# Research Papers — 2025-11 · bundle page 165 of 197 > Full-text markdown of papers #8201–8250 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/165 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/164.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/166.md) ### Simplex-FEM Networks (SiFEN): Learning A Triangulated Function Approximator Authors: Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui, Ibrahim Ouahbi, Yassine Maleh Published: 2025-11-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.04804v2 We introduce Simplex-FEM Networks (SiFEN), a learned piecewise-polynomial predictor that represents f: R^d -> R^k as a globally C^r finite-element field on a learned simplicial mesh in an optionally warped input space. Each query activates exactly one simplex and at most d+1 basis functions via barycentric coordinates, yielding explicit locality, controllable smoothness, and cache-friendly sparsity. SiFEN pairs degree-m Bernstein-Bezier polynomials with a light invertible warp and trains end-to-end with shape regularization, semi-discrete OT coverage, and differentiable edge flips. Under standard shape-regularity and bi-Lipschitz warp assumptions, SiFEN achieves the classic FEM approximation rate M^(-m/d) with M mesh vertices. Empirically, on synthetic approximation tasks, tabular regression/classification, and as a drop-in head on compact CNNs, SiFEN matches or surpasses MLPs and KANs at matched parameter budgets, improves calibration (lower ECE/Brier), and reduces inference latency due to geometric locality. These properties make SiFEN a compact, interpretable, and theoretically grounded alternative to dense MLPs and edge-spline networks. --- ### Data Efficiency and Transfer Robustness in Biomedical Image Segmentation: A Study of Redundancy and Forgetting with Cellpose Authors: Shuo Zhao, Jianxu Chen Published: 2025-11-06 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.04803v1 Generalist biomedical image segmentation models such as Cellpose are increasingly applied across diverse imaging modalities and cell types. However, two critical challenges remain underexplored: (1) the extent of training data redundancy and (2) the impact of cross domain transfer on model retention. In this study, we conduct a systematic empirical analysis of these challenges using Cellpose as a case study. First, to assess data redundancy, we propose a simple dataset quantization (DQ) strategy for constructing compact yet diverse training subsets. Experiments on the Cyto dataset show that image segmentation performance saturates with only 10% of the data, revealing substantial redundancy and potential for training with minimal annotations. Latent space analysis using MAE embeddings and t-SNE confirms that DQ selected patches capture greater feature diversity than random sampling. Second, to examine catastrophic forgetting, we perform cross domain finetuning experiments and observe significant degradation in source domain performance, particularly when adapting from generalist to specialist domains. We demonstrate that selective DQ based replay reintroducing just 5-10% of the source data effectively restores source performance, while full replay can hinder target adaptation. Additionally, we find that training domain sequencing improves generalization and reduces forgetting in multi stage transfer. Our findings highlight the importance of data centric design in biomedical image segmentation and suggest that efficient training requires not only compact subsets but also retention aware learning strategies and informed domain ordering. The code is available at https://github.com/MMV-Lab/biomedseg-efficiency. --- ### Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models Authors: Chenxi Liu, Junjie Liang, Yuqi Jia, Bochuan Cao, Yang Bai, Heng Huang, Xun Chen Published: 2025-11-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.04800v1 Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative Policy Optimization (GRPO) family has demonstrated strong performance in training LLMs with RLVR. However, as models train longer and scale larger, more training prompts become residual prompts, those with zero variance rewards that provide no training signal. Consequently, fewer prompts contribute to training, reducing diversity and hindering effectiveness. To fully exploit these residual prompts, we propose the Explore Residual Prompts in Policy Optimization (ERPO) framework, which encourages exploration on residual prompts and reactivates their training signals. ERPO maintains a history tracker for each prompt and adaptively increases the sampling temperature for residual prompts that previously produced all correct responses. This encourages the model to generate more diverse reasoning traces, introducing incorrect responses that revive training signals. Empirical results on the Qwen2.5 series demonstrate that ERPO consistently surpasses strong baselines across multiple mathematical reasoning benchmarks. --- ### MDM: Manhattan Distance Mapping of DNN Weights for Parasitic-Resistance-Resilient Memristive Crossbars Authors: Matheus Farias, Wanghley Martins, H. T. Kung Published: 2025-11-06 Categories: cs.AR, cs.AI, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2511.04798v1 Manhattan Distance Mapping (MDM) is a post-training deep neural network (DNN) weight mapping technique for memristive bit-sliced compute-in-memory (CIM) crossbars that reduces parasitic resistance (PR) nonidealities. PR limits crossbar efficiency by mapping DNN matrices into small crossbar tiles, reducing CIM-based speedup. Each crossbar executes one tile, requiring digital synchronization before the next layer. At this granularity, designers either deploy many small crossbars in parallel or reuse a few sequentially-both increasing analog-to-digital conversions, latency, I/O pressure, and chip area. MDM alleviates PR effects by optimizing active-memristor placement. Exploiting bit-level structured sparsity, it feeds activations from the denser low-order side and reorders rows according to the Manhattan distance, relocating active cells toward regions less affected by PR and thus lowering the nonideality factor (NF). Applied to DNN models on ImageNet-1k, MDM reduces NF by up to 46% and improves accuracy under analog distortion by an average of 3.6% in ResNets. Overall, it provides a lightweight, spatially informed method for scaling CIM DNN accelerators. --- ### 3D Gaussian Point Encoders Authors: Jim James, Ben Wilson, Simon Lucey, James Hays Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04797v1 In this work, we introduce the 3D Gaussian Point Encoder, an explicit per-point embedding built on mixtures of learned 3D Gaussians. This explicit geometric representation for 3D recognition tasks is a departure from widely used implicit representations such as PointNet. However, it is difficult to learn 3D Gaussian encoders in end-to-end fashion with standard optimizers. We develop optimization techniques based on natural gradients and distillation from PointNets to find a Gaussian Basis that can reconstruct PointNet activations. The resulting 3D Gaussian Point Encoders are faster and more parameter efficient than traditional PointNets. As in the 3D reconstruction literature where there has been considerable interest in the move from implicit (e.g., NeRF) to explicit (e.g., Gaussian Splatting) representations, we can take advantage of computational geometry heuristics to accelerate 3D Gaussian Point Encoders further. We extend filtering techniques from 3D Gaussian Splatting to construct encoders that run 2.7 times faster as a comparable accuracy PointNet while using 46% less memory and 88% fewer FLOPs. Furthermore, we demonstrate the effectiveness of 3D Gaussian Point Encoders as a component in Mamba3D, running 1.27 times faster and achieving a reduction in memory and FLOPs by 42% and 54% respectively. 3D Gaussian Point Encoders are lightweight enough to achieve high framerates on CPU-only devices. --- ### Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Models Authors: Gabriel Missael Barco, Ronan Legin, Connor Stone, Yashar Hezaveh, Laurence Perreault-Levasseur Published: 2025-11-06 Categories: astro-ph.IM, astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2511.04792v1 Score-based models can serve as expressive, data-driven priors for scientific inverse problems. In strong gravitational lensing, they enable posterior inference of a background galaxy from its distorted, multiply-imaged observation. Previous work, however, assumes that the lens mass distribution (and thus the forward operator) is known. We relax this assumption by jointly inferring the source and a parametric lens-mass profile, using a sampler based on GibbsDDRM but operating in continuous time. The resulting reconstructions yield residuals consistent with the observational noise, and the marginal posteriors of the lens parameters recover true values without systematic bias. To our knowledge, this is the first successful demonstration of joint source-and-lens inference with a score-based prior. --- ### DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Authors: Lei Gao, Chaoyi Jiang, Hossein Entezari Zarch, Daniel Wong, Mark Hill, Murali Annavaram Published: 2025-11-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.04791v2 Modern LLM serving systems must sustain high throughput while meeting strict latency SLOs across two distinct inference phases: compute-intensive prefill and memory-bound decode phases. Existing approaches either (1) aggregate both phases on shared GPUs, leading to interference between prefill and decode phases, which degrades Time-Between-Tokens (TBT); or (2) disaggregate the two phases across GPUs, improving latency but wasting resources through duplicated models and KV cache transfers. We present DuetServe, a unified LLM serving framework that achieves disaggregation-level isolation within a single GPU. DuetServe operates in aggregated mode by default and dynamically activates SM-level GPU spatial multiplexing when TBT degradation is predicted. Its key idea is to decouple prefill and decode execution only when needed through fine-grained, adaptive SM partitioning that