# Research Papers — 2025-11 · bundle page 20 of 197 > Full-text markdown of papers #951–1000 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/20 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/19.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/21.md) ### Predicting and Interpolating Spatiotemporal Environmental Data: A Case Study of Groundwater Storage in Bangladesh Authors: Anna Pazola, Mohammad Shamsudduha, Richard G. Taylor, Allan Tucker Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22378v1 Geospatial observational datasets are often limited to point measurements, making temporal prediction and spatial interpolation essential for constructing continuous fields. This study evaluates two deep learning strategies for addressing this challenge: (1) a grid-to-grid approach, where gridded predictors are used to model rasterised targets (aggregation before modelling), and (2) a grid-to-point approach, where gridded predictors model point targets, followed by kriging interpolation to fill the domain (aggregation after modelling). Using groundwater storage data from Bangladesh as a case study, we compare the effcacy of these approaches. Our findings indicate that spatial interpolation is substantially more difficult than temporal prediction. In particular, nearest neighbours are not always the most similar, and uncertainties in geology strongly influence point temporal behaviour. These insights motivate future work on advanced interpolation methods informed by clustering locations based on time series dynamics. Demonstrated on groundwater storage, the conclusions are applicable to other environmental variables governed by indirectly observable factors. Code is available at https://github.com/pazolka/interpolation-prediction-gwsa. --- ### Conditionals Based on Selection Functions, Modal Operators and Probabilities Authors: Tommaso Flaminio, Lluis Godo, Gluliano Rosella Published: 2025-11-27 Categories: cs.LO, cs.AI, cs.DM arXiv: https://arxiv.org/abs/2511.22377v1 Methods for probability updating, of which Bayesian conditionalization is the most well-known and widely used, are modeling tools that aim to represent the process of modifying an initial epistemic state, typically represented by a prior probability function P, which is adjusted in light of new information. Notably, updating methods and conditional sentences seem to intuitively share a deep connection, as is evident in the case of conditionalization. The present work contributes to this line of research and aims at shedding new light on the relationship between updating methods and conditional connectives. Departing from previous literature that often focused on a specific type of conditional or a particular updating method, our goal is to prove general results concerning the connection between conditionals and their probabilities. This will allow us to characterize the probabilities of certain conditional connectives and to understand what class of updating procedures can be represented using specific conditional connectives. Broadly, we adopt a general perspective that encompasses a large class of conditionals and a wide range of updating methods, enabling us to prove some general results concerning their interrelation. --- ### On the Complexity of the Grounded Semantics for Infinite Argumentation Frameworks Authors: Uri Andrews, Luca San Mauro Published: 2025-11-27 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2511.22376v1 Argumentation frameworks, consisting of arguments and an attack relation representing conflicts, are fundamental for formally studying reasoning under conflicting information. We use methods from mathematical logic, specifically computability and set theory, to analyze the grounded extension, a widely-used model of maximally skeptical reasoning, defined as the least fixed-point of a natural defense operator. Without additional constraints, finding this fixed-point requires transfinite iterations. We identify the exact ordinal number corresponding to the length of this iterative process and determine the complexity of deciding grounded acceptance, showing it to be maximally complex. This shows a marked distinction from the finite case where the grounded extension is polynomial-time computable, thus simpler than other reasoning problems explored in formal argumentation. --- ### Distributed Knowing How Authors: Bin Liu, Yanjing Wang Published: 2025-11-27 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2511.22374v1 Distributed knowledge is a key concept in the standard epistemic logic of knowledge-that. In this paper, we propose a corresponding notion of distributed knowledge-how and study its logic. Our framework generalizes two existing traditions in the logic of know-how: the individual-based multi-step framework and the coalition-based single-step framework. In particular, we assume a group can accomplish more than what its individuals can jointly do. The distributed knowledge-how is based on the distributed knowledge-that of a group whose multi-step strategies derive from distributed actions that subgroups can collectively perform. As the main result, we obtain a sound and strongly complete proof system for our logic of distributed knowledge-how, which closely resembles the logic of distributed knowledge-that in both the axioms and the proof method of completeness. --- ### SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning Authors: Hugo Hazard, Zafeirios Fountas, Martin A. Benfeghoul, Adnan Oomerjee, Jun Wang, Haitham Bou-Ammar Published: 2025-11-27 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.22367v1 Continual learning, one's ability to adapt to a sequence of tasks without forgetting previously acquired knowledge, remains a major challenge in machine learning and a key gap between artificial and human intelligence. While regularisation and replay perform well in vision, they lag behind multi-task learning for large language models (LLMs), especially at scale with many tasks. We revisit replay and argue that two failure modes drive this gap: selection (what to rehearse) and integration (how to consolidate new knowledge). To address selection, we propose Surprise-prioritised Replay (SuRe), a simple, architecture-agnostic rule that ranks and stores the most surprising (high Negative Log-Likelihood) sequences. SuRe achieves state-of-the-art performance in the Large Number of Tasks (LNT) setting and delivers the best overall average across both Standard CL and LNT benchmarks. To address integration, we add a dual-learner design with fast and slow LoRA adapters merged via an exponential moving average (EMA), enabling rapid adaptation while stabilising long-term knowledge. Combining SuRe with the dual learner yields further gains, including improvements of up to +5 accuracy points on LNT over prior SOTA. Ablation studies confirm that our proposed method remains robust under reduced replay frequency and small buffer size, demonstrating both effectiveness and sample efficiency. Taken together, our results establish replay as a strong baseline for continual LLM fine-tuning and demonstrate that surprise-based selection and slow-weight consolidation are complementary components for mitigating catastrophic forgetting. --- ### BINDER: Instantly Adaptive Mobile Manipulation with Open-Vocabulary Commands Authors: Seongwon Cho, Daechul Ahn, Donghyun Shin, Hyeonbeom Choi, San Kim, Jonghyun Choi Published: 2025-11-27 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.22364v2 Open-vocabulary mobile manipulation (OVMM) requires robots to follow language instructions, navigate, and manipulate while updating their world representation under dynamic environmental changes. However, most prior approaches update their world representation only at discrete update points such as navigation targets, waypoints, or the end of an action step, leaving robots blind between updates and causing cascading failures: overlooked objects, late error detection, and delayed replanning. To address this limitation, we propose BINDER (Bridging INstant and DEliberative Reasoning), a dual process framework that decouples strategic planning from continuous environment monitoring. Specifically, BINDER integrates a Deliberative Response Module (DRM, a multimodal LLM for task planning) with an Instant Response Module (IRM, a VideoLLM for continuous monitoring). The two modules play complementary roles: the DRM performs strategic planning with structured 3D scene updates and guides what the IRM attends to, while the IRM analyzes video streams to update memory, correct ongoing actions, and trigger replanning when necessary. Through this bidirectional coordination, the modules address the trade off between maintaining awareness and avoiding costly updates, enabling robust adaptation under dynamic conditions. Evaluated in three real world environments with dynamic object placement, BINDER achieves substantially higher success and efficiency than SoTA baselines, demonstrating its effectiveness for real world deployment. --- ### Efficient-Husformer: Efficient Multimodal Transformer Hyperparameter Optimization for Stress and Cognitive Loads Authors: Merey Orazaly, Fariza Temirkhanova, Jurn-Gyu Park Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22362v1 Transformer-based models have gained considerable attention in the field of physiological signal analysis. They leverage long-range dependencies and complex patterns in temporal signals, allowing them to achieve performance superior to traditional RNN and CNN models. However, they require high computational intensity and memory demands. In this work, we present Efficient-Husformer, a novel Transformer-based architecture developed with hyperparameter optimization (HPO) for multi-class stress detection across two multimodal physiological datasets (WESAD and CogLoad). The main contributions of this work are: (1) the design of a structured search space, targeting effective hyperparameter optimization; (2) a comprehensive ablation study evaluating