# Research Papers — 2025-12 · bundle page 170 of 175 > Full-text markdown of papers #8451–8500 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/170 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/169.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/171.md) ### Storage capacity of perceptron with variable selection Authors: Yingying Xu, Masayuki Ohzeki, Yoshiyuki Kabashima Published: 2025-12-01 Categories: cs.IT, cond-mat.dis-nn, stat.ML arXiv: https://arxiv.org/abs/2512.01861v1 A central challenge in machine learning is to distinguish genuine structure from chance correlations in high-dimensional data. In this work, we address this issue for the perceptron, a foundational model of neural computation. Specifically, we investigate the relationship between the pattern load $α$ and the variable selection ratio $ρ$ for which a simple perceptron can perfectly classify $P = αN$ random patterns by optimally selecting $M = ρN$ variables out of $N$ variables. While the Cover--Gardner theory establishes that a random subset of $ρN$ dimensions can separate $αN$ random patterns if and only if $α< 2ρ$, we demonstrate that optimal variable selection can surpass this bound by developing a method, based on the replica method from statistical mechanics, for enumerating the combinations of variables that enable perfect pattern classification. This not only provides a quantitative criterion for distinguishing true structure in the data from spurious regularities, but also yields the storage capacity of associative memory models with sparse asymmetric couplings. --- ### COACH: Collaborative Agents for Contextual Highlighting -- A Multi-Agent Framework for Sports Video Analysis Authors: Tsz-To Wong, Ching-Chun Huang, Hong-Han Shuai Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01853v2 Intelligent sports video analysis demands a comprehensive understanding of temporal context, from micro-level actions to macro-level game strategies. Existing end-to-end models often struggle with this temporal hierarchy, offering solutions that lack generalization, incur high development costs for new tasks, and suffer from poor interpretability. To overcome these limitations, we propose a reconfigurable Multi-Agent System (MAS) as a foundational framework for sports video understanding. In our system, each agent functions as a distinct "cognitive tool" specializing in a specific aspect of analysis. The system's architecture is not confined to a single temporal dimension or task. By leveraging iterative invocation and flexible composition of these agents, our framework can construct adaptive pipelines for both short-term analytic reasoning (e.g., Rally QA) and long-term generative summarization (e.g., match summaries). We demonstrate the adaptability of this framework using two representative tasks in badminton analysis, showcasing its ability to bridge fine-grained event detection and global semantic organization. This work presents a paradigm shift towards a flexible, scalable, and interpretable system for robust, cross-task sports video intelligence. The project homepage is available at https://aiden1020.github.io/COACH-project-page --- ### BHRAM-IL: A Benchmark for Hallucination Recognition and Assessment in Multiple Indian Languages Authors: Hrishikesh Terdalkar, Kirtan Bhojani, Aryan Dongare, Omm Aditya Behera Published: 2025-12-01 Categories: cs.CL, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2512.01852v1 Large language models (LLMs) are increasingly deployed in multilingual applications but often generate plausible yet incorrect or misleading outputs, known as hallucinations. While hallucination detection has been studied extensively in English, under-resourced Indian languages remain largely unexplored. We present BHRAM-IL, a benchmark for hallucination recognition and assessment in multiple Indian languages, covering Hindi, Gujarati, Marathi, Odia, along with English. The benchmark comprises 36,047 curated questions across nine categories spanning factual, numerical, reasoning, and linguistic tasks. We evaluate 14 state-of-the-art multilingual LLMs on a benchmark subset of 10,265 questions, analyzing cross-lingual and factual hallucinations across languages, models, scales, categories, and domains using category-specific metrics normalized to (0,1) range. Aggregation over all categories and models yields a primary score of 0.23 and a language-corrected fuzzy score of 0.385, demonstrating the usefulness of BHRAM-IL for hallucination-focused evaluation. The dataset, and the code for generation and evaluation are available on GitHub (https://github.com/sambhashana/BHRAM-IL/) and HuggingFace (https://huggingface.co/datasets/sambhashana/BHRAM-IL/) to support future research in multilingual hallucination detection and mitigation. --- ### Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching Authors: Yue Pan, Tao Sun, Liyuan Zhu, Lucas Nunes, Iro Armeni, Jens Behley, Cyrill Stachniss Published: 2025-12-01 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.01850v2 Point cloud registration aligns multiple unposed point clouds into a common reference frame and is a core step for 3D reconstruction and robot localization without initial guess. In this work, we cast registration as conditional generation: a learned, continuous point-wise velocity field transports noisy points to a registered scene, from which the pose of each view is recovered. Unlike prior methods that perform correspondence matching to estimate pairwise transformations and then optimize a pose graph for multi-view registration, our model directly generates the registered point cloud, yielding both efficiency and point-level global consistency. By scaling the training data and conducting test-time rigidity enforcement, our approach achieves state-of-the-art results on existing pairwise registration benchmarks and on our proposed cross-domain multi-view registration benchmark. The superior zero-shot performance on this benchmark shows that our method generalizes across view counts, scene scales, and sensor modalities even with low overlap. Source code available at: https://github.com/PRBonn/RAP. --- ### Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability Authors: Jinghan Jia, Nathalie Baracaldo, Sijia Liu Published: 2025-12-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.01848v1 Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving. However, this explicit reasoning process also introduces new safety risks, as unsafe behaviors often emerge within intermediate reasoning trajectories, even when final answers appear harmless. Existing safety alignment approaches primarily rely on supervised fine-tuning (SFT) over safety-oriented long CoT datasets. While intuitive, we find that SFT produces inconsistent safety improvements, degrades reasoning ability, and generalizes poorly across model families. These limitations suggest that purely supervised approaches are insufficient for robust safety alignment in LRMs. To address this, we investigate reinforcement learning (RL) as a complementary optimization framework for LRM safety training. Unlike SFT, RL directly optimizes model policies with reward feedback, enabling more adaptive and stable alignment. Extensive experiments across multiple model families and benchmarks show that RL achieves stronger and more consistent safety gains while maintaining reasoning competence. Further analysis of reflection dynamics and token-level entropy reveals that RL suppresses unsafe exploratory reasoning while preserving reflective depth, leading to safer and more reliable reasoning processes. --- ### PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models Authors: Zeqing Wang, Keze Wang, Lei Zhang Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01843v3 Driven by the growing capacity and training scale, Text-to-Video (T2V) generation models have recently achieved substantial progress in video quality, length, and instruction-following capability. However, whether these models can understand physics and generate physically plausible videos remains a question. While Vision-Language Models (VLMs) have been widely used as general-purpose evaluators in various applications, they struggle to identify the physically impossible content from generated videos. To investigate this issue, we construct a \textbf{PID} (\textbf{P}hysical \textbf{I}mplausibility \textbf{D}etection) dataset, which consists of a \textit{test split} of 500 manually annotated videos and a \textit{train split} of 2,588 paired videos, where each implausible video is generated by carefully rewriting the caption of its corresponding real-world video to induce T2V models producing physically implausible content. With the constructed dataset, we introduce a lightweight fine-tuning approach, enabling VLMs to not only detect physically implausible events but also generate textual explanations on the violated physical principles. Taking the fine-tuned VLM as a physical plausibility detector and explainer, namely \textbf{PhyDetEx}, we benchmark a series of state-of-the-art T2V models to assess their adherence to physical laws. Our findings show that although recent T2V models have made notable progress toward generating physically plausible content, understanding and adhering to physical laws remains a challenging issue, especially for open-source models. Our dataset, training code, and checkpoints are available at \href{https://github.com/Zeqing-Wang/PhyDetEx}{https://github.com/Zeqing-Wang/PhyDetEx}. --- ### Mitigating Gender Bias in Depression Detection via Counterfactual Inference Authors: Mingxuan Hu, Hongbo Ma, Xinlan Wu, Ziqi Liu, Jiaqi Liu, Yangbin Chen Published: 2025-12-01 Categories: cs.LG, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.01834v2 Audio-based depression