# Research Papers — 2025-11 · bundle page 36 of 197 > Full-text markdown of papers #1751–1800 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/36 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/35.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/37.md) ### Thinking in 360°: Humanoid Visual Search in the Wild Authors: Heyang Yu, Yinan Han, Xiangyu Zhang, Baiqiao Yin, Bowen Chang, Xiangyu Han, Xinhao Liu, Jing Zhang, Marco Pavone, Chen Feng, Saining Xie, Yiming Li Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20351v2 Humans rely on the synergistic control of head (cephalomotor) and eye (oculomotor) to efficiently search for visual information in 360°. However, prior approaches to visual search are limited to a static image, neglecting the physical embodiment and its interaction with the 3D world. How can we develop embodied visual search agents as efficient as humans while bypassing the constraints imposed by real-world hardware? To this end, we propose humanoid visual search where a humanoid agent actively rotates its head to search for objects or paths in an immersive world represented by a 360° panoramic image. To study visual search in visually-crowded real-world scenarios, we build H* Bench, a new benchmark that moves beyond household scenes to challenging in-the-wild scenes that necessitate advanced visual-spatial reasoning capabilities, such as transportation hubs, large-scale retail spaces, urban streets, and public institutions. Our experiments first reveal that even top-tier proprietary models falter, achieving only ~30% success in object and path search. We then use post-training techniques to enhance the open-source Qwen2.5-VL, increasing its success rate by over threefold for both object search (14.83% to 47.38%) and path search (6.44% to 24.94%). Notably, the lower ceiling of path search reveals its inherent difficulty, which we attribute to the demand for sophisticated spatial commonsense. Our results not only show a promising path forward but also quantify the immense challenge that remains in building MLLM agents that can be seamlessly integrated into everyday human life. --- ### Thinking in 360°: Humanoid Visual Search in the Wild Authors: Heyang Yu, Yinan Han, Xiangyu Zhang, Baiqiao Yin, Bowen Chang, Xiangyu Han, Xinhao Liu, Jing Zhang, Marco Pavone, Chen Feng, Saining Xie, Yiming Li Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20351v1 Humans rely on the synergistic control of head (cephalomotor) and eye (oculomotor) to efficiently search for visual information in 360°. However, prior approaches to visual search are limited to a static image, neglecting the physical embodiment and its interaction with the 3D world. How can we develop embodied visual search agents as efficient as humans while bypassing the constraints imposed by real-world hardware? To this end, we propose humanoid visual search where a humanoid agent actively rotates its head to search for objects or paths in an immersive world represented by a 360° panoramic image. To study visual search in visually-crowded real-world scenarios, we build H* Bench, a new benchmark that moves beyond household scenes to challenging in-the-wild scenes that necessitate advanced visual-spatial reasoning capabilities, such as transportation hubs, large-scale retail spaces, urban streets, and public institutions. Our experiments first reveal that even top-tier proprietary models falter, achieving only ~30% success in object and path search. We then use post-training techniques to enhance the open-source Qwen2.5-VL, increasing its success rate by over threefold for both object search (14.83% to 47.38%) and path search (6.44% to 24.94%). Notably, the lower ceiling of path search reveals its inherent difficulty, which we attribute to the demand for sophisticated spatial commonsense. Our results not only show a promising path forward but also quantify the immense challenge that remains in building MLLM agents that can be seamlessly integrated into everyday human life. --- ### Complexity Reduction Study Based on RD Costs Approximation for VVC Intra Partitioning Authors: M. E. A. Kherchouche, F. Galpin, T. Dumas, F. Schnitzler, D. Menard, L. Zhang Published: 2025-11-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.20349v1 In this paper, a complexity study is conducted for Versatile Video Codec (VVC) intra partitioning to accelerate the exhaustive search involved in Rate-Distortion Optimization (RDO) process. To address this problem, two main machine learning techniques are proposed and compared. Unlike existing methods, the proposed approaches are size independent and incorporate the Rate-Distortion (RD) costs of neighboring blocks as input features. The first method is a regression based technique that predicts normalized RD costs of a given Coding Unit (CU). As partitioning possesses the Markov property, the associated decision-making problem can be modeled as a Markov Decision Process (MDP) and solved by Reinforcement Learning (RL). The second approach is a RL agent learned from trajectories of CU decision across two depths with Deep Q-Network (DQN) algorithm. Then a pre-determined thresholds are applied for both methods to select a suitable split for the current CU. --- ### Material-informed Gaussian Splatting for 3D World Reconstruction in a Digital Twin Authors: Andy Huynh, João Malheiro Silva, Holger Caesar, Tong Duy Son Published: 2025-11-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.20348v3 3D reconstruction for Digital Twins often relies on LiDAR-based methods, which provide accurate geometry but lack the semantics and textures naturally captured by cameras. Traditional LiDAR-camera fusion approaches require complex calibration and still struggle with certain materials like glass, which are visible in images but poorly represented in point clouds. We propose a camera-only pipeline that reconstructs scenes using 3D Gaussian Splatting from multi-view images, extracts semantic material masks via vision models, converts Gaussian representations to mesh surfaces with projected material labels, and assigns physics-based material properties for accurate sensor simulation in modern graphics engines and simulators. This approach combines photorealistic reconstruction with physics-based material assignment, providing sensor simulation fidelity comparable to LiDAR-camera fusion while eliminating hardware complexity and calibration requirements. We validate our camera-only method using an internal dataset from an instrumented test vehicle, leveraging LiDAR as ground truth for reflectivity validation alongside image similarity metrics. --- ### Material-informed Gaussian Splatting for 3D World Reconstruction in a Digital Twin Authors: João Malheiro Silva, Andy Huynh, Tong Duy Son, Holger Caesar Published: 2025-11-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.20348v1 3D reconstruction for Digital Twins often relies on LiDAR-based methods, which provide accurate geometry but lack the semantics and textures naturally captured by cameras. Traditional LiDAR-camera fusion approaches require complex calibration and still struggle with certain materials like glass, which are visible in images but poorly represented in point clouds. We propose a camera-only pipeline that reconstructs scenes using 3D Gaussian Splatting from multi-view images, extracts semantic material masks via vision models, converts Gaussian representations to mesh surfaces with projected material labels, and assigns physics-based material properties for accurate sensor simulation in modern graphics engines and simulators. This approach combines photorealistic reconstruction with physics-based material assignment, providing sensor simulation fidelity comparable to LiDAR-camera fusion while eliminating hardware complexity and calibration requirements. We validate our camera-only method using an internal dataset from an instrumented test vehicle, leveraging LiDAR as ground truth for reflectivity validation alongside image similarity metrics. --- ### Soft Adaptive Policy Optimization Authors: Chang Gao, Chujie Zheng, Xiong-Hui Chen, Kai Dang, Shixuan Liu, Bowen Yu, An Yang, Shuai Bai, Jingren Zhou, Junyang Lin Published: 2025-11-25 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.20347v2 Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often exhibit high variance-a phenomenon exacerbated in Mixture-of-Experts models-leading to unstable updates. Existing group-based policy optimization methods, such as GSPO and GRPO, alleviate this problem via hard clipping, making it difficult to maintain both stability and effective learning. We propose Soft Adaptive Policy Optimization (SAPO), which replaces hard clipping with a smooth, temperature-controlled gate that adaptively attenuates off-policy updates while preserving useful learning signals. Compared with GSPO and GRPO, SAPO is both sequence-coherent and token-adaptive. Like GSPO, SAPO maintains sequence-level coherence, but its soft gating forms a continuous trust region that avoids the brittle hard clipping band used in GSPO. When a sequence contains a few highly off-policy tokens, GSPO suppresses all gradients for that sequence, whereas SAPO selectively down-weights only the offending tokens and preserves the learning signal from the near-on-policy ones, improving sample efficiency. Relative to GRPO, SAPO replaces hard token-level clipping with smooth, temperature-controlled scaling, enabling more informative and stable updates. Empirical results on mathematical reasoning benchmarks indicate that SAPO exhibits improved training stability and higher Pass@1 performance under comparable training budgets. Moreover, we employ SAPO to train the Qwen3-VL model series, demonstrating that SAPO yields consistent performance gains across diverse tasks and different model sizes. Overall, SAPO provides a more reliable, scalable, and effective optimization strategy for RL training of