the impact of architectural decisions; (3) consistent performance improvements over the original Husformer, with the best configuration achieving an accuracy of 88.41 and 92.61 (improvements of 13.83% and 6.98%) on WESAD and CogLoad datasets, respectively. The best-performing configuration is achieved with the (L + dm) or (L + FFN) modality combinations, using a single layer, 3 attention heads, a model dimension of 18/30, and FFN dimension of 120/30, resulting in a compact model with only about 30k parameters. --- ### AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows Authors: Zhenglin Zhou, Fan Ma, Chengzhuo Gui, Xiaobo Xia, Hehe Fan, Yi Yang, Tat-Seng Chua Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22357v1 Training-free 3D editing aims to modify 3D shapes based on human instructions without model finetuning. It plays a crucial role in 3D content creation. However, existing approaches often struggle to produce strong or geometrically stable edits, largely due to inconsistent latent anchors introduced by timestep-dependent noise during diffusion sampling. To address these limitations, we introduce AnchorFlow, which is built upon the principle of latent anchor consistency. Specifically, AnchorFlow establishes a global latent anchor shared between the source and target trajectories, and enforces coherence using a relaxed anchor-alignment loss together with an anchor-aligned update rule. This design ensures that transformations remain stable and semantically faithful throughout the editing process. By stabilizing the latent reference space, AnchorFlow enables more pronounced semantic modifications. Moreover, AnchorFlow is mask-free. Without mask supervision, it effectively preserves geometric fidelity. Experiments on the Eval3DEdit benchmark show that AnchorFlow consistently delivers semantically aligned and structurally robust edits across diverse editing types. Code is at https://github.com/ZhenglinZhou/AnchorFlow. --- ### AutoTailor: Automatic and Efficient Adaptive Model Deployment for Diverse Edge Devices Authors: Mengyang Liu, Chenyu Lu, Haodong Tian, Fang Dong, Ruiting Zhou, Wei Wang, Dian Shen, Guangtong Li, Ye Wan, Li Li Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22355v1 On-device machine learning (ML) has become a fundamental component of emerging mobile applications. Adaptive model deployment delivers efficient inference for heterogeneous device capabilities and performance requirements through customizing neural architectures. SuperNet-based approaches offer a promising solution by generating a large number of model variants from a pre-trained ML model. However, applying SuperNet in existing frameworks suffers from tedious model-aware development and time-consuming hardware-aware profiling, which limits their practical adoption. We present AutoTailor, the first framework to enable automated, end-to-end SuperNet-based adaptive model deployment for edge devices. Unlike manual SuperNet construction, AutoTailor employs a computation graph-guided compilation approach to automatically transform user-provided ML models into SuperNets. To support efficient specialization, AutoTailor incorporates learning-free latency and accuracy predictors, enabling low-cost yet accurate performance prediction. Our extended evaluations demonstrate that AutoTailor reduces the lines of code for SuperNet construction by 11--27$\times$, decreases hardware-aware profiling costs by at least 11$\times$, and achieves up to 15.60\% absolute accuracy improvement and 60.03\% latency reduction compared to state-of-the-art approaches across diverse models and devices. --- ### INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifacts Authors: Anshul Bagaria Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22351v1 The growing realism of AI-generated images produced by recent GAN and diffusion models has intensified concerns over the reliability of visual media. Yet, despite notable progress in deepfake detection, current forensic systems degrade sharply under real-world conditions such as severe downsampling, compression, and cross-domain distribution shifts. Moreover, most detectors operate as opaque classifiers, offering little insight into why an image is flagged as synthetic, undermining trust and hindering adoption in high-stakes settings. We introduce INSIGHT (Interpretable Neural Semantic and Image-based Generative-forensic Hallucination Tracing), a unified multimodal framework for robust detection and transparent explanation of AI-generated images, even at extremely low resolutions (16x16 - 64x64). INSIGHT combines hierarchical super-resolution for amplifying subtle forensic cues without inducing misleading artifacts, Grad-CAM driven multi-scale localization to reveal spatial regions indicative of generative patterns, and CLIP-guided semantic alignment to map visual anomalies to human-interpretable descriptors. A vision-language model is then prompted using a structured ReAct + Chain-of-Thought protocol to produce consistent, fine-grained explanations, verified through a dual-stage G-Eval + LLM-as-a-judge pipeline to minimize hallucinations and ensure factuality. Across diverse domains, including animals, vehicles, and abstract synthetic scenes, INSIGHT substantially improves both detection robustness and explanation quality under extreme degradation, outperforming prior detectors and black-box VLM baselines. Our results highlight a practical path toward transparent, reliable AI-generated image forensics and establish INSIGHT as a step forward in trustworthy multimodal content verification. --- ### Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment Authors: Yang Chen, Xiaowei Xu, Shuai Wang, Chenhui Zhu, Ruxue Wen, Xubin Li, Tiezheng Ge, Limin Wang Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22345v2 Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for density estimation, and the reverse pass generates new samples from this space. This characteristic creates an intrinsic synergy between representation learning and data generation. However, the generative quality of standard NFs is limited by poor semantic representations from log-likelihood optimization. To remedy this, we propose a novel alignment strategy that creatively leverages the invertibility of NFs: instead of regularizing the forward pass, we align the intermediate features of the generative (reverse) pass with representations from a powerful vision foundation model, demonstrating superior effectiveness over naive alignment. We also introduce a novel training-free, test-time optimization algorithm for classification, which provides a more intrinsic evaluation of the NF's embedded semantic knowledge. Comprehensive experiments demonstrate that our approach accelerates the training of NFs by over 3.3$\times$, while simultaneously delivering significant improvements in both generative quality and classification accuracy. New state-of-the-art results for NFs are established on ImageNet 64$\times$64 and 256$\times$256. Our code is available at https://github.com/MCG-NJU/FlowBack. --- ### Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning Authors: Denis Huseljic, Marek Herde, Lukas Rauch, Paul Hahn, Bernhard Sick Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22344v2 Existing active learning (AL) strategies capture fundamentally different notions of data value, e.g., uncertainty or representativeness. Consequently, the effectiveness of strategies can vary substantially across datasets, models, and even AL cycles. Committing to a single strategy risks suboptimal performance, as no single strategy dominates throughout the entire AL process. We introduce REFINE, an ensemble AL method that combines multiple strategies without knowing in advance which will perform best. In each AL cycle, REFINE operates in two stages: (1) Progressive filtering iteratively refines the unlabeled pool by considering an ensemble of AL strategies, retaining promising candidates capturing different notions of value. (2) Coverage-based selection then chooses a final batch from this refined pool, ensuring all previously identified notions of value are accounted for. Extensive experiments across 6 classification datasets and 3 foundation models show that REFINE consistently outperforms individual strategies and existing ensemble methods. Notably, progressive filtering serves as a powerful preprocessing step that improves the performance of any individual AL strategy applied to the refined pool, which we demonstrate on an audio spectrogram classification use case. Finally, the ensemble of REFINE can be easily extended with upcoming state-of-the-art AL strategies. --- ### Test Time Training for AC Power Flow Surrogates via Physics and Operational Constraint Refinement Authors: Panteleimon Dogoulis, Mohammad Iman Alizadeh, Sylvain Kubler, Maxime Cordy Published: 2025-11-27 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2511.22343v1 Power Flow (PF) calculation based on machine learning (ML) techniques offer significant computational advantages over traditional numerical methods but often struggle to maintain full physical consistency. This paper introduces a physics-informed test-time training (PI-TTT) framework that enhances the accuracy and feasibility of ML-based PF surrogates by enforcing AC power flow equalities and operational constraints directly at inference time. The proposed method performs a lightweight self-supervised refinement of the surrogate outputs through few gradient-based updates, enabling local adaptation to unseen operating conditions without requiring labeled data. Extensive experiments on the IEEE 14-, 118-, and 300-bus systems and the PEGASE 1354-bus network show that PI-TTT reduces power flow residuals and operational constraint violations by one to two orders of magnitude compared with purely ML-based models, while preserving their computational advantage. The results demonstrate that PI-TTT provides fast, accurate, and physically reliable predictions, representing a