detection models have demonstrated promising performance but often suffer from gender bias due to imbalanced training data. Epidemiological statistics show a higher prevalence of depression in females, leading models to learn spurious correlations between gender and depression. Consequently, models tend to over-diagnose female patients while underperforming on male patients, raising significant fairness concerns. To address this, we propose a novel Counterfactual Debiasing Framework grounded in causal inference. We construct a causal graph to model the decision-making process and identify gender bias as the direct causal effect of gender on the prediction. During inference, we employ counterfactual inference to estimate and subtract this direct effect, ensuring the model relies primarily on authentic acoustic pathological features. Extensive experiments on the DAIC-WOZ dataset using two advanced acoustic backbones demonstrate that our framework not only significantly reduces gender bias but also improves overall detection performance compared to existing debiasing strategies. --- ### Deconstructing Generative Diversity: An Information Bottleneck Analysis of Discrete Latent Generative Models Authors: Yudi Wu, Wenhao Zhao, Dianbo Liu Published: 2025-12-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.01831v1 Generative diversity varies significantly across discrete latent generative models such as AR, MIM, and Diffusion. We propose a diagnostic framework, grounded in Information Bottleneck (IB) theory, to analyze the underlying strategies resolving this behavior. The framework models generation as a conflict between a 'Compression Pressure' - a drive to minimize overall codebook entropy - and a 'Diversity Pressure' - a drive to maximize conditional entropy given an input. We further decompose this diversity into two primary sources: 'Path Diversity', representing the choice of high-level generative strategies, and 'Execution Diversity', the randomness in executing a chosen strategy. To make this decomposition operational, we introduce three zero-shot, inference-time interventions that directly perturb the latent generative process and reveal how models allocate and express diversity. Application of this probe-based framework to representative AR, MIM, and Diffusion systems reveals three distinct strategies: "Diversity-Prioritized" (MIM), "Compression-Prioritized" (AR), and "Decoupled" (Diffusion). Our analysis provides a principled explanation for their behavioral differences and informs a novel inference-time diversity enhancement technique. --- ### OpenREAD: Reinforced Open-Ended Reasoning for End-to-End Autonomous Driving with LLM-as-Critic Authors: Songyan Zhang, Wenhui Huang, Zhan Chen, Chua Jiahao Collister, Qihang Huang, Chen Lv Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01830v2 Recently, two-stage fine-tuning strategies, e.g., acquiring essential driving knowledge through supervised fine-tuning (SFT) and further enhancing decision-making and planning via reinforcement fine-tuning (RFT), have shown strong potential in advancing the knowledge-driven autonomous driving (AD) paradigm. However, the learning nature of SFT still limits the generalization of reasoning, thereby constraining the full potential of driving performance. Meanwhile, current RFT approaches are primarily applied to downstream tasks, since scene understanding is an open-ended problem where corresponding rewards are difficult to quantify. To address these limitations, we propose OpenREAD, an OPEN-ended REasoning reinforced vision-language model (VLM)-based autonomous driving (AD) framework that enables end-to-end RFT across the full spectrum from high-level reasoning to low-level trajectory planning. Specifically, we begin by constructing large-scale Chain-of-Thought (CoT) annotations on open-source driving-related knowledge datasets, and employ the powerful Qwen3 large language model (LLM) as the critic in RFT to quantify reasoning quality for open-ended questions during reward modeling. Extensive experiments confirm that joint end-to-end RFT yields substantial improvements in both upstream and downstream tasks, enabling OpenREAD to achieve state-of-the-art performance on reasoning and planning benchmarks. --- ### CauSight: Learning to Supersense for Visual Causal Discovery Authors: Yize Zhang, Meiqi Chen, Sirui Chen, Bo Peng, Yanxi Zhang, Tianyu Li, Chaochao Lu Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01827v1 Causal thinking enables humans to understand not just what is seen, but why it happens. To replicate this capability in modern AI systems, we introduce the task of visual causal discovery. It requires models to infer cause-and-effect relations among visual entities across diverse scenarios instead of merely perceiving their presence. To this end, we first construct the Visual Causal Graph dataset (VCG-32K), a large-scale collection of over 32,000 images annotated with entity-level causal graphs, and further develop CauSight, a novel vision-language model to perform visual causal discovery through causally aware reasoning. Our training recipe integrates three components: (1) training data curation from VCG-32K, (2) Tree-of-Causal-Thought (ToCT) for synthesizing reasoning trajectories, and (3) reinforcement learning with a designed causal reward to refine the reasoning policy. Experiments show that CauSight outperforms GPT-4.1 on visual causal discovery, achieving over a threefold performance boost (21% absolute gain). Our code, model, and dataset are fully open-sourced at project page: https://github.com/OpenCausaLab/CauSight. --- ### HERMES: Heterogeneous Application-Enabled Routing Middleware for Edge-IoT Systems Authors: Jéssica Consciência, António Grilo Published: 2025-12-01 Categories: cs.NI, cs.NE arXiv: https://arxiv.org/abs/2512.01824v2 The growth of the Internet of Things has enabled a new generation of applications, pushing computation and intelligence toward the network edge. This trend, however, exposes challenges, as the heterogeneity of devices and the complex requirements of applications are often misaligned with the assumptions of traditional routing protocols, which lack the flexibility to accommodate application-layer metrics and policies. This work addresses this gap by proposing a software framework that enhances routing flexibility by dynamically incorporating application-aware decisions. The core of the work establishes a multi-hop Wi-Fi network of heterogeneous devices, specifically ESP8266, ESP32, and Raspberry Pi 3B. The routing layer follows a proactive approach, while the network is fault-tolerant, maintaining operation despite both node loss and message loss. On top of this, a middleware layer introduces three strategies for influencing routing behavior: two adapt the path a message traverses until arriving at the destination, while the third allows applications to shape the network topology. This layer offers a flexible interface for diverse applications. The framework was validated on a physical testbed through edge intelligence use cases, including distributing neural network inference computations across multiple devices and offloading the entire workload to the most capable node. Distributed inference is useful in scenarios requiring low latency, energy efficiency, privacy, and autonomy. Experimental results indicated that device heterogeneity significantly impacts network performance. Throughput and inference duration analysis showed the influence of the strategies on application behaviour, revealed that topology critically affects decentralized performance, and demonstrated the suitability of the framework for complex tasks. --- ### InnoGym: Benchmarking the Innovation Potential of AI Agents Authors: Jintian Zhang, Kewei Xu, Jingsheng Zheng, Zhuoyun Yu, Yuqi Zhu, Yujie Luo, Lanning Wei, Shuofei Qiao, Lun Du, Da Zheng, Shumin Deng, Huajun Chen et al. Published: 2025-12-01 Categories: cs.CL, cs.AI, cs.CV, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2512.01822v2 LLMs and Agents have achieved impressive progress in code generation, mathematical reasoning, and scientific discovery. However, existing benchmarks primarily measure correctness, overlooking the diversity of methods behind solutions. True innovation depends not only on producing correct answers but also on the originality of the approach. We present InnoGym, the first benchmark and framework designed to systematically evaluate the innovation potential of AI agents. InnoGym introduces two complementary metrics: performance gain, which measures improvement over the best-known solutions, and novelty, which captures methodological differences from prior approaches. The benchmark includes 18 carefully curated tasks from real-world engineering and scientific domains, each standardized through resource filtering, evaluator validation, and solution collection. In addition, we provide iGym, a unified execution environment for reproducible and long-horizon evaluations. Extensive experiments show that while some agents produce novel approaches, their lack of robustness limits performance gains. These results highlight a key gap between creativity and effectiveness, underscoring the need for benchmarks that evaluate both. --- ### Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling Authors: Meng Cao, Haokun Lin, Haoyuan Li, Haoran Tang, Rongtao Xu, Dong An, Xue Liu, Ian Reid, Xiaodan Liang Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01821v2 Spatial reasoning, the ability to understand and interpret the 3D structure of the world, is a critical yet underdeveloped capability in Multimodal Large Language Models (MLLMs). Current methods predominantly rely on verbal descriptive tuning, which suffers from visual illiteracy, i.e., they learn spatial concepts