# Research Papers — 2025-11 · bundle page 142 of 197 > Full-text markdown of papers #7051–7100 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/142 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/141.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/143.md) ### Learning Sparse Label Couplings for Multilabel Chest X-Ray Diagnosis Authors: Utkarsh Prakash Srivastava, Kaushik Gupta, Kaushik Nath Published: 2025-11-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.07801v1 We study multilabel classification of chest X-rays and present a simple, strong pipeline built on SE-ResNeXt101 $(32 \times 4d)$. The backbone is finetuned for 14 thoracic findings with a sigmoid head, trained using Multilabel Iterative Stratification (MIS) for robust cross-validation splits that preserve label co-occurrence. To address extreme class imbalance and asymmetric error costs, we optimize with Asymmetric Loss, employ mixed-precision (AMP), cosine learning-rate decay with warm-up, gradient clipping, and an exponential moving average (EMA) of weights. We propose a lightweight Label-Graph Refinement module placed after the classifier: given per-label probabilities, it learns a sparse, trainable inter-label coupling matrix that refines logits via a single message-passing step while adding only an L1-regularized parameter head. At inference, we apply horizontal flip test-time augmentation (TTA) and average predictions across MIS folds (a compact deep ensemble). Evaluation uses macro AUC averaging classwise ROC-AUC and skipping single-class labels in a fold to reflect balanced performance across conditions. On our dataset, a strong SE-ResNeXt101 baseline attains competitive macro AUC (e.g., 92.64% in our runs). Adding the Label-Graph Refinement consistently improves validation macro AUC across folds with negligible compute. The resulting method is reproducible, hardware-friendly, and requires no extra annotations, offering a practical route to stronger multilabel CXR classifiers. --- ### From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory Authors: Siyu Xia, Zekun Xu, Jiajun Chai, Wentian Fan, Yan Song, Xiaohan Wang, Guojun Yin, Wei Lin, Haifeng Zhang, Jun Wang Published: 2025-11-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.07800v1 Large Language Models (LLMs) based agents have demonstrated remarkable potential in autonomous task-solving across complex, open-ended environments. A promising approach for improving the reasoning capabilities of LLM agents is to better utilize prior experiences in guiding current decisions. However, LLMs acquire experience either through implicit memory via training, which suffers from catastrophic forgetting and limited interpretability, or explicit memory via prompting, which lacks adaptability. In this paper, we introduce a novel agent-centric, trainable, multi-layered graph memory framework and evaluate how context memory enhances the ability of LLMs to utilize parametric information. The graph abstracts raw agent trajectories into structured decision paths in a state machine and further distills them into high-level, human-interpretable strategic meta-cognition. In order to make memory adaptable, we propose a reinforcement-based weight optimization procedure that estimates the empirical utility of each meta-cognition based on reward feedback from downstream tasks. These optimized strategies are then dynamically integrated into the LLM agent's training loop through meta-cognitive prompting. Empirically, the learnable graph memory delivers robust generalization, improves LLM agents' strategic reasoning performance, and provides consistent benefits during Reinforcement Learning (RL) training. --- ### Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation Authors: Runmin Cong, Anpeng Wang, Bin Wan, Cong Zhang, Xiaofei Zhou, Wei Zhang Published: 2025-11-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.07798v1 Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adaptation to new domains. To address this issue, we propose a Divide-and-Conquer Decoupled Network (DCDNet). In the training stage, to tackle feature entanglement that impedes cross-domain generalization and rapid adaptation, we propose the Adversarial-Contrastive Feature Decomposition (ACFD) module. It decouples backbone features into category-relevant private and domain-relevant shared representations via contrastive learning and adversarial learning. Then, to mitigate the potential degradation caused by the disentanglement, the Matrix-Guided Dynamic Fusion (MGDF) module adaptively integrates base, shared, and private features under spatial guidance, maintaining structural coherence. In addition, in the fine-tuning stage, to enhanced model generalization, the Cross-Adaptive Modulation (CAM) module is placed before the MGDF, where shared features guide private features via modulation ensuring effective integration of domain-relevant information. Extensive experiments on four challenging datasets show that DCDNet outperforms existing CD-FSS methods, setting a new state-of-the-art for cross-domain generalization and few-shot adaptation. --- ### Design, Results and Industry Implications of the World's First Insurance Large Language Model Evaluation Benchmark Authors: Hua Zhou, Bing Ma, Yufei Zhang, Yi Zhao Published: 2025-11-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.07794v1 This paper comprehensively elaborates on the construction methodology, multi-dimensional evaluation system, and underlying design philosophy of CUFEInse v1.0. Adhering to the principles of "quantitative-oriented, expert-driven, and multi-validation," the benchmark establishes an evaluation framework covering 5 core dimensions, 54 sub-indicators, and 14,430 high-quality questions, encompassing insurance theoretical knowledge, industry understanding, safety and compliance, intelligent agent application, and logical rigor. Based on this benchmark, a comprehensive evaluation was conducted on 11 mainstream large language models. The evaluation results reveal that general-purpose models suffer from common bottlenecks such as weak actuarial capabilities and inadequate compliance adaptation. High-quality domain-specific training demonstrates significant advantages in insurance vertical scenarios but exhibits shortcomings in business adaptation and compliance. The evaluation also accurately identifies the common bottlenecks of current large models in professional scenarios such as insurance actuarial, underwriting and claim settlement reasoning, and compliant marketing copywriting. The establishment of CUFEInse not only fills the gap in professional evaluation benchmarks for the insurance field, providing academia and industry with a professional, systematic, and authoritative evaluation tool, but also its construction concept and methodology offer important references for the evaluation paradigm of large models in vertical fields, serving as an authoritative reference for academic model optimization and industrial model selection. Finally, the paper looks forward to the future iteration direction of the evaluation benchmark and the core development direction of "domain adaptation + reasoning enhancement" for insurance large models. --- ### HybridGuard: Enhancing Minority-Class Intrusion Detection in Dew-Enabled Edge-of-Things Networks Authors: Binayak Kara, Ujjwal Sahua, Ciza Thomas, Jyoti Prakash Sahoo Published: 2025-11-11 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.07793v1 Securing Dew-Enabled Edge-of-Things (EoT) networks against sophisticated intrusions is a critical challenge. This paper presents HybridGuard, a framework that integrates machine learning and deep learning to improve intrusion detection. HybridGuard addresses data imbalance through mutual information based feature selection, ensuring that the most relevant features are used to improve detection performance, especially for minority attack classes. The framework leverages Wasserstein Conditional Generative Adversarial Networks with Gradient Penalty (WCGAN-GP) to further reduce class imbalance and enhance detection precision. It adopts a two-phase architecture called DualNetShield to support advanced traffic analysis and anomaly detection, improving the granular identification of threats in complex EoT environments. HybridGuard is evaluated on the UNSW-NB15, CIC-IDS-2017, and IOTID20 datasets, where it demonstrates strong performance across diverse attack scenarios and outperforms existing solutions in adapting to evolving cybersecurity threats. This approach establishes HybridGuard as an effective tool for protecting EoT networks against modern intrusions. --- ### CC30k: A Citation Contexts Dataset for Reproducibility-Oriented Sentiment Analysis Authors: Rochana R. Obadage, Sarah M. Rajtmajer, Jian Wu Published: 2025-11-11 Categories: cs.DL, cs.CL arXiv: https://arxiv.org/abs/2511.07790v1 Sentiments about the reproducibility of cited papers in downstream literature offer community perspectives and have shown as a promising signal of the actual reproducibility of published findings. To train effective models to effectively predict reproducibility-oriented sentiments and further systematically study their correlation with reproducibility, we introduce the CC30k dataset, comprising a total of 30,734 citation contexts in machine learning papers. Each citation context is labeled with one of three reproducibility-oriented sentiment labels: Positive, Negative, or Neutral, reflecting the cited paper's perceived reproducibility or replicability. Of these, 25,829 are labeled through crowdsourcing, supplemented with negatives generated through a controlled pipeline to counter the scarcity of negative labels. Unlike traditional sentiment analysis datasets, CC30k focuses on reproducibility-oriented sentiments, addressing a research gap in resources for computational reproducibility studies. The dataset was created through a pipeline