provides phase isolation only when contention threatens latency service level objectives. DuetServe integrates (1) an attention-aware roofline model to forecast iteration latency, (2) a partitioning optimizer that selects the optimal SM split to maximize throughput under TBT constraints, and (3) an interruption-free execution engine that eliminates CPU-GPU synchronization overhead. Evaluations show that DuetServe improves total throughput by up to 1.3x while maintaining low generation latency compared to state-of-the-art frameworks. --- ### Causal Structure and Representation Learning with Biomedical Applications Authors: Caroline Uhler, Jiaqi Zhang Published: 2025-11-06 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2511.04790v1 Massive data collection holds the promise of a better understanding of complex phenomena and, ultimately, better decisions. Representation learning has become a key driver of deep learning applications, as it allows learning latent spaces that capture important properties of the data without requiring any supervised annotations. Although representation learning has been hugely successful in predictive tasks, it can fail miserably in causal tasks including predicting the effect of a perturbation/intervention. This calls for a marriage between representation learning and causal inference. An exciting opportunity in this regard stems from the growing availability of multi-modal data (observational and perturbational, imaging-based and sequencing-based, at the single-cell level, tissue-level, and organism-level). We outline a statistical and computational framework for causal structure and representation learning motivated by fundamental biomedical questions: how to effectively use observational and perturbational data to perform causal discovery on observed causal variables; how to use multi-modal views of the system to learn causal variables; and how to design optimal perturbations. --- ### Conditional Neural ODE for Longitudinal Parkinson's Disease Progression Forecasting Authors: Xiaoda Wang, Yuji Zhao, Kaiqiao Han, Xiao Luo, Sanne van Rooij, Jennifer Stevens, Lifang He, Liang Zhan, Yizhou Sun, Wei Wang, Carl Yang Published: 2025-11-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.04789v1 Parkinson's disease (PD) shows heterogeneous, evolving brain-morphometry patterns. Modeling these longitudinal trajectories enables mechanistic insight, treatment development, and individualized 'digital-twin' forecasting. However, existing methods usually adopt recurrent neural networks and transformer architectures, which rely on discrete, regularly sampled data while struggling to handle irregular and sparse magnetic resonance imaging (MRI) in PD cohorts. Moreover, these methods have difficulty capturing individual heterogeneity including variations in disease onset, progression rate, and symptom severity, which is a hallmark of PD. To address these challenges, we propose CNODE (Conditional Neural ODE), a novel framework for continuous, individualized PD progression forecasting. The core of CNODE is to model morphological brain changes as continuous temporal processes using a neural ODE model. In addition, we jointly learn patient-specific initial time and progress speed to align individual trajectories into a shared progression trajectory. We validate CNODE on the Parkinson's Progression Markers Initiative (PPMI) dataset. Experimental results show that our method outperforms state-of-the-art baselines in forecasting longitudinal PD progression. --- ### EETnet: a CNN for Gaze Detection and Tracking for Smart-Eyewear Authors: Andrea Aspesi, Andrea Simpsi, Aaron Tognoli, Simone Mentasti, Luca Merigo, Matteo Matteucci Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04779v1 Event-based cameras are becoming a popular solution for efficient, low-power eye tracking. Due to the sparse and asynchronous nature of event data, they require less processing power and offer latencies in the microsecond range. However, many existing solutions are limited to validation on powerful GPUs, with no deployment on real embedded devices. In this paper, we present EETnet, a convolutional neural network designed for eye tracking using purely event-based data, capable of running on microcontrollers with limited resources. Additionally, we outline a methodology to train, evaluate, and quantize the network using a public dataset. Finally, we propose two versions of the architecture: a classification model that detects the pupil on a grid superimposed on the original image, and a regression model that operates at the pixel level. --- ### Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid Authors: Zahida Kausar, Seemab Latif, Raja Khurram Shahzad, Mehwish Fatima Published: 2025-11-06 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2511.04776v3 Generative Artificial Intelligence (GenAI) represents a rapidly expanding digital infrastructure whose energy demand and associated CO2 emissions are emerging as a new category of climate risk. This study introduces G-TRACE (GenAI Transformative Carbon Estimator), a