through textual symbols alone, devoid of connection to their visual manifestations. To bridge this gap, this paper introduces MILO, an Implicit spatIaL wOrld modeling paradigm that simulates human-like spatial imagination. MILO integrates a visual generator to provide geometry-aware feedback, thereby implicitly grounding the MLLM's symbolic reasoning in perceptual experience. Complementing this paradigm, we propose RePE (Relative Positional Encoding), a novel encoding scheme that captures relative camera-pose transformations, offering superior performance over absolute coordinate systems. To support the training, we construct GeoGen, a large-scale Geometry-aware Generative dataset with approximately 2,241 videos and 67,827 observation-action-outcome triplets. Experiments demonstrate that our approach significantly enhances spatial reasoning capabilities across multiple baselines and benchmarks, offering a more holistic understanding of 3D space. --- ### Dimension-free error estimate for diffusion model and optimal scheduling Authors: Valentin de Bortoli, Romuald Elie, Anna Kazeykina, Zhenjie Ren, Jiacheng Zhang Published: 2025-12-01 Categories: stat.ML, cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2512.01820v1 Diffusion generative models have emerged as powerful tools for producing synthetic data from an empirically observed distribution. A common approach involves simulating the time-reversal of an Ornstein-Uhlenbeck (OU) process initialized at the true data distribution. Since the score function associated with the OU process is typically unknown, it is approximated using a trained neural network. This approximation, along with finite time simulation, time discretization and statistical approximation, introduce several sources of error whose impact on the generated samples must be carefully understood. Previous analyses have quantified the error between the generated and the true data distributions in terms of Wasserstein distance or Kullback-Leibler (KL) divergence. However, both metrics present limitations: KL divergence requires absolute continuity between distributions, while Wasserstein distance, though more general, leads to error bounds that scale poorly with dimension, rendering them impractical in high-dimensional settings. In this work, we derive an explicit, dimension-free bound on the discrepancy between the generated and the true data distributions. The bound is expressed in terms of a smooth test functional with bounded first and second derivatives. The key novelty lies in the use of this weaker, functional metric to obtain dimension-independent guarantees, at the cost of higher regularity on the test functions. As an application, we formulate and solve a variational problem to minimize the time-discretization error, leading to the derivation of an optimal time-scheduling strategy for the reverse-time diffusion. Interestingly, this scheduler has appeared previously in the literature in a different context; our analysis provides a new justification for its optimality, now grounded in minimizing the discretization bias in generative sampling. --- ### Decision Tree Embedding by Leaf-Means Authors: Cencheng Shen, Yuexiao Dong, Carey E. Priebe Published: 2025-12-01 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.01819v1 Decision trees and random forest remain highly competitive for classification on medium-sized, standard datasets due to their robustness, minimal preprocessing requirements, and interpretability. However, a single tree suffers from high estimation variance, while large ensembles reduce this variance at the cost of substantial computational overhead and diminished interpretability. In this paper, we propose Decision Tree Embedding (DTE), a fast and effective method that leverages the leaf partitions of a trained classification tree to construct an interpretable feature representation. By using the sample means within each leaf region as anchor points, DTE maps inputs into an embedding space defined by the tree's partition structure, effectively circumventing the high variance inherent in decision-tree splitting rules. We further introduce an ensemble extension based on additional bootstrap trees, and pair the resulting embedding with linear discriminant analysis for classification. We establish several population-level theoretical properties of DTE, including its preservation of conditional density under mild conditions and a characterization of the resulting classification error. Empirical studies on synthetic and real datasets demonstrate that DTE strikes a strong balance between accuracy and computational efficiency, outperforming or matching random forest and shallow neural networks while requiring only a fraction of their training time in most cases. Overall, the proposed DTE method can be viewed either as a scalable decision tree classifier that improves upon standard split rules, or as a neural network model whose weights are learned from tree-derived anchor points, achieving an intriguing integration of both paradigms. --- ### Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning Authors: Lama Alssum, Hasan Abed Al Kader Hammoud, Motasem Alfarra, Juan C Leon Alcazar, Bernard Ghanem Published: 2025-12-01 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.01818v1 Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model's tendency to overwrite previously acquired knowledge with new information. We present a novel approach to address this challenge, focusing on the intersection of memory-based methods and regularization approaches. We formulate a regularization strategy, termed Information Maximization (IM) regularizer, for memory-based continual learning methods, which is based exclusively on the expected label distribution, thus making it class-agnostic. As a consequence, IM regularizer can be directly integrated into various rehearsal-based continual learning methods, reducing forgetting and favoring faster convergence. Our empirical validation shows that, across datasets and regardless of the number of tasks, our proposed regularization strategy consistently improves baseline performance at the expense of a minimal computational overhead. The lightweight nature of IM ensures that it remains a practical and scalable solution, making it applicable to real-world continual learning scenarios where efficiency is paramount. Finally, we demonstrate the data-agnostic nature of our regularizer by applying it to video data, which presents additional challenges due to its temporal structure and higher memory requirements. Despite the significant domain gap, our experiments show that IM regularizer also improves the performance of video continual learning methods. --- ### Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights Authors: Juanxi Tian, Siyuan Li, Conghui He, Lijun Wu, Cheng Tan Published: 2025-12-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.01816v1 Current multimodal models aim to transcend the limitations of single-modality representations by unifying understanding and generation, often using text-to-image (T2I) tasks to calibrate semantic consistency. However, their reliance on static, single-image generation in training and evaluation leads to overfitting to static pattern matching and semantic fusion, while fundamentally hindering their ability to model dynamic processes that unfold over time. To address these constraints, we propose Envision-a causal event progression benchmark for chained text-to-multi-image generation. Grounded in world knowledge and structured by spatiotemporal causality, it reorganizes existing evaluation dimensions and includes 1,000 four-stage prompts spanning six scientific and humanities domains. To transition evaluation from single images to sequential frames and assess whether models truly internalize world knowledge while adhering to causal-temporal constraints, we introduce Envision-Score, a holistic metric integrating multi-dimensional consistency, physicality, and aesthetics. Comprehensive evaluation of 15 models (10 specialized T2I models, 5 unified models) uncovers: specialized T2I models demonstrate proficiency in aesthetic rendering yet lack intrinsic world knowledge. Unified multimodal models bridge this gap, consistently outperforming specialized counterparts in causal narrative coherence. However, even these unified architectures remain subordinate to closed-source models and struggle to overcome the core challenge of spatiotemporal consistency. This demonstrates that a focus on causally-isolated single images impedes multi-frame reasoning and generation, promoting static pattern matching over dynamic world modeling-ultimately limiting world knowledge internalization, generation. --- ### DeepCAVE: A Visualization and Analysis Tool for Automated Machine Learning Authors: Sarah Segel, Helena Graf, Edward Bergman, Kristina Thieme, Marcel Wever, Alexander Tornede, Frank Hutter, Marius Lindauer Published: 2025-12-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.01810v1 Hyperparameter optimization (HPO), as a central paradigm of AutoML, is crucial for leveraging the full potential of machine learning (ML) models; yet its complexity poses challenges in understanding and debugging the optimization process. We present DeepCAVE, a tool for interactive visualization and analysis, providing insights into HPO. Through an interactive dashboard, researchers, data scientists, and ML engineers can explore various aspects of the HPO process and identify issues, untouched potentials, and new insights about the ML model being tuned. By empowering users with actionable insights, DeepCAVE contributes to the interpretability of HPO and ML on a design level and aims to foster the development of more robust and efficient methodologies in the future. --- ### Much