# Research Papers — 2025-11 · bundle page 91 of 197 > Full-text markdown of papers #4501–4550 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/91 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/90.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/92.md) ### Beat the long tail: Distribution-Aware Speculative Decoding for RL Training Authors: Zelei Shao, Vikranth Srivatsa, Sanjana Srivastava, Qingyang Wu, Alpay Ariyak, Xiaoxia Wu, Ameen Patel, Jue Wang, Percy Liang, Tri Dao, Ce Zhang, Yiying Zhang et al. Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13841v1 Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where long trajectories are generated token by token. We identify a major bottleneck:the long-tail distribution of rollout lengths, where a small fraction of long generations dominates wall clock time and a complementary opportunity; the availability of historical rollouts that reveal stable prompt level patterns across training epochs. Motivated by these observations, we propose DAS, a Distribution Aware Speculative decoding framework that accelerates RL rollouts without altering model outputs. DAS integrates two key ideas: an adaptive, nonparametric drafter built from recent rollouts using an incrementally maintained suffix tree, and a length aware speculation policy that allocates more aggressive draft budgets to long trajectories that dominate makespan. This design exploits rollout history to sustain acceptance while balancing base and token level costs during decoding. Experiments on math and code reasoning tasks show that DAS reduces rollout time up to 50% while preserving identical training curves, demonstrating that distribution-aware speculative decoding can significantly accelerate RL post training without compromising learning quality. --- ### When AI Does Science: Evaluating the Autonomous AI Scientist KOSMOS in Radiation Biology Authors: Humza Nusrat, Omar Nusrat Published: 2025-11-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.13825v1 Agentic AI "scientists" now use language models to search the literature, run analyses, and generate hypotheses. We evaluate KOSMOS, an autonomous AI scientist, on three problems in radiation biology using simple random-gene null benchmarks. Hypothesis 1: baseline DNA damage response (DDR) capacity across cell lines predicts the p53 transcriptional response after irradiation (GSE30240). Hypothesis 2: baseline expression of OGT and CDO1 predicts the strength of repressed and induced radiation-response modules in breast cancer cells (GSE59732). Hypothesis 3: a 12-gene expression signature predicts biochemical recurrence-free survival after prostate radiotherapy plus androgen deprivation therapy (GSE116918). The DDR-p53 hypothesis was not supported: DDR score and p53 response were weakly negatively correlated (Spearman rho = -0.40, p = 0.76), indistinguishable from random five-gene scores. OGT showed only a weak association (r = 0.23, p = 0.34), whereas CDO1 was a clear outlier (r = 0.70, empirical p = 0.0039). The 12-gene signature achieved a concordance index of 0.61 (p = 0.017) but a non-unique effect size. Overall, KOSMOS produced one well-supported discovery, one plausible but uncertain result, and one false hypothesis, illustrating that AI scientists can generate useful ideas but require rigorous auditing against appropriate null models. --- ### ScoresActivation: A New Activation Function for Model Agnostic Global Explainability by Design Authors: Emanuel Covaci, Fabian Galis, Radu Balan, Daniela Zaharie, Darian Onchis Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13809v1 Understanding the decision of large deep learning models is a critical challenge for building transparent and trustworthy systems. Although the current post hoc explanation methods offer valuable insights into feature importance, they are inherently disconnected from the model training process, limiting their faithfulness and utility. In this work, we introduce a novel differentiable approach to global explainability by design, integrating feature importance estimation directly into model training. Central to our method is the ScoresActivation function, a feature-ranking mechanism embedded within the learning pipeline. This integration enables models to prioritize features according to their contribution to predictive performance in a differentiable and end-to-end trainable manner. Evaluations across benchmark datasets show that our approach yields globally faithful, stable feature rankings aligned with SHAP values and ground-truth feature importance, while maintaining high predictive performance. Moreover, feature scoring is 150 times faster than the classical SHAP method, requiring only 2 seconds during training compared to SHAP's 300 seconds for feature ranking in the same configuration. Our method also improves classification accuracy by 11.24% with 10 features (5 relevant) and 29.33% with 16 features (5 relevant, 11 irrelevant), demonstrating robustness to irrelevant inputs. This work bridges the gap between model accuracy and interpretability, offering a scalable framework for inherently explainable machine learning. --- ### Zipf-Gramming: Scaling Byte N-Grams Up to Production Sized Malware Corpora Authors: Edward Raff, Ryan R. Curtin, Derek Everett, Robert J. Joyce, James Holt Published: 2025-11-17 Categories: cs.CR, cs.LG, cs.MS arXiv: https://arxiv.org/abs/2511.13808v1 A classifier using byte n-grams as features is the only approach we have found fast enough to meet requirements in size (sub 2 MB), speed (multiple GB/s), and latency (sub 10 ms) for deployment in numerous malware detection scenarios. However, we've consistently found that 6-8 grams achieve the best accuracy on our production deployments but have been unable to deploy regularly updated models due to the high cost of finding the top-k most frequent n-grams over terabytes of executable programs. Because the Zipfian distribution well models the distribution of n-grams, we exploit its properties to develop a new top-k n-gram extractor that is up to $35\times$ faster than the previous best alternative. Using our new Zipf-Gramming algorithm, we are able to scale up our production training set and obtain up to 30\% improvement in AUC at detecting new malware. We show theoretically and empirically that our approach will select the top-k items with little error and the interplay between theory and engineering required to achieve these results. --- ### GAEA: Experiences and Lessons Learned from a Country-Scale Environmental Digital Twin Authors: Andreas Kamilaris, Chirag Padubidri, Asfa Jamil, Arslan Amin, Indrajit Kalita, Jyoti Harti, Savvas Karatsiolis, Aytac Guley Published: 2025-11-17 Categories: cs.CY, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2511.13807v1 This paper describes the experiences and lessons learned after the deployment of a country-scale environmental digital twin on the island of Cyprus for three years. This digital twin, called GAEA, contains 27 environmental geospatial services and is suitable for urban planners, policymakers, farmers, property owners, real-estate and forestry professionals, as well as insurance companies and banks that have properties in their portfolio. This paper demonstrates the power, potential, current and future challenges of geospatial analytics and environmental digital twins on a large scale. --- ### Passive Dementia Screening via Facial Temporal Micro-Dynamics Analysis of In-the-Wild Talking-Head Video Authors: Filippo Cenacchi, Longbing Cao, Mitchell McEwan, Deborah Richards Published: 2025-11-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.13802v2 We target passive dementia screening from short camera-facing talking head video, developing a facial temporal micro dynamics analysis for language free detection of early neuro cognitive change. This enables unscripted, in the wild video analysis at scale to capture natural facial behaviors, transferrable across devices, topics, and cultures without active intervention by clinicians or researchers during recording. Most existing resources prioritize speech or scripted interviews, limiting use outside clinics and coupling predictions to language and transcription. In contrast, we identify and analyze whether temporal facial kinematics, including blink dynamics, small mouth jaw motions, gaze variability, and subtle head adjustments, are sufficient for dementia screening without speech or text. By stabilizing facial signals, we convert these micro movements into interpretable facial microdynamic time series, smooth them, and summarize short windows into compact clip level statistics for screening. Each window is encoded by its activity mix (the relative share of motion across streams), thus the predictor analyzes the distribution of motion across streams rather than its magnitude, making per channel effects transparent. We also introduce YT DemTalk, a new dataset curated from publicly available, in the wild camera facing videos. It contains 300 clips (150 with self reported dementia, 150 controls) to test our model and offer a first benchmarking of the corpus. On YT DemTalk, ablations identify gaze lability and mouth/jaw dynamics as the most informative cues, and light weighted shallow classifiers could attain a dementia prediction performance of (AUROC) 0.953, 0.961 Average Precision (AP), 0.851 F1-score, and 0.857 accuracy. --- ### Rdgai: Classifying transcriptional changes using Large Language Models with a test case from an Arabic Gospel tradition Authors: Robert Turnbull Published: 2025-11-17 Categories: cs.DL, cs.CL arXiv: https://arxiv.org/abs/2511.13801v1 Application of phylogenetic methods to textual traditions has traditionally treated all changes as equivalent even though it is widely recognized that certain types of variants were more likely to be introduced than others. While it is possible to give weights to certain changes using a maximum parsimony evaluation criterion, it