cross-modal, region-aware framework that quantifies training- and inference-related emissions across modalities and deployment geographies. Using real-world analytics and microscopic simulation, G-TRACE measures energy use and carbon intensity per output type (text, image, video) and reveals how decentralized inference amplifies small per-query energy costs into system-level impacts. Through the Ghibli-style image generation trend (2024-2025), we estimate 4,309 MWh of energy consumption and 2,068 tCO2 emissions, illustrating how viral participation inflates individual digital actions into tonne-scale consequences. Building on these findings, we propose the AI Sustainability Pyramid, a seven-level governance model linking carbon accounting metrics (L1-L7) with operational readiness, optimization, and stewardship. This framework translates quantitative emission metrics into actionable policy guidance for sustainable AI deployment. The study contributes to the quantitative assessment of emerging digital infrastructures as a novel category of climate risk, supporting adaptive governance for sustainable technology deployment. By situating GenAI within climate-risk frameworks, the work advances data-driven methods for aligning technological innovation with global decarbonization and resilience objectives. --- ### SLOFetch: Compressed-Hierarchical Instruction Prefetching for Cloud Microservices Authors: Zerui Bao, Di Zhu, Liu Jiang, Shiqi Sheng, Ziwei Wang, Haoyun Zhang Published: 2025-11-06 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2511.04774v3 Large-scale networked services rely on deep soft-ware stacks and microservice orchestration, which increase instruction footprints and create frontend stalls that inflate tail latency and energy. We revisit instruction prefetching for these cloud workloads and present a design that aligns with SLO driven and self optimizing systems. Building on the Entangling Instruction Prefetcher (EIP), we introduce a Compressed Entry that captures up to eight destinations around a base using 36 bits by exploiting spatial clustering, and a Hierarchical Metadata Storage scheme that keeps only L1 resident and frequently queried entries on chip while virtualizing bulk metadata into lower levels. We further add a lightweight Online ML Controller that scores prefetch profitability using context features and a bandit adjusted threshold. On data center applications, our approach preserves EIP like speedups with smaller on chip state and improves efficiency for networked services in the ML era. --- ### Global 3D Reconstruction of Clouds & Tropical Cyclones Authors: Shirin Ermis, Cesar Aybar, Lilli Freischem, Stella Girtsou, Kyriaki-Margarita Bintsi, Emiliano Diaz Salas-Porras, Michael Eisinger, William Jones, Anna Jungbluth, Benoit Tremblay Published: 2025-11-06 Categories: cs.CV, physics.ao-ph arXiv: https://arxiv.org/abs/2511.04773v3 Accurate forecasting of tropical cyclones (TCs) remains challenging due to limited satellite observations probing TC structure and difficulties in resolving cloud properties involved in TC intensification. Recent research has demonstrated the capabilities of machine learning methods for 3D cloud reconstruction from satellite observations. However, existing approaches have been restricted to regions where TCs are uncommon, and are poorly validated for intense storms. We introduce a new framework, based on a pre-training--fine-tuning pipeline, that learns from multiple satellites with global coverage to translate 2D satellite imagery into 3D cloud maps of relevant cloud properties. We apply our model to a custom-built TC dataset to evaluate performance in the most challenging and relevant conditions. We show that we can - for the first time - create global instantaneous 3D cloud maps and accurately reconstruct the 3D structure of intense storms. Our model not only extends available satellite observations but also provides estimates when observations are missing entirely. This is crucial for advancing our understanding of TC intensification and improving forecasts. --- ### Machine Learning-Driven Analysis of kSZ Maps to Predict CMB Optical Depth $τ$ Authors: Farshid Farhadi Khouzani, Abinash Kumar Shaw, Paul La Plante, Bryar Mustafa Shareef, Laxmi Gewali Published: 2025-11-06 Categories: astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2511.04770v2 Upcoming measurements of the kinetic Sunyaev-Zel'dovich (kSZ) effect, which results from Cosmic Microwave Background (CMB) photons scattering off moving electrons, offer a powerful probe of the Epoch of Reionization (EoR). The kSZ signal contains key information about the timing, duration, and spatial structure of the EoR. A precise measurement of the CMB optical depth $τ$, a key parameter that characterizes the universe's integrated electron density, would significantly constrain models of early structure formation. However, the weak kSZ signal is difficult to extract from CMB observations due to significant contamination from astrophysical foregrounds. We present a machine learning approach to extract $τ$ from simulated kSZ maps. We train advanced machine learning models, including swin transformers, on high-resolution seminumeric simulations of the kSZ signal. To robustly quantify prediction uncertainties of $τ$, we employ the Laplace Approximation (LA). This approach provides an efficient and principled Gaussian approximation to the posterior distribution over the model's weights, allowing for reliable error estimation. We investigate and compare two distinct application modes: a post-hoc LA applied to a pre-trained model, and an online LA where model weights and hyperparameters are optimized jointly by maximizing the marginal likelihood. This approach provides a framework for robustly constraining $τ$ and its associated uncertainty, which can enhance the analysis of upcoming CMB surveys like the Simons Observatory and CMB-S4. --- ### FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow Authors: Rubens Lacouture, Nathan Zhang, Ritvik Sharma, Marco Siracusa, Fredrik Kjolstad, Kunle Olukotun, Olivia Hsu Published: 2025-11-06 Categories: cs.LG, cs.AR, cs.PL arXiv: https://arxiv.org/abs/2511.04768v2 As deep learning models scale, sparse computation and specialized dataflow hardware have emerged as powerful solutions to address efficiency. We propose FuseFlow, a compiler that converts sparse machine learning models written in PyTorch to fused sparse dataflow graphs for reconfigurable dataflow architectures (RDAs). FuseFlow is the first compiler to support general cross-expression fusion of sparse operations. In addition to fusion across kernels (expressions), FuseFlow also supports optimizations like parallelization, dataflow ordering, and sparsity blocking. It targets a cycle-accurate dataflow simulator for microarchitectural analysis of fusion strategies. We use FuseFlow for design-space exploration across four real-world machine learning applications with sparsity, showing that full fusion (entire cross-expression fusion across all computation in an end-to-end model) is not always optimal for sparse models-fusion granularity depends on the model itself. FuseFlow also provides a heuristic to identify and prune suboptimal configurations. Using Fuseflow, we achieve performance improvements, including a ~2.7x speedup over an unfused baseline for GPT-3 with BigBird block-sparse attention. --- ### DARN: Dynamic Adaptive Regularization Networks for Efficient and Robust Foundation Model Adaptation Authors: Dhenenjay Yadav, Rohan Sawai Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04766v1 Foundation models (FMs) offer powerful representations for geospatial analysis, but adapting them effectively remains challenging. Standard adaptation methods, whether full fine-tuning or efficient frozen-backbone approaches, typically employ decoders with fixed regularization strategies, failing to account for the significant heterogeneity in satellite imagery. We introduce Dynamic Adaptive Regularization Networks (DARN), a novel decoder architecture designed to address this limitation. DARN integrates three key innovations: (1) a lightweight Task Complexity Predictor (TCP) that estimates per-sample difficulty, (2) Adaptive Dropout Modulation (ADM), dynamically adjusting dropout rates (from 0.1 to 0.5) based on predicted complexity, and (3) Dynamic Capacity Gating (DCG) that modulates channel activation. We provide theoretical justifications linking DARN's optimization to stationary point convergence and its mechanism to adaptive information bottlenecks. Empirically, DARN demonstrates exceptional performance across both major adaptation paradigms. In full fine-tuning (unfrozen backbone), DARN achieves a new state-of-the-art on the multi-task GeoBench benchmark (86.66% mIoU, +5.56 pp over prior SOTA). In efficient adaptation (frozen backbone), DARN achieves SOTA-competitive accuracy (90.5% mIoU on Sen1Floods11) while delivering substantial advantages crucial for real-world deployment: superior out-of-distribution (OOD) generalization (+9.5 pp mIoU on AI4SmallFarms), enhanced robustness (17% relative reduction in corruption error), and improved performance on minority classes. DARN offers a more intelligent, robust, and efficient approach to leveraging FMs in critical geospatial applications. --- ### When Data Falls Short: Grokking Below the Critical Threshold Authors: Vaibhav Singh, Eugene Belilovsky, Rahaf Aljundi Published: 2025-11-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.04760v1 In this paper, we investigate the phenomenon of grokking, where models exhibit delayed generalization following overfitting on training data. We focus on data-scarce regimes where the number of training samples falls below the critical threshold, making grokking unobservable, and on practical scenarios involving distribution shift. We first show that Knowledge Distillation (KD) from a model that has already grokked on a distribution (p1) can induce and accelerate grokking on a different distribution (p2), even when the available data lies below the critical threshold. This highlights the value of KD for deployed models that must adapt to new distributions under