LLMs. --- ### Soft Adaptive Policy Optimization Authors: Chang Gao, Chujie Zheng, Xiong-Hui Chen, Kai Dang, Shixuan Liu, Bowen Yu, An Yang, Shuai Bai, Jingren Zhou, Junyang Lin Published: 2025-11-25 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.20347v1 Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often exhibit high variance-a phenomenon exacerbated in Mixture-of-Experts models-leading to unstable updates. Existing group-based policy optimization methods, such as GSPO and GRPO, alleviate this problem via hard clipping, making it difficult to maintain both stability and effective learning. We propose Soft Adaptive Policy Optimization (SAPO), which replaces hard clipping with a smooth, temperature-controlled gate that adaptively attenuates off-policy updates while preserving useful learning signals. Compared with GSPO and GRPO, SAPO is both sequence-coherent and token-adaptive. Like GSPO, SAPO maintains sequence-level coherence, but its soft gating forms a continuous trust region that avoids the brittle hard clipping band used in GSPO. When a sequence contains a few highly off-policy tokens, GSPO suppresses all gradients for that sequence, whereas SAPO selectively down-weights only the offending tokens and preserves the learning signal from the near-on-policy ones, improving sample efficiency. Relative to GRPO, SAPO replaces hard token-level clipping with smooth, temperature-controlled scaling, enabling more informative and stable updates. Empirical results on mathematical reasoning benchmarks indicate that SAPO exhibits improved training stability and higher Pass@1 performance under comparable training budgets. Moreover, we employ SAPO to train the Qwen3-VL model series, demonstrating that SAPO yields consistent performance gains across diverse tasks and different model sizes. Overall, SAPO provides a more reliable, scalable, and effective optimization strategy for RL training of LLMs. --- ### The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models Authors: Taewhoo Lee, Minju Song, Chanwoong Yoon, Jungwoo Park, Jaewoo Kang Published: 2025-11-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.20344v1 Analogical reasoning is at the core of human cognition, serving as an important foundation for a variety of intellectual activities. While prior work has shown that LLMs can represent task patterns and surface-level concepts, it remains unclear whether these models can encode high-level relational concepts and apply them to novel situations through structured comparisons. In this work, we explore this fundamental aspect using proportional and story analogies, and identify three key findings. First, LLMs effectively encode the underlying relationships between analogous entities; both attributive and relational information propagate through mid-upper layers in correct cases, whereas reasoning failures reflect missing relational information within these layers. Second, unlike humans, LLMs often struggle not only when relational information is missing, but also when attempting to apply it to new entities. In such cases, strategically patching hidden representations at critical token positions can facilitate information transfer to a certain extent. Lastly, successful analogical reasoning in LLMs is marked by strong structural alignment between analogous situations, whereas failures often reflect degraded or misplaced alignment. Overall, our findings reveal that LLMs exhibit emerging but limited capabilities in encoding and applying high-level relational concepts, highlighting both parallels and gaps with human cognition. --- ### AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend Authors: Hengyi Wang, Lourdes Agapito Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20343v1 We present AMB3R, a multi-view feed-forward model for dense 3D reconstruction on a metric-scale that addresses diverse 3D vision tasks. The key idea is to leverage a sparse, yet compact, volumetric scene representation as our backend, enabling geometric reasoning with spatial compactness. Although trained solely for multi-view reconstruction, we demonstrate that AMB3R can be seamlessly extended to uncalibrated visual odometry (online) or large-scale structure from motion without the need for task-specific fine-tuning or test-time optimization. Compared to prior pointmap-based models, our approach achieves state-of-the-art performance in camera pose, depth, and metric-scale estimation, 3D reconstruction, and even surpasses optimization-based SLAM and SfM methods with dense reconstruction priors on common benchmarks. --- ### Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios Authors: Luohe Shi, Zuchao Li, Lefei Zhang, Baoyuan Qi, Guoming Liu, Hai Zhao Published: 2025-11-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.20340v1 Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing power, then generate a complex and massive draft tree using a small autoregressive language model to improve overall prediction accuracy. However, methods like batching have been widely applied in mainstream model inference systems as a superior alternative to speculative decoding, as they compress the available idle computing power. Therefore, performing speculative decoding with low verification resources and low scheduling costs has become an important research problem. We believe that more capable models that allow for parallel generation on draft sequences are what we truly need. Recognizing the fundamental nature of draft models to only generate sequences of limited length, we propose SpecFormer, a novel architecture that integrates unidirectional and bidirectional attention mechanisms. SpecFormer combines the autoregressive model's ability to extract information from the entire input sequence with the parallel generation benefits of non-autoregressive models. This design eliminates the reliance on large prefix trees and achieves consistent acceleration, even in large-batch scenarios. Through lossless speculative decoding experiments across models of various scales, we demonstrate that SpecFormer sets a new standard for scaling LLM inference with lower training demands and reduced computational costs. --- ### ShelfRectNet: Single View Shelf Image Rectification with Homography Estimation Authors: Onur Berk Tore, Ibrahim Samil Yalciner, Server Calap Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20335v1 Estimating homography from a single image remains a challenging yet practically valuable task, particularly in domains like retail, where only one viewpoint is typically available for shelf monitoring and product alignment. In this paper, we present a deep learning framework that predicts a 4-point parameterized homography matrix to rectify shelf images captured from arbitrary angles. Our model leverages a ConvNeXt-based backbone for enhanced feature representation and adopts normalized coordinate regression for improved stability. To address data scarcity and promote generalization, we introduce a novel augmentation strategy by modeling and sampling synthetic homographies. Our method achieves a mean corner error of 1.298 pixels on the test set. When compared with both classical computer vision and deep learning-based approaches, our method demonstrates competitive performance in both accuracy and inference speed. Together, these results establish our approach as a robust and efficient solution for realworld single-view rectification. To encourage further research in this domain, we will make our dataset, ShelfRectSet, and code publicly available --- ### NNGPT: Rethinking AutoML with Large Language Models Authors: Roman Kochnev, Waleed Khalid, Tolgay Atinc Uzun, Xi Zhang, Yashkumar Sanjaybhai Dhameliya, Furui Qin, Chandini Vysyaraju, Raghuvir Duvvuri, Avi Goyal, Dmitry Ignatov, Radu Timofte Published: 2025-11-25 Categories: cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2511.20333v1 Building self-improving AI systems remains a fundamental challenge in the AI domain. We present NNGPT, an open-source framework that turns a large language model (LLM) into a self-improving AutoML engine for neural network development, primarily for computer vision. Unlike previous frameworks, NNGPT extends the dataset of neural networks by generating new models, enabling continuous fine-tuning of LLMs based on closed-loop system of generation, assessment, and self-improvement. It integrates within one unified workflow five synergistic LLM-based pipelines: zero-shot architecture synthesis, hyperparameter optimization (HPO), code-aware accuracy/early-stop prediction, retrieval-augmented synthesis of scope-closed PyTorch blocks (NN-RAG), and reinforcement learning. Built on the LEMUR dataset as an audited corpus with reproducible metrics, NNGPT emits from a single prompt and validates network architecture, preprocessing code, and hyperparameters, executes them end-to-end, and learns from result. The PyTorch adapter makes NNGPT framework-agnostic, enabling strong performance: NN-RAG achieves 73% executability on 1,289 targets, 3-shot prompting boosts accuracy on common datasets, and hash-based deduplication saves hundreds of runs. One-shot prediction matches search-based AutoML, reducing the need for numerous trials. HPO on LEMUR achieves RMSE 0.60, outperforming Optuna (0.64), while the code-aware predictor reaches RMSE 0.14 with Pearson r=0.78. The system has already generated over 5K validated models, proving NNGPT as an autonomous AutoML engine. Upon acceptance, the code, prompts, and checkpoints will be released for public access to enable reproducibility and facilitate community usage. --- ### 3D Motion Perception of Binocular Vision Target with PID-CNN Authors: Jiazhao Shi, Pan Pan, Haotian Shi Published: 2025-11-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.20332v3 This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception capability. Understood the ability of neural networks to fit nonlinear problems from