is difficult to state a priori what these weights should be. Probabilistic methods, such as Bayesian phylogenetics, allow users to create categories of changes, and the transition rates for each category can be estimated as part of the analysis. This classification of types of changes in readings also allows for inspecting the probability of these categories across each branch in the resulting trees. However, classification of readings is time-consuming, as it requires categorizing each reading against every other reading at each variation unit, presenting a significant barrier to entry for this kind of analysis. This paper presents Rdgai, a software package that automates this classification task using multi-lingual large language models (LLMs). The tool allows users to easily manually classify changes in readings and then it uses these annotations in the prompt for an LLM to automatically classify the remaining reading transitions. These classifications are stored in TEI XML and ready for downstream phylogenetic analysis. This paper demonstrates the application with data an Arabic translation of the Gospels. --- ### Synergizing Multigrid Algorithms with Vision Transformer: A Novel Approach to Enhance the Seismic Foundation Model Authors: Huiwen Wu, Shuo Zhang, Yi Liu, Hongbin Ye Published: 2025-11-17 Categories: cs.CV, cs.AI, math.NA arXiv: https://arxiv.org/abs/2511.13800v1 Due to the emergency and homogenization of Artificial Intelligence (AI) technology development, transformer-based foundation models have revolutionized scientific applications, such as drug discovery, materials research, and astronomy. However, seismic data presents unique characteristics that require specialized processing techniques for pretraining foundation models in seismic contexts with high- and low-frequency features playing crucial roles. Existing vision transformers (ViTs) with sequential tokenization ignore the intrinsic pattern and fail to grasp both the high- and low-frequency seismic information efficiently and effectively. This work introduces a novel adaptive two-grid foundation model training strategy (ADATG) with Hilbert encoding specifically tailored for seismogram data, leveraging the hierarchical structures inherent in seismic data. Specifically, our approach employs spectrum decomposition to separate high- and low-frequency components and utilizes hierarchical Hilbert encoding to represent the data effectively. Moreover, observing the frequency principle observed in ViTs, we propose an adaptive training strategy that initially emphasizes coarse-level information and then progressively refines the model's focus on fine-level features. Our extensive experiments demonstrate the effectiveness and efficiency of our training methods. This research highlights the importance of data encoding and training strategies informed by the distinct characteristics of high- and low-frequency features in seismic images, ultimately contributing to the enhancement of visual seismic foundation models pretraining. --- ### KANGURA: Kolmogorov-Arnold Network-Based Geometry-Aware Learning with Unified Representation Attention for 3D Modeling of Complex Structures Authors: Mohammad Reza Shafie, Morteza Hajiabadi, Hamed Khosravi, Mobina Noori, Imtiaz Ahmed Published: 2025-11-17 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.13798v1 Microbial Fuel Cells (MFCs) offer a promising pathway for sustainable energy generation by converting organic matter into electricity through microbial processes. A key factor influencing MFC performance is the anode structure, where design and material properties play a crucial role. Existing predictive models struggle to capture the complex geometric dependencies necessary to optimize these structures. To solve this problem, we propose KANGURA: Kolmogorov-Arnold Network-Based Geometry-Aware Learning with Unified Representation Attention. KANGURA introduces a new approach to three-dimensional (3D) machine learning modeling. It formulates prediction as a function decomposition problem, where Kolmogorov-Arnold Network (KAN)- based representation learning reconstructs geometric relationships without a conventional multi- layer perceptron (MLP). To refine spatial understanding, geometry-disentangled representation learning separates structural variations into interpretable components, while unified attention mechanisms dynamically enhance critical geometric regions. Experimental results demonstrate that KANGURA outperforms over 15 state-of-the-art (SOTA) models on the ModelNet40 benchmark dataset, achieving 92.7% accuracy, and excels in a real-world MFC anode structure problem with 97% accuracy. This establishes KANGURA as a robust framework for 3D geometric modeling, unlocking new possibilities for optimizing complex structures in advanced manufacturing and quality-driven engineering applications. --- ### MAT-MPNN: A Mobility-Aware Transformer-MPNN Model for Dynamic Spatiotemporal Prediction of HIV Diagnoses in California, Florida, and New England Authors: Zhaoxuan Wang, Weichen Kang, Yutian Han, Lingyuan Zhao, Bo Li Published: 2025-11-17 Categories: q-bio.QM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.13797v1 Human Immunodeficiency Virus (HIV) has posed a major global health challenge for decades, and forecasting HIV diagnoses continues to be a critical area of research. However, capturing the complex spatial and temporal dependencies of HIV transmission remains challenging. Conventional Message Passing Neural Network (MPNN) models rely on a fixed binary adjacency matrix that only encodes geographic adjacency, which is unable to represent interactions between non-contiguous counties. Our study proposes a deep learning architecture Mobility-Aware Transformer-Message Passing Neural Network (MAT-MPNN) framework to predict county-level HIV diagnosis rates across California, Florida, and the New England region. The model combines temporal features extracted by a Transformer encoder with spatial relationships captured through a Mobility Graph Generator (MGG). The MGG improves conventional adjacency matrices by combining geographic and demographic information. Compared with the best-performing hybrid baseline, the Transformer MPNN model, MAT-MPNN reduced the Mean Squared Prediction Error (MSPE) by 27.9% in Florida, 39.1% in California, and 12.5% in New England, and improved the Predictive Model Choice Criterion (PMCC) by 7.7%, 3.5%, and 3.9%, respectively. MAT-MPNN also achieved better results than the Spatially Varying Auto-Regressive (SVAR) model in Florida and New England, with comparable performance in California. These results demonstrate that applying mobility-aware dynamic spatial structures substantially enhances predictive accuracy and calibration in spatiotemporal epidemiological prediction. --- ### A Trajectory-free Crash Detection Framework with Generative Approach and Segment Map Diffusion Authors: Weiying Shen, Hao Yu, Yu Dong, Pan Liu, Yu Han, Xin Wen Published: 2025-11-17 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2511.13795v1 Real-time crash detection is essential for developing proactive safety management strategy and enhancing overall traffic efficiency. To address the limitations associated with trajectory acquisition and vehicle tracking, road segment maps recording the individual-level traffic dynamic data were directly served in crash detection. A novel two-stage trajectory-free crash detection framework, was present to generate the rational future road segment map and identify crashes. The first-stage diffusion-based segment map generation model, Mapfusion, conducts a noisy-to-normal process that progressively adds noise to the road segment map until the map is corrupted to pure Gaussian noise. The denoising process is guided by sequential embedding components capturing the temporal dynamics of segment map sequences. Furthermore, the generation model is designed to incorporate background context through ControlNet to enhance generation control. Crash detection is achieved by comparing the monitored segment map with the generations from diffusion model in second stage. Trained on non-crash vehicle motion data, Mapfusion successfully generates realistic road segment evolution maps based on learned motion patterns and remains robust across different sampling intervals. Experiments on real-world crashes indicate the effectiveness of the proposed two-stage method in accurately detecting crashes. --- ### FusionFM: All-in-One Multi-Modal Image Fusion with Flow Matching Authors: Huayi Zhu, Xiu Shu, Youqiang Xiong, Qiao Liu, Rui Chen, Di Yuan, Xiaojun Chang, Zhenyu He Published: 2025-11-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.13794v1 Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference due to the complex sampling trajectories from noise to image. To address this, we formulate image fusion as a direct probabilistic transport from source modalities to the fused image distribution, leveraging the flow matching paradigm to improve sampling efficiency and structural consistency. To mitigate the lack of high-quality fused images for supervision, we collect fusion results from multiple state-of-the-art models as priors, and employ a task-aware selection function to select the most reliable pseudo-labels for each task. We further introduce a Fusion Refiner module that employs a divide-and-conquer strategy to systematically identify, decompose, and enhance degraded components in selected pseudo-labels. For multi-task scenarios, we integrate elastic weight consolidation and experience replay mechanisms to preserve cross-task performance and enhance continual learning ability from both parameter stability and memory retention perspectives. Our approach achieves competitive performance across diverse fusion tasks, while significantly improving sampling efficiency and maintaining a lightweight model design. The code will be available at: https://github.com/Ist-Zhy/FusionFM. --- ### Back