limited data. We then study training on the joint distribution (p1, p2) and demonstrate that while standard supervised training fails when either distribution has insufficient data, distilling from models grokked on the individual distributions enables generalization. Finally, we examine a continual pretraining setup, where a grokked model transitions from p1 to p2, and find that KD both accelerates generalization and mitigates catastrophic forgetting, achieving strong performance even with only 10% of the data. Together, our results provide new insights into the mechanics of grokking under knowledge transfer and underscore the central role of KD in enabling generalization in low-data and evolving distribution settings. --- ### ScheduleStream: Temporal Planning with Samplers for GPU-Accelerated Multi-Arm Task and Motion Planning & Scheduling Authors: Caelan Garrett, Fabio Ramos Published: 2025-11-06 Categories: cs.RO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.04758v2 Bimanual and humanoid robots are appealing because of their human-like ability to leverage multiple arms to efficiently complete tasks. However, controlling multiple arms at once is computationally challenging due to the growth in the hybrid discrete-continuous action space. Task and Motion Planning (TAMP) algorithms can efficiently plan in hybrid spaces but generally produce plans, where only one arm is moving at a time, rather than schedules that allow for parallel arm motion. In order to extend TAMP to produce schedules, we present ScheduleStream, the first general-purpose framework for planning & scheduling with sampling operations. ScheduleStream models temporal dynamics using hybrid durative actions, which can be started asynchronously and persist for a duration that's a function of their parameters. We propose domain-independent algorithms that solve ScheduleStream problems without any application-specific mechanisms. We apply ScheduleStream to Task and Motion Planning & Scheduling (TAMPAS), where we use GPU acceleration within samplers to expedite planning. We compare ScheduleStream algorithms to several ablations in simulation and find that they produce more efficient solutions. We demonstrate ScheduleStream on several real-world bimanual robot tasks at https://schedulestream.github.io. --- ### Surprisal reveals diversity gaps in image captioning and different scorers change the story Authors: Nikolai Ilinykh, Simon Dobnik Published: 2025-11-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.04754v1 We quantify linguistic diversity in image captioning with surprisal variance - the spread of token-level negative log-probabilities within a caption set. On the MSCOCO test set, we compare five state-of-the-art vision-and-language LLMs, decoded with greedy and nucleus sampling, to human captions. Measured with a caption-trained n-gram LM, humans display roughly twice the surprisal variance of models, but rescoring the same captions with a general-language model reverses the pattern. Our analysis introduces the surprisal-based diversity metric for image captioning. We show that relying on a single scorer can completely invert conclusions, thus, robust diversity evaluation must report surprisal under several scorers. --- ### CPO: Condition Preference Optimization for Controllable Image Generation Authors: Zonglin Lyu, Ming Li, Xinxin Liu, Chen Chen Published: 2025-11-06 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.04753v1 To enhance controllability in text-to-image generation, ControlNet introduces image-based control signals, while ControlNet++ improves pixel-level cycle consistency between generated images and the input control signal. To avoid the prohibitive cost of back-propagating through the sampling process, ControlNet++ optimizes only low-noise timesteps (e.g., $t < 200$) using a single-step approximation, which not only ignores the contribution of high-noise timesteps but also introduces additional approximation errors. A straightforward alternative for optimizing controllability across all timesteps is Direct Preference Optimization (DPO), a fine-tuning method that increases model preference for more controllable images ($I^{w}$) over less controllable ones ($I^{l}$). However, due to uncertainty in generative models, it is difficult to ensure that win--lose image pairs differ only in controllability while keeping other factors, such as image quality, fixed. To address this, we propose performing preference learning over control conditions rather than generated images. Specifically, we construct winning and losing control signals, $\mathbf{c}^{w}$ and $\mathbf{c}^{l}$, and train the model to prefer $\mathbf{c}^{w}$. This method, which we term \textit{Condition Preference Optimization} (CPO), eliminates confounding factors and yields a low-variance training objective. Our approach theoretically exhibits lower contrastive loss variance than DPO and empirically achieves superior results. Moreover, CPO requires less computation and storage for dataset curation. Extensive experiments show that CPO significantly improves controllability