the perspective of PID. Considered a single-layer neural network as using a second-order difference equation and a nonlinearity to describe a local problem. Multilayer networks gradually transform the raw representation to the desired representation through multiple such combinations. Analysed some reference principles for designing neural networks. Designed a relatively small PID convolutional neural network, with a total of 17 layers and 413 thousand parameters. Implemented a simple but practical feature reuse method by concatenation and pooling. The network was trained and tested using the simulated randomly moving ball datasets, and the experimental results showed that the prediction accuracy was close to the upper limit that the input image resolution can represent. Analysed the experimental results and errors, as well as the existing shortcomings and possible directions for improvement. Finally, discussed the advantages of high-dimensional convolution in improving computational efficiency and feature space utilization. As well as the potential advantages of using PID information to implement memory and attention mechanisms. --- ### 3D Motion Perception of Binocular Vision Target with PID-CNN Authors: Shi Jiazhao, Pan Pan, Shi Haotian Published: 2025-11-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.20332v1 This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception capability. Understood the ability of neural networks to fit nonlinear problems from the perspective of PID. Considered a single-layer neural network as using a second-order difference equation and a nonlinearity to describe a local problem. Multilayer networks gradually transform the raw representation to the desired representation through multiple such combinations. Analysed some reference principles for designing neural networks. Designed a relatively small PID convolutional neural network, with a total of 17 layers and 413 thousand parameters. Implemented a simple but practical feature reuse method by concatenation and pooling. The network was trained and tested using the simulated randomly moving ball datasets, and the experimental results showed that the prediction accuracy was close to the upper limit that the input image resolution can represent. Analysed the experimental results and errors, as well as the existing shortcomings and possible directions for improvement. Finally, discussed the advantages of high-dimensional convolution in improving computational efficiency and feature space utilization. As well as the potential advantages of using PID information to implement memory and attention mechanisms. --- ### ArtiBench and ArtiBrain: Benchmarking Generalizable Vision-Language Articulated Object Manipulation Authors: Yuhan Wu, Tiantian Wei, Shuo Wang, ZhiChao Wang, Yanyong Zhang, Daniel Cremers, Yan Xia Published: 2025-11-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.20330v2 Interactive articulated manipulation requires long-horizon, multi-step interactions with appliances while maintaining physical consistency. Existing vision-language and diffusion-based policies struggle to generalize across parts, instances, and categories. We first introduce ArtiBench, a five-level benchmark covering kitchen, storage, office, and tool environments. ArtiBench enables structured evaluation from cross-part and cross-instance variation to long-horizon multi-object tasks, revealing the core generalization challenges of articulated object manipulation. Building on this benchmark, we propose ArtiBrain, a modular framework that unifies high-level reasoning with adaptive low-level control. ArtiBrain uses a VLM-based Task Reasoner (GPT-4.1) to decompose and validate subgoals, and employs a Hybrid Controller that combines geometry-aware keyframe execution with affordance-guided diffusion for precise and interpretable manipulation. An Affordance Memory Bank continually accumulates successful execution episodes and propagates part-level actionable affordances to unseen articulated parts and configurations. Extensive experiments on ArtiBench show that our ArtiBrain significantly outperforms state-of-the-art multimodal and diffusion-based methods in robustness and generalization. Code and dataset will be released upon acceptance. --- ### ArtiBench and ArtiBrain: Benchmarking Generalizable Vision-Language Articulated Object Manipulation Authors: Yuhan Wu, Tiantian Wei, Shuo Wang, ZhiChao Wang, Yanyong Zhang, Daniel Cremers, Yan Xia Published: 2025-11-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.20330v1 Interactive articulated manipulation requires long-horizon, multi-step interactions with appliances while maintaining physical consistency. Existing vision-language and diffusion-based policies struggle to generalize across parts, instances, and categories. We first introduce ArtiBench, a five-level benchmark covering kitchen, storage, office, and tool environments. ArtiBench enables structured evaluation from cross-part and cross-instance variation to long-horizon multi-object tasks, revealing the core generalization challenges of articulated object manipulation. Building on this benchmark, we propose ArtiBrain, a modular framework that unifies high-level reasoning with adaptive low-level control. ArtiBrain uses a VLM-based Task Reasoner (GPT-4.1) to decompose and validate subgoals, and employs a Hybrid Controller that combines geometry-aware keyframe execution with affordance-guided diffusion for precise and interpretable manipulation. An Affordance Memory Bank continually accumulates successful execution episodes and propagates part-level actionable affordances to unseen articulated parts and configurations. Extensive experiments on ArtiBench show that our ArtiBrain significantly outperforms state-of-the-art multimodal and diffusion-based methods in robustness and generalization. Code and dataset will be released upon acceptance. --- ### MXtalTools: A Toolkit for Machine Learning on Molecular Crystals Authors: Michael Kilgour, Mark E. Tuckerman, Jutta Rogal Published: 2025-11-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.20327v1 We present MXtalTools, a flexible Python package for the data-driven modelling of molecular crystals, facilitating machine learning studies of the molecular solid state. MXtalTools comprises several classes of utilities: (1) synthesis, collation, and curation of molecule and crystal datasets, (2) integrated workflows for model training and inference, (3) crystal parameterization and representation, (4) crystal structure sampling and optimization, (5) end-to-end differentiable crystal sampling, construction and analysis. Our modular functions can be integrated into existing workflows or combined and used to build novel modelling pipelines. MXtalTools leverages CUDA acceleration to enable high-throughput crystal modelling. The Python code is available open-source on our GitHub page, with detailed documentation on ReadTheDocs. --- ### AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models Authors: Tianyi Yan, Tao Tang, Xingtai Gui, Yongkang Li, Jiasen Zhesng, Weiyao Huang, Lingdong Kong, Wencheng Han, Xia Zhou, Xueyang Zhang, Yifei Zhan, Kun Zhan et al. Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20325v3 End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail events. Reinforcement Learning (RL) offers a promising path to overcome these limitations, yet its success in autonomous driving has been elusive. We identify a fundamental flaw hindering this progress: a deep seated optimistic bias in the world models used for RL. To address this, we introduce a framework for post-training policy refinement built around an Impartial World Model. Our primary contribution is to teach this model to be honest about danger. We achieve this with a novel data synthesis pipeline, Counterfactual Synthesis, which systematically generates a rich curriculum of plausible collisions and off-road events. This transforms the model from a passive scene completer into a veridical forecaster that remains faithful to the causal link between actions and outcomes. We then integrate this Impartial World Model into our closed-loop RL framework, where it serves as an internal critic. During refinement, the agent queries the critic to ``dream" of the outcomes for candidate actions. We demonstrate through extensive experiments, including on a new Risk Foreseeing Benchmark, that our model significantly outperforms baselines in predicting failures. Consequently, when used as a critic, it enables a substantial reduction in safety violations in challenging simulations, proving that teaching a model to dream of danger is a critical step towards building truly safe and intelligent autonomous agents. --- ### AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models Authors: Tianyi Yan, Tao Tang, Xingtai Gui, Yongkang Li, Jiasen Zhesng, Weiyao Huang, Lingdong Kong, Wencheng Han, Xia Zhou, Xueyang Zhang, Yifei Zhan, Kun Zhan et al. Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20325v1 End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail events. Reinforcement Learning (RL) offers a promising path to overcome these limitations, yet its success in autonomous driving has been elusive. We identify a fundamental flaw hindering this progress: a deep seated optimistic bias in the world models used for RL. To address this, we introduce a framework for post-training policy refinement built around an Impartial World Model. Our primary contribution is to teach this model to be honest about danger. We achieve this with a novel data synthesis pipeline, Counterfactual Synthesis, which systematically generates a rich curriculum of plausible collisions and off-road events. This transforms the model from a passive scene completer into a veridical forecaster that remains faithful to the causal link between actions and outcomes. We then integrate this Impartial World Model into our closed-loop RL framework, where it serves as an internal critic. During refinement, the agent queries the critic to ``dream" of the outcomes for candidate actions. We demonstrate through extensive experiments, including on a new Risk Foreseeing Benchmark, that our model significantly outperforms baselines in predicting failures. Consequently, when used as a critic, it enables a substantial reduction in safety violations in challenging simulations, proving that teaching a model to dream of danger is a critical step towards building truly safe and intelligent autonomous agents. --- ### Modified Equations for Stochastic Optimization Authors: Stefan Perko Published: 2025-11-25 Categories: math.PR, math.NA, stat.ML arXiv: https://arxiv.org/abs/2511.20322v1 In this thesis, we extend the recently introduced theory of stochastic modified equations (SMEs) for stochastic gradient optimization algorithms. In Ch. 3 we study time-inhomogeneous SDEs driven by Brownian motion. For certain SDEs we prove a 1st and 2nd-order weak approximation properties, and we compute their linear error terms explicitly, under certain regularity conditions. In Ch. 4 we instantiate our results for SGD, working out the example of linear regression explicitly. We use this example to compare the linear error terms of gradient flow and two commonly used 1st-order SMEs for SGD in Ch. 5. In the second part of the thesis we introduce and study a novel diffusion approximation for SGD without replacement (SGDo) in the finite-data setting. In Ch. 6 we motivate and define the notion of an epoched Brownian motion (EBM). We argue that Young differential equations (YDEs) driven by EBMs serve as continuous-time models for SGDo for any shuffling scheme whose induced permutations converge to a det. permuton. Further, we prove a.s. convergence for these YDEs in the strongly convex setting. Moreover, we compute an upper asymptotic bound on the convergence rate which is as sharp as, or better than previous results for SGDo. In Ch. 7 we study scaling limits of families of random walks (RW) that share the same increments up to a random permutation. We show weak convergence under the assumption that the sequence of permutations converges to a det. (higher-dimensional) permuton. This permuton determines the covariance function of the limiting Gaussian process. Conversely, we show that every Gaussian process with a covariance function determined by a permuton in this way arises as a weak scaling limit of families of RW with shared increments. Finally, we apply our weak convergence theory to show that EBMs arise as scaling limits of RW with finitely many distinct increments. --- ### Active Inference in Discrete State Spaces from First Principles Authors: Patrick Kenny Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.20321v3 We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle. We show how the optimizations that need to be carried out in order to implement active inference in discrete state spaces can be formulated as constrained divergence minimization problems which can be solved by standard mean field methods that do not appeal to the idea of expected free energy. When it is used to model perception, the perception/action divergence criterion that we propose coincides with variational free energy. When it is used to model action, it differs from an expected free energy functional by an entropy regularizer. --- ### Active Inference in Discrete State Spaces from First Principles Authors: Patrick Kenny Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.20321v1 We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle. We show how the optimizations that need to be carried out in order to implement active inference in discrete state spaces can be formulated as constrained divergence minimization problems which can be solved by standard mean field methods that do not appeal to the idea of expected free energy. When it is used to model perception, the perception/action divergence criterion that we propose coincides with variational free energy. When it is used to model action, it differs from an expected free energy functional by an entropy regularizer. --- ### IrisNet: Infrared Image Status Awareness Meta Decoder for Infrared Small Targets Detection Authors: Xuelin Qian, Jiaming Lu, Zixuan Wang, Wenxuan Wang, Zhongling Huang, Dingwen Zhang, Junwei Han Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20319v1 Infrared Small Target Detection (IRSTD) faces significant challenges due to low signal-to-noise ratios, complex backgrounds, and the absence of discernible target features. While deep learning-based encoder-decoder frameworks have advanced the field, their static pattern learning suffers from pattern drift across diverse scenarios (\emph{e.g.}, day/night variations, sky/maritime/ground domains), limiting robustness. To address this, we propose IrisNet, a novel meta-learned framework that dynamically adapts detection strategies to the input infrared image status. Our approach establishes a dynamic mapping between infrared image features and entire decoder parameters via an image-to-decoder transformer. More concretely, we represent the parameterized decoder as a structured 2D tensor preserving hierarchical layer correlations and enable the transformer to model inter-layer dependencies through self-attention while generating adaptive decoding patterns via cross-attention. To further enhance the perception ability of infrared images, we integrate high-frequency components to supplement target-position and scene-edge information. Experiments on NUDT-SIRST, NUAA-SIRST, and IRSTD-1K datasets demonstrate the superiority of our IrisNet, achieving state-of-the-art performance. --- ### Geometry of Decision Making in Language Models Authors: Abhinav Joshi, Divyanshu Bhatt, Ashutosh Modi Published: 2025-11-25 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.20315v1 Large Language Models (LLMs) show strong generalization across diverse tasks, yet the internal decision-making processes behind their predictions remain opaque. In this work, we study the geometry of hidden representations in LLMs through the lens of \textit{intrinsic dimension} (ID), focusing specifically on decision-making dynamics in a multiple-choice question answering (MCQA) setting. We perform a large-scale study, with 28 open-weight transformer models and estimate ID across layers using multiple estimators, while also quantifying per-layer performance on MCQA tasks. Our findings reveal a consistent ID pattern across models: early layers operate on low-dimensional manifolds, middle layers expand this space, and later layers compress it again, converging to decision-relevant representations. Together, these results suggest LLMs implicitly learn to project linguistic inputs onto structured, low-dimensional manifolds aligned with task-specific decisions, providing new geometric insights into how generalization and reasoning emerge in language models. --- ### Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries Authors: Alexander Beiser, Flavio Martinelli, Wulfram Gerstner, Johanni Brea Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.20312v1 Network weights can be reverse-engineered given enough informative samples of a network's input-output function. In a teacher-student setup, this translates into collecting a dataset of the teacher mapping -- querying the teacher -- and fitting a student to imitate such mapping. A sensible choice of queries is the dataset the teacher is trained on. But current methods fail when the teacher parameters are more numerous than the training data, because the student overfits to the queries instead of aligning its parameters to the teacher. In this work, we explore augmentation techniques to best sample the input-output mapping of a teacher network, with the goal of eliciting a rich set of representations from the teacher hidden layers. We discover that standard augmentations such as rotation, flipping, and adding noise, bring little to no improvement to the identification problem. We design new data augmentation techniques tailored to better sample the representational space of the network's hidden layers. With our augmentations we extend the state-of-the-art range of recoverable network sizes. To test their scalability, we show that we can recover networks of up to 100 times more parameters than training data-points. --- ### TReFT: Taming Rectified Flow Models For One-Step Image Translation Authors: Shengqian Li, Ming Gao, Yi Liu, Zuzeng Lin, Feng Wang, Feng Dai Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20307v1 Rectified Flow (RF) models have advanced high-quality image and video synthesis via optimal transport theory. However, when applied to image-to-image translation, they still depend on costly multi-step denoising, hindering real-time applications. Although the recent adversarial training paradigm, CycleGAN-Turbo, works in pretrained diffusion models for one-step image translation, we find that directly applying it to RF models leads to severe convergence issues. In this paper, we analyze these challenges and propose TReFT, a novel method to Tame Rectified Flow models for one-step image Translation. Unlike previous works, TReFT directly uses the velocity predicted by pretrained DiT or UNet as output-a simple yet effective design that tackles the convergence issues under adversarial training with one-step inference. This design is mainly motivated by a novel observation that, near the end of the denoising process, the velocity predicted by pretrained RF models converges to the vector from origin to the final clean image, a property we further justify through theoretical analysis. When applying TReFT to large pretrained RF models such as SD3.5 and FLUX, we introduce memory-efficient latent cycle-consistency and identity losses during training, as well as lightweight architectural simplifications for faster inference. Pretrained RF models finetuned with