Ado About Noising: Dispelling the Myths of Generative Robotic Control Authors: Chaoyi Pan, Giri Anantharaman, Nai-Chieh Huang, Claire Jin, Daniel Pfrommer, Chenyang Yuan, Frank Permenter, Guannan Qu, Nicholas Boffi, Guanya Shi, Max Simchowitz Published: 2025-12-01 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.01809v3 Generative models, like flows and diffusions, have recently emerged as popular and efficacious policy parameterizations in robotics. There has been much speculation as to the factors underlying their successes, ranging from capturing multi-modal action distribution to expressing more complex behaviors. In this work, we perform a comprehensive evaluation of popular generative control policies (GCPs) on common behavior cloning (BC) benchmarks. We find that GCPs do not owe their success to their ability to capture multi-modality or to express more complex observation-to-action mappings. Instead, we find that their advantage stems from iterative computation, as long as intermediate steps are supervised during training and this supervision is paired with a suitable level of stochasticity. As a validation of our findings, we show that a minimum iterative policy (MIP), a lightweight two-step regression-based policy, essentially matches the performance of flow GCPs, and often outperforms distilled shortcut models. Our results suggest that the distribution-fitting component of GCPs is less salient than commonly believed, and point toward new design spaces focusing solely on control performance. Project page: https://simchowitzlabpublic.github.io/much-ado-about-noising-project/ --- ### Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos Authors: Xavier Thomas, Youngsun Lim, Ananya Srinivasan, Audrey Zheng, Deepti Ghadiyaram Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01803v3 Despite rapid advances in video generative models, robust metrics for evaluating visual and temporal correctness of complex human actions remain elusive. Critically, existing pure-vision encoders and Multimodal Large Language Models (MLLMs) are strongly appearance-biased, lack temporal understanding, and thus struggle to discern intricate motion dynamics and anatomical implausibilities in generated videos. We tackle this gap by introducing a novel evaluation metric derived from a learned latent space of real-world human actions. Our method first captures the nuances, constraints, and temporal smoothness of real-world motion by fusing appearance-agnostic human skeletal geometry features with appearance-based features. We posit that this combined feature space provides a robust representation of action plausibility. Given a generated video, our metric quantifies its action quality by measuring the distance between its underlying representations and this learned real-world action distribution. For rigorous validation, we develop a new multi-faceted benchmark specifically designed to probe temporally challenging aspects of human action fidelity. Through extensive experiments, we show that our metric achieves substantial improvement of more than 68% compared to existing state-of-the-art methods on our benchmark, performs competitively on established external benchmarks, and has a stronger correlation with human perception. Our in-depth analysis reveals critical limitations in current video generative models and establishes a new standard for advanced research in video generation. --- ### GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation Authors: Yunfei Li, Xiao Ma, Jiafeng Xu, Yu Cui, Zhongren Cui, Zhigang Han, Liqun Huang, Tao Kong, Yuxiao Liu, Hao Niu, Wanli Peng, Jingchao Qiao et al. Published: 2025-12-01 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.01801v3 We present GR-RL, a robotic learning framework that turns a generalist vision-language-action (VLA) policy into a highly capable specialist for long-horizon dexterous manipulation. Assuming the optimality of human demonstrations is core to existing VLA policies. However, we claim that in highly dexterous and precise manipulation tasks, human demonstrations are noisy and suboptimal. GR-RL proposes a multi-stage training pipeline that filters, augments, and reinforces the demonstrations by reinforcement learning. First, GR-RL learns a vision-language-conditioned task progress, filters the demonstration trajectories, and only keeps the transitions that contribute positively to the progress. Specifically, we show that by directly applying offline RL with sparse reward, the resulting $Q$-values can be treated as a robust progress function. Next, we introduce morphological symmetry augmentation that greatly improves the generalization and performance of GR-RL. Lastly, to better align the VLA policy with its deployment behaviors for high-precision control, we perform online RL by learning a latent space noise predictor. With this pipeline, GR-RL is, to our knowledge, the first learning-based policy that can autonomously lace up a shoe by threading shoelaces through multiple eyelets with an 83.3% success rate, a task requiring long-horizon reasoning, millimeter-level precision, and compliant soft-body interaction. We hope GR-RL provides a step toward enabling generalist robot foundation models to specialize into reliable real-world experts. --- ### H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs Authors: Cheng Gao, Huimin Chen, Chaojun Xiao, Zhiyi Chen, Zhiyuan Liu, Maosong Sun Published: 2025-12-01 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2512.01797v2 Large language models (LLMs) frequently generate hallucinations -- plausible but factually incorrect outputs -- undermining their reliability. While prior work has examined hallucinations from macroscopic perspectives such as training data and objectives, the underlying neuron-level mechanisms remain largely unexplored. In this paper, we conduct a systematic investigation into hallucination-associated neurons (H-Neurons) in LLMs from three perspectives: identification, behavioral impact, and origins. Regarding their identification, we demonstrate that a remarkably sparse subset of neurons (less than $0.1\%$ of total neurons) can reliably predict hallucination occurrences, with strong generalization across diverse scenarios. In terms of behavioral impact, controlled interventions reveal that these neurons are causally linked to over-compliance behaviors. Concerning their origins, we trace these neurons back to the pre-trained base models and find that these neurons remain predictive for hallucination detection, indicating they emerge during pre-training. Our findings bridge macroscopic behavioral patterns with microscopic neural mechanisms, offering insights for developing more reliable LLMs. --- ### An hybrid stochastic Newton algorithm for logistic regression Authors: Bernard Bercu, Luis Fredes, Eméric Gbaguidi Published: 2025-12-01 Categories: stat.CO, math.PR, math.ST, stat.ML arXiv: https://arxiv.org/abs/2512.01790v1 In this paper, we investigate a second-order stochastic algorithm for solving large-scale binary classification problems. We propose to make use of a new hybrid stochastic Newton algorithm that includes two weighted components in the Hessian matrix estimation: the first one coming from the natural Hessian estimate and the second associated with the stochastic gradient information. Our motivation comes from the fact that both parts evaluated at the true parameter of logistic regression, are equal to the Hessian matrix. This new formulation has several advantages and it enables us to prove the almost sure convergence of our stochastic algorithm to the true parameter. Moreover, we significantly improve the almost sure rate of convergence to the Hessian matrix. Furthermore, we establish the central limit theorem for our hybrid stochastic Newton algorithm. Finally, we show a surprising result on the almost sure convergence of the cumulative excess risk. --- ### SAM3-UNet: Simplified Adaptation of Segment Anything Model 3 Authors: Xinyu Xiong, Zihuang Wu, Lei Lu, Yufa Xia Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01789v1 In this paper, we introduce SAM3-UNet, a simplified variant of Segment Anything Model 3 (SAM3), designed to adapt SAM3 for downstream tasks at a low cost. Our SAM3-UNet consists of three components: a SAM3 image encoder, a simple adapter for parameter-efficient fine-tuning, and a lightweight U-Net-style decoder. Preliminary experiments on multiple tasks, such as mirror detection and salient object detection, demonstrate that the proposed SAM3-UNet outperforms the prior SAM2-UNet and other state-of-the-art methods, while requiring less than 6 GB of GPU memory during training with a batch size of 12. The code is publicly available at https://github.com/WZH0120/SAM3-UNet. --- ### Learned Image Compression for Earth Observation: Implications for Downstream Segmentation Tasks Authors: Christian Mollière, Iker Cumplido, Marco Zeulner, Lukas Liesenhoff, Matthias Schubert, Julia Gottfriedsen Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01788v1 The rapid growth of data from satellite-based Earth observation (EO) systems poses significant challenges in data transmission and storage. We evaluate the potential of task-specific learned compression algorithms in this context to reduce data volumes while retaining crucial information. In detail, we compare traditional compression (JPEG 2000) versus a learned compression approach (Discretized Mixed Gaussian Likelihood) on three EO segmentation tasks: Fire, cloud, and building detection. Learned compression notably outperforms JPEG 2000 for large-scale, multi-channel optical imagery in both reconstruction quality (PSNR) and segmentation accuracy. However, traditional codecs remain competitive on smaller, single-channel thermal infrared datasets due to