promising direction for scalable and physics-consistent learning in power system analysis. --- ### Unexplored flaws in multiple-choice VQA make benchmarking unreliable Authors: Fabio Rosenthal, Sebastian Schmidt, Thorsten Graf, Thorsten Bagdonat, Stephan Günnemann, Leo Schwinn Published: 2025-11-27 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.22341v3 Previous works identify sensitivity to option order as a key issue in multiple-choice VQA (MC-VQA) evaluation and propose protocols to mitigate this effect. We show that such mitigation is insufficient to ensure the validity of MC-VQA as a reliable benchmark for Multimodal Large Language Model (MLLMs): performance remains highly sensitive to semantically neutral prompt format choices that are not controlled by current benchmarks. In a large-scale study spanning seven MLLMs and five MC-VQAs datasets, we find frequent rank reversals even under order-invariant evaluation. These reversals arise when we systematically vary option ID sets, delimiters, and separators, yielding 48 semantically equivalent prompt formats. Mechanistic analyses trace this instability to low-level language modeling effects: tokenizer-induced fusion or removal of option ID tokens introduces corrupted option ID tokens into the input sequence, while the choice of option ID sets directly affects the reliability of attention patterns for option selection. Accordingly, MC-VQA rankings correlate weakly with open-ended evaluation, indicating that MC-VQA reflects option-selection dynamics in addition to multimodal reasoning. These findings identify prompt formatting as a major, previously under-controlled confounder in MC-VQA benchmarking and motivate evaluation protocols that explicitly control prompt format sensitivity. --- ### Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends Authors: Pablo Prieto, Pablo Abad Published: 2025-11-27 Categories: cs.PF, cs.AI arXiv: https://arxiv.org/abs/2511.22334v2 Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy consumption, making them unsuitable for large language models (LLMs). Fortunately, Small Language Models (SLMs) offer lightweight alternatives that bring AI inference to resource-constrained environments by significantly reducing computational cost while remaining suitable for specialization and customization. In this scenario, selecting the hardware platform that best balances performance and efficiency for SLM inference is challenging due to strict resource limitations. To address this issue, this study evaluates the inference performance and energy efficiency of commercial CPUs (Intel and ARM), GPUs (NVIDIA), and NPUs (RaiderChip) for running SLMs. GPUs, the usual platform of choice, are compared against commercial NPUs and recent multi-core CPUs. While NPUs leverage custom hardware designs optimized for computation, modern CPUs increasingly incorporate dedicated features targeting language-model workloads. Using a common execution framework and a suite of state-of-the-art SLMs, we analyze both maximum achievable performance and processing and energy efficiency across commercial solutions available for each platform. The results indicate that specialized backends outperform general-purpose CPUs, with NPUs achieving the highest performance by a wide margin. Bandwidth normalization proves essential for fair cross-architecture comparisons. Although low-power ARM processors deliver competitive results when energy usage is considered, metrics that combine performance and power (such as EDP) again highlight NPUs as the dominant architecture. These findings show that designs optimized for both efficiency and performance offer a clear advantage for edge workloads. --- ### PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel Authors: Jinjun Yi, Zhixin Zhao, Yitao Hu, Ke Yan, Weiwei Sun, Hao Wang, Laiping Zhao, Yuhao Zhang, Wenxin Li, Keqiu Li Published: 2025-11-27 Categories: cs.DC, cs.CL arXiv: https://arxiv.org/abs/2511.22333v3 LLM serving is increasingly dominated by decode attention, which is a memory-bound operation due to massive KV cache loading from global memory. Meanwhile, real-world workloads exhibit substantial, hierarchical shared prefixes across requests (e.g., system prompts, tools/templates, RAG). Existing attention implementations fail to fully exploit prefix sharing: one-query-per-CTA execution repeatedly loads shared prefix KV cache, while one-size-fits-all tiling leaves on-chip resources idle and exacerbates bubbles for uneven KV lengths. These choices amplify memory bandwidth pressure and stall memory-bound decode attention. This paper introduces PAT, a prefix-aware attention kernel implementation for LLM decoding that organizes execution with a pack-forward-merge paradigm. PAT packs queries by shared prefix to reduce repeated memory accesses, runs a customized multi-tile kernel to achieve high resource efficiency. It further applies practical multi-stream forwarding and KV splitting to reduce resource bubbles. The final merge performs online softmax with negligible overhead. We implement PAT as an off-the-shelf plugin for vLLM. Evaluation on both real-world and synthetic workloads shows that PAT reduces attention latency by 53.5% on average and TPOT by 17.0-93.1% under the same configurations against state-of-the-art attention kernels. PAT's source code is publicly available at https://github.com/flashserve/PAT. --- ### On the Condition Number Dependency in Bilevel Optimization Authors: Lesi Chen, Kaiyi Ji, Jingzhao Zhang Published: 2025-11-27 Categories: math.OC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.22331v4 Bilevel optimization minimizes an objective function, defined by an upper-level problem whose feasible region is the solution of a lower-level problem. We study the oracle complexity of finding an $ε$-stationary point with first-order methods when the upper-level problem is nonconvex, and the lower-level problem is strongly convex. Recent works achieve a $\tilde{\mathcal{O}}(\bar κ_y^{7/2} ε^{-2})$ upper bound that is near-optimal in $ε$. In this work, we establish a new $Ω(κ_y^{5/2} ε^{-2})$ lower bound, where $κ_y \le \bar κ_y$ is the lower-level condition number. Our lower bound establishes the first provable gap {in terms of condition number dependency} between bilevel problems and minimax problems in this setup, and \textit{is tight up to logarithmic factors when the lower-level function is quadratic.} Our lower bounds can be extended to various settings. (1) For second-order and arbitrarily smooth problems, we show lower bounds of $Ω(κ_y^{9/4} ε^{-7/4})$ and $Ω(κ_y^{13/6} ε^{-5/3})$, respectively. (2) For convex--strongly-convex problems, we improve the previously best lower bound (Ji and Liang, JMLR 2022) from $Ω(κ_y /\sqrtε)$ to $Ω(κ_y^{3/2} / \sqrtε)$. (3) For stochastic nonconvex--strongly-convex problems, we also show the lower bounds of $Ω(κ_y^4 ε^{-4})$ and $Ω(κ_y^{9/2} ε^{-4})$ for stochastic Hessian-vector-product and stochastic first-order methods, respectively. --- ### Prompt-based Consistent Video Colorization Authors: Silvia Dani, Tiberio Uricchio, Lorenzo Seidenari Published: 2025-11-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.22330v1 Existing video colorization methods struggle with temporal flickering or demand extensive manual input. We propose a novel approach automating high-fidelity video colorization using rich semantic guidance derived from language and segmentation. We employ a language-conditioned diffusion model to colorize grayscale frames. Guidance is provided via automatically generated object masks and textual prompts; our primary automatic method uses a generic prompt, achieving state-of-the-art results without specific color input. Temporal stability is achieved by warping color information from previous frames using optical flow (RAFT); a correction step detects and fixes inconsistencies introduced by warping. Evaluations on standard benchmarks (DAVIS30, VIDEVO20) show our method achieves state-of-the-art performance in colorization accuracy (PSNR) and visual realism (Colorfulness, CDC), demonstrating the efficacy of automated prompt-based guidance for consistent video colorization. --- ### Content Adaptive Encoding For Interactive Game Streaming Authors: Shakarim Soltanayev, Odysseas Zisimopoulos, Mohammad Ashraful Anam, Man Cheung Kung, Angeliki Katsenou, Yiannis Andreopoulos Published: 2025-11-27 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.22327v1 Video-on-demand streaming has benefitted from \textit{content-adaptive encoding} (CAE), i.e., adaptation of resolution and/or quantization parameters for each scene based on convex hull optimization. However, CAE is very challenging to develop and deploy for interactive game streaming (IGS). Commercial IGS services impose ultra-low latency encoding with no lookahead or buffering, and have extremely tight compute constraints for any CAE algorithm execution. We propose the first CAE approach for resolution adaptation in IGS based on compact encoding metadata from past frames. Specifically, we train a convolutional neural network (CNN) to infer the best resolution from the options available for the upcoming scene based on a running window of aggregated coding block statistics from the current scene. By deploying the trained CNN within a practical IGS setup based on HEVC encoding, our proposal: (i) improves over the default fixed-resolution ladder of HEVC by 2.3 Bjøntegaard Delta-VMAF points; (ii) infers using 1ms of a single CPU core per scene, thereby having no latency overhead. --- ### Tracing Footsteps of Similar Cities: Modeling Urban Economic Vitality with Dynamic Inter-City Graph Embeddings Authors: Xiaofeng Li, Xiangyi Xiao, Xiaocong Du, Ying Zhang, Haipeng Zhang Published: 2025-11-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.22325v1 Urban economic vitality is a crucial indicator of a city's long-term growth potential, comprising key metrics such as the annual number of new companies and the population employed. However, modeling urban