that includes robust data cleansing, careful crowd selection, and thorough validation. The resulting dataset achieves a labeling accuracy of 94%. We then demonstrated that the performance of three large language models significantly improves on the reproducibility-oriented sentiment classification after fine-tuning using our dataset. The dataset lays the foundation for large-scale assessments of the reproducibility of machine learning papers. The CC30k dataset and the Jupyter notebooks used to produce and analyze the dataset are publicly available at https://github.com/lamps-lab/CC30k . --- ### Physical Consistency of Aurora's Encoder: A Quantitative Study Authors: Benjamin Richards, Pushpa Kumar Balan Published: 2025-11-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.07787v1 The high accuracy of large-scale weather forecasting models like Aurora is often accompanied by a lack of transparency, as their internal representations remain largely opaque. This "black box" nature hinders their adoption in high-stakes operational settings. In this work, we probe the physical consistency of Aurora's encoder by investigating whether its latent representations align with known physical and meteorological concepts. Using a large-scale dataset of embeddings, we train linear classifiers to identify three distinct concepts: the fundamental land-sea boundary, high-impact extreme temperature events, and atmospheric instability. Our findings provide quantitative evidence that Aurora learns physically consistent features, while also highlighting its limitations in capturing the rarest events. This work underscores the critical need for interpretability methods to validate and build trust in the next generation of Al-driven weather models. --- ### A Closed-Form Framework for Schrödinger Bridges Between Arbitrary Densities Authors: Hanwen Huang Published: 2025-11-11 Categories: stat.CO, stat.ML arXiv: https://arxiv.org/abs/2511.07786v2 Score-based generative models have recently attracted significant attention for their ability to generate high-fidelity data by learning maps from simple Gaussian priors to complex data distributions. A natural generalization of this idea to transformations between arbitrary probability distributions leads to the Schrödinger Bridge (SB) problem. However, SB solutions rarely admit closed-form expressios and are commonly obtained through iterative stochastic simulation procedures, which are computationally intensive and can be unstable. In this work, we introduce a unified closed-form framework for representing the stochastic dynamics of SB systems. Our formulation subsumes previously known analytical solutions including the Schrödinger Föllmer process and the Gaussian SB as specific instances. Notably, the classical Gaussian SB solution, previously derived using substantially more sophisticated tools such as Riemannian geometry and generator theory, follows directly from our formulation as an immediate corollary. Leveraging this framework, we develop a simulation-free algorithm that infers SB dynamics directly from samples of the source and target distributions. We demonstrate the versatility of our approach in two settings: (i) modeling developmental trajectories in single-cell genomics and (ii) solving image restoration tasks such as inpainting and deblurring. This work opens a new direction for efficient and scalable nonlinear diffusion modeling across scientific and machine learning applications. --- ### Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval Authors: Likang Peng, Chao Su, Wenyuan Wu, Yuan Sun, Dezhong Peng, Xi Peng, Xu Wang Published: 2025-11-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.07780v2 Cross-modal hashing (CMH) facilitates efficient retrieval across different modalities (e.g., image and text) by encoding data into compact binary representations. While recent methods have achieved remarkable performance, they often rely heavily on fully annotated datasets, which are costly and labor-intensive to obtain. In real-world scenarios, particularly in multi-label datasets, label noise is prevalent and severely degrades retrieval performance. Moreover, existing CMH approaches typically overlook the partial semantic overlaps inherent in multi-label data, limiting their robustness and generalization. To tackle these challenges, we propose a novel framework named Semantic-Consistent Bidirectional Contrastive Hashing (SCBCH). The framework comprises two complementary modules: (1) Cross-modal Semantic-Consistent Classification (CSCC), which leverages cross-modal semantic consistency to estimate sample reliability and reduce the impact of noisy labels; (2) Bidirectional Soft Contrastive Hashing (BSCH), which dynamically generates soft contrastive sample pairs based on multi-label semantic overlap, enabling adaptive contrastive learning between semantically similar and dissimilar samples across modalities. Extensive experiments on four widely-used cross-modal retrieval benchmarks validate the effectiveness and robustness of our method, consistently outperforming state-of-the-art approaches under noisy multi-label conditions. --- ### Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism Authors: Gina Sohn, Genghan Zhang, Konstantin Hossfeld, Jungwoo Kim, Nathan Sobotka, Nathan Zhang, Olivia Hsu, Kunle Olukotun Published: 2025-11-11 Categories: cs.PL, cs.AR, cs.LG arXiv: https://arxiv.org/abs/2511.07776v2 Dynamic behaviors are becoming prevalent in tensor applications, like machine learning, where many widely used models contain data-dependent tensor shapes and control flow. However, the limited expressiveness of prior programming abstractions for spatial dataflow accelerators (SDAs) forces these dynamic behaviors to be implemented statically and/or unoptimized. To address these challenges, we present Streaming Tensor Programs (STeP), a streaming abstraction that enables dynamic tensor workloads to run efficiently on SDAs. STeP introduces flexible routing operators, an explicit memory hierarchy, and symbolic-shape semantics that expose dynamic data rates and tensor dimensions. These capabilities unlock new optimizations, like dynamic tiling, dynamic parallelization, and configuration time-multiplexing, that adapt SDA execution to dynamic behaviors while preserving dataflow efficiency. Using a cycle-approximate simulator on representative LLM layers and a full model with real-world traces, STeP enables: dynamic tiling that breaks the Pareto-optimal frontier from prior work, dynamic parallelization that improves latency by ~2.72x, and configuration time-multiplexing that increases compute utilization by ~2.64x over prior SDA abstractions and their implementations. --- ### SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought Authors: Shourya Batra, Pierce Tillman, Samarth Gaggar, Shashank Kesineni, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary Published: 2025-11-11 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.07772v2 As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-level privacy, recent findings reveal that LLMs often leak private information through their internal reasoning processes, violating contextual privacy expectations. These leaky thoughts occur when models inadvertently expose sensitive details in their reasoning traces, even when final outputs appear safe. The challenge lies in preventing such leakage without compromising the model's reasoning capabilities, requiring a delicate balance between privacy and utility. We introduce Steering Activations towards Leakage-free Thinking (SALT), a lightweight test-time intervention that mitigates privacy leakage in model's Chain of Thought (CoT) by injecting targeted steering vectors into hidden state. We identify the high-leakage layers responsible for this behavior. Through experiments across multiple LLMs, we demonstrate that SALT achieves reductions including $18.2\%$ reduction in CPL on QwQ-32B, $17.9\%$ reduction in CPL on Llama-3.1-8B, and $31.2\%$ reduction in CPL on Deepseek in contextual privacy leakage dataset AirGapAgent-R while maintaining comparable task performance and utility. Our work establishes SALT as a practical approach for test-time privacy protection in reasoning-capable language models, offering a path toward safer deployment of LLM-based personal agents. --- ### Taking the Road Less Scheduled with Adaptive Polyak Steps Authors: Dimitris Oikonomou, Matthew Buchholz, Yuen-Man Pun, Robert M. Gower, Nicolas Loizou Published: 2025-11-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.07767v2 Schedule-Free SGD, proposed in (Defazio et al., 2024), achieves optimal convergence rates without requiring the training horizon in advance, by replacing learning rate schedules with a principled form of iterate averaging. However, the method still requires tuning a base learning rate whose optimal value depends on unknown problem constants. In this work, we continue down this road by deriving Polyak-type step sizes for Schedule-Free SGD and Adam that compute the learning rate at each iteration from the sampled loss, gradient, and current iterates alone. We first propose an oracle variant that uses per-sample optimal function values and prove an $O(1/\sqrt{t})$ anytime last-iterate rate for convex Lipschitz objectives. We then remove the oracle requirement with a safeguarded variant that replaces the unknown optimal values with any available lower bound, achieving the same rate up to a neighborhood that vanishes under interpolation. Both step sizes reduce to existing Polyak rules for standard SGD when momentum is set to zero, unifying standard and schedule-free Polyak methods. Numerical experiments on language modeling, including pretraining and distillation, show that the proposed methods match or surpass tuned Schedule-Free baselines while offering greater robustness to hyperparameter choices. --- ### Determinism of Randomness: Prompt-Residual