limited data and architectural constraints. Additionally, joint end-to-end optimization of compression and segmentation models does not improve performance over standalone optimization. --- ### Who Judges the Judge? LLM Jury-on-Demand: Building Trustworthy LLM Evaluation Systems Authors: Xiaochuan Li, Ke Wang, Girija Gouda, Shubham Choudhary, Yaqun Wang, Linwei Hu, Joel Vaughan, Freddy Lecue Published: 2025-12-01 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.01786v1 As Large Language Models (LLMs) become integrated into high-stakes domains, there is a growing need for evaluation methods that are both scalable for real-time deployment and reliable for critical decision-making. While human evaluation is reliable, it is slow and costly. Single LLM judges are biased, and static juries lack adaptability. To overcome these limitations, we propose LLM Jury-on-Demand - a dynamic, learning-based framework for scalable and context-aware evaluation. Our method trains a set of reliability predictors to assess when LLM judges will agree with human experts, leveraging token distributions, embeddings, and structural input features. This enables a fully adaptive evaluation where, for each data point, an optimal jury of the most reliable judges is dynamically selected, and their scores are aggregated using their reliability as weights. Experiments on summarization and RAG benchmarks show that our dynamic jury system achieves significantly higher correlation with human judgment than both single-judge and static-jury baselines. These results highlight the promise of adaptive, learning-based juries for building scalable, more reliable and trustworthy evaluation systems for modern LLMs in high-stakes domains. --- ### The Active and Noise-Tolerant Strategic Perceptron Authors: Maria-Florina Balcan, Hedyeh Beyhaghi Published: 2025-12-01 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2512.01783v2 We initiate the study of active learning algorithms for classifying strategic agents. Active learning is a well-established framework in machine learning in which the learner selectively queries labels, often achieving substantially higher accuracy and efficiency than classical supervised methods-especially in settings where labeling is costly or time-consuming, such as hiring, admissions, and loan decisions. Strategic classification, however, addresses scenarios where agents modify their features to obtain more favorable outcomes, resulting in observed data that is not truthful. Such manipulation introduces challenges beyond those in learning from clean data. Our goal is to design active and noise-tolerant algorithms that remain effective in strategic environments-algorithms that classify strategic agents accurately while issuing as few label requests as possible. The central difficulty is to simultaneously account for strategic manipulation and preserve the efficiency gains of active learning. Our main result is an algorithm for actively learning linear separators in the strategic setting that preserves the exponential improvement in label complexity over passive learning previously obtained only in the non-strategic case. Specifically, for data drawn uniformly from the unit sphere, we show that a modified version of the Active Perceptron algorithm (DKM05,YZ17) achieves excess error $ε$ using only $\tilde{O}(d \ln \frac{1}ε)$ label queries and incurs at most $\tilde{O}(d \ln \frac{1}ε)$ additional mistakes relative to the optimal classifier, even in the nonrealizable case, when a $\tildeΩ(ε)$ fraction of inputs have inconsistent labels with the optimal classifier. The algorithm is computationally efficient and, under these distributional assumptions, requires substantially fewer label queries than prior work on strategic Perceptron (ABBN21). --- ### Dual Randomized Smoothing: Beyond Global Noise Variance Authors: Chenhao Sun, Yuhao Mao, Martin Vechev Published: 2025-12-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.01782v4 Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With RS, achieving high accuracy at small radii requires a small noise variance, while achieving high accuracy at large radii requires a large noise variance. However, the global noise variance used in the standard RS formulation leads to a fundamental limitation: there exists no global noise variance that simultaneously achieves strong performance at both small and large radii. To break through the global variance limitation, we propose a dual RS framework which enables input-dependent noise variances. To achieve that, we first prove that RS remains valid with input-dependent noise variances, provided the variance is locally constant around each input. Building on this result, we introduce two components: (i) a variance estimator predicts an optimal noise variance for each input, (ii) this estimated variance is then used by a standard RS classifier. The variance estimator is independently smoothed via RS to ensure local constancy, enabling flexible design. We also introduce training strategies to iteratively optimize the two components. Experiments on CIFAR-10 demonstrate that our dual RS method provides strong performance for both small and large radii-unattainable with global noise variance-while incurring only a 60% computational overhead at inference. Moreover, it outperforms prior input-dependent noise approaches across most radii, with gains at radii 0.5, 0.75, and 1.0 of 15.6%, 20.0%, and 15.7%. On ImageNet, dual RS remains effective across all radii, with advantages of 8.6%, 17.1%, and 9.1% at radii 0.5, 1.0, and 1.5. Additionally, the dual RS framework provides a routing perspective for certified robustness, improving the accuracy-robustness trade-off with off-the-shelf expert RS models. --- ### How Does RL Post-training Induce Skill Composition? A Case Study on Countdown Authors: Simon Park, Simran Kaur, Sanjeev Arora Published: 2025-12-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.01775v1 While reinforcement learning (RL) successfully enhances reasoning in large language models, its role in fostering compositional generalization (the ability to synthesize novel skills from known components) is often conflated with mere length generalization. To this end, we study what RL post-training teaches about skill composition and how the structure of the composition affects the skill transfer. We focus on the Countdown task (given n numbers and a target, form an expression that evaluates to the target) and analyze model solutions as expression trees, where each subtree corresponds to a reusable subtask and thus can be viewed as a ``skill.'' Tracking tree shapes and their success rates over training, we find: (i) out-of-distribution (OOD) generalization to larger n and to unseen tree shapes, indicating compositional reuse of subtasks; (ii) a structure-dependent hierarchy of learnability -- models master shallow balanced trees (workload is balanced between subtasks) before deep unbalanced ones, with persistent fragility on right-heavy structures (even when the composition depth is the same as some left-heavy structures). Our diagnostic reveals what is learned, in what order, and where generalization fails, clarifying how RL-only post-training induces OOD generalization beyond what standard metrics such as pass@k reveal. --- ### Evaluating SAM2 for Video Semantic Segmentation Authors: Syed Hesham Syed Ariff, Yun Liu, Guolei Sun, Jing Yang, Henghui Ding, Xue Geng, Xudong Jiang Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01774v1 The Segmentation Anything Model 2 (SAM2) has proven to be a powerful foundation model for promptable visual object segmentation in both images and videos, capable of storing object-aware memories and transferring them temporally through memory blocks. While SAM2 excels in video object segmentation by providing dense segmentation masks based on prompts, extending it to dense Video Semantic Segmentation (VSS) poses challenges due to the need for spatial accuracy, temporal consistency, and the ability to track multiple objects with complex boundaries and varying scales. This paper explores the extension of SAM2 for VSS, focusing on two primary approaches and highlighting firsthand observations and common challenges faced during this process. The first approach involves using SAM2 to extract unique objects as masks from a given image, with a segmentation network employed in parallel to generate and refine initial predictions. The second approach utilizes the predicted masks to extract unique feature vectors, which are then fed into a simple network for classification. The resulting classifications and masks are subsequently combined to produce the final segmentation. Our experiments suggest that leveraging SAM2 enhances overall performance in VSS, primarily due to its precise predictions of object boundaries. --- ### Robust Rigid and Non-Rigid Medical Image Registration Using Learnable Edge Kernels Authors: Ahsan Raza Siyal, Markus Haltmeier, Ruth Steiger, Malik Galijasevic, Elke Ruth Gizewski, Astrid Ellen Grams Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01771v1 Medical image registration is crucial for various clinical and research applications including disease diagnosis or treatment planning which require alignment of images from different modalities, time points, or subjects. Traditional registration techniques often struggle with challenges such as contrast differences, spatial distortions, and modality-specific variations. To address these limitations, we propose a method that integrates learnable edge kernels with learning-based rigid and non-rigid registration techniques. Unlike conventional layers that learn all features without specific bias, our approach begins with a predefined edge detection kernel, which is then perturbed with