economic vitality remains challenging. This study develops ECO-GROW, a multi-graph framework modeling China's inter-city networks (2005-2021) to generate urban embeddings that model urban economic vitality. Traditional approaches relying on static city-level aggregates fail to capture a fundamental dynamic: the developmental trajectory of one city today may mirror that of its structurally similar counterparts tomorrow. ECO-GROW overcomes this limitation by integrating industrial linkages, POI similarities, migration similarities and temporal network evolution over 15 years. The framework combines a Dynamic Top-K GCN to adaptively select influential inter-city connections and an adaptive Graph Scorer mechanism to dynamically weight cross-regional impacts. Additionally, the model incorporates a link prediction task based on Barabasi Proximity, optimizing the graph representation. Experimental results demonstrate ECO-GROW's superior accuracy in predicting entrepreneurial activities and employment trends compared to conventional models. By open-sourcing our code, we enable government agencies and public sector organizations to leverage big data analytics for evidence-based urban planning, economic policy formulation, and resource allocation decisions that benefit society at large. --- ### RELiQ: Scalable Entanglement Routing via Reinforcement Learning in Quantum Networks Authors: Tobias Meuser, Jannis Weil, Aninda Lahiri, Marius Paraschiv Published: 2025-11-27 Categories: quant-ph, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2511.22321v1 Quantum networks are becoming increasingly important because of advancements in quantum computing and quantum sensing, such as recent developments in distributed quantum computing and federated quantum machine learning. Routing entanglement in quantum networks poses several fundamental as well as technical challenges, including the high dynamicity of quantum network links and the probabilistic nature of quantum operations. Consequently, designing hand-crafted heuristics is difficult and often leads to suboptimal performance, especially if global network topology information is unavailable. In this paper, we propose RELiQ, a reinforcement learning-based approach to entanglement routing that only relies on local information and iterative message exchange. Utilizing a graph neural network, RELiQ learns graph representations and avoids overfitting to specific network topologies - a prevalent issue for learning-based approaches. Our approach, trained on random graphs, consistently outperforms existing local information heuristics and learning-based approaches when applied to random and real-world topologies. When compared to global information heuristics, our method achieves similar or superior performance because of its rapid response to topology changes. --- ### Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization Authors: Jinying Xiao, Bin Ji, Shasha Li, Xiaodong Liu, Ma Jun, Chao Wang, Wei Li, Ye Zhong, Xuan Xie, Nyima Tashi, Jie Yu Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22316v2 Large Language Models (LLMs) quantization facilitates deploying LLMs in resource-limited settings, but existing methods that combine incompatible gradient optimization and quantization truncation lead to serious convergence pathology. This prolongs quantization time and degrades LLMs' task performance. Our studies confirm that Straight-Through Estimator (STE) on Stiefel manifolds introduce non-smoothness and gradient noise, obstructing optimization convergence and blocking high-fidelity quantized LLM development despite extensive training. To tackle the above limitations, we propose SingleQuant, a single-pass quantization framework that decouples from quantization truncation, thereby eliminating the above non-smoothness and gradient noise factors. Specifically, SingleQuant constructs Alignment Rotation Transformation (ART) and Uniformity Rotation Transformation (URT) targeting distinct activation outliers, where ART achieves smoothing of outlier values via closed-form optimal rotations, and URT reshapes distributions through geometric mapping. Both matrices comprise strictly formulated Givens rotations with predetermined dimensions and rotation angles, enabling promising LLMs task performance within a short time. Experimental results demonstrate SingleQuant's superiority over the selected baselines across diverse tasks on 7B-70B LLMs. To be more precise, SingleQuant enables quantized LLMs to achieve higher task performance while necessitating less time for quantization. For example, when quantizing LLaMA-2-13B, SingleQuant achieves 1,400$\times$ quantization speedup and increases +0.57\% average task performance compared to the selected best baseline. --- ### Named Entity Recognition for the Kurdish Sorani Language: Dataset Creation and Comparative Analysis Authors: Bakhtawar Abdalla, Rebwar Mala Nabi, Hassan Eshkiki, Fabio Caraffini Published: 2025-11-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.22315v1 This work contributes towards balancing the inclusivity and global applicability of natural language processing techniques by proposing the first 'name entity recognition' dataset for Kurdish Sorani, a low-resource and under-represented language, that consists of 64,563 annotated tokens. It also provides a tool for facilitating this task in this and many other languages and performs a thorough comparative analysis, including classic machine learning models and neural systems. The results obtained challenge established assumptions about the advantage of neural approaches within the context of NLP. Conventional methods, in particular CRF, obtain F1-scores of 0.825, outperforming the results of BiLSTM-based models (0.706) significantly. These findings indicate that simpler and more computationally efficient classical frameworks can outperform neural architectures in low-resource settings. --- ### DeXposure: A Dataset and Benchmarks for Inter-protocol Credit Exposure in Decentralized Financial Networks Authors: Wenbin Wu, Kejiang Qian, Alexis Lui, Christopher Jack, Yue Wu, Peter McBurney, Fengxiang He, Bryan Zhang Published: 2025-11-27 Categories: cs.LG, cs.CE, cs.SI, econ.GN arXiv: https://arxiv.org/abs/2511.22314v1 We curate the DeXposure dataset, the first large-scale dataset for inter-protocol credit exposure in decentralized financial networks, covering global markets of 43.7 million entries across 4.3 thousand protocols, 602 blockchains, and 24.3 thousand tokens, from 2020 to 2025. A new measure, value-linked credit exposure between protocols, is defined as the inferred financial dependency relationships derived from changes in Total Value Locked (TVL). We develop a token-to-protocol model using DefiLlama metadata to infer inter-protocol credit exposure from the token's stock dynamics, as reported by the protocols. Based on the curated dataset, we develop three benchmarks for machine learning research with financial applications: (1) graph clustering for global network measurement, tracking the structural evolution of credit exposure networks, (2) vector autoregression for sector-level credit exposure dynamics during major shocks (Terra and FTX), and (3) temporal graph neural networks for dynamic link prediction on temporal graphs. From the analysis, we observe (1) a rapid growth of network volume, (2) a trend of concentration to key protocols, (3) a decline of network density (the ratio of actual connections to possible connections), and (4) distinct shock propagation across sectors, such as lending platforms, trading exchanges, and asset management protocols. The DeXposure dataset and code have been released publicly. We envision they will help with research and practice in machine learning as well as financial risk monitoring, policy analysis, DeFi market modeling, amongst others. The dataset also contributes to machine learning research by offering benchmarks for graph clustering, vector autoregression, and temporal graph analysis. --- ### Sentiment Analysis Of Shopee Product Reviews Using Distilbert Authors: Zahri Aksa Dautd, Aviv Yuniar Rahman Published: 2025-11-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.22313v2 The rapid growth of digital commerce has led to the accumulation of a massive number of consumer reviews on online platforms. Shopee, as one of the largest e-commerce platforms in Southeast Asia, receives millions of product reviews every day containing valuable information regarding customer satisfaction and preferences. Manual analysis of these reviews is inefficient, thus requiring a computational approach such as sentiment analysis. This study examines the use of DistilBERT, a lightweight transformer-based deep learning model, for sentiment classification on Shopee product reviews. The dataset used consists of approximately one million English-language reviews that have been preprocessed and trained using the distilbert-base-uncased model. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics, and compared against benchmark models such as BERT and SVM. The results show that DistilBERT achieved an accuracy of 94.8%, slightly below BERT (95.3%) but significantly higher than SVM (90.2%), with computation time reduced by more than 55%. These findings demonstrate that DistilBERT provides an optimal balance between accuracy and efficiency, making it suitable for large scale sentiment analysis on e-commerce platforms. Keywords: Sentiment Analysis, DistilBERT, Shopee Reviews, Natural Language Processing, Deep Learning, Transformer Models. --- ### Token-Level Marginalization for Multi-Label LLM Classifiers Authors: Anjaneya Praharaj, Jaykumar Kasundra Published: 2025-11-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.22312v1 This paper addresses the critical challenge of deriving interpretable confidence scores from generative language models (LLMs) when applied to multi-label content safety classification. While models like LLaMA Guard are effective for identifying unsafe content and its categories, their generative architecture inherently lacks direct class-level probabilities, which hinders model confidence assessment and performance interpretation. This limitation complicates the setting of dynamic thresholds for content moderation and impedes fine-grained error analysis. This research proposes and evaluates three novel token-level probability estimation approaches to bridge this gap. The aim is to enhance model interpretability and accuracy, and evaluate the generalizability of this framework across different instruction-tuned models. Through extensive experimentation on a synthetically generated, rigorously annotated dataset, it is demonstrated that leveraging token logits significantly improves the interpretability and reliability of generative classifiers, enabling more nuanced content safety moderation. --- ### Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation Authors: Fiona Y. Wang, Di Sheng Lee, David L. Kaplan, Markus J. Buehler Published: 2025-11-27 Categories: cs.AI, cond-mat.mes-hall, cond-mat.soft, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.22311v1 Designing proteins de novo with tailored structural, physicochemical, and functional properties remains a grand challenge in biotechnology, medicine, and materials science, due to the vastness of sequence space and the complex coupling between sequence, structure, and function. Current state-of-the-art generative methods, such as protein language models (PLMs) and diffusion-based architectures, often require extensive fine-tuning, task-specific data, or model reconfiguration to support objective-directed design, thereby limiting their flexibility and scalability. To overcome these limitations, we present a decentralized, agent-based framework inspired by swarm intelligence for de novo protein design. In this approach, multiple large language model (LLM) agents operate in parallel, each assigned to a specific residue position. These agents iteratively propose context-aware mutations by integrating design objectives, local neighborhood interactions, and memory and feedback from previous iterations. This position-wise, decentralized coordination enables emergent design of diverse, well-defined sequences without reliance on motif scaffolds or multiple sequence alignments, validated with experiments on proteins with alpha helix and coil structures. Through analyses of residue conservation, structure-based metrics, and sequence convergence and embeddings, we demonstrate that the framework exhibits emergent behaviors and effective navigation of the protein fitness landscape. Our method achieves efficient, objective-directed designs within a few GPU-hours and operates entirely without fine-tuning or specialized training, offering a generalizable and adaptable solution for protein design. Beyond proteins, the approach lays the groundwork for collective LLM-driven design across biomolecular systems and other scientific discovery tasks. --- ### Small Object Detection for Birds with Swin Transformer Authors: Da Huo, Marc A. Kastner, Tingwei Liu, Yasutomo Kawanishi, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22310v1 Object detection is the task of detecting objects in an image. In this task, the detection of small objects is particularly difficult. Other than the small size, it is also accompanied by difficulties due to blur, occlusion, and so on. Current small object detection methods are tailored to small and dense situations, such as pedestrians in a crowd or far objects in remote sensing scenarios. However, when the target object is small and sparse, there is a lack of objects available for training, making it more difficult to learn effective features. In this paper, we propose a specialized method for detecting a specific category of small objects; birds. Particularly, we improve the features learned by the neck; the sub-network between the backbone and the prediction head, to learn more effective features with a hierarchical design. We employ Swin Transformer to upsample the image features. Moreover, we change the shifted window size for adapting to small objects. Experiments show that the proposed Swin Transformer-based neck combined with CenterNet can lead to good performance by changing the window sizes. We further find that smaller window sizes (default 2) benefit mAPs for small object detection. --- ### Enhanced Conditional Generation of Double Perovskite by Knowledge-Guided Language Model Feedback Authors: Inhyo Lee, Junhyeong Lee, Jongwon Park, KyungTae Lim, Seunghwa Ryu Published: 2025-11-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.22307v2 Double perovskites (DPs) are promising candidates for sustainable energy technologies due to their compositional tunability and compatibility with low-energy fabrication, yet their vast design space poses a major challenge for conditional materials discovery. This work introduces a multi-agent, text gradient-driven framework that performs DP composition generation under natural-language conditions by integrating three complementary feedback sources: LLM-based self-evaluation, DP-specific domain knowledge-informed feedback, and ML surrogate-based feedback. Analogous to how knowledge-informed machine learning improves the reliability of conventional data-driven models, our framework incorporates domain-informed text gradients to guide the generative process toward physically meaningful regions of the DP composition space. Systematic comparison of three incremental configurations, (i) pure LLM generation, (ii) LLM generation with LLM reasoning-based feedback, and (iii) LLM generation with domain knowledge-guided feedback, shows that iterative guidance from knowledge-informed gradients improves stability-condition satisfaction without additional training data, achieving over 98% compositional validity and up to 54% stable or metastable candidates, surpassing both the LLM-only baseline (43%) and prior GAN-based results (27%). Analyses of ML-based gradients further reveal that they enhance performance in in-distribution (ID) regions but become unreliable in out-of-distribution (OOD) regimes. Overall, this work provides the first systematic analysis of multi-agent, knowledge-guided text gradients for DP discovery and establishes a generalizable blueprint for MAS-driven generative materials design aimed at advancing sustainable technologies. --- ### FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts Authors: Dario Fenoglio, Mohan Li, Pietro Barbiero, Nicholas D. Lane, Marc Langheinrich, Martin Gjoreski Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22305v1 Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy. Traditional FL methods often use a global model to fit all clients, assuming that clients' data are independent and identically distributed (IID). However, when this assumption does not hold, the global model accuracy may drop significantly, limiting FL applicability in real-world scenarios. To address this gap, we propose FLUX, a novel clustering-based FL (CFL) framework that addresses the four most common types of distribution shifts during both training and test time. To this end, FLUX leverages privacy-preserving client-side descriptor extraction and unsupervised clustering to ensure robust performance and scalability across varying levels and types of distribution shifts. Unlike existing CFL methods addressing non-IID client distribution shifts, FLUX i) does not require any prior knowledge of the types of distribution shifts or the number of client clusters, and ii) supports test-time adaptation, enabling unseen and unlabeled clients to benefit from the most suitable cluster-specific models. Extensive experiments across four standard benchmarks, two real-world datasets and ten state-of-the-art baselines show that FLUX improves performance and stability under diverse distribution shifts, achieving an average accuracy gain of up to 23 percentage points over the best-performing baselines, while maintaining computational and communication overhead comparable to FedAvg. --- ### When AI Bends Metal: AI-Assisted Optimization of Design Parameters in Sheet Metal Forming Authors: Ahmad Tarraf, Koutaiba Kassem-Manthey, Seyed Ali Mohammadi, Philipp Martin, Lukas Moj, Semih Burak, Enju Park, Christian Terboven, Felix Wolf Published: 2025-11-27 Categories: cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2511.22302v2 Numerical simulations have revolutionized the industrial design process by reducing prototyping costs, design iterations, and enabling product engineers to explore the design space more efficiently. However, the growing scale of simulations demands substantial expert knowledge, computational resources, and time. A key challenge is identifying input parameters that yield optimal results, as iterative simulations are costly and can have a large environmental impact. This paper presents an AI-assisted workflow that reduces expert involvement in parameter optimization through the use of Bayesian optimization. Furthermore, we present an active learning variant of the approach, assisting the expert if desired. A deep learning model provides an initial parameter estimate, from which the optimization cycle iteratively refines the design until a termination condition (e.g.,energy budget or iteration limit) is met. We demonstrate our approach, based on a sheet metal forming process, and show how it enables us to accelerate the exploration of the design space while reducing the need for expert involvement. --- ### Data-driven informative priors for Bayesian inference with quasi-periodic data Authors: Javier Lopez-Santiago, Luca Martino, Joaquin Miguez, Gonzalo Vazquez-Vilar Published: 2025-11-27 Categories: stat.ML, astro-ph.IM, astro-ph.SR, cs.LG arXiv: https://arxiv.org/abs/2511.22296v1 Bayesian computational strategies for inference can be inefficient in approximating the posterior distribution in models that exhibit some form of periodicity. This is because the probability mass of the marginal posterior