Seed Shaping for Diffusion Generation Authors: Song Yan, Wei Zhai, Chenfeng Wang, Xinliang Bi, Jian Yang, Yancheng Cai, Yusen Zhang, Yunwei Lan, Tao Zhang, GuanYe Xiong, Min Li, Zheng-Jun Zha Published: 2025-11-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.07756v6 Diffusion models start generation from an isotropic Gaussian latent, yet changing only the random seed can lead to large differences in prompt faithfulness, composition, and visual quality. We study this seed sensitivity through the semantic map from initial noise to generated meaning. Although the sampling flow is locally invertible, the subsequent semantic projection is many-to-one, inducing a degenerate pullback semi-metric on the latent space: most local directions are nearly semantic-invariant, while semantic-sensitive variation is concentrated in a much smaller horizontal subspace. This provides an explanatory geometric view of the seed lottery. Motivated by this view, we introduce a training-free prompt-residual seed-shaping procedure. Rather than claiming to recover the exact horizontal space, the method uses a single high-noise cold-start prompt residual as a model-coupled proxy, injects only its tangential component, and retracts the seed to the original Gaussian radius shell. This keeps the initialization prior-compatible while adding only one conditional/unconditional probe before standard sampling. Across multiple generation benchmarks, the method improves alignment and quality metrics over standard sampling, supporting both the practical value of the proxy and the explanatory relevance of semantic anisotropy. --- ### Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks Authors: Aja Khanal, Ahmed Faid, Apurva Narayan Published: 2025-11-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.07755v1 Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger misclassifications. Most existing defenses assume a single patch and fail when multiple localized disruptions occur, the type of scenario adversaries and real-world artifacts often exploit. We propose Filtered-ViT, a new vision transformer architecture that integrates SMART Vector Median Filtering (SMART-VMF), a spatially adaptive, multi-scale, robustness-aware mechanism that enables selective suppression of corrupted regions while preserving semantic detail. On ImageNet with LaVAN multi-patch attacks, Filtered-ViT achieves 79.8% clean accuracy and 46.3% robust accuracy under four simultaneous 1\% patches, outperforming existing defenses. Beyond synthetic benchmarks, a real-world case study on radiographic medical imagery shows that Filtered-ViT mitigates natural artifacts such as occlusions and scanner noise without degrading diagnostic content. This establishes Filtered-ViT as the first transformer to demonstrate unified robustness against both adversarial and naturally occurring patch-like disruptions, charting a path toward reliable vision systems in truly high-stakes environments. --- ### Back to the Future: The Role of Past and Future Context Predictability in Incremental Language Production Authors: Shiva Upadhye, Richard Futrell Published: 2025-11-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.07752v4 Contextual predictability shapes how we choose and encode words in production. The effects of a word's predictability given preceding or past context are generally well-understood in both production and comprehension, but studies of naturalistic production have also revealed a poorly-understood yet robust backward predictability effect of a word given only its future context, which may be linked to future planning. Across two studies of naturalistic speech, we revisit backward predictability using improved operationalizations, introducing a conceptually motivated information-theoretic measure that quantifies the information shared between a word and future context under the constraints imposed by the past context. Study 1 shows that this measure produces effects qualitatively similar to backward predictability while explaining unique variance in phonetic reduction. Study 2 examines substitution errors within a generative framework that models lexical, contextual, and communicative influences on word choice to predict the identity of the word that surfaces as an error. Within this framework, we find that past-conditioned predictability increases error likelihood, whereas future-conditioned predictability reduces it. Further, our proposed measure emerges as the strongest contextual predictor of error identity, subsuming backward predictability. Analysis of error types further reveals graded trade offs in how speakers prioritize form-, meaning-, and context-based information during lexical planning. Together, these findings illuminate how past and future context shape word choice and encoding, linking contextual predictability to mechanisms of incremental planning in sentence production. --- ### Class Incremental Medical Image Segmentation via Prototype-Guided Calibration and Dual-Aligned Distillation Authors: Shengqian Zhu, Chengrong Yu, Qiang Wang, Ying Song, Guangjun Li, Jiafei Wu, Xiaogang Xu, Zhang Yi, Junjie Hu Published: 2025-11-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.07749v2 Class incremental medical image segmentation (CIMIS) aims to preserve knowledge of previously learned classes while learning new ones without relying on old-class labels. However, existing methods 1) either adopt one-size-fits-all strategies that treat all spatial regions and feature channels equally, which may hinder the preservation of accurate old knowledge, 2) or focus solely on aligning local prototypes with global ones for old classes while overlooking their local representations in new data, leading to knowledge degradation. To mitigate the above issues, we propose Prototype-Guided Calibration Distillation (PGCD) and Dual-Aligned Prototype Distillation (DAPD) for CIMIS in this paper. Specifically, PGCD exploits prototype-to-feature similarity to calibrate class-specific distillation intensity in different spatial regions, effectively reinforcing reliable old knowledge and suppressing misleading information from old classes. Complementarily, DAPD aligns the local prototypes of old classes extracted from the current model with both global prototypes and local prototypes, further enhancing segmentation performance on old categories. Comprehensive evaluations on two widely used multi-organ segmentation benchmarks demonstrate that our method outperforms state-of-the-art methods, highlighting its robustness and generalization capabilities. --- ### Auto-US: An Ultrasound Video Diagnosis Agent Using Video Classification Framework and LLMs Authors: Yuezhe Yang, Yiyue Guo, Wenjie Cai, Qingqing Ruan, Siying Wang, Xingbo Dong, Zhe Jin, Yong Dai Published: 2025-11-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.07748v1 AI-assisted ultrasound video diagnosis presents new opportunities to enhance the efficiency and accuracy of medical imaging analysis. However, existing research remains limited in terms of dataset diversity, diagnostic performance, and clinical applicability. In this study, we propose \textbf{Auto-US}, an intelligent diagnosis agent that integrates ultrasound video data with clinical diagnostic text. To support this, we constructed \textbf{CUV Dataset} of 495 ultrasound videos spanning five categories and three organs, aggregated from multiple open-access sources. We developed \textbf{CTU-Net}, which achieves state-of-the-art performance in ultrasound video classification, reaching an accuracy of 86.73\% Furthermore, by incorporating large language models, Auto-US is capable of generating clinically meaningful diagnostic suggestions. The final diagnostic scores for each case exceeded 3 out of 5 and were validated by professional clinicians. These results demonstrate the effectiveness and clinical potential of Auto-US in real-world ultrasound applications. Code and data are available at: https://github.com/Bean-Young/Auto-US. --- ### VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics Authors: Daniel Cher, Brian Wei, Srikumar Sastry, Nathan Jacobs Published: 2025-11-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.07744v1 We introduce VectorSynth, a diffusion-based framework for pixel-accurate satellite image synthesis conditioned on polygonal geographic annotations with semantic attributes. Unlike prior text- or layout-conditioned models, VectorSynth learns dense cross-modal correspondences that align imagery and semantic vector geometry, enabling fine-grained, spatially grounded edits. A vision language alignment module produces pixel-level embeddings from polygon semantics; these embeddings guide a conditional image generation framework to respect both spatial extents and semantic cues. VectorSynth supports interactive workflows that mix language prompts with geometry-aware conditioning, allowing rapid what-if simulations, spatial edits, and map-informed content generation. For training and evaluation, we assemble a collection of satellite scenes paired with pixel-registered polygon annotations spanning diverse urban scenes with both built and natural features. We observe strong improvements over prior methods in semantic fidelity and structural realism, and show that our trained vision language model demonstrates fine-grained spatial grounding. The code and data are available at https://github.com/mvrl/VectorSynth. --- ### UltraGS: Real-Time Physically-Decoupled Gaussian Splatting for Ultrasound Novel View Synthesis Authors: Yuezhe Yang, Qingqing Ruan, Wenjie Cai, Yudang Dong, Dexin Yang, Xingbo Dong, Zhe Jin, Yong Dai Published: 2025-11-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.07743v3 Ultrasound imaging is a cornerstone of non-invasive clinical diagnostics, yet its limited field of view poses challenges for novel view synthesis. We present UltraGS, a real-time framework that adapts Gaussian