random noise. These kernels are learned during training to extract optimal edge features tailored to the task. This adaptive edge detection enhances the registration process by capturing diverse structural features critical in medical imaging. To provide clearer insight into the contribution of each component in our design, we introduce four variant models for rigid registration and four variant models for non-rigid registration. We evaluated our approach using a dataset provided by the Medical University across three setups: rigid registration without skull removal, with skull removal, and non-rigid registration. Additionally, we assessed performance on two publicly available datasets. Across all experiments, our method consistently outperformed state-of-the-art techniques, demonstrating its potential to improve multi-modal image alignment and anatomical structure analysis. --- ### VideoScoop: A Non-Traditional Domain-Independent Framework For Video Analysis Authors: Hafsa Billah Published: 2025-12-01 Categories: cs.CV, cs.DB arXiv: https://arxiv.org/abs/2512.01769v1 Automatically understanding video contents is important for several applications in Civic Monitoring (CM), general Surveillance (SL), Assisted Living (AL), etc. Decades of Image and Video Analysis (IVA) research have advanced tasks such as content extraction (e.g., object recognition and tracking). Identifying meaningful activities or situations (e.g., two objects coming closer) remains difficult and cannot be achieved by content extraction alone. Currently, Video Situation Analysis (VSA) is done manually with a human in the loop, which is error-prone and labor-intensive, or through custom algorithms designed for specific video types or situations. These algorithms are not general-purpose and require a new algorithm/software for each new situation or video from a new domain. This report proposes a general-purpose VSA framework that overcomes the above limitations. Video contents are extracted once using state-of-the-art Video Content Extraction technologies. They are represented using two alternative models -- the extended relational model (R++) and graph models. When represented using R++, the extracted contents can be used as data streams, enabling Continuous Query Processing via the proposed Continuous Query Language for Video Analysis. The graph models complement this by enabling the detection of situations that are difficult or impossible to detect using the relational model alone. Existing graph algorithms and newly developed algorithms support a wide variety of situation detection. To support domain independence, primitive situation variants across domains are identified and expressed as parameterized templates. Extensive experiments were conducted across several interesting situations from three domains -- AL, CM, and SL-- to evaluate the accuracy, efficiency, and robustness of the proposed approach using a dataset of videos of varying lengths from these domains. --- ### On the Unreasonable Effectiveness of Last-layer Retraining Authors: John C. Hill, Tyler LaBonte, Xinchen Zhang, Vidya Muthukumar Published: 2025-12-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.01766v2 Last-layer retraining (LLR) methods -- wherein the last layer of a neural network is reinitialized and retrained on a held-out set following ERM training -- have garnered interest as an efficient approach to rectify dependence on spurious correlations and improve performance on minority groups. Surprisingly, LLR has been found to improve worst-group accuracy even when the held-out set is an imbalanced subset of the training set. We initially hypothesize that this ``unreasonable effectiveness'' of LLR is explained by its ability to mitigate neural collapse through the held-out set, resulting in the implicit bias of gradient descent benefiting robustness. Our empirical investigation does not support this hypothesis. Instead, we present strong evidence for an alternative hypothesis: that the success of LLR is primarily due to better group balance in the held-out set. We conclude by showing how the recent algorithms CB-LLR and AFR perform implicit group-balancing to elicit a robustness improvement. --- ### HiconAgent: History Context-aware Policy Optimization for GUI Agents Authors: Xurui Zhou, Gongwei Chen, Yuquan Xie, Zaijing Li, Kaiwen Zhou, Shuai Wang, Shuo Yang, Zhuotao Tian, Rui Shao Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01763v2 Graphical User Interface (GUI) agents require effective use of historical context to perform sequential navigation tasks. While incorporating past actions and observations can improve decision making, naive use of full history leads to excessive computational overhead and distraction from irrelevant information. To address this, we introduce HiconAgent, a GUI agent trained with History Context-aware Policy Optimization (HCPO) for efficient and effective utilization of historical information. HCPO optimizes history usage in both sampling and policy updates through two complementary components: (1) Dynamic Context Sampling (DCS) presents the agent with variable length histories during sampling, enabling adaptive use of the most relevant context; (2) Anchor-guided History Compression (AHC) refines the policy update phase with a dual branch strategy where the compressed branch removes history observations while keeping history actions as information flow anchors. The compressed and uncompressed branches are coupled through a history-enhanced alignment loss to enforce consistent history usage while maintaining efficiency. Experiments on mainstream GUI navigation benchmarks demonstrate strong performance. Despite being smaller, HiconAgent-3B outperforms GUI-R1-7B by +8.46 percent grounding accuracy and +11.32 percent step success rate on GUI-Odyssey, while achieving comparable results on AndroidControl and AITW with up to 2.47x computational speedup and 60 percent FLOPs reduction. --- ### Weight Space Representation Learning via Neural Field Adaptation Authors: Zhuoqian Yang, Mathieu Salzmann, Sabine Süsstrunk Published: 2025-12-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.01759v3 We investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruction, generation, and analysis tasks on 2D and 3D data, we find that multiplicative LoRA weights achieve high representation quality while exhibiting distinctiveness and semantic structure. When used with latent diffusion models, multiplicative LoRA weights enable higher-quality generation than existing weight-space methods. --- ### Mofasa: A Step Change in Metal-Organic Framework Generation Authors: Vaidotas Simkus, Anders Christensen, Steven Bennett, Ian Johnson, Mark Neumann, James Gin, Jonathan Godwin, Benjamin Rhodes Published: 2025-12-01 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2512.01756v1 Mofasa is an all-atom latent diffusion model with state-of-the-art performance for generating Metal-Organic Frameworks (MOFs). These are highly porous crystalline materials used to harvest water from desert air, capture carbon dioxide, store toxic gases and catalyse chemical reactions. In recognition of their value, the development of MOFs recently received a Nobel Prize in Chemistry. In many ways, MOFs are well-suited for exploiting generative models in chemistry: they are rationally-designable materials with a large combinatorial design space and strong structure-property couplings. And yet, to date, a high performance generative model has been lacking. To fill this gap, we introduce Mofasa, a general-purpose latent diffusion model that jointly samples positions, atom-types and lattice vectors for systems as large as 500 atoms. Mofasa avoids handcrafted assembly algorithms common in the literature, unlocking the simultaneous discovery of metal nodes, linkers and topologies. To help the scientific community build on our work, we release MofasaDB, an annotated library of hundreds of thousands of sampled MOF structures, along with a user-friendly web interface for search and discovery: https://mofux.ai/ . --- ### FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing Authors: Yucheng Liao, Jiajun Liang, Kaiqian Cui, Baoquan Zhao, Haoran Xie, Wei Liu, Qing Li, Xudong Mao Published: 2025-12-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.01755v2 Instruction-based image editing through natural language has emerged as a powerful paradigm for intuitive visual manipulation. While recent models achieve impressive results on single edits, they suffer from severe quality degradation under multi-turn editing. Through systematic analysis, we identify progressive loss of high-frequency information as the primary cause of this quality degradation. We present FreqEdit, a training-free framework that enables stable editing across 10+ consecutive iterations. Our approach comprises three synergistic components: (1) high-frequency feature injection from reference velocity fields to preserve fine-grained details, (2) an adaptive injection strategy that spatially modulates injection strength for precise region-specific control, and (3) a path compensation mechanism that periodically recalibrates the editing trajectory to prevent over-constraint. Extensive experiments demonstrate that FreqEdit achieves superior performance in both identity preservation and instruction following compared to seven state-of-the-art baselines. --- ### Multimodal Mixture-of-Experts for ISAC in Low-Altitude Wireless Networks Authors: Kai Zhang, Wentao Yu, Hengtao He, Shenghui Song, Jun Zhang, Khaled B. Letaief Published: 2025-12-01 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2512.01750v1 Integrated sensing and communication (ISAC) is a key enabler for low-altitude wireless networks (LAWNs), providing simultaneous environmental perception and data