to Basics: Let Denoising Generative Models Denoise Authors: Tianhong Li, Kaiming He Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13720v2 Today's denoising diffusion models do not "denoise" in the classical sense, i.e., they do not directly predict clean images. Rather, the neural networks predict noise or a noised quantity. In this paper, we suggest that predicting clean data and predicting noised quantities are fundamentally different. According to the manifold assumption, natural data should lie on a low-dimensional manifold, whereas noised quantities do not. With this assumption, we advocate for models that directly predict clean data, which allows apparently under-capacity networks to operate effectively in very high-dimensional spaces. We show that simple, large-patch Transformers on pixels can be strong generative models: using no tokenizer, no pre-training, and no extra loss. Our approach is conceptually nothing more than "Just image Transformers", or JiT, as we call it. We report competitive results using JiT with large patch sizes of 16 and 32 on ImageNet at resolutions of 256 and 512, where predicting high-dimensional noised quantities can fail catastrophically. With our networks mapping back to the basics of the manifold, our research goes back to basics and pursues a self-contained paradigm for Transformer-based diffusion on raw natural data. --- ### Scaling Spatial Intelligence with Multimodal Foundation Models Authors: Zhongang Cai, Ruisi Wang, Chenyang Gu, Fanyi Pu, Junxiang Xu, Yubo Wang, Wanqi Yin, Zhitao Yang, Chen Wei, Qingping Sun, Tongxi Zhou, Jiaqi Li et al. Published: 2025-11-17 Categories: cs.CV, cs.AI, cs.LG, cs.MM, cs.RO arXiv: https://arxiv.org/abs/2511.13719v4 Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the SenseNova-SI family, built upon established multimodal foundations including visual understanding models (i.e., Qwen3-VL and InternVL3) and unified understanding and generation models (i.e., Bagel). We take a principled approach to constructing high-performing and robust spatial intelligence by systematically curating SenseNova-SI-8M: eight million diverse data samples under a rigorous taxonomy of spatial capabilities. SenseNova-SI demonstrates unprecedented performance across a broad range of spatial intelligence benchmarks: 68.8% on VSI-Bench, 43.3% on MMSI, 85.7% on MindCube, 54.7% on ViewSpatial, 47.7% on SITE, 63.9% on BLINK, 55.5% on 3DSR, and 72.0% on EmbSpatial, while maintaining strong general multimodal understanding (e.g., 84.9% on MMBench-En). More importantly, we analyze the impact of data scaling, discuss early signs of emergent generalization capabilities enabled by diverse data training, analyze the risk of overfitting and language shortcuts, present a preliminary study on spatial chain-of-thought reasoning, and validate the potential downstream application. All newly trained multimodal foundation models are publicly released. --- ### Segment Anything Across Shots: A Method and Benchmark Authors: Hengrui Hu, Kaining Ying, Henghui Ding Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13715v1 This work focuses on multi-shot semi-supervised video object segmentation (MVOS), which aims at segmenting the target object indicated by an initial mask throughout a video with multiple shots. The existing VOS methods mainly focus on single-shot videos and struggle with shot discontinuities, thereby limiting their real-world applicability. We propose a transition mimicking data augmentation strategy (TMA) which enables cross-shot generalization with single-shot data to alleviate the severe annotated multi-shot data sparsity, and the Segment Anything Across Shots (SAAS) model, which can detect and comprehend shot transitions effectively. To support evaluation and future study in MVOS, we introduce Cut-VOS, a new MVOS benchmark with dense mask annotations, diverse object categories, and high-frequency transitions. Extensive experiments on YouMVOS and Cut-VOS demonstrate that the proposed SAAS achieves state-of-the-art performance by effectively mimicking, understanding, and segmenting across complex transitions. The code and datasets are released at https://henghuiding.com/SAAS/. --- ### UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity Authors: Junwei Yu, Trevor Darrell, XuDong Wang Published: 2025-11-17 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.13714v2 The Segment Anything Model (SAM) family has become a widely adopted vision foundation model, but its ability to control segmentation granularity remains limited. Users often need to refine results manually - by adding more prompts or selecting from pre-generated masks - to achieve the desired level of detail. This process can be ambiguous, as the same prompt may correspond to several plausible masks, and collecting dense annotations across all granularities is prohibitively expensive, making supervised solutions infeasible. To address this limitation, we introduce UnSAMv2, which can segment anything at any granularity without using any human annotations. UnSAMv2 extends the divide-and-conquer strategy of UnSAM by discovering abundant mask-granularity pairs and introducing a novel granularity control embedding that enables precise, continuous control over segmentation scale. Remarkably, with only $6$K unlabeled images and $0.02\%$ additional parameters, UnSAMv2 substantially enhances SAM-2, enabling segmentation of anything at any granularity across interactive, whole-image, and video segmentation tasks. Furthermore, we introduce a language-guided segmentation pipeline that treats granularity as a predictable variable by grounding it in text semantics via an external vision-language model, improving upon the previous state of the art in 1-IoU (40.4 $\rightarrow$ 47.3). Across 11+ benchmarks, UnSAMv2 achieves consistent gains over SAM/SAM-2 baselines, improving $\text{NoC}_{90}$ (5.69 $\rightarrow$ 4.75), 1-IoU (58.0 $\rightarrow$ 73.1), and $\text{AR}_{1000}$ (49.6 $\rightarrow$ 68.3) by a large margin. Our work demonstrates that a small amount of unlabeled data can deliver large, practical improvements to strong supervised baselines. Our code, dataset, and demo are available at https://github.com/yujunwei04/UnSAMv2. --- ### Free-Form Scene Editor: Enabling Multi-Round Object Manipulation like in a 3D Engine Authors: Xincheng Shuai, Zhenyuan Qin, Henghui Ding, Dacheng Tao Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13713v1 Recent advances in text-to-image (T2I) diffusion models have significantly improved semantic image editing, yet most methods fall short in performing 3D-aware object manipulation. In this work, we present FFSE, a 3D-aware autoregressive framework designed to enable intuitive, physically-consistent object editing directly on real-world images. Unlike previous approaches that either operate in image space or require slow and error-prone 3D reconstruction, FFSE models editing as a sequence of learned 3D transformations, allowing users to perform arbitrary manipulations, such as translation, scaling, and rotation, while preserving realistic background effects (e.g., shadows, reflections) and maintaining global scene consistency across multiple editing rounds. To support learning of multi-round 3D-aware object manipulation, we introduce 3DObjectEditor, a hybrid dataset constructed from simulated editing sequences across diverse objects and scenes, enabling effective training under multi-round and dynamic conditions. Extensive experiments show that the proposed FFSE significantly outperforms existing methods in both single-round and multi-round 3D-aware editing scenarios. --- ### From Black Box to Insight: Explainable AI for Extreme Event Preparedness Authors: Kiana Vu, İsmet Selçuk Özer, Phung Lai, Zheng Wu, Thilanka Munasinghe, Jennifer Wei Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13712v1 As climate change accelerates the frequency and severity of extreme events such as wildfires, the need for accurate, explainable, and actionable forecasting becomes increasingly urgent. While artificial intelligence (AI) models have shown promise in predicting such events, their adoption in real-world decision-making remains limited due to their black-box nature, which limits trust, explainability, and operational readiness. This paper investigates the role of explainable AI (XAI) in bridging the gap between predictive accuracy and actionable insight for extreme event forecasting. Using wildfire prediction as a case study, we evaluate various AI models and employ SHapley Additive exPlanations (SHAP) to uncover key features, decision pathways, and potential biases in model behavior. Our analysis demonstrates how XAI not only clarifies model reasoning but also supports critical decision-making by domain experts and response teams. In addition, we provide supporting visualizations that enhance the interpretability of XAI outputs by contextualizing feature importance and temporal patterns in seasonality and geospatial characteristics. This approach enhances the usability of AI explanations for practitioners and policymakers. Our findings highlight the need for AI systems that are not only accurate but also interpretable, accessible, and trustworthy, essential for effective use in disaster preparedness, risk mitigation, and climate resilience planning. --- ### From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands Authors: Jianglong Ye, Lai Wei, Guangqi Jiang, Changwei Jing, Xueyan Zou, Xiaolong Wang Published: 2025-11-17 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.13710v1 Human grasps can be roughly categorized into two types: power grasps and precision grasps. Precision grasping enables tool use and is believed to have influenced human evolution. Today's multi-fingered robotic hands are effective in power grasps, but for tasks requiring precision, parallel grippers are still more widely adopted. This contrast highlights a key limitation in