Splatting to sensorless ultrasound imaging by integrating explicit radiance fields with lightweight, physics-inspired acoustic modeling. UltraGS employs depth-aware Gaussian primitives with learnable fields of view to improve geometric consistency under unconstrained probe motion, and introduces PD Rendering, a differentiable acoustic operator that combines low-order spherical harmonics with first-order wave effects for efficient intensity synthesis. We further present a clinical ultrasound dataset acquired under real-world scanning protocols. Extensive evaluations across three datasets demonstrate that UltraGS establishes a new performance-efficiency frontier, achieving state-of-the-art results in PSNR (up to 29.55) and SSIM (up to 0.89) while achieving real-time synthesis at 64.69 fps on a single GPU. The code and dataset are open-sourced at: https://github.com/Bean-Young/UltraGS. --- ### From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training Authors: Donglai Xu, Hongzheng Yang, Yuzhi Zhao, Pingping Zhang, Jinpeng Chen, Wenao Ma, Zhijian Hou, Mengyang Wu, Xiaolei Li, Senkang Hu, Ziyi Guan, Jason Chun Lok Li et al. Published: 2025-11-11 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.07738v2 Reinforcement Learning with Verifiable Rewards (RLVR) for Multimodal Large Language Models (MLLMs) is highly dependent on high-quality labeled data, which is often scarce and prone to substantial annotation noise in real-world scenarios. Existing unsupervised RLVR methods, including pure entropy minimization, can overfit to incorrect labels and limit the crucial reward ranking signal for Group-Relative Policy Optimization (GRPO). To address these challenges and enhance noise tolerance, we propose a novel two-stage, token-level entropy optimization method for RLVR. This approach dynamically guides the model from exploration to exploitation during training. In the initial exploration phase, token-level entropy maximization promotes diverse and stochastic output generation, serving as a strong regularizer that prevents premature convergence to noisy labels and ensures sufficient intra-group variation, which enables more reliable reward gradient estimation in GRPO. As training progresses, the method transitions into the exploitation phase, where token-level entropy minimization encourages the model to produce confident and deterministic outputs, thereby consolidating acquired knowledge and refining prediction accuracy. Empirically, across three MLLM backbones - Qwen2-VL-2B, Qwen2-VL-7B, and Qwen2.5-VL-3B - spanning diverse noise settings and multiple tasks, our phased strategy consistently outperforms prior approaches by unifying and enhancing external, internal, and entropy-based methods, delivering robust and superior performance across the board. --- ### TurboSAT: Gradient-Guided Boolean Satisfiability Accelerated on GPU-CPU Hybrid System Authors: Steve Dai, Cunxi Yu, Kalyan Krishnamani, Brucek Khailany Published: 2025-11-11 Categories: cs.LO, cs.AI, cs.LG, cs.MS arXiv: https://arxiv.org/abs/2511.07737v1 While accelerated computing has transformed many domains of computing, its impact on logical reasoning, specifically Boolean satisfiability (SAT), remains limited. State-of-the-art SAT solvers rely heavily on inherently sequential conflict-driven search algorithms that offer powerful heuristics but limit the amount of parallelism that could otherwise enable significantly more scalable SAT solving. Inspired by neural network training, we formulate the SAT problem as a binarized matrix-matrix multiplication layer that could be optimized using a differentiable objective function. Enabled by this encoding, we combine the strengths of parallel differentiable optimization and sequential search to accelerate SAT on a hybrid GPU-CPU system. In this system, the GPUs leverage parallel differentiable solving to rapidly evaluate SAT clauses and use gradients to stochastically explore the solution space and optimize variable assignments. Promising partial assignments generated by the GPUs are post-processed on many CPU threads which exploit conflict-driven sequential search to further traverse the solution subspaces and identify complete assignments. Prototyping the hybrid solver on an NVIDIA DGX GB200 node, our solver achieves runtime speedups up to over 200x when compared to a state-of-the-art CPU-based solver on public satisfiable benchmark problems from the SAT Competition. --- ### Global Optimization on Graph-Structured Data via Gaussian Processes with Spectral Representations Authors: Shu Hong, Yongsheng Mei, Mahdi Imani, Tian Lan Published: 2025-11-11 Categories: cs.LG, cs.AI, cs.SI, eess.SP arXiv: https://arxiv.org/abs/2511.07734v2 Bayesian optimization (BO) is a powerful framework for optimizing expensive black-box objectives, yet extending it to graph-structured domains remains challenging due to the discrete and combinatorial nature of graphs. Existing approaches often rely either on full graph topology, which is impractical for large or partially observed graphs, or on incremental local exploration, which can lead to slow convergence. We introduce a scalable framework for global optimization over graphs that builds Gaussian process (GP) surrogates from low-rank spectral representations inferred from sparse structural observations. The method fits a low-rank graph surrogate to the observed connections and uses its spectrum to define a kernel over all nodes, so that function evaluations and structural observations jointly refine a global model, enabling efficient global search and principled uncertainty estimation even with limited data. We further show how a limited budget of structural observations can be allocated according to its expected value for the optimization. We also provide theoretical analysis establishing conditions under which the surrogate geometry is identified under different sampling regimes, and bounding the optimization error incurred under an estimated geometry. Experiments on synthetic and real-world datasets demonstrate that our approach achieves lower regret and improved optimization performance compared to prior methods. --- ### ViPRA: Video Prediction for Robot Actions Authors: Sandeep Routray, Hengkai Pan, Unnat Jain, Shikhar Bahl, Deepak Pathak Published: 2025-11-11 Categories: cs.RO, cs.AI, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.07732v2 Can we turn a video prediction model into a robot policy? Videos, including those of humans or teleoperated robots, capture rich physical interactions. However, most of them lack labeled actions, which limits their use in robot learning. We present Video Prediction for Robot Actions (ViPRA), a simple pretraining-finetuning framework that learns continuous robot control from these actionless videos. Instead of directly predicting actions, we train a video-language model to predict both future visual observations and motion-centric latent actions, which serve as intermediate representations of scene dynamics. We train these latent actions using perceptual losses and optical flow consistency to ensure they reflect physically grounded behavior. For downstream control, we introduce a chunked flow matching decoder that maps latent actions to robot-specific continuous action sequences, using only 100 to 200 teleoperated demonstrations. This approach avoids expensive action annotation, supports generalization across embodiments, and enables smooth, high-frequency continuous control upto 22 Hz via chunked action decoding. Unlike prior latent action works that treat pretraining as autoregressive policy learning, ViPRA explicitly models both what changes and how. Our method outperforms strong baselines, with a 16% gain on the SIMPLER benchmark and a 13% improvement across real world manipulation tasks. We have released models and code at https://vipra-project.github.io --- ### Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning Authors: Bill Chunyuan Zheng, Vivek Myers, Benjamin Eysenbach, Sergey Levine Published: 2025-11-11 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2511.07730v3 Learning how to reach goals in an environment is a longstanding challenge in AI, yet reasoning over long horizons remains a challenge for modern methods. The key question is how to estimate the temporal distance between pairs of observations. While temporal difference methods leverage local updates to provide optimality guarantees, they often perform worse than Monte Carlo methods that perform global updates (e.g., with multi-step returns), which lack such guarantees. We show how these approaches can be integrated into a practical offline GCRL method that fits a quasimetric distance using a multistep Monte-Carlo return. We show our method outperforms existing offline GCRL methods on long-horizon simulated tasks with up to 4000 steps, even with visual observations. We also demonstrate that our method can enable stitching in the real-world robotic manipulation domain (Bridge setup). Our approach is the first end-to-end offline GCRL method that enables multistep stitching in this real-world manipulation domain from an unlabeled offline dataset of visual observations and demonstrate robust horizon generalization. --- ### A Ranking-Based Optimization Algorithm for the Vehicle Relocation Problem in Car Sharing Services Authors: Piotr Szwed, Paweł Skrzynski, Jarosław Wąs Published: 2025-11-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.07724v1 The paper addresses the Vehicle Relocation Problem in free-floating car-sharing services by presenting a solution focused on strategies for repositioning vehicles and transferring personnel with the use of scooters. Our method begins by dividing the service area into zones that group regions with similar temporal patterns of vehicle presence and service demand, allowing the application of discrete optimization methods. In the next stage, we propose a fast ranking-based algorithm