distribution of the parameter representing the period is usually highly concentrated in a very small region of the parameter space. Therefore, it is necessary to provide as much information as possible to the inference method through the parameter prior distribution. We intend to show that it is possible to construct a prior distribution from the data by fitting a Gaussian process (GP) with a periodic kernel. More specifically, we want to show that it is possible to approximate the marginal posterior distribution of the hyperparameter corresponding to the period in the kernel. Subsequently, this distribution can be used as a prior distribution for the inference method. We use an adaptive importance sampling method to approximate the posterior distribution of the hyperparameters of the GP. Then, we use the marginal posterior distribution of the hyperparameter related to the periodicity in order to construct a prior distribution for the period of the parametric model. This workflow is empirical Bayes, implemented as a modular (cut) transfer of a GP posterior for the period to the parametric model. We applied the proposed methodology to both synthetic and real data. We approximated the posterior distribution of the period of the GP kernel and then passed it forward as a posterior-as-prior with no feedback. Finally, we analyzed its impact on the marginal posterior distribution. --- ### Structure is Supervision: Multiview Masked Autoencoders for Radiology Authors: Sonia Laguna, Andrea Agostini, Alain Ryser, Samuel Ruiperez-Campillo, Irene Cannistraci, Moritz Vandenhirtz, Stephan Mandt, Nicolas Deperrois, Farhad Nooralahzadeh, Michael Krauthammer, Thomas M. Sutter, Julia E. Vogt Published: 2025-11-27 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.22294v4 Building robust medical machine learning systems requires pretraining strategies that exploit the intrinsic structure present in clinical data. We introduce Multiview Masked Autoencoder (MVMAE), a self-supervised framework that leverages the natural multi-view organization of radiology studies to learn view-invariant and disease-relevant representations. MVMAE combines masked image reconstruction with cross-view alignment, transforming clinical redundancy across projections into a powerful self-supervisory signal. We further extend this approach with MVMAE-V2T, which incorporates radiology reports as an auxiliary text-based learning signal to enhance semantic grounding while preserving fully vision-based inference. Evaluated on a downstream disease classification task on three large-scale public datasets, MIMIC-CXR, CheXpert, and PadChest, MVMAE consistently outperforms supervised and vision-language baselines. Furthermore, MVMAE-V2T provides additional gains, particularly in low-label regimes where structured textual supervision is most beneficial. Together, these results establish the importance of structural and textual supervision as complementary paths toward scalable, clinically grounded medical foundation models. --- ### GLA-Grad++: An Improved Griffin-Lim Guided Diffusion Model for Speech Synthesis Authors: Teysir Baoueb, Xiaoyu Bie, Mathieu Fontaine, Gaël Richard Published: 2025-11-27 Categories: cs.SD, cs.LG, eess.AS, eess.SP arXiv: https://arxiv.org/abs/2511.22293v1 Recent advances in diffusion models have positioned them as powerful generative frameworks for speech synthesis, demonstrating substantial improvements in audio quality and stability. Nevertheless, their effectiveness in vocoders conditioned on mel spectrograms remains constrained, particularly when the conditioning diverges from the training distribution. The recently proposed GLA-Grad model introduced a phase-aware extension to the WaveGrad vocoder that integrated the Griffin-Lim algorithm (GLA) into the reverse process to reduce inconsistencies between generated signals and conditioning mel spectrogram. In this paper, we further improve GLA-Grad through an innovative choice in how to apply the correction. Particularly, we compute the correction term only once, with a single application of GLA, to accelerate the generation process. Experimental results demonstrate that our method consistently outperforms the baseline models, particularly in out-of-domain scenarios. --- ### Adaptive tumor growth forecasting via neural & universal ODEs Authors: Kavya Subramanian, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat Published: 2025-11-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.22292v1 Forecasting tumor growth is critical for optimizing treatment. Classical growth models such as the Gompertz and Bertalanffy equations capture general tumor dynamics but may fail to adapt to patient-specific variability, particularly with limited data available. In this study, we leverage Neural Ordinary Differential Equations (Neural ODEs) and Universal Differential Equations (UDEs), two pillars of Scientific Machine Learning (SciML), to construct adaptive tumor growth models capable of learning from experimental data. Using the Gompertz model as a baseline, we replace rigid terms with adaptive neural networks to capture hidden dynamics through robust modeling in the Julia programming language. We use our models to perform forecasting under data constraints and symbolic recovery to transform the learned dynamics into explicit mathematical expressions. Our approach has the potential to improve predictive accuracy, guiding dynamic and effective treatment strategies for improved clinical outcomes. --- ### Online Dynamic Pricing of Complementary Products Authors: Marco Mussi, Marcello Restelli Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22291v1 Traditional pricing paradigms, once dominated by static models and rule-based heuristics, are increasingly being replaced by dynamic, data-driven approaches powered by machine learning algorithms. Despite their growing sophistication, most dynamic pricing algorithms focus on optimizing the price of each product independently, disregarding potential interactions among items. By neglecting these interdependencies in consumer demand across related goods, sellers may fail to capture the full potential of coordinated pricing strategies. In this paper, we address this problem by exploring dynamic pricing mechanisms designed explicitly for complementary products, aiming to exploit their joint demand structure to maximize overall revenue. We present an online learning algorithm considering both positive and negative interactions between products' demands. The algorithm utilizes transaction data to identify advantageous complementary relationships through an integer programming problem between different items, and then optimizes pricing strategies using data-driven and computationally efficient multi-armed bandit solutions based on heteroscedastic Gaussian processes. We validate our solution in a simulated environment, and we demonstrate that our solution improves the revenue w.r.t. a comparable learning algorithm ignoring such interactions. --- ### Match-and-Fuse: Consistent Generation from Unstructured Image Sets Authors: Kate Feingold, Omri Kaduri, Tali Dekel Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22287v2 We present Match-and-Fuse - a zero-shot, training-free method for consistent controlled generation of unstructured image sets - collections that share a common visual element, yet differ in viewpoint, time of capture, and surrounding content. Unlike existing methods that operate on individual images or densely sampled videos, our framework performs set-to-set generation: given a source set and user prompts, it produces a new set that preserves cross-image consistency of shared content. Our key idea is to model the task as a graph, where each node corresponds to an image and each edge triggers a joint generation of image pairs. This formulation consolidates all pairwise generations into a unified framework, enforcing local consistency while ensuring global coherence across the entire set. This is achieved by fusing internal features across image pairs, guided by dense input correspondences, without requiring masks or manual supervision, and by leveraging an emergent prior in text-to-image models that encourages coherent generation when multiple views share a single canvas. Match-and-Fuse achieves state-of-the-art consistency and visual quality, and unlocks new capabilities for content creation from image collections. --- ### The Hidden Cost of Approximation in Online Mirror Descent Authors: Ofir Schlisselberg, Uri Sherman, Tomer Koren, Yishay Mansour Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22283v2 Online mirror descent (OMD) is a fundamental algorithmic paradigm that underlies many algorithms in optimization, machine learning and sequential decision-making. The OMD iterates are defined as solutions to optimization subproblems which, oftentimes, can be solved only approximately, leading to an inexact version of the algorithm. Nonetheless, existing OMD analyses typically assume an idealized error free setting, thereby limiting our understanding of performance guarantees that should be expected in practice. In this work we initiate a systematic study into inexact OMD, and uncover an intricate relation between regularizer smoothness and robustness to approximation errors. When the regularizer is uniformly smooth, we establish a tight bound on the excess regret due to errors. Then, for barrier regularizers over the simplex and its subsets, we identify a sharp separation: negative entropy requires exponentially small errors to avoid linear regret, whereas log-barrier and Tsallis regularizers remain robust even when the errors are only polynomial. Finally, we show that when the losses are stochastic and the domain is the simplex, negative entropy regains robustness-but this property does not extend to all subsets, where exponentially small errors are again necessary to avoid suboptimal regret. --- ### Collapse of Patches: Ranking Image Patches for Efficient Visual Modeling Authors: Wei Guo, Shunqi