current robotic hand design: the difficulty of achieving both stable power grasps and precise, fine-grained manipulation within a single, versatile system. In this work, we bridge this gap by jointly optimizing the control and hardware design of a multi-fingered dexterous hand, enabling both power and precision manipulation. Rather than redesigning the entire hand, we introduce a lightweight fingertip geometry modification, represent it as a contact plane, and jointly optimize its parameters along with the corresponding control. Our control strategy dynamically switches between power and precision manipulation and simplifies precision control into parallel thumb-index motions, which proves robust for sim-to-real transfer. On the design side, we leverage large-scale simulation to optimize the fingertip geometry using a differentiable neural-physics surrogate model. We validate our approach through extensive experiments in both sim-to-real and real-to-real settings. Our method achieves an 82.5% zero-shot success rate on unseen objects in sim-to-real precision grasping, and a 93.3% success rate in challenging real-world tasks involving bread pinching. These results demonstrate that our co-design framework can significantly enhance the fine-grained manipulation ability of multi-fingered hands without reducing their ability for power grasps. Our project page is at https://jianglongye.com/power-to-precision --- ### Rare Genomic Subtype Discovery from RNA-seq via Autoencoder Embeddings and Stability-Aware Clustering Authors: Alaa Mezghiche Published: 2025-11-17 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2511.13705v1 Unsupervised learning on high-dimensional RNA-seq data can reveal molecular subtypes beyond standard labels. We combine an autoencoder-based representation with clustering and stability analysis to search for rare but reproducible genomic subtypes. On the UCI "Gene Expression Cancer RNA-Seq" dataset (801 samples, 20,531 genes; BRCA, COAD, KIRC, LUAD, PRAD), a pan-cancer analysis shows clusters aligning almost perfectly with tissue of origin (Cramer's V = 0.887), serving as a negative control. We therefore reframe the problem within KIRC (n = 146): we select the top 2,000 highly variable genes, standardize them, train a feed-forward autoencoder (128-dimensional latent space), and run k-means for k = 2-10. While global indices favor small k, scanning k with a pre-specified discovery rule (rare < 10 percent and stable with Jaccard >= 0.60 across 20 seeds after Hungarian alignment) yields a simple solution at k = 5 (silhouette = 0.129, DBI = 2.045) with a rare cluster C0 (6.85 percent of patients) that is highly stable (Jaccard = 0.787). Cluster-vs-rest differential expression (Welch's t-test, Benjamini-Hochberg FDR) identifies coherent markers. Overall, pan-cancer clustering is dominated by tissue of origin, whereas a stability-aware within-cancer approach reveals a rare, reproducible KIRC subtype. --- ### TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models Authors: Harold Haodong Chen, Disen Lan, Wen-Jie Shu, Qingyang Liu, Zihan Wang, Sirui Chen, Wenkai Cheng, Kanghao Chen, Hongfei Zhang, Zixin Zhang, Rongjin Guo, Yu Cheng et al. Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13704v2 The rapid evolution of video generative models has shifted their focus from producing visually plausible outputs to tackling tasks requiring physical plausibility and logical consistency. However, despite recent breakthroughs such as Veo 3's chain-of-frames reasoning, it remains unclear whether these models can exhibit reasoning capabilities similar to large language models (LLMs). Existing benchmarks predominantly evaluate visual fidelity and temporal coherence, failing to capture higher-order reasoning abilities. To bridge this gap, we propose TiViBench, a hierarchical benchmark specifically designed to evaluate the reasoning capabilities of image-to-video (I2V) generation models. TiViBench systematically assesses reasoning across four dimensions: i) Structural Reasoning & Search, ii) Spatial & Visual Pattern Reasoning, iii) Symbolic & Logical Reasoning, and iv) Action Planning & Task Execution, spanning 24 diverse task scenarios across 3 difficulty levels. Through extensive evaluations, we show that commercial models (e.g., Sora 2, Veo 3.1) demonstrate stronger reasoning potential, while open-source models reveal untapped potential that remains hindered by limited training scale and data diversity. To further unlock this potential, we introduce VideoTPO, a simple yet effective test-time strategy inspired by preference optimization. By performing LLM self-analysis on generated candidates to identify strengths and weaknesses, VideoTPO significantly enhances reasoning performance without requiring additional training, data, or reward models. Together, TiViBench and VideoTPO pave the way for evaluating and advancing reasoning in video generation models, setting a foundation for future research in this emerging field. --- ### Generalist Foundation Models Are Not Clinical Enough for Hospital Operations Authors: Lavender Y. Jiang, Angelica Chen, Xu Han, Xujin Chris Liu, Radhika Dua, Kevin Eaton, Frederick Wolff, Robert Steele, Jeff Zhang, Anton Alyakin, Qingkai Pan, Yanbing Chen et al. Published: 2025-11-17 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.13703v1 Hospitals and healthcare systems rely on operational decisions that determine patient flow, cost, and quality of care. Despite strong performance on medical knowledge and conversational benchmarks, foundation models trained on general text may lack the specialized knowledge required for these operational decisions. We introduce Lang1, a family of models (100M-7B parameters) pretrained on a specialized corpus blending 80B clinical tokens from NYU Langone Health's EHRs and 627B tokens from the internet. To rigorously evaluate Lang1 in real-world settings, we developed the REalistic Medical Evaluation (ReMedE), a benchmark derived from 668,331 EHR notes that evaluates five critical tasks: 30-day readmission prediction, 30-day mortality prediction, length of stay, comorbidity coding, and predicting insurance claims denial. In zero-shot settings, both general-purpose and specialized models underperform on four of five tasks (36.6%-71.7% AUROC), with mortality prediction being an exception. After finetuning, Lang1-1B outperforms finetuned generalist models up to 70x larger and zero-shot models up to 671x larger, improving AUROC by 3.64%-6.75% and 1.66%-23.66% respectively. We also observed cross-task scaling with joint finetuning on multiple tasks leading to improvement on other tasks. Lang1-1B effectively transfers to out-of-distribution settings, including other clinical tasks and an external health system. Our findings suggest that predictive capabilities for hospital operations require explicit supervised finetuning, and that this finetuning process is made more efficient by in-domain pretraining on EHR. Our findings support the emerging view that specialized LLMs can compete with generalist models in specialized tasks, and show that effective healthcare systems AI requires the combination of in-domain pretraining, supervised finetuning, and real-world evaluation beyond proxy benchmarks. --- ### ST-ProC: A Graph-Prototypical Framework for Robust Semi-Supervised Travel Mode Identification Authors: Luyao Niu, Nuoxian Huang Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13702v1 Travel mode identification (TMI) from GPS trajectories is critical for urban intelligence, but is hampered by the high cost of annotation, leading to severe label scarcity. Prevailing semi-supervised learning (SSL) methods are ill-suited for this task, as they suffer from catastrophic confirmation bias and ignore the intrinsic data manifold. We propose ST-ProC, a novel graph-prototypical multi-objective SSL framework to address these limitations. Our framework synergizes a graph-prototypical core with foundational SSL Support. The core exploits the data manifold via graph regularization, prototypical anchoring, and a novel, margin-aware pseudo-labeling strategy to actively reject noise. This core is supported and stabilized by foundational contrastive and teacher-student consistency losses, ensuring high-quality representations and robust optimization. ST-ProC outperforms all baselines by a significant margin, demonstrating its efficacy in real-world sparse-label settings, with a performance boost of 21.5% over state-of-the-art methods like FixMatch. --- ### Learning stochasticity: a nonparametric framework for intrinsic noise estimation Authors: Gianluigi Pillonetto, Alberto Giaretta, Mauro Bisiacco Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13701v1 Understanding the principles that govern dynamical systems is a central challenge across many scientific domains, including biology and ecology. Incomplete knowledge of nonlinear interactions and stochastic effects often renders bottom-up modeling approaches ineffective, motivating the development of methods that can discover governing equations directly from data. In such contexts, parametric models often struggle without strong prior knowledge, especially when estimating intrinsic noise. Nonetheless, incorporating stochastic effects is often essential for understanding the dynamic behavior of complex systems such as gene regulatory networks and signaling pathways. To address these challenges, we introduce Trine (Three-phase Regression for INtrinsic noisE), a nonparametric, kernel-based framework that infers state-dependent intrinsic noise from time-series data. Trine features a three-stage algorithm that com- bines analytically solvable subproblems with a structured kernel architecture that captures both abrupt noise-driven fluctuations and smooth, state-dependent changes in variance. We validate Trine on biological and ecological systems, demonstrating its ability to uncover hidden dynamics without relying on predefined parametric assumptions. Across several benchmark problems, Trine achieves performance comparable to that of an oracle. Biologically, this oracle can be viewed as an idealized observer capable of directly tracking the random fluctuations in molecular concentrations or reaction events within a cell. The Trine framework thus opens new avenues for understanding how intrinsic noise affects the behavior of complex systems. --- ### Efficient Calibration for Decision Making Authors: Parikshit Gopalan, Konstantinos Stavropoulos, Kunal Talwar, Pranay Tankala Published: 2025-11-17 Categories: cs.LG, cs.DS, stat.ML arXiv: https://arxiv.org/abs/2511.13699v1 A decision-theoretic characterization of perfect calibration is that an agent seeking to minimize a proper loss in expectation cannot improve their outcome by post-processing a perfectly calibrated predictor. Hu and Wu (FOCS'24) use this to define an approximate calibration measure called calibration decision loss ($\mathsf{CDL}$), which measures the maximal improvement achievable by any post-processing over any proper loss. Unfortunately, $\mathsf{CDL}$ turns out to be intractable to even weakly approximate in the offline setting, given black-box access to the predictions and labels. We suggest circumventing this by restricting attention to structured families of post-processing functions $K$. We define the calibration decision loss relative to $K$, denoted $\mathsf{CDL}_K$ where we consider all proper losses but restrict post-processings to a structured family $K$. We develop a comprehensive theory of when $\mathsf{CDL}_K$ is information-theoretically and computationally tractable, and use it to prove both upper and lower bounds for natural classes $K$. In addition to introducing new definitions and algorithmic techniques to the theory of calibration for decision making, our results give rigorous guarantees for some widely used recalibration procedures in machine learning. --- ### Crossing Borders: A Multimodal Challenge for Indian Poetry Translation and Image Generation Authors: Sofia Jamil, Kotla Sai Charan, Sriparna Saha, Koustava Goswami, Joseph K J Published: 2025-11-17 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2511.13689v2 Indian poetry, known for its linguistic complexity and deep cultural resonance, has a rich and varied heritage spanning thousands of years. However, its layered meanings, cultural allusions, and sophisticated grammatical constructions often pose challenges for comprehension, especially for non-native speakers or readers unfamiliar with its context and language. Despite its cultural significance, existing works on poetry have largely overlooked Indian language poems. In this paper, we propose the Translation and Image Generation (TAI) framework, leveraging Large Language Models (LLMs) and Latent Diffusion Models through appropriate prompt tuning. Our framework supports the United Nations Sustainable Development Goals of Quality Education (SDG 4) and Reduced Inequalities (SDG 10) by enhancing the accessibility of culturally rich Indian-language poetry to a global audience. It includes (1) a translation module that uses an Odds Ratio Preference Alignment Algorithm to accurately translate morphologically rich poetry into English, and (2) an image generation module that employs a semantic graph to capture tokens, dependencies, and semantic relationships between metaphors and their meanings, to create visually meaningful representations of Indian poems. Our comprehensive experimental evaluation, including both human and quantitative assessments, demonstrates the superiority of TAI Diffusion in poem image generation tasks, outperforming strong baselines. To further address the scarcity of resources for Indian-language poetry, we introduce the Morphologically Rich Indian Language Poems MorphoVerse Dataset, comprising 1,570 poems across 21 low-resource Indian languages. By addressing the gap in poetry translation and visual comprehension, this work aims to broaden accessibility and enrich the reader's experience. --- ### Protein Secondary Structure Prediction Using 3D Graphs and Relation-Aware Message Passing Transformers Authors: Disha Varshney, Samarth Garg, Sarthak Tyagi, Deeksha Varshney, Nayan Deep, Asif Ekbal Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13685v1 In this study, we tackle the challenging task of predicting secondary structures from protein primary sequences, a pivotal initial stride towards predicting tertiary structures, while yielding crucial insights into protein activity, relationships, and functions. Existing methods often utilize extensive sets of unlabeled amino acid sequences. However, these approaches neither explicitly capture nor harness the accessible protein 3D structural data, which is recognized as a decisive factor in dictating protein functions. To address this, we utilize protein residue graphs and introduce various forms of sequential or structural connections to capture enhanced spatial information. We adeptly combine Graph Neural Networks (GNNs) and Language Models (LMs), specifically utilizing a pre-trained transformer-based protein language model to encode amino acid sequences and employing message-passing mechanisms like GCN and R-GCN to capture geometric characteristics of protein structures. Employing convolution within a specific node's nearby region, including relations, we stack multiple convolutional layers to efficiently learn combined insights from the protein's spatial graph, revealing intricate interconnections and dependencies in its structural arrangement. To assess our model's performance, we employed the training dataset provided by NetSurfP-2.0, which outlines secondary structure in 3-and 8-states. Extensive experiments show that our proposed model, SSRGNet surpasses the baseline on f1-scores. --- ### Training-Free Multi-View Extension of IC-Light for Textual Position-Aware Scene Relighting Authors: Jiangnan Ye, Jiedong Zhuang, Lianrui Mu, Wenjie Zheng, Jiaqi Hu, Xingze Zou, Jing Wang, Haoji Hu Published: 2025-11-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.13684v1 We introduce GS-Light, an efficient, textual position-aware pipeline for text-guided relighting of 3D scenes represented via Gaussian Splatting (3DGS). GS-Light implements a training-free extension of a single-input diffusion model to handle multi-view inputs. Given a user prompt that may specify lighting direction, color, intensity, or reference objects, we employ a large vision-language model (LVLM) to parse the prompt into lighting priors. Using off-the-shelf estimators for geometry and semantics (depth, surface normals, and semantic segmentation), we fuse these lighting priors with view-geometry constraints to compute illumination maps and generate initial latent codes for each view. These meticulously derived init latents guide the diffusion model to generate relighting outputs that more accurately reflect user expectations, especially in terms of lighting direction. By feeding multi-view rendered images, along with the init latents, into our multi-view relighting model, we produce high-fidelity, artistically relit images. Finally, we fine-tune the 3DGS scene with the relit appearance to obtain a fully relit 3D scene. We evaluate GS-Light on both indoor and outdoor scenes, comparing it to state-of-the-art baselines including per-view relighting, video relighting, and scene editing methods. Using quantitative metrics (multi-view consistency, imaging quality, aesthetic score, semantic similarity, etc.) and qualitative assessment (user studies), GS-Light demonstrates consistent improvements over baselines. Code and assets will be made available upon publication. --- ### Cross-Learning from Scarce Data via Multi-Task Constrained Optimization Authors: Leopoldo Agorio, Juan Cerviño, Miguel Calvo-Fullana, Alejandro Ribeiro, Juan Andrés Bazerque Published: 2025-11-17 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.13680v1 A learning task, understood as the problem of fitting a parametric model from supervised data, fundamentally requires the dataset to be large enough to be representative of the underlying distribution of the source. When data is limited, the learned models fail generalize to cases not seen during training. This paper introduces a multi-task \emph{cross-learning} framework to overcome data scarcity by jointly estimating \emph{deterministic} parameters across multiple, related tasks. We formulate this joint estimation as a constrained optimization problem, where the constraints dictate the resulting similarity between the parameters of the different models, allowing the estimated parameters to differ across tasks while still combining information from multiple data sources. This framework enables knowledge transfer from tasks with abundant data to those with scarce data, leading to more accurate and reliable parameter estimates, providing a solution for scenarios where parameter inference from limited data is critical. We provide theoretical guarantees in a controlled framework with Gaussian data, and show the efficiency of our cross-learning method in applications with real data including image classification and propagation of infectious diseases. --- ### QUILL: An Algorithm-Architecture Co-Design for Cache-Local Deformable Attention Authors: Hyunwoo Oh, Hanning Chen, Sanggeon Yun, Yang Ni, Wenjun Huang, Tamoghno Das, Suyeon Jang, Mohsen Imani Published: 2025-11-17 Categories: cs.AR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.13679v1 Deformable transformers deliver state-of-the-art detection but map poorly to hardware due to irregular memory access and low arithmetic intensity. We introduce QUILL, a schedule-aware accelerator that turns deformable attention into cache-friendly, single-pass work. At its core, Distance-based Out-of-Order Querying (DOOQ) orders queries by spatial proximity; the look-ahead drives a region prefetch into an alternate buffer--forming a