over the state-of-the-art ControlNet++ across multiple control types: over $10\%$ error rate reduction in segmentation, $70$--$80\%$ in human pose, and consistent $2$--$5\%$ reductions in edge and depth maps. --- ### Regularized GLISp for sensor-guided human-in-the-loop optimization Authors: Matteo Cercola, Michele Lomuscio, Dario Piga, Simone Formentin Published: 2025-11-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.04751v1 Human-in-the-loop calibration is often addressed via preference-based optimization, where algorithms learn from pairwise comparisons rather than explicit cost evaluations. While effective, methods such as Preferential Bayesian Optimization or Global optimization based on active preference learning with radial basis functions (GLISp) treat the system as a black box and ignore informative sensor measurements. In this work, we introduce a sensor-guided regularized extension of GLISp that integrates measurable descriptors into the preference-learning loop through a physics-informed hypothesis function and a least-squares regularization term. This injects grey-box structure, combining subjective feedback with quantitative sensor information while preserving the flexibility of preference-based search. Numerical evaluations on an analytical benchmark and on a human-in-the-loop vehicle suspension tuning task show faster convergence and superior final solutions compared to baseline GLISp. --- ### Knowledge-based anomaly detection for identifying network-induced shape artifacts Authors: Rucha Deshpande, Tahsin Rahman, Miguel Lago, Adarsh Subbaswamy, Jana G. Delfino, Ghada Zamzmi, Elim Thompson, Aldo Badano, Seyed Kahaki Published: 2025-11-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.04729v1 Synthetic data provides a promising approach to address data scarcity for training machine learning models; however, adoption without proper quality assessments may introduce artifacts, distortions, and unrealistic features that compromise model performance and clinical utility. This work introduces a novel knowledge-based anomaly detection method for detecting network-induced shape artifacts in synthetic images. The introduced method utilizes a two-stage framework comprising (i) a novel feature extractor that constructs a specialized feature space by analyzing the per-image distribution of angle gradients along anatomical boundaries, and (ii) an isolation forest-based anomaly detector. We demonstrate the effectiveness of the method for identifying network-induced shape artifacts in two synthetic mammography datasets from models trained on CSAW-M and VinDr-Mammo patient datasets respectively. Quantitative evaluation shows that the method successfully concentrates artifacts in the most anomalous partition (1st percentile), with AUC values of 0.97 (CSAW-syn) and 0.91 (VMLO-syn). In addition, a reader study involving three imaging scientists confirmed that images identified by the method as containing network-induced shape artifacts were also flagged by human readers with mean agreement rates of 66% (CSAW-syn) and 68% (VMLO-syn) for the most anomalous partition, approximately 1.5-2 times higher than the least anomalous partition. Kendall-Tau correlations between algorithmic and human rankings were 0.45 and 0.43 for the two datasets, indicating reasonable agreement despite the challenging nature of subtle artifact detection. This method is a step forward in the responsible use of synthetic data, as it allows developers to evaluate synthetic images for known anatomic constraints and pinpoint and address specific issues to improve the overall quality of a synthetic dataset. --- ### Trustworthiness Calibration Framework for Phishing Email Detection Using Large Language Models Authors: Daniyal Ganiuly, Assel Smaiyl Published: 2025-11-06 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.04728v1 Phishing emails continue to pose a persistent challenge to online communication, exploiting human trust and evading automated filters through realistic language and adaptive tactics. While large language models (LLMs) such as GPT-4 and LLaMA-3-8B achieve strong accuracy in text classification, their deployment in security systems requires assessing reliability beyond benchmark performance. To address this, this study introduces the Trustworthiness Calibration Framework (TCF), a reproducible methodology for evaluating phishing detectors across three dimensions: calibration, consistency, and robustness. These components are integrated into a bounded index, the Trustworthiness Calibration Index (TCI), and complemented by the Cross-Dataset Stability (CDS) metric that quantifies stability of trustworthiness across datasets. Experiments conducted on five corpora, such as SecureMail 2025, Phishing Validation 2024, CSDMC2010, Enron-Spam, and Nazario, using DeBERTa-v3-base, LLaMA-3-8B, and GPT-4 demonstrate that GPT-4 achieves the strongest overall trust profile, followed by LLaMA-3-8B and DeBERTa-v3-base. Statistical analysis confirms that reliability varies independently of raw accuracy, underscoring the importance of trust-aware