that makes its decisions on the basis of the number of cars available in each zone, the projected probability density of demand, and estimated trip durations. The experiments were carried out on the basis of real-world data originating from a major car-sharing service operator in Poland. The results of this algorithm are evaluated against scenarios without optimization that constitute a baseline and compared with the results of an exact algorithm to solve the Mixed Integer Programming (MIP) model. As performance metrics, the total travel time was used. Under identical conditions (number of vehicles, staff, and demand distribution), the average improvements with respect to the baseline of our algorithm and MIP solver were equal to 8.44\% and 19.6\% correspondingly. However, it should be noted that the MIP model also mimicked decisions on trip selection, which are excluded by current services business rules. The analysis of results suggests that, depending on the size of the workforce, the application of the proposed solution allows for improving performance metrics by roughly 3%-10%. --- ### Critical Confabulation: Can LLMs Hallucinate for Social Good? Authors: Peiqi Sui, Eamon Duede, Hoyt Long, Richard Jean So Published: 2025-11-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.07722v2 LLMs hallucinate, yet some confabulations can have social affordances if carefully bounded. We propose critical confabulation (inspired by critical fabulation from literary and social theory), the use of LLM hallucinations to "fill-in-the-gap" for omissions in archives due to social and political inequality, and reconstruct divergent yet evidence-bound narratives for history's ``hidden figures''. We simulate these gaps with an open-ended narrative cloze task: asking LLMs to generate a masked event in a character-centric timeline sourced from a novel corpus of unpublished texts. We evaluate audited (for data contamination), fully-open models (the OLMo-2 family) and unaudited open-weight and proprietary baselines under a range of prompts designed to elicit controlled and useful hallucinations. Our findings validate LLMs' foundational narrative understanding capabilities to perform critical confabulation, and show how controlled and well-specified hallucinations can support LLM applications for knowledge production without collapsing speculation into a lack of historical accuracy and fidelity. --- ### Operational machine learning for remote spectroscopic detection of CH$_{4}$ point sources Authors: Vít Růžička, Gonzalo Mateo-García, Itziar Irakulis-Loitxate, Juan Emmanuel Johnson, Manuel Montesino San Martín, Anna Allen, Alma Raunak, Carol Castaneda, Luis Guanter, David R. Thompson Published: 2025-11-11 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.07719v2 Mitigating anthropogenic methane sources is one of the most cost-effective levers to slow down global warming. While satellite-based imaging spectrometers, such as EMIT, PRISMA, and EnMAP, can detect these point sources, current methane retrieval methods based on matched filters produce a high number of false detections requiring manual verification. To address this challenge, we deployed a ML system for detecting methane emissions within the Methane Alert and Response System (MARS) of UNEP's IMEO. This represents the first operational deployment of automated methane point-source detection using spaceborne imaging spectrometers, providing regular global coverage and scalability to future constellations with even higher data volumes. This task required several technical advances. First, we created one of the largest and most diverse and global ML ready datasets to date of annotated methane plumes from three imaging spectrometer missions, and quantitatively compared different deep learning model configurations. Second, we extended prior evaluation methodologies from small, tiled datasets to full granules that are more representative of operational use. This revealed that deep learning models still produce a large number of false detections, a problem we addressed with model ensembling, which reduced false detections by over 74%. During 11 months of operational deployment, our system processed more than 25,000 hyperspectral products faciliting the verification of 2,851 distinct methane leaks, which resulted in 834 stakeholder notifications. We further demonstrate the model's utility in verifying mitigation success through case studies in Libya, Argentina, Oman, and Azerbaijan. Our work represents a critical step towards a global AI-assisted methane leak detection system, which is required to process the dramatically higher data volumes expected from current and future imaging spectrometers. --- ### RoboTAG: End-to-end Robot Configuration Estimation via Topological Alignment Graph Authors: Yifan Liu, Fangneng Zhan, Wanhua Li, Haowen Sun, Katerina Fragkiadaki, Hanspeter Pfister Published: 2025-11-11 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.07717v2 Estimating robot pose from a monocular RGB image is a challenge in robotics and computer vision. Existing methods typically build networks on top of 2D visual backbones and depend heavily on labeled data for training, which is often scarce in real-world scenarios, causing a sim-to-real gap. Moreover, these approaches reduce the 3D-based problem to 2D domain, neglecting the 3D priors. To address these, we propose Robot Topological Alignment Graph (RoboTAG), which incorporates a 3D branch to inject 3D priors while enabling co-evolution of the 2D and 3D representations, alleviating the reliance on labels. Specifically, the RoboTAG consists of a 3D branch and a 2D branch, where nodes represent the states of the camera and robot system, and edges capture the dependencies between these variables or denote alignments between them. Closed loops are then defined in the graph, on which a consistency supervision across branches can be applied. Experimental results demonstrate that our method is effective across robot types, suggesting new possibilities of alleviating the data bottleneck in robotics. --- ### Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling Authors: Jiale Liu, Haoming Zhou, Yishu Liu, Bingzhi Chen, Yuncheng Jiang Published: 2025-11-11 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2511.07710v3 Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained alignment requires precise correspondence between localized visual regions and textual tokens, often hindered by noisy attention mechanisms and oversimplified modeling of cross-modal relationships. In this work, we identify two fundamental limitations of existing approaches: the lack of robust intra-modal mechanisms to assess the significance of visual and textual tokens, leading to poor generalization in complex scenes; and the absence of fine-grained uncertainty modeling, which fails to capture the one-to-many and many-to-one nature of region-word correspondences. To address these issues, we propose a unified approach that incorporates significance-aware and granularity-aware modeling and region-level uncertainty modeling. Our method leverages modality-specific biases to identify salient features without relying on brittle cross-modal attention, and represents region features as a mixture of Gaussian distributions to capture fine-grained uncertainty. Extensive experiments on Flickr30K and MS-COCO demonstrate that our approach achieves state-of-the-art performance across various backbone architectures, significantly enhancing the robustness and interpretability of fine-grained image-text alignment. --- ### A Negotiation-Based Multi-Agent Reinforcement Learning Approach for Dynamic Scheduling of Reconfigurable Manufacturing Systems Authors: Manonmani Sekar, Nasim Nezamoddini Published: 2025-11-11 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2511.07707v1 Reconfigurable manufacturing systems (RMS) are critical for future market adjustment given their rapid adaptation to fluctuations in consumer demands, the introduction of new technological advances, and disruptions in linked supply chain sections. The adjustable hard settings of such systems require a flexible soft planning mechanism that enables realtime production planning and scheduling amid the existing complexity and variability in their configuration settings. This study explores the application of multi agent reinforcement learning (MARL) for dynamic scheduling in soft planning of the RMS settings. In the proposed framework, deep Qnetwork (DQN) agents trained in centralized training learn optimal job machine assignments in real time while adapting to stochastic events such as machine breakdowns and reconfiguration delays. The model also incorporates a negotiation with an attention mechanism to enhance state representation and improve decision focus on critical system features. Key DQN enhancements including prioritized experience replay, nstep returns, double DQN and soft target update are used to stabilize and accelerate learning. Experiments conducted in a simulated RMS environment demonstrate that the proposed approach outperforms baseline heuristics in reducing makespan and tardiness while improving machine utilization. The reconfigurable manufacturing environment was extended to simulate realistic challenges, including machine failures and reconfiguration times. Experimental results show that while the enhanced DQN agent is effective in adapting to dynamic conditions, machine breakdowns increase variability in key performance metrics such as makespan, throughput, and total tardiness. The results confirm the advantages of applying the MARL mechanism for intelligent and adaptive scheduling in dynamic reconfigurable manufacturing environments. --- ### A survey: Information search time optimization based on RAG (Retrieval Augmentation Generation) chatbot Authors: Jinesh Patel, Arpit Malhotra, Ajay Pande, Prateek Caire Published: 2025-11-10 