TReFT achieve performance comparable to sota methods across multiple image translation datasets while enabling real-time inference. --- ### TaCo: Capturing Spatio-Temporal Semantic Consistency in Remote Sensing Change Detection Authors: Han Guo, Chenyang Liu, Haotian Zhang, Bowen Chen, Zhengxia Zou, Zhenwei Shi Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20306v1 Remote sensing change detection (RSCD) aims to identify surface changes across bi-temporal satellite images. Most previous methods rely solely on mask supervision, which effectively guides spatial localization but provides limited constraints on the temporal semantic transitions. Consequently, they often produce spatially coherent predictions while still suffering from unresolved semantic inconsistencies. To address this limitation, we propose TaCo, a spatio-temporal semantic consistent network, which enriches the existing mask-supervised framework with a spatio-temporal semantic joint constraint. TaCo conceptualizes change as a semantic transition between bi-temporal states, in which one temporal feature representation can be derived from the other via dedicated transition features. To realize this, we introduce a Text-guided Transition Generator that integrates textual semantics with bi-temporal visual features to construct the cross-temporal transition features. In addition, we propose a spatio-temporal semantic joint constraint consisting of bi-temporal reconstruct constraints and a transition constraint: the former enforces alignment between reconstructed and original features, while the latter enhances discrimination for changes. This design can yield substantial performance gains without introducing any additional computational overhead during inference. Extensive experiments on six public datasets, spanning both binary and semantic change detection tasks, demonstrate that TaCo consistently achieves SOTA performance. --- ### RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches Authors: Changpeng He, Yang Lu, Yanqing Xu, Chong-Yung Chi, Arumugam Nallanathan Published: 2025-11-25 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2511.20305v2 This paper investigates a reconfigurable intelligent surface (RIS)-assisted multi-waveguide pinching-antenna (PA) system (PASS) for multi-user downlink information transmission, motivated by the unknown impact of the integration of emerging PASS and RIS on wireless communications. First, we formulate sum rate (SR) and energy efficiency (EE) maximization problems in a unified framework, subject to constraints on the movable region of PAs, total power budget, and tunable phase of RIS elements. Then, by leveraging a graph-structured topology of the RIS-assisted PASS, a novel three-stage graph neural network (GNN) is proposed, which learns PA positions based on user locations, and RIS phase shifts according to composite channel conditions at the first two stages, respectively, and finally determines beamforming vectors. Specifically, the proposed GNN is achieved through unsupervised training, together with three implementation strategies for its integration with convex optimization, thus offering trade-offs between inference time and solution optimality. Extensive numerical results are provided to validate the effectiveness of the proposed GNN, and to support its unique attributes of viable generalization capability, good performance reliability, and real-time applicability. Moreover, the impact of key parameters on RIS-assisted PASS is illustrated and analyzed. --- ### RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches Authors: Changpeng He, Yang Lu, Yanqing Xu, Chong-Yung Chi, Bo Ai, Arumugam Nallanathan Published: 2025-11-25 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2511.20305v1 This paper investigates a reconfigurable intelligent surface (RIS)-assisted multi-waveguide pinching-antenna (PA) system (PASS) for multi-user downlink information transmission, motivated by the unknown impact of the integration of emerging PASS and RIS on wireless communications. First, we formulate sum rate (SR) and energy efficiency (EE) maximization problems in a unified framework, subject to constraints on the movable region of PAs, total power budget, and tunable phase of RIS elements. Then, by leveraging a graph-structured topology of the RIS-assisted PASS, a novel three-stage graph neural network (GNN) is proposed, which learns PA positions based on user locations, and RIS phase shifts according to composite channel conditions at the first two stages, respectively, and finally determines beamforming vectors. Specifically, the proposed GNN is achieved through unsupervised training, together with three implementation strategies for its integration with convex optimization, thus offering trade-offs between inference time and solution optimality. Extensive numerical results are provided to validate the effectiveness of the proposed GNN, and to support its unique attributes of viable generalization capability, good performance reliability, and real-time applicability. Moreover, the impact of key parameters on RIS-assisted PASS is illustrated and analyzed. --- ### CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation Authors: Shilei Cao, Ziyang Gong, Hehai Lin, Yang Liu, Jiashun Cheng, Xiaoxing Hu, Haoyuan Liang, Guowen Li, Chengwei Qin, Hong Cheng, Xue Yang, Juepeng Zheng et al. Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20302v3 In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstream tasks. However, existing specialized PEFT methods often fail when applied to large-scale Earth observation tasks, as they are unable to fully handle the multifaceted and unpredictable domain gaps (e.g., spatial, semantic, and frequency shifts) inherent in RS data. To overcome this, we propose CrossEarth-Gate, which introduces two primary contributions. First, we establish a comprehensive RS module toolbox to address multifaceted domain gaps, comprising spatial, semantic, and frequency modules. Second, we develop a Fisher-guided adaptive selection mechanism that operates on this toolbox. This selection is guided by Fisher Information to quantify each module's importance by measuring its contribution to the task-specific gradient flow. It dynamically activates only the most critical modules at the appropriate layers, guiding the gradient flow to maximize adaptation effectiveness and efficiency. Comprehensive experiments validate the efficacy and generalizability of our method, where CrossEarth-Gate achieves state-of-the-art performance on 16 out of 18 cross-domain benchmarks for RS semantic segmentation. --- ### CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation Authors: Shilei Cao, Ziyang Gong, Hehai Lin, Yang Liu, Jiashun Cheng, Xiaoxing Hu, Haoyuan Liang, Guowen Li, Chengwei Qin, Hong Cheng, Xue Yang, Juepeng Zheng et al. Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20302v1 In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstream tasks. However, existing specialized PEFT methods often fail when applied to large-scale Earth observation tasks, as they are unable to fully handle the multifaceted and unpredictable domain gaps (\eg, spatial, semantic, and frequency shifts) inherent in RS data. To overcome this, we propose CrossEarth-Gate, which introduces two primary contributions. First, we establish a comprehensive RS module toolbox to address multifaceted domain gaps, comprising spatial, semantic, and frequency modules. Second, we develop a Fisher-guided adaptive selection mechanism that operates on this toolbox. This selection is guided by Fisher Information to quantify each module's importance by measuring its contribution to the task-specific gradient flow. It dynamically activates only the most critical modules at the appropriate layers, guiding the gradient flow to maximize adaptation effectiveness and efficiency. Comprehensive experiments validate the efficacy and generalizability of our method, where CrossEarth-Gate achieves state-of-the-art performance across 16 cross-domain benchmarks for RS semantic segmentation. The code of the work will be released. --- ### Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge Authors: Shashank Kirtania, Param Biyani, Priyanshu Gupta, Yasharth Bajpai, Roshni Iyer, Sumit Gulwani, Gustavo Soares Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.20297v2 Large Language Model (LLM)-based agents are increasingly capable of complex, multi-step tasks such as GUI automation, tool use, and data manipulation, yet they cannot learn from experience: each new session rediscovers solutions from scratch. We introduce BREW (Bootstrapping expeRientially-learned Environmental knoWledge), a framework that distills an agent's past interaction trajectories into a structured, retrievable knowledge base (KB) of natural-language recipes, concept-level procedural documents that capture what to do, when it applies, and what to watch out for. Drawing on the principle of library learning from program synthesis, BREW decomposes agent memory into modular, concept-localized documents and formalizes KB construction as a state-space search problem. To navigate this space, we introduce Expand-and-Gather Monte Carlo Tree Search (EG-MCTS), a reward-guided algorithm that jointly optimizes recipe accuracy and retrievability across parallel, per-concept search trees. We further adapt hindsight relabeling to convert near-miss trajectories into positive demonstrations, surfacing latent agent competencies as reusable knowledge. On three domain-grounded benchmarks, OSWorld, tau^2-Bench, and SpreadSheetBench, BREW achieves 10-20% gains in task success and 10-15% fewer execution steps over base agents, while consistently outperforming existing memory-augmented baselines that can degrade below memoryless performance. The resulting KB is inspectable, modular, and extensible, providing a transparent and controllable substrate for agent optimization. --- ### Improving