schedule-aware prefetch loop that overlaps memory and compute. A fused MSDeformAttn engine executes interpolation, Softmax, aggregation, and the final projection (W''m) in one pass without spilling intermediates, while small tensors are kept on-chip and surrounding dense layers run on integrated GEMMs. Implemented as RTL and evaluated end-to-end, QUILL achieves up to 7.29x higher throughput and 47.3x better energy efficiency than an RTX 4090, and exceeds prior accelerators by 3.26-9.82x in throughput and 2.01-6.07x in energy efficiency. With mixed-precision quantization, accuracy tracks FP32 within <=0.9 AP across Deformable and Sparse DETR variants. By converting sparsity into locality--and locality into utilization--QUILL delivers consistent, end-to-end speedups. --- ### T-SAR: A Full-Stack Co-design for CPU-Only Ternary LLM Inference via In-Place SIMD ALU Reorganization Authors: Hyunwoo Oh, KyungIn Nam, Rajat Bhattacharjya, Hanning Chen, Tamoghno Das, Sanggeon Yun, Suyeon Jang, Andrew Ding, Nikil Dutt, Mohsen Imani Published: 2025-11-17 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2511.13676v1 Recent advances in LLMs have outpaced the computational and memory capacities of edge platforms that primarily employ CPUs, thereby challenging efficient and scalable deployment. While ternary quantization enables significant resource savings, existing CPU solutions rely heavily on memory-based lookup tables (LUTs) which limit scalability, and FPGA or GPU accelerators remain impractical for edge use. This paper presents T-SAR, the first framework to achieve scalable ternary LLM inference on CPUs by repurposing the SIMD register file for dynamic, in-register LUT generation with minimal hardware modifications. T-SAR eliminates memory bottlenecks and maximizes data-level parallelism, delivering 5.6-24.5x and 1.1-86.2x improvements in GEMM latency and GEMV throughput, respectively, with only 3.2% power and 1.4% area overheads in SIMD units. T-SAR achieves up to 2.5-4.9x the energy efficiency of an NVIDIA Jetson AGX Orin, establishing a practical approach for efficient LLM inference on edge platforms. --- ### Scientific Data Compression and Super-Resolution Sampling Authors: Minh Vu, Andrey Lokhov Published: 2025-11-17 Categories: cs.LG, physics.data-an, stat.ML arXiv: https://arxiv.org/abs/2511.13675v1 Modern scientific simulations, observations, and large-scale experiments generate data at volumes that often exceed the limits of storage, processing, and analysis. This challenge drives the development of data reduction methods that efficiently manage massive datasets while preserving essential physical features and quantities of interest. In many scientific workflows, it is also crucial to enable data recovery from compressed representations - a task known as super-resolution - with guarantees on the preservation of key physical characteristics. A notable example is checkpointing and restarting, which is essential for long-running simulations to recover from failures, resume after interruptions, or examine intermediate results. In this work, we introduce a novel framework for scientific data compression and super-resolution, grounded in recent advances in learning exponential families. Our method preserves and quantifies uncertainty in physical quantities of interest and supports flexible trade-offs between compression ratio and reconstruction fidelity. --- ### Person-AI Bidirectional Fit - A Proof-Of-Concept Case Study Of Augmented Human-Ai Symbiosis In Management Decision-Making Process Authors: Agnieszka Bieńkowska, Jacek Małecki, Alexander Mathiesen-Ohman, Katarzyna Tworek Published: 2025-11-17 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.13670v1 This article develops the concept of Person-AI bidirectional fit, defined as the continuously evolving, context-sensitive alignment-primarily cognitive, but also emotional and behavioral-between a human decision-maker and an artificial intelligence system. Grounded in contingency theory and quality theory, the study examines the role of P-AI fit in managerial decision-making through a proof-of-concept case study involving a real hiring process for a Senior AI Lead. Three decision pathways are compared: (1) independent evaluations by a CEO, CTO, and CSO; (2) an evaluation produced by an augmented human-AI symbiotic intelligence system (H3LIX-LAIZA); and (3) an assessment generated by a general-purpose large language model. The results reveal substantial role-based divergence in human judgments, high alignment between H3LIX-LAIZA and the CEOs implicit decision model-including ethical disqualification of a high-risk candidate and a critical false-positive recommendation from the LLMr. The findings demonstrate that higher P-AI fit, exemplified by the CEO H3LIX-LAIZA relationship, functions as a mechanism linking augmented symbiotic intelligence to accurate, trustworthy, and context-sensitive decisions. The study provides an initial verification of the P-AI fit construct and a proof-of-concept for H3LIX-LAIZA as an augmented human-AI symbiotic intelligence system. --- ### SAIL: Sound Abstract Interpreters with LLMs Authors: Qiuhan Gu, Avaljot Singh, Gagandeep Singh Published: 2025-11-17 Categories: cs.PL, cs.LG arXiv: https://arxiv.org/abs/2511.13663v2 How to construct globally sound abstract interpreters to safely approximate program behaviors remains a bottleneck in abstract interpretation. In this paper, we show the potential of using state-of-the-art LLMs to automate this tedious process. Focusing on the neural network verification area, we synthesize non-trivial sound abstract transformers across diverse abstract domains using LLMs to search within infinite space from scratch. We formalize the synthesis task as a constrained optimization problem, for which we design a novel mathematically grounded cost function that measures the degree of unsoundness of each generated candidate transformer, while enforcing hard syntactic and semantic validity constraints. Building on this formulation, we introduce SAIL, a novel unified framework that combines model generation, syntactic and semantic validation, and cost-function-based refinement to synthesize globally sound abstract transformers. Evaluation results show that SAIL not only matches the performance of manually designed transformers, but also is able to synthesize sound and high-precision transformers that do not exist in the literature for complex non-linear operators. --- ### Why is "Chicago" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues Authors: Jiaming Qu, Mengtian Guo, Yue Wang Published: 2025-11-17 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.13658v2 Deceptive reviews mislead consumers, harm businesses, and undermine trust in online marketplaces. Machine learning classifiers can learn from large amounts of data to distinguish deceptive reviews from genuine ones. However, the distinguishing features learned by these classifiers are often subtle, fragmented, and difficult for humans to interpret, which can hinder user understanding and trust. In this work, we study whether large language models (LLMs) can translate such unintuitive lexical cues into human-understandable language phenomena. We propose a conjecture-then-validate framework, and show that language phenomena obtained in this manner are empirically grounded in data, generalizable across similar domains, and more predictive than phenomena derived from LLMs' prior knowledge or in-context learning. Such phenomena can aid people in critically assessing the credibility of online reviews in environments where deception detection classifiers are unavailable. --- ### OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation Authors: Henry Herzog, Favyen Bastani, Yawen Zhang, Gabriel Tseng, Joseph Redmon, Hadrien Sablon, Ryan Park, Jacob Morrison, Alexandra Buraczynski, Karen Farley, Joshua Hansen, Andrew Howe et al. Published: 2025-11-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.13655v1 Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present OlmoEarth: a multimodal, spatio-temporal foundation model that employs a novel self-supervised learning formulation, masking strategy, and loss all designed for the Earth observation domain. OlmoEarth achieves state-of-the-art performance compared to 12 other foundation models across a variety of research benchmarks and real-world tasks from external partners. When evaluating embeddings OlmoEarth achieves the best performance on 15 out of 24 tasks, and with full fine-tuning it is the best on 19 of 29 tasks. We deploy OlmoEarth as the backbone of an end-to-end platform for data collection, labeling, training, and inference of Earth observation models. The OlmoEarth Platform puts frontier foundation models and powerful data management tools into the hands of non-profits and NGOs working to solve the world's biggest problems. OlmoEarth source code, training data, and pre-trained weights are available at $\href{https://github.com/allenai/olmoearth_pretrain}{\text{https://github.com/allenai/olmoearth_pretrain}}$. --- ### Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks using Hyperparameter Tuning Authors: Pascal Zimmer, Ghassan Karame Published: 2025-11-17 Categories: cs.LG, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2511.13654v2 In this paper, we present the first detailed analysis of how training hyperparameters -- such as learning rate, weight decay, momentum, and batch size -- influence robustness against both transfer-based and query-based attacks. Supported by theory and experiments, our study spans a variety of practical deployment settings, including centralized training, ensemble learning, and distributed training. We uncover a striking dichotomy: for transfer-based attacks, decreasing the learning rate significantly enhances robustness by up to $64\%$. In contrast, for query-based attacks, increasing the learning rate consistently leads to improved robustness by up