Mao, Zhuonan Liang, Xuanhua Yin, Heng Wang, Weidong Cai Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22281v2 Observing certain patches in an image reduces the uncertainty of others. Their realization lowers the distribution entropy of each remaining patch feature, analogous to collapsing a particle's wave function in quantum mechanics. This phenomenon can intuitively be called patch collapse. To identify which patches are most relied on during a target region's collapse, we learn an autoencoder that softly selects a subset of informative patches during reconstruction. Graphing these learned dependencies for each patch's PageRank score reveals the optimal patch order to realize an image. We show that respecting this order benefits various masked image modeling methods. First, autoregressive image generation can be boosted by finetuning with the ordered generation sequence. Second, we introduce a new setup for image classification by exposing Vision Transformers only to high-rank patches in the collapse order. Seeing 22% of such patches is sufficient to achieve high accuracy. With these experiments, we propose patch collapse as a novel image modeling perspective that promotes vision efficiency. --- ### TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation Authors: Henrijs Princis, Arindam Sharma, Cristina David Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22277v2 Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and flexible framework to date for exploring decoding strategies, constraints, and hyperparameters in LLMs, and use it in code generation to enforce correctness and structure during decoding rather than relying on prompt engineering. TreeCoder represents decoding as a tree search over candidate programs, where both decoding strategies and constraint functions - such as style, syntax, execution - are treated as first-class, optimisable components. This design enables systematic exploration and automatic tuning of decoding configurations using standard optimisation techniques. Experiments on the MBPP (Python) and SQL-Spider benchmarks show that TreeCoder consistently improves accuracy across open-source models such as CodeLlama, Mistral and DeepSeek, often outperforming their unconstrained baselines by considerable margins. --- ### RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems Authors: Mengfan Li, Xuanhua Shi, Yang Deng Published: 2025-11-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.22275v1 Large Language models are revolutionizing the conversational recommender systems through their impressive capabilities in instruction comprehension, reasoning, and human interaction. A core factor underlying effective recommendation dialogue is the ability to infer and reason about users' mental states (such as desire, intention, and belief), a cognitive capacity commonly referred to as Theory of Mind. Despite growing interest in evaluating ToM in LLMs, current benchmarks predominantly rely on synthetic narratives inspired by Sally-Anne test, which emphasize physical perception and fail to capture the complexity of mental state inference in realistic conversational settings. Moreover, existing benchmarks often overlook a critical component of human ToM: behavioral prediction, the ability to use inferred mental states to guide strategic decision-making and select appropriate conversational actions for future interactions. To better align LLM-based ToM evaluation with human-like social reasoning, we propose RecToM, a novel benchmark for evaluating ToM abilities in recommendation dialogues. RecToM focuses on two complementary dimensions: Cognitive Inference and Behavioral Prediction. The former focus on understanding what has been communicated by inferring the underlying mental states. The latter emphasizes what should be done next, evaluating whether LLMs can leverage these inferred mental states to predict, select, and assess appropriate dialogue strategies. Extensive experiments on state-of-the-art LLMs demonstrate that RecToM poses a significant challenge. While the models exhibit partial competence in recognizing mental states, they struggle to maintain coherent, strategic ToM reasoning throughout dynamic recommendation dialogues, particularly in tracking evolving intentions and aligning conversational strategies with inferred mental states. --- ### UCB for Large-Scale Pure Exploration: Beyond Sub-Gaussianity Authors: Zaile Li, Weiwei Fan, L. Jeff Hong Published: 2025-11-27 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.22273v2 Selecting the best alternative from a finite set is the central objective of ranking and selection (R&S) and best arm identification (BAI). Traditional R&S or BAI approaches have predominantly relied on Gaussian or sub-Gaussian assumptions on the performance distributions of all alternatives, which limit their applicability to non-sub-Gaussian---especially heavy-tailed---problems. The need to move beyond sub-Gaussianity may become even more critical in large-scale problems, which tend to be especially sensitive to distributional specifications. In this paper, motivated by the widespread use of upper confidence bound (UCB) algorithms in sequential decision making, we investigate their performance in large-scale, non-sub-Gaussian R&S settings. We consider the simplest category of UCB algorithms, where the UCB value for each alternative is defined as the sample mean plus an exploration bonus that depends only on its own sample size. We abstract this into a meta-UCB algorithm and propose letting it select the alternative with the largest sample size as the best upon stopping. For this meta-UCB algorithm, we first derive a distribution-free lower bound on the probability of correct selection. Building on this bound, we first study the indifference-zone formulation and show that the meta-UCB algorithm---and therefore a broad class of UCB algorithms---achieves sample optimality as long as the variances are uniformly bounded. We then extend sample optimality to a non-indifference-zone configuration with polynomially shrinking mean gaps under the same variance assumption. These results demonstrate the applicability of UCB algorithms to large-scale R&S problems with non-sub-Gaussian distributions. Numerical experiments support our results and provide additional insights into the comparative behaviors of UCB algorithms within and beyond our meta-UCB framework. --- ### Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs Authors: Zhongjie Shi, Puyu Wang, Chenyang Zhang, Yuan Cao Published: 2025-11-27 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.22270v2 Modern deep learning techniques focus on extracting intricate information from data to achieve accurate predictions. However, the training datasets may be crowdsourced and include sensitive information, such as personal contact details, financial data, and medical records. As a result, there is a growing emphasis on developing privacy-preserving training algorithms for neural networks that maintain good performance while preserving privacy. In this paper, we investigate the generalization and privacy performances of the differentially private gradient descent (DP-GD) algorithm, which is a private variant of the gradient descent (GD) by incorporating additional noise into the gradients during each iteration. Moreover, we identify a concrete learning task where DP-GD can achieve superior generalization performance compared to GD in training two-layer Huberized ReLU convolutional neural networks (CNNs). Specifically, we demonstrate that, under mild conditions, a small signal-to-noise ratio can result in GD producing training models with poor test accuracy, whereas DP-GD can yield training models with good test accuracy and privacy guarantees if the signal-to-noise ratio is not too small. This indicates that DP-GD has the potential to enhance model performance while ensuring privacy protection in certain learning tasks. Numerical simulations are further conducted to support our theoretical results. --- ### FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning Authors: Yuan Yao, Lixu Wang, Jiaqi Wu, Jin Song, Simin Chen, Zehua Wang, Zijian Tian, Wei Chen, Huixia Li, Xiaoxiao Li Published: 2025-11-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.22265v2 Federated learning (FL) enables collaborative training across clients while preserving privacy. While most existing FL methods assume homogeneous model architectures, client heterogeneity in both data and resources makes this assumption impractical, thus motivating model-heterogeneous FL. To address this problem, we propose Federated Representation Entanglement (FedRE), a framework built upon a novel form of client knowledge termed entangled representation. Specifically, each client aggregates its local representations into a single entangled representation using normalized random weights, and then applies the same weights to integrate the corresponding one-hot label encodings into an entangled-label encoding. Both are subsequently uploaded to the server to train a global classifier. During training, each entangled representation is supervised across categories via its entangled-label encoding, while random weights are re-sampled at each round to introduce diversity, alleviating overconfidence in the global classifier and yielding smoother decision boundaries. Moreover, each client uploads a single entangled representation along with its entangled-label encoding, mitigating the risk of representation inversion attacks and reducing communication overhead. Extensive experiments demonstrate that FedRE achieves an effective trade-off among model performance, privacy protection, and communication overhead. The codes are available at https://github.com/AIResearch-Group/FedRE. --- ### DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving Authors: Xiaosong Jia, Yanhao Liu, Yu Hong, Renqiu Xia, Junqi You, Bin Sun, Zhihui Hao, Junchi Yan Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22264v2 