European countries. The methodology integrates physics-guided feature selection and class definition with a deep neural network architecture featuring 5 hidden layers and dual regularization strategies. The model achieves 78.1\% test accuracy and 78.5% validation accuracy, demonstrating significant improvements over baseline approaches: +5.0% over shallow networks, +4.0% over limited feature sets, and +2.0% over single regularization strategies. Comprehensive ablation studies validate the effectiveness of physics-guided feature selection, variable thresholding for realistic class distribution, and cross-country energy pattern analysis. The proposed system provides a production-ready solution for heat pump stress detection with 181,348 parameters and 720 seconds training time on AMD Ryzen 9 7950X with RTX 4080 hardware. --- ### GNSS Jammer Direction Finding in Dynamic Scenarios Using an Inertial-based Multi-Antenna System Authors: Lucas Heublein, Thorsten Nowak, Tobias Feigl, Jaspar Pahl, Felix Ott Published: 2025-11-23 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2512.05128v1 Jamming devices disrupt signals from the global navigation satellite system (GNSS) and pose a significant threat by compromising the reliability of accurate positioning. Consequently, the detection and localization of these interference signals are essential to achieve situational awareness, mitigating their impact, and implementing effective countermeasures. In this paper, we utilize a two-times-two patch antenna system (i.e., the software defined radio device Ettus USRP X440) to predict the angle, elevation, and distance to the jamming source based on in-phase and quadrature (IQ) samples. We propose to use an inertial measurement unit (IMU) attached to the antenna system to predict the relative movement of the antenna in dynamic scenarios. We present a synthetic aperture system that enables coherent spatial imaging using platform motion to synthesize larger virtual apertures, offering superior angular resolution without mechanically rotating antennas. While classical angle-of-arrival (AoA) methods exhibit reduced accuracy in multipath environments due to signal reflections and scattering, leading to localization errors, we utilize a methodology that fuses IQ and Fast Fourier Transform (FFT)-computed spectrograms with 22 AoA features and the predicted relative movement to enhance GNSS jammer direction finding. --- ### Bayesian Optimization and Convolutional Neural Networks for Zernike-Based Wavefront Correction in High Harmonic Generation Authors: Guilherme Grancho D. Fernandes, Duarte Alexandrino, Eduardo Silva, João Matias, Joaquim Pereira Published: 2025-11-23 Categories: physics.optics, cs.LG arXiv: https://arxiv.org/abs/2512.05127v1 High harmonic generation (HHG) is a nonlinear process that enables table-top generation of tunable, high-energy, coherent, ultrashort radiation pulses in the extreme ultraviolet (EUV) to soft X-ray range. These pulses find applications in photoemission spectroscopy in condensed matter physics, pump-probe spectroscopy for high-energy-density plasmas, and attosecond science. However, optical aberrations in the high-power laser systems required for HHG degrade beam quality and reduce efficiency. We present a machine learning approach to optimize aberration correction using a spatial light modulator. We implemented and compared Bayesian optimization and convolutional neural network (CNN) methods to predict optimal Zernike polynomial coefficients for wavefront correction. Our CNN achieved promising results with 80.39% accuracy on test data, demonstrating the potential for automated aberration correction in HHG systems. --- ### SyncVoice: Simple and Effective Automatic Video Dubbing with Vision-Augmented TTS Authors: Kaidi Wang, Yi He, Wenhao Guan, Weijie Wu, Peijie Chen, Hongwu Ding, Xiong Zhang, Di Wu, Meng Meng, Jian Luan, Lin Li, Qingyang Hong Published: 2025-11-23 Categories: eess.AS, cs.AI, cs.CL, cs.CV, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2512.05126v2 Automatic video dubbing aims to generate high-fidelity speech that is temporally aligned with visual content. However, existing methods still suffer from limited speech naturalness, insufficient audio-visual synchronization, and poor scalability beyond monolingual settings. To address these challenges, we propose SyncVoice, a simple and effective dubbing framework that lightly integrates a Text-Visual Fusion Module into a pretrained text-to-speech (TTS) system. This module aligns visual features with linguistic representations, enabling temporally synchronized speech synthesis without complex architectural redesign. Experiments on the LRS3 dataset show that SyncVoice achieves state-of-the-art performance in zero-shot dubbing. Further training on a large-scale bilingual audio-visual dataset improves vocal fidelity while preserving synchronization, yielding a single unified model for both Chinese and English dubbing. ---