transmission in complex aerial scenarios. By combining heterogeneous sensing modalities such as visual, radar, lidar, and positional information, multimodal ISAC can improve both situational awareness and robustness of LAWNs. However, most existing multimodal fusion approaches use static fusion strategies that treat all modalities equally and cannot adapt to channel heterogeneity or time-varying modality reliability in dynamic low-altitude environments. To address this fundamental limitation, we propose a mixture-of-experts (MoE) framework for multimodal ISAC in LAWNs. Each modality is processed by a dedicated expert network, and a lightweight gating module adaptively assigns fusion weights according to the instantaneous informativeness and reliability of each modality. To improve scalability under the stringent energy constraints of aerial platforms, we further develop a sparse MoE variant that selectively activates only a subset of experts, thereby reducing computation overhead while preserving the benefits of adaptive fusion. Comprehensive simulations on three typical ISAC tasks in LAWNs demonstrate that the proposed frameworks consistently outperform conventional multimodal fusion baselines in terms of learning performance and training sample efficiency. --- ### SA-ADP: Sensitivity-Aware Adaptive Differential Privacy for Large Language Models Authors: Stella Etuk, Ashraf Matrawy Published: 2025-12-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.01748v1 Despite advances in the use of large language models (LLMs) in downstream tasks, their ability to memorize information has raised privacy concerns. Therefore, protecting personally identifiable information (PII) during LLM training remains a fundamental challenge. Conventional methods like Differential Privacy-Stochastic Gradient Descent (DP-SGD) provide robust privacy protection via uniform noising, protecting PII regardless of its distinct sensitivity. This comes at the expense of the model's utility, leading to a trade-off. In this paper, we propose SA-ADP, a sensitivity-aware approach that allocates noise based on the sensitivity of individual PII. We evaluated our method on four datasets (ABCD, CUSTOMERSIM, Wikitext-2, and UNSW-NB15 ). Our results show that SA-ADP achieves results comparable to the baseline (No-DP) and the conventional DP-SGD. This means that our method did not degrade the model's utility while still maintaining strong privacy protection. --- ### MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention Authors: Pedro M. P. Curvo, Jan-Willem van de Meent, Maksim Zhdanov Published: 2025-12-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.01738v2 A key scalability challenge in neural solvers for industrial-scale physics simulations is efficiently capturing both fine-grained local interactions and long-range global dependencies across millions of spatial elements. We introduce the Multi-Scale Patch Transformer (MSPT), an architecture that combines local point attention within patches with global attention to coarse patch-level representations. To partition the input domain into spatially-coherent patches, we employ ball trees, which handle irregular geometries efficiently. This dual-scale design enables MSPT to scale to millions of points on a single GPU. We validate our method on standard PDE benchmarks (elasticity, plasticity, fluid dynamics, porous flow) and large-scale aerodynamic datasets (ShapeNet-Car, Ahmed-ML), achieving state-of-the-art accuracy with substantially lower memory footprint and computational cost. --- ### Automating modeling in mechanics: LLMs as designers of physics-constrained neural networks for constitutive modeling of materials Authors: Marius Tacke, Matthias Busch, Kian Abdolazizi, Jonas Eichinger, Kevin Linka, Christian Cyron, Roland Aydin Published: 2025-12-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.01735v1 Large language model (LLM)-based agentic frameworks increasingly adopt the paradigm of dynamically generating task-specific agents. We suggest that not only agents but also specialized software modules for scientific and engineering tasks can be generated on demand. We demonstrate this concept in the field of solid mechanics. There, so-called constitutive models are required to describe the relationship between mechanical stress and body deformation. Constitutive models are essential for both the scientific understanding and industrial application of materials. However, even recent data-driven methods of constitutive modeling, such as constitutive artificial neural networks (CANNs), still require substantial expert knowledge and human labor. We present a framework in which an LLM generates a CANN on demand, tailored to a given material class and dataset provided by the user. The framework covers LLM-based architecture selection, integration of physical constraints, and complete code generation. Evaluation on three benchmark problems demonstrates that LLM-generated CANNs achieve accuracy comparable to or greater than manually engineered counterparts, while also exhibiting reliable generalization to unseen loading scenarios and extrapolation to large deformations. These findings indicate that LLM-based generation of physics-constrained neural networks can substantially reduce the expertise required for constitutive modeling and represent a step toward practical end-to-end automation. --- ### Beyond Scaffold: A Unified Spatio-Temporal Gradient Tracking Method Authors: Yan Huang, Jinming Xu, Jiming Chen, Karl Henrik Johansson Published: 2025-12-01 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2512.01732v1 In distributed and federated learning algorithms, communication overhead is often reduced by performing multiple local updates between communication rounds. However, due to data heterogeneity across nodes and the local gradient noise within each node, this strategy can lead to the drift of local models away from the global optimum. To address this issue, we revisit the well-known federated learning method Scaffold (Karimireddy et al., 2020) under a gradient tracking perspective, and propose a unified spatio-temporal gradient tracking algorithm, termed ST-GT, for distributed stochastic optimization over time-varying graphs. ST-GT tracks the global gradient across neighboring nodes to mitigate data heterogeneity, while maintaining a running average of local gradients to substantially suppress noise, with slightly more storage overhead. Without assuming bounded data heterogeneity, we prove that ST-GT attains a linear convergence rate for strongly convex problems and a sublinear rate for nonconvex cases. Notably, ST-GT achieves the first linear speed-up in communication complexity with respect to the number of local updates per round $τ$ for the strongly-convex setting. Compared to traditional gradient tracking methods, ST-GT reduces the topology-dependent noise term from $σ^2$ to $σ^2/τ$, where $σ^2$ denotes the noise level, thereby improving communication efficiency. --- ### Reasoning About the Unsaid: Misinformation Detection with Omission-Aware Graph Inference Authors: Zhengjia Wang, Danding Wang, Qiang Sheng, Jiaying Wu, Juan Cao Published: 2025-12-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.01728v1 This paper investigates the detection of misinformation, which deceives readers by explicitly fabricating misleading content or implicitly omitting important information necessary for informed judgment. While the former has been extensively studied, omission-based deception remains largely overlooked, even though it can subtly guide readers toward false conclusions under the illusion of completeness. To pioneer in this direction, this paper presents OmiGraph, the first omission-aware framework for misinformation detection. Specifically, OmiGraph constructs an omission-aware graph for the target news by utilizing a contextual environment that captures complementary perspectives of the same event, thereby surfacing potentially omitted contents. Based on this graph, omission-oriented relation modeling is then proposed to identify the internal contextual dependencies, as well as the dynamic omission intents, formulating a comprehensive omission relation representation. Finally, to extract omission patterns for detection, OmiGraph introduces omission-aware message-passing and aggregation that establishes holistic deception perception by integrating the omission contents and relations. Experiments show that, by considering the omission perspective, our approach attains remarkable performance, achieving average improvements of +5.4% F1 and +5.3% ACC on two large-scale benchmarks. --- ### Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks Authors: Jiannan Guan, Qiguang Chen, Libo Qin, Dengyun Peng, Jinhao Liu, Liangyu Huo, Jian Xie, Wanxiang Che Published: 2025-12-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.01725v1 Large Language Models (LLMs) excel in reasoning tasks requiring a single correct answer, but they perform poorly in multi-solution tasks that require generating comprehensive and diverse answers. We attribute this limitation to \textbf{reasoning overconfidence}: a tendency to express undue certainty in an incomplete solution set. To examine the effect, we introduce \textit{MuSoBench}, a benchmark of multi-solution problems. Experiments show that the conventional short chain-of-thought (Short-CoT) prompting paradigm exhibits pronounced overconfidence, whereas the emerging long chain-of-thought (Long-CoT) approach mitigates it through iterative exploration and self-reflection. We further characterise observable behaviours and influential factors. To probe the underlying cause, we propose the \textbf{cognitive-rigidity hypothesis}, which posits that overconfidence arises when the reasoning process