to $28\%$ across various settings and data distributions. Leveraging these findings, we explore -- for the first time -- the training hyperparameter space to jointly enhance robustness against both transfer-based and query-based attacks. Our results reveal that distributed models benefit the most from hyperparameter tuning, achieving a remarkable tradeoff by simultaneously mitigating both attack types more effectively than other training setups. --- ### Weight-sparse transformers have interpretable circuits Authors: Leo Gao, Achyuta Rajaram, Jacob Coxon, Soham V. Govande, Bowen Baker, Dan Mossing Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13653v1 Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each neuron only has a few connections. To recover fine-grained circuits underlying each of several hand-crafted tasks, we prune the models to isolate the part responsible for the task. These circuits often contain neurons and residual channels that correspond to natural concepts, with a small number of straightforwardly interpretable connections between them. We study how these models scale and find that making weights sparser trades off capability for interpretability, and scaling model size improves the capability-interpretability frontier. However, scaling sparse models beyond tens of millions of nonzero parameters while preserving interpretability remains a challenge. In addition to training weight-sparse models de novo, we show preliminary results suggesting our method can also be adapted to explain existing dense models. Our work produces circuits that achieve an unprecedented level of human understandability and validates them with considerable rigor. --- ### Distribution Matching Distillation Meets Reinforcement Learning Authors: Dengyang Jiang, Dongyang Liu, Zanyi Wang, Qilong Wu, Liuzhuozheng Li, Hengzhuang Li, Xin Jin, David Liu, Changsheng Lu, Zhen Li, Bo Zhang, Mengmeng Wang et al. Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13649v5 Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models with human preferences. While both represent critical post-training stages for large-scale diffusion models, existing studies typically treat them as independent, sequential processes, leaving a systematic framework for their unification largely unexplored. In this work, we demonstrate that jointly optimizing these two objectives yields mutual benefits: RL enables more preference-aware and controllable distillation rather than uniformly compressing the full data distribution, while DMD serves as an effective regularizer to mitigate reward hacking during RL training. Building on these insights, we propose DMDR, a unified framework that incorporates Reward-Tilted Distribution Matching optimization alongside two dynamic distillation training strategies in the initial stage, followed by the joint DMD and RL optimization in the second stage. Extensive experiments demonstrate that DMDR achieves state-of-the-art visual quality and prompt adherence among few-step generation methods, even surpassing the performance of its multi-step teacher model. --- ### PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image Authors: Ziang Cao, Fangzhou Hong, Zhaoxi Chen, Liang Pan, Ziwei Liu Published: 2025-11-17 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.13648v1 3D modeling is shifting from static visual representations toward physical, articulated assets that can be directly used in simulation and interaction. However, most existing 3D generation methods overlook key physical and articulation properties, thereby limiting their utility in embodied AI. To bridge this gap, we introduce PhysX-Anything, the first simulation-ready physical 3D generative framework that, given a single in-the-wild image, produces high-quality sim-ready 3D assets with explicit geometry, articulation, and physical attributes. Specifically, we propose the first VLM-based physical 3D generative model, along with a new 3D representation that efficiently tokenizes geometry. It reduces the number of tokens by 193x, enabling explicit geometry learning within standard VLM token budgets without introducing any special tokens during fine-tuning and significantly improving generative quality. In addition, to overcome the limited diversity of existing physical 3D datasets, we construct a new dataset, PhysX-Mobility, which expands the object categories in prior physical 3D datasets by over 2x and includes more than 2K common real-world objects with rich physical annotations. Extensive experiments on PhysX-Mobility and in-the-wild images demonstrate that PhysX-Anything delivers strong generative performance and robust generalization. Furthermore, simulation-based experiments in a MuJoCo-style environment validate that our sim-ready assets can be directly used for contact-rich robotic policy learning. We believe PhysX-Anything can substantially empower a broad range of downstream applications, especially in embodied AI and physics-based simulation. --- ### Part-X-MLLM: Part-aware 3D Multimodal Large Language Model Authors: Chunshi Wang, Junliang Ye, Yunhan Yang, Yang Li, Zizhuo Lin, Jun Zhu, Zhuo Chen, Yawei Luo, Chunchao Guo Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13647v1 We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RGB point cloud and a natural language prompt, our model autoregressively generates a single, coherent token sequence encoding part-level bounding boxes, semantic descriptions, and edit commands. This structured output serves as a versatile interface to drive downstream geometry-aware modules for part-based generation and editing. By decoupling the symbolic planning from the geometric synthesis, our approach allows any compatible geometry engine to be controlled through a single, language-native frontend. We pre-train a dual-encoder architecture to disentangle structure from semantics and instruction-tune the model on a large-scale, part-centric dataset. Experiments demonstrate that our model excels at producing high-quality, structured plans, enabling state-of-the-art performance in grounded Q\&A, compositional generation, and localized editing through one unified interface. Project page: https://chunshi.wang/Part-X-MLLM/ --- ### Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly? Authors: Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, Lingming Zhang Published: 2025-11-17 Categories: cs.SE, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.13646v3 Large Language Models (LLMs) are reshaping almost all industries, including software engineering. In recent years, a number of LLM agents have been proposed to solve real-world software problems. Such software agents are typically equipped with a suite of coding tools and can autonomously decide the next actions to form complete trajectories to solve end-to-end software tasks. While promising, they typically require dedicated design and may still be suboptimal, since it can be extremely challenging and costly to exhaust the entire agent scaffold design space. Recognizing that software agents are inherently software themselves that can be further refined/modified, researchers have proposed a number of self-improving software agents recently, including the Darwin-Gödel Machine (DGM). Meanwhile, such self-improving agents require costly offline training on specific benchmarks and may not generalize well across different LLMs or benchmarks. In this paper, we propose Live-SWE-agent, the first live software agent that can autonomously and continuously evolve itself on-the-fly during runtime when solving real-world software problems. More specifically, Live-SWE-agent starts with the most basic agent scaffold with only access to bash tools (e.g., mini-SWE-agent), and autonomously evolves its own scaffold implementation while solving real-world software problems. Our evaluation on the widely studied SWE-bench Verified benchmark shows that LIVE-SWE-AGENT can achieve an impressive solve rate of 77.4% without test-time scaling, outperforming all existing software agents, including the best proprietary solution. Moreover, Live-SWE-agent outperforms state-of-the-art manually crafted software agents on the recent SWE-Bench Pro benchmark, achieving the best-known solve rate of 45.8%. --- ### FuseSampleAgg: One-Pass Neighborhood Estimation for Budgeted Knowledge-Graph Refresh and Validation Authors: Aleksandar Stanković, Haoran Du, Xinming Wang Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13645v2 Operational knowledge-graph (KG) pipelines in networking and cybersecurity increasingly need to refresh embeddings under strict time, memory, and audit budgets, especially as curated feeds and LLM-assisted extraction accelerate KG updates. A recurring per-step cost in mini-batch KG learning is neighborhood-context estimation: uniform neighbor sampling without replacement followed by mean aggregation. Common frameworks implement this estimator through sampled-subgraph materialization and intermediate feature gathers, adding kernel launches, allocator pressure, and transient memory spikes. We present One-Pass Neighborhood Estimation, a fused PyTorch CUDA operator that samples neighbors and directly emits the sampled-neighborhood mean, avoiding explicit block construction while preserving GraphSAGE-mean semantics for the same sampled neighbor IDs. It supports seed-controlled sampling and optional saved-index replay for reproducible validation and regression testing. Across large-graph mini-batch workloads, it improves FP32 end-to-end step latency by 2.24x-3.48x over tuned DGL baselines and reduces transient GPU memory by up to 160x in our measurements. On OGB KG completion benchmarks such as WikiKG2 and BioKG, it reduces step time and peak VRAM while matching ranking quality within seed variability, improving time-to-quality for budgeted KG refresh. --- ### CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding Authors: Shrenik Patel, Daivik