Feed-forward reconstruction has been progressed rapidly, with the Visual Geometry Grounded Transformer (VGGT) being a notable baseline. However, directly applying VGGT to autonomous driving (AD) fails to capture three domain-specific priors: (i) Sparse Spatial Overlap: the overlap among mutli-view cameras is minimal due to $360^{\circ}$ coverage requirements under budget control, which renders global attention among all images inefficient; (ii) Calibrated Geometric Constraints: the absolute distance among cameras is generally accessible for AD data with calibration process before driving. Standard VGGT is unable to directly utilize such information for absolute scale scene reconstruction; (iii) Rigid Extrinsic Constancy: relative poses of multi-view cameras are approximately static, i.e., the ego-motion is the same for all cameras. To bridge these gaps, we propose DriveVGGT, a scale-aware reconstruction framework that explicitly integrates these priors through three targeted components. First, for the Sparse Spatial Overlap in (i), we introduce a Temporal Video Attention (TVA) module to process multi-camera videos independently. Second, for Calibrated Geometric Constraints in (ii), a Multi-camera Consistency Attention (MCA) module is designed to directly utilize the calibration information among cameras with a scale head for absolute scale scene reconstruction. Finally, to utilize Rigid Extrinsic Constancy in (iii), we reformulate the decoding process of VGGT into factorized sequential pose head and ego motion head. On AD datasets, experiments demonstrate that DriveVGGT reduces inference time by 49.3\% while improving depth and pose estimation compared to vanilla VGGT in long-sequence scenarios. It consistently outperforms recent SOTA variants. Meanwhile, extensive ablation studies verify the effectiveness of each devised module. --- ### Efficiency and Effectiveness of SPLADE Models on Billion-Scale Web Document Title Authors: Taeryun Won, Tae Kwan Lee, Hiun Kim, Hyemin Lee Published: 2025-11-27 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.22263v1 This paper presents a comprehensive comparison of BM25, SPLADE, and Expanded-SPLADE models in the context of large-scale web document retrieval. We evaluate the effectiveness and efficiency of these models on datasets spanning from tens of millions to billions of web document titles. SPLADE and Expanded-SPLADE, which utilize sparse lexical representations, demonstrate superior retrieval performance compared to BM25, especially for complex queries. However, these models incur higher computational costs. We introduce pruning strategies, including document-centric pruning and top-k query term selection, boolean query with term threshold to mitigate these costs and improve the models' efficiency without significantly sacrificing retrieval performance. The results show that Expanded-SPLADE strikes the best balance between effectiveness and efficiency, particularly when handling large datasets. Our findings offer valuable insights for deploying sparse retrieval models in large-scale search engines. --- ### Can Protective Watermarking Safeguard the Copyright of 3D Gaussian Splatting? Authors: Wenkai Huang, Yijia Guo, Gaolei Li, Lei Ma, Hang Zhang, Liwen Hu, Jiazheng Wang, Jianhua Li, Tiejun Huang Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22262v2 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for 3D scenes, widely adopted due to its exceptional efficiency and high-fidelity visual quality. Given the significant value of 3DGS assets, recent works have introduced specialized watermarking schemes to ensure copyright protection and ownership verification. However, can existing 3D Gaussian watermarking approaches genuinely guarantee robust protection of the 3D assets? In this paper, for the first time, we systematically explore and validate possible vulnerabilities of 3DGS watermarking frameworks. We demonstrate that conventional watermark removal techniques designed for 2D images do not effectively generalize to the 3DGS scenario due to the specialized rendering pipeline and unique attributes of each gaussian primitives. Motivated by this insight, we propose GSPure, the first watermark purification framework specifically for 3DGS watermarking representations. By analyzing view-dependent rendering contributions and exploiting geometrically accurate feature clustering, GSPure precisely isolates and effectively removes watermark-related Gaussian primitives while preserving scene integrity. Extensive experiments demonstrate that our GSPure achieves the best watermark purification performance, reducing watermark PSNR by up to 16.34dB while minimizing degradation to original scene fidelity with less than 1dB PSNR loss. Moreover, it consistently outperforms existing methods in both effectiveness and generalization. Our code is available at https://github.com/insightlab-CG-3DV/GSPure. --- ### Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable Critiques Authors: Guifeng Wang, Yuanfeng Song, Meng Yang, Tao Zhu, Xiaoming Yin, Xing Chen Published: 2025-11-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.22258v1 Text-to-SQL, a pivotal natural language processing (NLP) task that converts textual queries into executable SQL, has seen substantial progress in recent years. However, existing evaluation and reward mechanisms used to train and assess the text-to-SQL models remain a critical bottleneck. Current approaches heavily rely on manually annotated gold SQL queries, which are costly to produce and impractical for large-scale evaluation. More importantly, most reinforcement learning (RL) methods in text-to-SQL leverage only the final binary execution outcome as the reward signal, a coarse-grained supervision that overlooks detailed structural and semantic errors from the perspective of rubrics. To address these challenges, we propose RuCo-C, a novel generative judge model for fine-grained, query-specific automatic evaluation using interpretable critiques without human intervention. Our framework first automatically generates query-specific evaluation rubrics for human-free annotation, linking them to interpretable critiques. Subsequently, it integrates densified reward feedback through a "progressive exploration" strategy during the RL training process, which dynamically adjusts the rewards to enhance the model's performance. Comprehensive experiments demonstrate that RuCo-C outperforms existing methods in text-to-SQL evaluation, yielding significant performance gains. --- ### UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation Authors: Dengbo Chen, Ziwei Zhao, Kexin Zhang, Shishuang Zhao, Junjie Hou, Yaqian Wang, Nianxi Liao, Anlan Sun, Fei Gao, Jia Ding, Yuhang Liu, Dong Wang Published: 2025-11-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.22256v1 Despite significant strides in medical foundation models, the ultrasound domain lacks a comprehensive solution capable of bridging low-level Ultrasound Grounded Perception (e.g., segmentation, localization) and high-level Ultrasound Comprehensive Interpretation (e.g., diagnosis, reasoning). To bridge this gap, we propose UMind-VL, a unified foundation model designed to synergize pixel-level structural understanding with complex clinical reasoning. We first introduce UMind-DS, a large-scale multimodal dataset comprising 1.2 million ultrasound image-text pairs across 16 anatomical regions, enriching standard data with pixel-level annotations and clinician-validated rationales. Architecturally, UMind-VL incorporates a lightweight Dynamic Convolutional Mask Decoder that generates masks via dynamic kernels conditioned on LLM outputs. This design, combined with task-specific tokens, unifies segmentation, detection, geometric measurement, and diagnosis tasks within a single framework. Extensive evaluations demonstrate that UMind-VL significantly outperforms existing generalist multimodal models and achieves performance on par with, or superior to, state-of-the-art specialist models across segmentation, detection, keypoint localization, and diagnostic reasoning benchmarks, while maintaining strong generalization ability. We demonstrate the capability of UMind-VL in Figure 1. --- ### Co-Evolving Agents: Learning from Failures as Hard Negatives Authors: Yeonsung Jung, Trilok Padhi, Sina Shaham, Dipika Khullar, Joonhyun Jeong, Ninareh Mehrabi, Eunho Yang Published: 2025-11-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.22254v5 Self-evolving agents improve their performance on long-horizon tasks by learning from their own interactions with an environment. A common approach uses the resulting failed trajectories as negatives for preference training. However, collecting an agent's own failures does not ensure that they provide informative supervision for further improvement. Obvious failures may be easy to reject without learning to identify errors in more plausible attempts. These plausible but incorrect trajectories can serve as hard negatives, helping agents learn to distinguish successful behavior from failures with less obvious errors. To enable agents to generate and learn from such informative negatives, we propose a co-evolving framework that couples a target agent's self-improvement with a failure agent trained to generate hard negatives. The failure agent learns exclusively from both agents' failed trajectories to generate higher-reward failures, which the target agent uses as negatives for preference training. As the target policy improves, its failures provide new training data for the failure agent. The updated failure agent, in turn, provides new negatives for target training, allowing negative generation to adapt alongside the target policy. Across online shopping, scientific reasoning, and interactive SQL querying, our framework improves average task reward by 5.7 over the baseline. These results demonstrate the value of learning to generate and use informative failures for agent self-improvement. We will make our code publicly available. ---