prematurely converges on a narrow set of thought paths. An attention-entropy analysis offers preliminary support for this view. These findings provide tools for assessing the completeness of LLM reasoning and highlight the need to move evaluation beyond single-answer accuracy toward comprehensive exploration. --- ### Probabilistic Neuro-Symbolic Reasoning for Sparse Historical Data: A Framework Integrating Bayesian Inference, Causal Models, and Game-Theoretic Allocation Authors: Saba Kublashvili Published: 2025-12-01 Categories: cs.AI, cs.GT, math.PR arXiv: https://arxiv.org/abs/2512.01723v1 Modeling historical events poses fundamental challenges for machine learning: extreme data scarcity (N << 100), heterogeneous and noisy measurements, missing counterfactuals, and the requirement for human interpretable explanations. We present HistoricalML, a probabilistic neuro-symbolic framework that addresses these challenges through principled integration of (1) Bayesian uncertainty quantification to separate epistemic from aleatoric uncertainty, (2) structural causal models for counterfactual reasoning under confounding, (3) cooperative game theory (Shapley values) for fair allocation modeling, and (4) attention based neural architectures for context dependent factor weighting. We provide theoretical analysis showing that our approach achieves consistent estimation in the sparse data regime when strong priors from domain knowledge are available, and that Shapley based allocation satisfies axiomatic fairness guarantees that pure regression approaches cannot provide. We instantiate the framework on two historical case studies: the 19th century partition of Africa (N = 7 colonial powers) and the Second Punic War (N = 2 factions). Our model identifies Germany's +107.9 percent discrepancy as a quantifiable structural tension preceding World War I, with tension factor 36.43 and 0.79 naval arms race correlation. For the Punic Wars, Monte Carlo battle simulations achieve a 57.3 percent win probability for Carthage at Cannae and 57.8 percent for Rome at Zama, aligning with historical outcomes. Counterfactual analysis reveals that Carthaginian political support (support score 6.4 vs Napoleon's 7.1), rather than military capability, was the decisive factor. --- ### Common Structure Discovery in Collections of Bipartite Networks: Application to Pollination Systems Authors: Louis Lacoste, Pierre Barbillon, Sophie Donnet Published: 2025-12-01 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2512.01716v1 Bipartite networks are widely used to encode the ecological interactions. Being able to compare the organization of bipartite networks is a first step toward a better understanding of how environmental factors shape community structure and resilience. Yet current methods for structure detection in bipartite networks overlook shared patterns across collections of networks. We introduce the \emph{colBiSBM}, a family of probabilistic models for collections of bipartite networks that extends the classical Latent Block Model (LBM). The proposed framework assumes that networks are independent realizations of a shared mesoscale structure, encoded through common inter-block connectivity parameters. We establish identifiability conditions for the different variants of \emph{colBiSBM} and develop a variational EM algorithm for parameter estimation, coupled with an adaptation of the Integrated Classification Likelihood (ICL) criterion for model selection. We demonstrate how our approach can be used to classify networks based on their topology or organization. Simulation studies highlight the ability of \emph{colBiSBM} to recover common structures, improve clustering performance, and enhance link prediction by borrowing strength across networks. An application to plant--pollinator networks highlights how the method uncovers shared ecological roles and partitions networks into sub-collections with similar connectivity patterns. These results illustrate the methodological and practical advantages of joint modeling over separate network analyses in the study of bipartite systems. --- ### Self-Supervised Borrowing Detection on Multilingual Wordlists Authors: Tim Wientzek Published: 2025-12-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.01713v1 This paper presents a fully self-supervised approach to borrowing detection in multilingual wordlists. The method combines two sources of information: PMI similarities based on a global correspondence model and a lightweight contrastive component trained on phonetic feature vectors. It further includes an automatic procedure for selecting decision thresholds without requiring labeled data. Experiments on benchmark datasets show that PMI alone already improves over existing string similarity measures such as NED and SCA, and that the combined similarity performs on par with or better than supervised baselines. An ablation study highlights the importance of character encoding, temperature settings and augmentation strategies. The approach scales to datasets of different sizes, works without manual supervision and is provided with a command-line tool that allows researchers to conduct their own studies. --- ### MMAG: Mixed Memory-Augmented Generation for Large Language Models Applications Authors: Stefano Zeppieri Published: 2025-12-01 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2512.01710v2 Large Language Models (LLMs) excel at generating coherent text within a single prompt but fall short in sustaining relevance, personalization, and continuity across extended interactions. Human communication, however, relies on multiple forms of memory, from recalling past conversations to adapting to personal traits and situational context. This paper introduces the Mixed Memory-Augmented Generation (MMAG) pattern, a framework that organizes memory for LLM-based agents into five interacting layers: conversational, long-term user, episodic and event-linked, sensory and context-aware, and short-term working memory. Drawing inspiration from cognitive psychology, we map these layers to technical components and outline strategies for coordination, prioritization, and conflict resolution. We demonstrate the approach through its implementation in the Heero conversational agent, where encrypted long-term bios and conversational history already improve engagement and retention. We further discuss implementation concerns around storage, retrieval, privacy, and latency, and highlight open challenges. MMAG provides a foundation for building memory-rich language agents that are more coherent, proactive, and aligned with human needs. --- ### Differentially Private and Federated Structure Learning in Bayesian Networks Authors: Ghita Fassy El Fehri, Aurélien Bellet, Philippe Bastien Published: 2025-12-01 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.01708v2 Learning the structure of a Bayesian network from decentralized data poses two major challenges: (i) ensuring rigorous privacy guarantees for participants, and (ii) avoiding communication costs that scale poorly with dimensionality. In this work, we introduce Fed-Sparse-BNSL, a novel federated method for learning linear Gaussian Bayesian network structures that addresses both challenges. By combining differential privacy with greedy updates that target only a few relevant edges per participant, Fed-Sparse-BNSL efficiently uses the privacy budget while keeping communication costs low. Our careful algorithmic design preserves model identifiability and enables accurate structure estimation. Experiments on synthetic and real datasets demonstrate that Fed-Sparse-BNSL achieves utility close to non-private baselines while offering substantially stronger privacy and communication efficiency. --- ### StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos Authors: Daeun Lee, Subhojyoti Mukherjee, Branislav Kveton, Ryan A. Rossi, Viet Dac Lai, Seunghyun Yoon, Trung Bui, Franck Dernoncourt, Mohit Bansal Published: 2025-12-01 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.01707v3 Streaming video understanding requires models not only to process temporally incoming frames, but also to anticipate user intention for realistic applications such as Augmented Reality (AR) glasses. While prior streaming benchmarks evaluate temporal reasoning, none measure whether Multimodal Large Language Models (MLLMs) can interpret or leverage human gaze signals within a streaming setting. To fill this gap, we introduce StreamGaze, the first benchmark designed to evaluate how effectively MLLMs utilize gaze for temporal and proactive reasoning in streaming videos. StreamGaze introduces gaze-guided past, present, and proactive tasks that comprehensively assess streaming video understanding. These tasks evaluate whether models can use real-time gaze signals to follow shifting attention and infer user intentions based only on past and currently observed frames. To build StreamGaze, we develop a gaze-video Question Answering (QA) generation pipeline that aligns egocentric videos with raw gaze trajectories through fixation extraction, region-specific visual prompting, and scanpath construction. This pipeline produces spatio-temporally grounded QA pairs that reflect human perceptual dynamics. Across all StreamGaze tasks, we observe substantial performance gaps between state-of-the-art MLLMs and human performance, highlighting key limitations in gaze-based temporal reasoning, intention modeling, and proactive prediction. We further provide detailed analyses of gaze prompting strategies, reasoning behaviors, and task-specific failure modes, offering insights into current limitations and directions for future research. All data and code are publicly available to support continued research in gaze-guided streaming video understanding. ---