Language Agents through BREW Authors: Shashank Kirtania, Param Biyani, Priyanshu Gupta, Yasharth Bajpai, Roshni Iyer, Sumit Gulwani, Gustavo Soares Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.20297v1 Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation, such as data manipulation, multistep planning, and computer-use automation. However, despite their versatility, current training paradigms for model weight optimization methods, like PPO and GRPO, remain relatively impractical with their high computational overhead for rollout convergence. In addition, the resulting agent policies are difficult to interpret, adapt, or incrementally improve. To address this, we investigate creating and refining structured memory of experiential learning of an agent from its environment as an alternative route to agent optimization. We introduce BREW (Bootstrapping expeRientially-learned Environmental knoWledge), a framework for agent optimization for downstream tasks via KB construction and refinement. In our formulation, we introduce an effective method for partitioning agent memory for more efficient retrieval and refinement. BREW uses task graders and behavior rubrics to learn insights while leveraging state-space search for ensuring robustness from the noise and non-specificity in natural language. Empirical results on real world, domain-grounded benchmarks -- OSWorld, $τ^2$Bench, and SpreadsheetBench -- show BREW achieves $10-20\%$ improvement in task precision, $10-15\%$ reduction in API/tool calls leading to faster execution time, all while maintaining computational efficiency on par with base models. Unlike prior work where memory is treated as static context, we establish the KB as a modular and controllable substrate for agent optimization -- an explicit lever for shaping behavior in a transparent, interpretable, and extensible manner. --- ### Prompting Lipschitz-constrained network for multiple-in-one sparse-view CT reconstruction Authors: Baoshun Shi, Ke Jiang, Qiusheng Lian, Xinran Yu, Huazhu Fu Published: 2025-11-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.20296v1 Despite significant advancements in deep learning-based sparse-view computed tomography (SVCT) reconstruction algorithms, these methods still encounter two primary limitations: (i) It is challenging to explicitly prove that the prior networks of deep unfolding algorithms satisfy Lipschitz constraints due to their empirically designed nature. (ii) The substantial storage costs of training a separate model for each setting in the case of multiple views hinder practical clinical applications. To address these issues, we elaborate an explicitly provable Lipschitz-constrained network, dubbed LipNet, and integrate an explicit prompt module to provide discriminative knowledge of different sparse sampling settings, enabling the treatment of multiple sparse view configurations within a single model. Furthermore, we develop a storage-saving deep unfolding framework for multiple-in-one SVCT reconstruction, termed PromptCT, which embeds LipNet as its prior network to ensure the convergence of its corresponding iterative algorithm. In simulated and real data experiments, PromptCT outperforms benchmark reconstruction algorithms in multiple-in-one SVCT reconstruction, achieving higher-quality reconstructions with lower storage costs. On the theoretical side, we explicitly demonstrate that LipNet satisfies boundary property, further proving its Lipschitz continuity and subsequently analyzing the convergence of the proposed iterative algorithms. The data and code are publicly available at https://github.com/shibaoshun/PromptCT. --- ### Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations Authors: Chao Wang, Chengan Che, Xinyue Chen, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20295v2 Counterfactual explanations (CFEs) are minimal and semantically meaningful modifications of the input of a model that alter the model predictions. They highlight the decisive features the model relies on, providing contrastive interpretations for classifiers. State-of-the-art visual counterfactual explanation methods have primarily focused on interpreting image classifiers, leaving the domain of video models relatively underexplored. For the video CFEs to be useful, they have to be physically plausible, temporally coherent, and exhibit smooth motion trajectories. Existing CFE image-based methods, designed to explain image classifiers, lack the capacity to generate temporally coherent, smooth and physically plausible video CFEs. To address this, we propose Back To The Feature (BTTF), an optimization framework that generates video CFEs. Our method introduces two novel features, 1) an optimization scheme to retrieve the initial latent noise conditioned by the first frame of the input video, 2) a two-stage optimization strategy to enable the search for counterfactual videos in the vicinity of the input video. Both optimization processes are guided solely by the target classifier, ensuring the explanation is faithful. To accelerate convergence, we also introduce a progressive optimization strategy that incrementally increases the number of denoising steps. Extensive experiments on video datasets such as Shape-Moving (motion classification), MEAD (emotion classification), and NTU RGB+D (action classification) show that our BTTF effectively generates valid, visually similar and realistic counterfactual videos that provide concrete insights into the classifier's decision-making mechanism. --- ### Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations Authors: Chao Wang, Chengan Che, Xinyue Chen, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20295v1 Counterfactual explanations (CFEs) are minimal and semantically meaningful modifications of the input of a model that alter the model predictions. They highlight the decisive features the model relies on, providing contrastive interpretations for classifiers. State-of-the-art visual counterfactual explanation methods are designed to explain image classifiers. The generation of CFEs for video classifiers remains largely underexplored. For the counterfactual videos to be useful, they have to be physically plausible, temporally coherent, and exhibit smooth motion trajectories. Existing CFE image-based methods, designed to explain image classifiers, lack the capacity to generate temporally coherent, smooth and physically plausible video CFEs. To address this, we propose Back To The Feature (BTTF), an optimization framework that generates video CFEs. Our method introduces two novel features, 1) an optimization scheme to retrieve the initial latent noise conditioned by the first frame of the input video, 2) a two-stage optimization strategy to enable the search for counterfactual videos in the vicinity of the input video. Both optimization processes are guided solely by the target classifier, ensuring the explanation is faithful. To accelerate convergence, we also introduce a progressive optimization strategy that incrementally increases the number of denoising steps. Extensive experiments on video datasets such as Shape-Moving (motion classification), MEAD (emotion classification), and NTU RGB+D (action classification) show that our BTTF effectively generates valid, visually similar and realistic counterfactual videos that provide concrete insights into the classifier's decision-making mechanism. --- ### Forgetting by Pruning: Data Deletion in Join Cardinality Estimation Authors: Chaowei He, Yuanjun Liu, Qingzhi Ma, Shenyuan Ren, Xizhao Luo, Lei Zhao, An Liu Published: 2025-11-25 Categories: cs.DB, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.20293v1 Machine unlearning in learned cardinality estimation (CE) systems presents unique challenges due to the complex distributional dependencies in multi-table relational data. Specifically, data deletion, a core component of machine unlearning, faces three critical challenges in learned CE models: attribute-level sensitivity, inter-table propagation and domain disappearance leading to severe overestimation in multi-way joins. We propose Cardinality Estimation Pruning (CEP), the first unlearning framework specifically designed for multi-table learned CE systems. CEP introduces Distribution Sensitivity Pruning, which constructs semi-join deletion results and computes sensitivity scores to guide parameter pruning, and Domain Pruning, which removes support for value domains entirely eliminated by deletion. We evaluate CEP on state-of-the-art architectures NeuroCard and FACE across IMDB and TPC-H datasets. Results demonstrate CEP consistently achieves the lowest Q-error in multi-table scenarios, particularly under high deletion ratios, often outperforming full retraining. Furthermore, CEP significantly reduces convergence iterations, incurring negligible computational overhead of 0.3%-2.5% of fine-tuning time. --- ### Schema Matching on Graph: Iterative Graph Exploration for Efficient and Explainable Data Integration Authors: Mingyu Jeon, Jaeyoung Suh, Suwan Cho Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.20285v2 Schema matching is a critical task in data integration, particularly in the medical domain where disparate Electronic Health Record (EHR) systems must be aligned to standard models like OMOP CDM. While Large Language Models (LLMs) have shown promise in schema matching, they suffer from hallucination and lack of up-to-date domain knowledge. Knowledge Graphs (KGs) offer a solution by providing structured, verifiable knowledge. However, existing KG-augmented LLM approaches often rely on inefficient complex multi-hop queries or storage-intensive vector-based retrieval methods. This paper introduces SMoG (Schema Matching on Graph), a novel framework that leverages iterative execution of simple 1-hop SPARQL queries, inspired by successful strategies in Knowledge Graph Question Answering (KGQA). SMoG enhances explainability and