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2601.07838v1 Retrieval-Augmented Generation (RAG) based chatbots are not only useful for information retrieval through questionanswering but also for making complex decisions based on injected private data.we present a survey on how much search time can be saved when retrieving complex information within an organization called "X Systems"(a stealth mode company) by using a RAG-based chatbot compared to traditional search methods. We compare the information retrieval time using standard search techniques versus the RAG-based chatbot for the same queries. Our results conclude that RAG-based chatbots not only save time in information retrieval but also optimize the search process effectively. This survey was conducted with a sample of 105 employees across departments, average time spending on information retrieval per query was taken as metric. Comparison shows us, there are average 80-95% improvement on search when use RAG based chatbot than using standard search. --- ### Harmonic Token Projection (HTP): A Vocabulary-Free, Training-Free, Deterministic, and Reversible Embedding Methodology Authors: Tcharlies Schmitz Published: 2025-11-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.20665v1 This paper introduces the Harmonic Token Projection (HTP), a reversible and deterministic framework for generating text embeddings without training, vocabularies, or stochastic parameters. Unlike neural embeddings that rely on statistical co-occurrence or optimization, HTP encodes each token analytically as a harmonic trajectory derived from its Unicode integer representation, establishing a bijective and interpretable mapping between discrete symbols and continuous vector space. The harmonic formulation provides phase-coherent projections that preserve both structure and reversibility, enabling semantic similarity estimation from purely geometric alignment. Experimental evaluation on the Semantic Textual Similarity Benchmark (STS-B) and its multilingual extension shows that HTP achieves a Spearman correlation of \r{ho} = 0.68 in English, maintaining stable performance across ten languages with negligible computational cost and sub-millisecond latency per sentence pair. This demonstrates that meaningful semantic relations can emerge from deterministic geometry, offering a transparent and efficient alternative to data-driven embeddings. Keywords: Harmonic Token Projection, reversible embedding, deterministic encoding, semantic similarity, multilingual representation. --- ### On the Probabilistic Learnability of Compact Neural Network Preimage Bounds Authors: Luca Marzari, Manuele Bicego, Ferdinando Cicalese, Alessandro Farinelli Published: 2025-11-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.11656v1 Although recent provable methods have been developed to compute preimage bounds for neural networks, their scalability is fundamentally limited by the #P-hardness of the problem. In this work, we adopt a novel probabilistic perspective, aiming to deliver solutions with high-confidence guarantees and bounded error. To this end, we investigate the potential of bootstrap-based and randomized approaches that are capable of capturing complex patterns in high-dimensional spaces, including input regions where a given output property holds. In detail, we introduce $\textbf{R}$andom $\textbf{F}$orest $\textbf{Pro}$perty $\textbf{Ve}$rifier ($\texttt{RF-ProVe}$), a method that exploits an ensemble of randomized decision trees to generate candidate input regions satisfying a desired output property and refines them through active resampling. Our theoretical derivations offer formal statistical guarantees on region purity and global coverage, providing a practical, scalable solution for computing compact preimage approximations in cases where exact solvers fail to scale. --- ### Automatic generation of DRI Statements Authors: Maurice Flechtner Published: 2025-11-10 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2511.11655v1 Assessing the quality of group deliberation is essential for improving our understanding of deliberative processes. The Deliberative Reason Index (DRI) offers a sophisticated metric for evaluating group reasoning, but its implementation has been constrained by the complex and time-consuming process of statement generation. This thesis introduces an innovative, automated approach to DRI statement generation that leverages advanced natural language processing (NLP) and large language models (LLMs) to substantially reduce the human effort involved in survey preparation. Key contributions are a systematic framework for automated DRI statement generation and a methodological innovation that significantly lowers the barrier to conducting comprehensive deliberative process assessments. In addition, the findings provide a replicable template for integrating generative artificial intelligence into social science research methodologies. --- ### Convergence of Multiagent Learning Systems for Traffic control Authors: Sayambhu Sen, Shalabh Bhatnagar Published: 2025-11-10 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.11654v2 Rapid urbanization in cities like Bangalore has led to severe traffic congestion, making efficient Traffic Signal Control (TSC) essential. Multi-Agent Reinforcement Learning (MARL), often modeling each traffic signal as an independent agent using Q-learning, has emerged as a promising strategy to reduce average commuter delays. While prior work Prashant L A et. al has empirically demonstrated the effectiveness of this approach, a rigorous theoretical analysis of its stability and convergence properties in the context of traffic control has not been explored. This paper bridges that gap by focusing squarely on the theoretical basis of this multi-agent algorithm. We investigate the convergence problem inherent in using independent learners for the cooperative TSC task. Utilizing stochastic approximation methods, we formally analyze the learning dynamics. The primary contribution of this work is the proof that the specific multi-agent reinforcement learning algorithm for traffic control is proven to converge under the given conditions extending it from single agent convergence proofs for asynchronous value iteration. --- ### GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs Authors: Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, BinBin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong et al. Published: 2025-11-10 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.11653v3 Large Language Models (LLMs) have emerged as powerful tools for passage reranking in information retrieval, leveraging their superior reasoning capabilities to address the limitations of conventional models on complex queries. However, current LLM-based reranking paradigms are fundamentally constrained by an efficiency-accuracy trade-off: (1) pointwise methods are efficient but ignore inter-document comparison, yielding suboptimal accuracy; (2) listwise methods capture global context but suffer from context-window constraints and prohibitive inference latency. To address these issues, we propose GroupRank, a novel paradigm that balances flexibility and context awareness. To unlock the full potential of groupwise reranking, we propose an answer-free data synthesis pipeline that fuses local pointwise signals with global listwise rankings. These samples facilitate supervised fine-tuning and reinforcement learning, with the latter guided by a specialized group-ranking reward comprising ranking-utility and group-alignment. These complementary components synergistically optimize document ordering and score calibration to reflect intrinsic query-document relevance. Experimental results show GroupRank achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED, while delivering a 6.4$\times$ inference speedup. --- ### How many stations are sufficient? Exploring the effect of urban weather station density reduction on imputation accuracy of air temperature and humidity Authors: Marvin Plein, Carsten F. Dormann, Andreas Christen Published: 2025-11-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.11652v1 Urban weather station networks (WSNs) are widely used to monitor urban weather and climate patterns and aid urban planning. However, maintaining WSNs is expensive and labor-intensive. Here, we present a step-wise station removal procedure to thin an existing WSN in Freiburg, Germany, and analyze the ability of WSN subsets to reproduce air temperature and humidity patterns of the entire original WSN for a year following a simulated reduction of WSN density. We found that substantial reductions in station numbers after one year of full deployment are possible while retaining high predictive accuracy. A reduction from 42 to 4 stations, for instance, increased mean prediction RMSEs from 0.69 K to 0.83 K for air temperature and from 3.8% to 4.4% for relative humidity, corresponding to RMSE increases of only 20% and 16%, respectively. Predictive accuracy is worse for remote stations in forests than for stations in built-up or open settings, but consistently better than a state-of-the-art numerical urban land-surface model (Surface Urban Energy and Water Balance Scheme). Stations located at the edges between built-up and rural areas are most valuable when reconstructing city-wide climate characteristics. Our study demonstrates the potential of thinning WSNs to maximize the efficient allocation of financial and personnel-related resources in urban climate research. --- ### Incomplete Depression Feature Selection with Missing EEG Channels Authors: Zhijian Gong, Wenjia Dong, Xueyuan Xu, Fulin Wei, Chunyu Liu, Li Zhuo Published: 2025-11-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.11651v1 As a critical mental health disorder, depression has severe effects on both human physical and mental well-being. Recent developments in