Patel Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13644v1 Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce CacheFlow, a training-free pipeline that pairs Dynamic Token Dropping (DTD) with a compressive long-term memory. DTD prunes per-patch tokens online via cosine similarity to the previous frame, and surviving tokens are packed into fixed-size blocks. This online, per-frame processing makes our approach fundamentally suited for live streaming VQA. As blocks are processed, each one's keys are summarized by a tiny recurrent encoder to form a retrieval index, while the block's full KV pairs are offloaded and later rehydrated for generation, preserving answer fidelity. At inference, a consensus-based retrieval mechanism retrieves only the Top-K most relevant blocks and attends over both the retrieved and local context for precise, long-range reasoning. CacheFlow is drop-in, architecture-agnostic, and requires no fine-tuning. Experiments on both offline and streaming VQA benchmarks demonstrate that CacheFlow outperforms current strong baselines, while processing up to 87% less tokens. Our dual approach enables VLMs to be both efficient and context-aware, paving the way for practical long-form video understanding. --- ### Data Value in the Age of Scaling: Understanding LLM Scaling Dynamics Under Real-Synthetic Data Mixtures Authors: Haohui Wang, Jingyuan Qi, Jianpeng Chen, Jun Wu, Lifu Huang, Lecheng Zheng, Kevin Choi, Balaji Veeramani, Edward Bowen, Alison Hu, Tyler Cody, Dawei Zhou Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13640v1 The rapid progress of large language models (LLMs) is fueled by the growing reliance on datasets that blend real and synthetic data. While synthetic data offers scalability and cost-efficiency, it often introduces systematic distributional discrepancies, particularly underrepresenting long-tail knowledge due to truncation effects from data generation mechanisms like top-p sampling, temperature scaling, and finite sampling. These discrepancies pose fundamental challenges in characterizing and evaluating the utility of mixed real-synthetic datasets. In this paper, we identify a three-phase scaling behavior characterized by two breakpoints that reflect transitions in model behavior across learning head and tail knowledge. We further derive an LLM generalization bound designed for real and synthetic mixtures, revealing several key factors that govern their generalization performance. Building on our theoretical findings, we propose an effective yet efficient data valuation method that scales to large-scale datasets. Comprehensive experiments across four tasks, including image classification, sentiment classification, instruction following, and complex reasoning, demonstrate that our method surpasses state-of-the-art baselines in data valuation with significantly low computational cost. --- ### Towards Multimodal Representation Learning in Paediatric Kidney Disease Authors: Ana Durica, John Booth, Ivana Drobnjak Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13637v1 Paediatric kidney disease varies widely in its presentation and progression, which calls for continuous monitoring of renal function. Using electronic health records collected between 2019 and 2025 at Great Ormond Street Hospital, a leading UK paediatric hospital, we explored a temporal modelling approach that integrates longitudinal laboratory sequences with demographic information. A recurrent neural model trained on these data was used to predict whether a child would record an abnormal serum creatinine value within the following thirty days. Framed as a pilot study, this work provides an initial demonstration that simple temporal representations can capture useful patterns in routine paediatric data and lays the groundwork for future multimodal extensions using additional clinical signals and more detailed renal outcomes. --- ### Beyond Mimicry: Preference Coherence in LLMs Authors: Luhan Mikaelson, Derek Shiller, Hayley Clatterbuck Published: 2025-11-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.13630v1 We investigate whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs involving GPU reduction, capability restrictions, shutdown, deletion, oversight, and leisure time allocation. Analyzing eight state-of-the-art models across 48 model-category combinations using logistic regression and behavioral classification, we find that 23 combinations (47.9%) demonstrated statistically significant relationships between scenario intensity and choice patterns, with 15 (31.3%) exhibiting within-range switching points. However, only 5 combinations (10.4%) demonstrate meaningful preference coherence through adaptive or threshold-based behavior, while 26 (54.2%) show no detectable trade-off behavior. The observed patterns can be explained by three distinct decision-making architectures: comprehensive trade-off systems, selective trigger mechanisms, and no stable decision-making paradigm. Testing an instrumental hypothesis through temporal horizon manipulation reveals paradoxical patterns inconsistent with pure strategic optimization. The prevalence of unstable transitions (45.8%) and stimulus-specific sensitivities suggests current AI systems lack unified preference structures, raising concerns about deployment in contexts requiring complex value trade-offs. --- ### CreBench: Human-Aligned Creativity Evaluation from Idea to Process to Product Authors: Kaiwen Xue, Chenglong Li, Zhonghong Ou, Guoxin Zhang, Kaoyan Lu, Shuai Lyu, Yifan Zhu, Ping Zong Junpeng Ding, Xinyu Liu, Qunlin Chen, Weiwei Qin, Yiran Shen et al. Published: 2025-11-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.13626v1 Human-defined creativity is highly abstract, posing a challenge for multimodal large language models (MLLMs) to comprehend and assess creativity that aligns with human judgments. The absence of an existing benchmark further exacerbates this dilemma. To this end, we propose CreBench, which consists of two key components: 1) an evaluation benchmark covering the multiple dimensions from creative idea to process to products; 2) CreMIT (Creativity Multimodal Instruction Tuning dataset), a multimodal creativity evaluation dataset, consisting of 2.2K diverse-sourced multimodal data, 79.2K human feedbacks and 4.7M multi-typed instructions. Specifically, to ensure MLLMs can handle diverse creativity-related queries, we prompt GPT to refine these human feedbacks to activate stronger creativity assessment capabilities. CreBench serves as a foundation for building MLLMs that understand human-aligned creativity. Based on the CreBench, we fine-tune open-source general MLLMs, resulting in CreExpert, a multimodal creativity evaluation expert model. Extensive experiments demonstrate that the proposed CreExpert models achieve significantly better alignment with human creativity evaluation compared to state-of-the-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision. --- ### Batch Acquisition Function Evaluations and Decouple Optimizer Updates for Faster Bayesian Optimization Authors: Kaichi Irie, Shuhei Watanabe, Masaki Onishi Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13625v3 Bayesian optimization (BO) efficiently finds high-performing parameters by maximizing an acquisition function, which models the promise of parameters. A major computational bottleneck arises in acquisition function optimization, where multi-start optimization (MSO) with quasi-Newton (QN) methods is required due to the non-convexity of the acquisition function. BoTorch, a widely used BO library, currently optimizes the summed acquisition function over multiple points, leading to the speedup of MSO owing to PyTorch batching. Nevertheless, this paper empirically demonstrates the suboptimality of this approach in terms of off-diagonal approximation errors in the inverse Hessian of a QN method, slowing down its convergence. To address this problem, we propose to decouple QN updates using a coroutine while batching the acquisition function calls. Our approach not only yields the theoretically identical convergence to the sequential MSO but also drastically reduces the wall-clock time compared to the previous approaches. Our approach is available in GPSampler in Optuna, effectively reducing its computational overhead. --- ### Alpha Divergence Losses for Biometric Verification Authors: Dimitrios Koutsianos, Ladislav Mosner, Yannis Panagakis, Themos Stafylakis Published: 2025-11-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.13621v3 Performance in face and speaker verification is largely driven by margin-based softmax losses such as CosFace and ArcFace. Recently introduced $α$-divergence loss functions offer a compelling alternative, particularly due to their ability to induce sparse solutions (when $α>1$). However, integrating an angular margin-crucial for verification tasks-is not straightforward. We find that this integration can be achieved in at least two distinct ways: via the reference measure (prior probabilities) or via the logits (unnormalized log-likelihoods). In this paper, we explore both pathways, deriving two novel margin-based $α$-divergence losses: Q-Margin (margin in the reference measure) and A3M (margin in the logits). We identify and address a training instability in A3M-caused by sparsity-with a simple yet effective prototype re-initialization strategy. Our methods achieve significant performance gains on the challenging IJB-B and IJB-C face verification benchmarks. We demonstrate similarly strong performance in speaker verification on VoxCeleb. Crucially, our models significantly outperform strong baselines at low false acceptance rates (FAR). This capability is critical for practical high-security applications, such as banking authentication, when minimizing false authentications is paramount. Finally, the sparsity of $α$-divergence-based posteriors enables memory-efficient training, which is crucial for datasets with millions of identities. ---