reliability by generating human-verifiable query paths while significantly reducing storage requirements by directly querying SPARQL endpoints. Experimental results on real-world medical datasets demonstrate that SMoG achieves performance comparable to state-of-the-art baselines, validating its effectiveness and efficiency in KG-augmented schema matching. --- ### SMoG: Schema Matching on Graph Authors: Mingyu Jeon, Jaeyoung Suh, Suwan Cho Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.20285v1 Schema matching is a critical task in data integration, par- ticularly in the medical domain where disparate Electronic Health Record (EHR) systems must be aligned to standard models like OMOP CDM. While Large Language Models (LLMs) have shown promise in schema matching, they suf- fer from hallucination and lack of up-to-date domain knowl- edge. Knowledge Graphs (KGs) offer a solution by pro- viding structured, verifiable knowledge. However, existing KG-augmented LLM approaches often rely on inefficient complex multi-hop queries or storage-intensive vector-based retrieval methods. This paper introduces SMoG (Schema Matching on Graph), a novel framework that leverages iter- ative execution of simple 1-hop SPARQL queries, inspired by successful strategies in Knowledge Graph Question An- swering (KGQA). SMoG enhances explainability and relia- bility by generating human-verifiable query paths while sig- nificantly reducing storage requirements by directly querying SPARQL endpoints. Experimental results on real-world med- ical datasets demonstrate that SMoG achieves performance comparable to state-of-the-art baselines, validating its effec- tiveness and efficiency in KG-augmented schema matching. --- ### Can LLMs Make (Personalized) Access Control Decisions? Authors: Friederike Groschupp, Daniele Lain, Aritra Dhar, Lara Magdalena Lazier, Srdjan Čapkun Published: 2025-11-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.20284v2 Precise access control decisions are crucial for the security of both traditional applications and emerging agent-based systems. Typically, these decisions are made by users during app installation or at runtime. However, due to the increasing complexity and automation of systems, making access control decisions can impose a significant cognitive burden on users, often overwhelming them and leading to suboptimal or even arbitrary choices. To address this problem, we investigate the ability of LLMs to make dynamic, context-aware decisions aligned with users' security preferences, expressed during a lightweight setup phase. As a case study, we analyze smartphone application permission requests, given their ubiquity and users' familiarity with them. We curated a dataset comprising 307 user privacy statements (short, natural-language descriptions of user preferences) and 14,682 corresponding permission decisions, gathered from smartphone users in an online data collection. We compare these decisions with those made by two versions of LLMs that are tasked with reasoning about the app and the request context: a general model and a personalized one (which incorporates user preferences). For the latter, we also collected user feedback on 1,298 of its decisions. Our results show that LLMs generally reflect users' preferences well, agreeing with the majority decision in up to 86% of cases, and can steer users toward safer behavior. However, the results also reveal a key trade-off in personalization: while incorporating user-specific privacy preferences improves agreement with individual decisions, strict adherence to these preferences may lead to less safe outcomes, as users tend to over-permission. --- ### Can LLMs Make (Personalized) Access Control Decisions? Authors: Friederike Groschupp, Daniele Lain, Aritra Dhar, Lara Magdalena Lazier, Srdjan Čapkun Published: 2025-11-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.20284v1 Precise access control decisions are crucial to the security of both traditional applications and emerging agent-based systems. Typically, these decisions are made by users during app installation or at runtime. Due to the increasing complexity and automation of systems, making these access control decisions can add a significant cognitive load on users, often overloading them and leading to suboptimal or even arbitrary access control decisions. To address this problem, we propose to leverage the processing and reasoning capabilities of large language models (LLMs) to make dynamic, context-aware decisions aligned with the user's security preferences. For this purpose, we conducted a user study, which resulted in a dataset of 307 natural-language privacy statements and 14,682 access control decisions made by users. We then compare these decisions against those made by two versions of LLMs: a general and a personalized one, for which we also gathered user feedback on 1,446 of its decisions. Our results show that in general, LLMs can reflect users' preferences well, achieving up to 86\% accuracy when compared to the decision made by the majority of users. Our study also reveals a crucial trade-off in personalizing such a system: while providing user-specific privacy preferences to the LLM generally improves agreement with individual user decisions, adhering to those preferences can also violate some security best practices. Based on our findings, we discuss design and risk considerations for implementing a practical natural-language-based access control system that balances personalization, security, and utility. --- ### Solving Heterogeneous Agent Models with Physics-informed Neural Networks Authors: Marta Grzeskiewicz Published: 2025-11-25 Categories: econ.GN, cs.LG arXiv: https://arxiv.org/abs/2511.20283v1 Understanding household behaviour is essential for modelling macroeconomic dynamics and designing effective policy. While heterogeneous agent models offer a more realistic alternative to representative agent frameworks, their implementation poses significant computational challenges, particularly in continuous time. The Aiyagari-Bewley-Huggett (ABH) framework, recast as a system of partial differential equations, typically relies on grid-based solvers that suffer from the curse of dimensionality, high computational cost, and numerical inaccuracies. This paper introduces the ABH-PINN solver, an approach based on Physics-Informed Neural Networks (PINNs), which embeds the Hamilton-Jacobi-Bellman and Kolmogorov Forward equations directly into the neural network training objective. By replacing grid-based approximation with mesh-free, differentiable function learning, the ABH-PINN solver benefits from the advantages of PINNs of improved scalability, smoother solutions, and computational efficiency. Preliminary results show that the PINN-based approach is able to obtain economically valid results matching the established finite-difference solvers. --- ### Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement Authors: Yang Liu, Xilin Zhao, Peisong Wen, Siran Dai, Qingming Huang Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20280v1 Recent progress in video generation has led to impressive visual quality, yet current models still struggle to produce results that align with real-world physical principles. To this end, we propose an iterative self-refinement framework that leverages large language models and vision-language models to provide physics-aware guidance for video generation. Specifically, we introduce a multimodal chain-of-thought (MM-CoT) process that refines prompts based on feedback from physical inconsistencies, progressively enhancing generation quality. This method is training-free and plug-and-play, making it readily applicable to a wide range of video generation models. Experiments on the PhyIQ benchmark show that our method improves the Physics-IQ score from 56.31 to 62.38. We hope this work serves as a preliminary exploration of physics-consistent video generation and may offer insights for future research. --- ### SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors Authors: Fabian Gülhan, Emil Mededovic, Yuli Wu, Johannes Stegmaier Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20279v3 End-to-end transformer architectures have driven significant progress in multi-object tracking by unifying detection and association into a single, heuristic-free framework. Despite these benefits, poor detection performance and the inherent conflict between detection and association in a joint architecture remain critical concerns. Recent approaches aim to mitigate these issues by employing advanced denoising or label assignment strategies, or by incorporating detection priors from external object detectors. In this paper, we propose SelfMOTR, a simple yet highly effective detector-free alternative that decouples proposal discovery from association using self-generated internal detection priors. Through extensive analysis and ablation studies, we show that end-to-end transformer trackers with joint detection-association decoding retain substantial hidden detection capacity, and we provide a practical detector-free mechanism for leveraging it. To shed light on these joint decoding dynamics, we draw inspiration from attention sink analyses in large language models, leveraging Track Attention Mass to show that standard generic queries exhibit unbalanced attention, frequently struggling to weigh track context against novel object discovery. SelfMOTR achieves highly competitive performance in complex, dynamic environments, yielding 69.2 HOTA on DanceTrack and leading with 71.1 HOTA on the Bird Flock Tracking (BFT) dataset. Project page: https://medem23.github.io/SM --- ### SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors Authors: Fabian Gülhan, Emil Mededovic, Yuli Wu, Johannes Stegmaier Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20279v1 Despite progress toward end-to-end tracking with transformer architectures, poor detection