EEG-based depression analysis have shown promise in improving depression detection accuracies. However, EEG features often contain redundant, irrelevant, and noisy information. Additionally, real-world EEG data acquisition frequently faces challenges, such as data loss from electrode detachment and heavy noise interference. To tackle the challenges, we propose a novel feature selection approach for robust depression analysis, called Incomplete Depression Feature Selection with Missing EEG Channels (IDFS-MEC). IDFS-MEC integrates missing-channel indicator information and adaptive channel weighting learning into orthogonal regression to lessen the effects of incomplete channels on model construction, and then utilizes global redundancy minimization learning to reduce redundant information among selected feature subsets. Extensive experiments conducted on MODMA and PRED-d003 datasets reveal that the EEG feature subsets chosen by IDFS-MEC have superior performance than 10 popular feature selection methods among 3-, 64-, and 128-channel settings. --- ### Enhanced Water Leak Detection with Convolutional Neural Networks and One-Class Support Vector Machine Authors: Daniele Ugo Leonzio, Paolo Bestagini, Marco Marcon, Stefano Tubaro Published: 2025-11-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.11650v1 Water is a critical resource that must be managed efficiently. However, a substantial amount of water is lost each year due to leaks in Water Distribution Networks (WDNs). This underscores the need for reliable and effective leak detection and localization systems. In recent years, various solutions have been proposed, with data-driven approaches gaining increasing attention due to their superior performance. In this paper, we propose a new method for leak detection. The method is based on water pressure measurements acquired at a series of nodes of a WDN. Our technique is a fully data-driven solution that makes only use of the knowledge of the WDN topology, and a series of pressure data acquisitions obtained in absence of leaks. The proposed solution is based on an feature extractor and a one-class Support Vector Machines (SVM) trained on no-leak data, so that leaks are detected as anomalies. The results achieved on a simulate dataset using the Modena WDN demonstrate that the proposed solution outperforms recent methods for leak detection. --- ### The Environmental Impact of Ensemble Techniques in Recommender Systems Authors: Jannik Nitschke Published: 2025-11-10 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2511.11649v1 Ensemble techniques in recommender systems have demonstrated accuracy improvements of 10-30%, yet their environmental impact remains unmeasured. While deep learning recommendation algorithms can generate up to 3,297 kg CO2 per paper, ensemble methods have not been sufficiently evaluated for energy consumption. This thesis investigates how ensemble techniques influence environmental impact compared to single optimized models. We conducted 93 experiments across two frameworks (Surprise for rating prediction, LensKit for ranking) on four datasets spanning 100,000 to 7.8 million interactions. We evaluated four ensemble strategies (Average, Weighted, Stacking/Rank Fusion, Top Performers) against simple baselines and optimized single models, measuring energy consumption with a smart plug. Results revealed a non-linear accuracy-energy relationship. Ensemble methods achieved 0.3-5.7% accuracy improvements while consuming 19-2,549% more energy depending on dataset size and strategy. The Top Performers ensemble showed best efficiency: 0.96% RMSE improvement with 18.8% energy overhead on MovieLens-1M, and 5.7% NDCG improvement with 103% overhead on MovieLens-100K. Exhaustive averaging strategies consumed 88-270% more energy for comparable gains. On the largest dataset (Anime, 7.8M interactions), the Surprise ensemble consumed 2,005% more energy (0.21 Wh vs. 0.01 Wh) for 1.2% accuracy improvement, producing 53.8 mg CO2 versus 2.6 mg CO2 for the single model. This research provides one of the first systematic measurements of energy and carbon footprint for ensemble recommender systems, demonstrates that selective strategies offer superior efficiency over exhaustive averaging, and identifies scalability limitations at industrial scale. These findings enable informed decisions about sustainable algorithm selection in recommender systems. --- ### Lightweight Time Series Data Valuation on Time Series Foundation Models via In-Context Finetuning Authors: Shunyu Wu, Tianyue Li, Yixuan Leng, Jingyi Suo, Jian Lou, Dan Li, See-Kiong Ng Published: 2025-11-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.11648v2 Time series foundation models (TSFMs) have demonstrated increasing capabilities due to their extensive pretraining on large volumes of diverse time series data. Consequently, the quality of time series data is crucial to TSFM performance, rendering an accurate and efficient data valuation of time series for TSFMs indispensable. However, traditional data valuation methods, such as influence functions, face severe computational bottlenecks due to their poor scalability with growing TSFM model sizes and often fail to preserve temporal dependencies. In this paper, we propose LTSV, a Lightweight Time Series Valuation on TSFMS via in-context finetuning. Grounded in the theoretical evidence that in-context finetuning approximates the influence function, LTSV estimates a sample's contribution by measuring the change in context loss after in-context finetuning, leveraging the strong generalization capabilities of TSFMs to produce robust and transferable data valuations. To capture temporal dependencies, we introduce temporal block aggregation, which integrates per-block influence scores across overlapping time windows. Experiments across multiple time series datasets and models demonstrate that LTSV consistently provides reliable and strong valuation performance, while maintaining manageable computational requirements. Our results suggest that in-context finetuning on time series foundation models provides a practical and effective bridge between data attribution and model generalization in time series learning. --- ### Environment-Aware Transfer Reinforcement Learning for Sustainable Beam Selection Authors: Dariush Salami, Ramin Hashemi, Parham Kazemi, Mikko A. Uusitalo Published: 2025-11-10 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2511.11647v1 This paper presents a novel and sustainable approach for improving beam selection in 5G and beyond networks using transfer learning and Reinforcement Learning (RL). Traditional RL-based beam selection models require extensive training time and computational resources, particularly when deployed in diverse environments with varying propagation characteristics posing a major challenge for scalability and energy efficiency. To address this, we propose modeling the environment as a point cloud, where each point represents the locations of gNodeBs (gNBs) and surrounding scatterers. By computing the Chamfer distance between point clouds, structurally similar environments can be efficiently identified, enabling the reuse of pre-trained models through transfer learning. This methodology leads to a 16x reduction in training time and computational overhead, directly contributing to energy efficiency. By minimizing the need for retraining in each new deployment, our approach significantly lowers power consumption and supports the development of green and sustainable Artificial Intelligence (AI) in wireless systems. Furthermore, it accelerates time-to-deployment, reduces carbon emissions associated with training, and enhances the viability of deploying AI-driven communication systems at the edge. Simulation results confirm that our approach maintains high performance while drastically cutting energy costs, demonstrating the potential of transfer learning to enable scalable, adaptive, and environmentally conscious RL-based beam selection strategies in dynamic and diverse propagation environments. --- ### What-If Decision Support for Product Line Extension Using Conditional Deep Generative Models Authors: Yinxing Li, Tsukasa Ishigaki Published: 2025-11-10 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2511.11646v2 Product line extension is a strategically important managerial decision that requires anticipating how consumer segments and purchasing contexts may respond to hypothetical product designs that do not yet exist in the market. Such decisions are inherently uncertain because managers must infer future outcomes from historical purchase data without direct market observations. This study addresses this challenge by proposing a data-driven decision support framework that enables forward-looking what-if analysis based on historical transaction data. We introduce a Conditional Tabular Variational Autoencoder (CTVAE) that learns the conditional joint distribution of product attributes and consumer characteristics from large-scale tabular data. By conditioning the generative process on controllable design variables such as container type, volume, flavor, and calorie content, the proposed model generates synthetic consumer attribute distributions for hypothetical line-extended products. This enables systematic exploration of alternative design scenarios without costly market pretests. The framework is evaluated using home-scan panel data covering more than 20,000 consumers and 700 soft drink products. Empirical results show that the CTVAE outperforms existing tabular generative models in capturing conditional consumer attribute distributions. Simulation-based analyses further demonstrate that the generated synthetic data support knowledge-driven reasoning for assessing cannibalization risks and identifying potential target segments. These findings highlight the value of conditional deep generative models as core components