performance and the conflict between detection and association in a joint architecture remain critical concerns. Recent approaches aim to mitigate these issues by (i) employing advanced denoising or label assignment strategies, or (ii) incorporating detection priors from external object detectors via distillation or anchor proposal techniques. Inspired by the success of integrating detection priors and by the key insight that MOTR-like models are secretly strong detection models, we introduce SelfMOTR, a novel tracking transformer that relies on self-generated detection priors. Through extensive analysis and ablation studies, we uncover and demonstrate the hidden detection capabilities of MOTR-like models, and present a practical set of tools for leveraging them effectively. On DanceTrack, SelfMOTR achieves strong performance, competing with recent state-of-the-art end-to-end tracking methods. --- ### DAPointMamba: Domain Adaptive Point Mamba for Point Cloud Completion Authors: Yinghui Li, Qianyu Zhou, Di Shao, Hao Yang, Ye Zhu, Richard Dazeley, Xuequan Lu Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20278v1 Domain adaptive point cloud completion (DA PCC) aims to narrow the geometric and semantic discrepancies between the labeled source and unlabeled target domains. Existing methods either suffer from limited receptive fields or quadratic complexity due to using CNNs or vision Transformers. In this paper, we present the first work that studies the adaptability of State Space Models (SSMs) in DA PCC and find that directly applying SSMs to DA PCC will encounter several challenges: directly serializing 3D point clouds into 1D sequences often disrupts the spatial topology and local geometric features of the target domain. Besides, the overlook of designs in the learning domain-agnostic representations hinders the adaptation performance. To address these issues, we propose a novel framework, DAPointMamba for DA PCC, that exhibits strong adaptability across domains and has the advantages of global receptive fields and efficient linear complexity. It has three novel modules. In particular, Cross-Domain Patch-Level Scanning introduces patch-level geometric correspondences, enabling effective local alignment. Cross-Domain Spatial SSM Alignment further strengthens spatial consistency by modulating patch features based on cross-domain similarity, effectively mitigating fine-grained structural discrepancies. Cross-Domain Channel SSM Alignment actively addresses global semantic gaps by interleaving and aligning feature channels. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our DAPointMamba outperforms state-of-the-art methods with less computational complexity and inference latency. --- ### HVAdam: A Full-Dimension Adaptive Optimizer Authors: Yiheng Zhang, Shaowu Wu, Yuanzhuo Xu, Jiajun Wu, Shang Xu, Steve Drew, Xiaoguang Niu Published: 2025-11-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.20277v2 Adaptive optimizers such as Adam have achieved great success in training large-scale models like large language models and diffusion models. However, they often generalize worse than non-adaptive methods, such as SGD on classical architectures like CNNs. We identify a key cause of this performance gap: adaptivity in pre-conditioners, which limits the optimizer's ability to adapt to diverse optimization landscapes. To address this, we propose Anon (Adaptivity Non-restricted Optimizer with Novel convergence technique), a novel optimizer with continuously tunable adaptivity , allowing it to interpolate between SGD-like and Adam-like behaviors and even extrapolate beyond both. To ensure convergence across the entire adaptivity spectrum, we introduce incremental delay update (IDU), a novel mechanism that is more flexible than AMSGrad's hard max-tracking strategy and enhances robustness to gradient noise. We theoretically establish convergence guarantees under both convex and non-convex settings. Empirically, Anon consistently outperforms state-of-the-art optimizers on representative image classification, diffusion, and language modeling tasks. These results demonstrate that adaptivity can serve as a valuable tunable design principle, and Anon provides the first unified and reliable framework capable of bridging the gap between classical and modern optimizers and surpassing their advantageous properties. --- ### HVAdam: A Full-Dimension Adaptive Optimizer Authors: Yiheng Zhang, Shaowu Wu, Yuanzhuo Xu, Jiajun Wu, Shang Xu, Steve Drew, Xiaoguang Niu Published: 2025-11-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.20277v1 Adaptive optimizers such as Adam have achieved great success in training large-scale models like large language models and diffusion models. However, they often generalize worse than non-adaptive methods, such as SGD on classical architectures like CNNs. We identify a key cause of this performance gap: adaptivity in pre-conditioners, which limits the optimizer's ability to adapt to diverse optimization landscapes. To address this, we propose Anon (Adaptivity Non-restricted Optimizer with Novel convergence technique), a novel optimizer with continuously tunable adaptivity , allowing it to interpolate between SGD-like and Adam-like behaviors and even extrapolate beyond both. To ensure convergence across the entire adaptivity spectrum, we introduce incremental delay update (IDU), a novel mechanism that is more flexible than AMSGrad's hard max-tracking strategy and enhances robustness to gradient noise. We theoretically establish convergence guarantees under both convex and non-convex settings. Empirically, Anon consistently outperforms state-of-the-art optimizers on representative image classification, diffusion, and language modeling tasks. These results demonstrate that adaptivity can serve as a valuable tunable design principle, and Anon provides the first unified and reliable framework capable of bridging the gap between classical and modern optimizers and surpassing their advantageous properties. --- ### SCLARO: A Dataset for Grounded Scenario-Level Scene Understanding and ScenarioCLIP for Benchmarking Authors: Advik Sinha, Saurabh Atreya, Aashutosh A, Sk Aziz Ali, Abhijit Das Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20274v2 In the paradigm of computer vision-based precise real-world scene understanding, joint reasoning in terms of contextual understanding about the objects present in a scene, their inter-object relations, and the action being performed is an essential prerequisite. However, prior works have not addressed all three jointly, and no large-scale dataset provides grounded annotations at all three levels across diverse visual scenarios. Hence, this work introduces the SCLARO (Scene-Contextual Localisation of Actions, Relations & Objects) dataset, consisting of 615,805 images spanning indoor, outdoor, and driving scenarios, annotated with global action captions, object bounding boxes, and relation triplets that supply structured scene context beyond a free-text caption. To benchmark the dataset, we propose ScenarioCLIP, a tri-level reference model that jointly encodes global scene context, objects, and inter-object relations using disentangled encoders and EMA-based knowledge distillation. We benchmark across a comprehensive suite of tasks on the SCLARO Dataset, namely zero-shot retrieval, linear probe, object detection, predicate classification, scene-graph classification, and out-of-domain generalisation. ScenarioCLIP's disentangled encoders improve over the previous works, such as PyramidCLIP's shared encoder, most notably at the object and relation levels and on out-of-domain generalisation. Code for the data generation pipeline and ScenarioCLIP is available at https://github.com/scenario-clip/SCLARO-ScenarioCLIP --- ### ScenarioCLIP: Pretrained Transferable Visual Language Models and Action-Genome Dataset for Natural Scene Analysis Authors: Advik Sinha, Saurabh Atreya, Aashutosh A, Sk Aziz Ali, Abhijit Das Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.20274v1 Until recently, the general corpus of CLIP-type fundamental models has widely explored either the retrieval of short descriptions or the classification of objects in the scene as SINGLE-object image classification task. The same holds for retrieving the image embedding (image retrieval task) given a text prompt. However, real-world scene images exhibit rich compositional structure involving multiple objects and actions. The latest methods in the CLIP-based literature improve class-level discrimination by mining harder negative image-text pairs and by refining permanent text prompts, often using LLMs. However, these improvements remain confined to predefined class lists and do not explicitly model relational or compositional structure. PyramidCLIP partially addresses this gap by aligning global and local visual features, yet it still lacks explicit modeling of inter-object relations. Hence, to further leverage this aspect for scene analysis, the proposed ScenarioCLIP model accepts input texts, grounded relations, and input images, along with focused regions highlighting relations. The proposed model is pretrained on curated scenario data, and finetuned for specialized downstream tasks, such as cross-modal retrieval and fine-grained visual understanding tasks. To address the lack of domain-specific datasets, we generate a novel dataset by extending image-text pairs from existing diverse indoor and outdoor scenario datasets that are publicly available. We used a pipeline of existing language models to ground action, object, and relations, filled by manual and automatic curation. We established a comprehensive benchmark for several scenario-based tasks and compared it with many baseline methods. ScenarioCLIP demonstrates robust zero-shot and finetune performance on various domain-specific tasks. Our code and dataset are available at https://github.com/scenario-clip/ScenarioCLIP ---