of decision support systems for product line extension planning. --- ### Slow - Motion Video Synthesis for Basketball Using Frame Interpolation Authors: Jiantang Huang Published: 2025-11-10 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.11644v1 Basketball broadcast footage is traditionally captured at 30-60 fps, limiting viewers' ability to appreciate rapid plays such as dunks and crossovers. We present a real-time slow-motion synthesis system that produces high-quality basketball-specific interpolated frames by fine-tuning the recent Real-Time Intermediate Flow Estimation (RIFE) network on the SportsSloMo dataset. Our pipeline isolates the basketball subset of SportsSloMo, extracts training triplets, and fine-tunes RIFE with human-aware random cropping. We compare the resulting model against Super SloMo and the baseline RIFE model using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) on held-out clips. The fine-tuned RIFE attains a mean PSNR of 34.3 dB and SSIM of 0.949, outperforming Super SloMo by 2.1 dB and the baseline RIFE by 1.3 dB. A lightweight Gradio interface demonstrates end-to-end 4x slow-motion generation on a single RTX 4070 Ti Super at approximately 30 fps. These results indicate that task-specific adaptation is crucial for sports slow-motion, and that RIFE provides an attractive accuracy-speed trade-off for consumer applications. --- ### Real-time pothole detection with onboard sensors and camera on vehicles Authors: Aswath Muthuselvam, Jeevak Raj S, Mohanaprasad K Published: 2025-11-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.11643v1 Road conditions play an important role in our everyday commute. With the proliferating number of vehicles on the road each year, it has become necessary to access the road conditions very frequently, this would ensure that the traffic also flows smoothly. Even the smallest crack in the road could be easily be chipped into a large pothole due to changing surface temperatures of the road and from the force of vehicles riding over it. In this paper, we have addressed how we could better identify these potholes in realtime with the help of onboard sensors in vehicles so that the data could be useful for analysis and better management of potholes on a large scale. For the implementation, we used an SVM classifier to detect potholes, we achieved 98.1% accuracy based on data collected from a local road for about 2 km which had 26 potholes distributed along the road. Code is available at: https://github.com/aswathselvam/Potholes --- ### Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models Authors: Shien Zhu, Samuel Bohl, Robin Oester, Gustavo Alonso Published: 2025-11-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10676v1 Mixture-of-Experts (MoE) Large Language Models (LLMs) efficiently scale-up the model while keeping relatively low inference cost. As MoE models only activate part of the experts, related work has proposed expert prediction and caching methods to prefetch the experts for faster inference. However, existing approaches utilize the activations from the previous layer for prediction, incurring low accuracy and leave the first layer unoptimized. Applying complex layers or even training standalone networks for better prediction introduces high computation overhead. In this paper, we propose pre-attention expert prediction to achieve accurate and lightweight expert prefetching. The key insight is that some functions in LLMs are ranking-preserving, indicating that matching the ranking of selected experts using simple linear functions is possible. Therefore, we utilize the activations before the attention block in the same layer with 2 linear functions and ranking-aware loss to achieve accurate prediction, which also supports prefetching in the first layer. Our lightweight, pre-attention expert routers achieve 93.03% accuracy on DeepSeek V2 Lite, 94.69% on Qwen3-30B, and 97.62% on Phi-mini-MoE, showing about 15% improvement on absolute accuracy over the state-of-the-art methods. --- ### Learn to Select: Exploring Label Distribution Divergence for In-Context Demonstration Selection in Text Classification Authors: Ye Jiang, Taihang Wang, Youzheng Liu, Yimin Wang, Yuhan Xia, Yunfei Long Published: 2025-11-10 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2511.10675v1 In-context learning (ICL) for text classification, which uses a few input-label demonstrations to describe a task, has demonstrated impressive performance on large language models (LLMs). However, the selection of in-context demonstrations plays a crucial role and can significantly affect LLMs' performance. Most existing demonstration selection methods primarily focus on semantic similarity between test inputs and demonstrations, often overlooking the importance of label distribution alignment. To address this limitation, we propose a two-stage demonstration selection method, TopK + Label Distribution Divergence (L2D), which leverages a fine-tuned BERT-like small language model (SLM) to generate label distributions and calculate their divergence for both test inputs and candidate demonstrations. This enables the selection of demonstrations that are not only semantically similar but also aligned in label distribution with the test input. Extensive experiments across seven text classification benchmarks show that our method consistently outperforms previous demonstration selection strategies. Further analysis reveals a positive correlation between the performance of LLMs and the accuracy of the underlying SLMs used for label distribution estimation. --- ### Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQL Authors: Thomas Cook, Kelly Patel, Sivapriya Vellaichamy, Udari Madhushani Sehwag, Saba Rahimi, Zhen Zeng, Sumitra Ganesh Published: 2025-11-10 Categories: cs.CL, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2511.10674v2 Large Language Models (LLMs) can generate SQL queries from natural language questions but struggle with database-specific schemas and tacit domain knowledge. We introduce a framework for continual learning from human feedback in text-to-SQL, where a learning agent receives natural language feedback to refine queries and distills the revealed knowledge for reuse on future tasks. This distilled knowledge is stored in a structured memory, enabling the agent to improve execution accuracy over time. We design and evaluate multiple variations of a learning agent architecture that vary in how they capture and retrieve past experiences. Experiments on the BIRD benchmark Dev set show that memory-augmented agents, particularly the Procedural Agent, achieve significant accuracy gains and error reduction by leveraging human-in-the-loop feedback. Our results highlight the importance of transforming tacit human expertise into reusable knowledge, paving the way for more adaptive, domain-aware text-to-SQL systems that continually learn from a human-in-the-loop. --- ### Large language models in materials science and the need for open-source approaches Authors: Fengxu Yang, Weitong Chen, Jack D. Evans Published: 2025-11-10 Categories: cs.CL, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2511.10673v1 Large language models (LLMs) are rapidly transforming materials science. This review examines recent LLM applications across the materials discovery pipeline, focusing on three key areas: mining scientific literature , predictive modelling, and multi-agent experimental systems. We highlight how LLMs extract valuable information such as synthesis conditions from text, learn structure-property relationships, and can coordinate agentic systems integrating computational tools and laboratory automation. While progress has been largely dependent on closed-source commercial models, our benchmark results demonstrate that open-source alternatives can match performance while offering greater transparency, reproducibility, cost-effectiveness, and data privacy. As open-source models continue to improve, we advocate their broader adoption to build accessible, flexible, and community-driven AI platforms for scientific discovery. --- ### Mamba-driven multi-perspective structural understanding for molecular ground-state conformation prediction Authors: Yuxin Gou, Aming Wu, Richang Hong, Meng Wang Published: 2025-11-10 Categories: physics.chem-ph, cs.AI arXiv: https://arxiv.org/abs/2511.09564v1 A comprehensive understanding of molecular structures is important for the prediction of molecular ground-state conformation involving property information. Meanwhile, state space model (e.g., Mamba) has recently emerged as a promising mechanism for long sequence modeling and has achieved remarkable results in various language and vision tasks. However, towards molecular ground-state conformation prediction, exploiting Mamba to understand molecular structure is underexplored. To this end, we strive to design a generic and efficient framework with Mamba to capture critical components. In general, molecular structure could be considered to consist of three elements, i.e., atom types, atom positions, and connections between atoms. Thus, considering the three elements, an approach of Mamba-driven multi-perspective structural understanding (MPSU-Mamba) is proposed to localize molecular ground-state conformation. Particularly, for complex and diverse molecules, three different kinds of dedicated scanning strategies are explored to construct a comprehensive perception of corresponding molecular structures. And a bright-channel guided mechanism is defined to discriminate the critical conformation-related atom information. Experimental results on QM9 and Molecule3D datasets indicate that MPSU-Mamba significantly outperforms existing methods. Furthermore, we observe that for the case of few training samples, MPSU-Mamba still achieves superior performance, demonstrating that our method is indeed beneficial for understanding molecular structures. ---