evaluation for real-world deployment. The proposed framework establishes a transparent and reproducible foundation for assessing model dependability in LLM-based phishing detection. --- ### IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs Authors: Ali Faraz, Akash, Shaharukh Khan, Raja Kolla, Akshat Patidar, Suranjan Goswami, Abhinav Ravi, Chandra Khatri, Shubham Agarwal Published: 2025-11-06 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.04727v1 Vision-language models (VLMs) have demonstrated impressive generalization across multimodal tasks, yet most evaluation benchmarks remain Western-centric, leaving open questions about their performance in culturally diverse and multilingual settings. To address this gap, we introduce IndicVisionBench, the first large-scale benchmark centered on the Indian subcontinent. Covering English and 10 Indian languages, our benchmark spans 3 multimodal tasks, including Optical Character Recognition (OCR), Multimodal Machine Translation (MMT), and Visual Question Answering (VQA), covering 6 kinds of question types. Our final benchmark consists of a total of ~5K images and 37K+ QA pairs across 13 culturally grounded topics. In addition, we release a paired parallel corpus of annotations across 10 Indic languages, creating a unique resource for analyzing cultural and linguistic biases in VLMs. We evaluate a broad spectrum of 8 models, from proprietary closed-source systems to open-weights medium and large-scale models. Our experiments reveal substantial performance gaps, underscoring the limitations of current VLMs in culturally diverse contexts. By centering cultural diversity and multilinguality, IndicVisionBench establishes a reproducible evaluation framework that paves the way for more inclusive multimodal research. --- ### Temporal convolutional and fusional transformer model with Bi-LSTM encoder-decoder for multi-time-window remaining useful life prediction Authors: Mohamadreza Akbari Pour, Mohamad Sadeq Karimi, Amir Hossein Mazloumi Published: 2025-11-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.04723v1 Health prediction is crucial for ensuring reliability, minimizing downtime, and optimizing maintenance in industrial systems. Remaining Useful Life (RUL) prediction is a key component of this process; however, many existing models struggle to capture fine-grained temporal dependencies while dynamically prioritizing critical features across time for robust prognostics. To address these challenges, we propose a novel framework that integrates Temporal Convolutional Networks (TCNs) for localized temporal feature extraction with a modified Temporal Fusion Transformer (TFT) enhanced by Bi-LSTM encoder-decoder. This architecture effectively bridges short- and long-term dependencies while emphasizing salient temporal patterns. Furthermore, the incorporation of a multi-time-window methodology improves adaptability across diverse operating conditions. Extensive evaluations on benchmark datasets demonstrate that the proposed model reduces the average RMSE by up to 5.5%, underscoring its improved predictive accuracy compared to state-of-the-art methods. By closing critical gaps in current approaches, this framework advances the effectiveness of industrial prognostic systems and highlights the potential of advanced time-series transformers for RUL prediction. --- ### AWEMixer: Adaptive Wavelet-Enhanced Mixer Network for Long-Term Time Series Forecasting Authors: Qianyang Li, Xingjun Zhang, Peng Tao, Shaoxun Wang, Yancheng Pan, Jia Wei Published: 2025-11-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.04722v1 Forecasting long-term time series in IoT environments remains a significant challenge due to the non-stationary and multi-scale characteristics of sensor signals. Furthermore, error accumulation causes a decrease in forecast quality when predicting further into the future. Traditional methods are restricted to operate in time-domain, while the global frequency information achieved by Fourier transform would be regarded as stationary signals leading to blur the temporal patterns of transient events. We propose AWEMixer, an Adaptive Wavelet-Enhanced Mixer Network including two innovative components: 1) a Frequency Router designs to utilize the global periodicity pattern achieved by Fast Fourier Transform to adaptively weight localized wavelet subband, and 2) a Coherent Gated Fusion Block to achieve selective integration of prominent frequency features with multi-scale temporal representation through cross-attention and gating mechanism, which realizes accurate time-frequency localization while remaining robust to noise. Seven public benchmarks validate that our model is more effective than recent state-of-the-art models. Specifically, our model consistently achieves performance improvement compared with transformer-based and MLP-based state-of-the-art models in long-sequence time series forecasting. Code is available at https://github.com/hit636/AWEMixer --- ### Learning to reason about rare diseases through retrieval-augmented agents Authors: Ha Young Kim, Jun Li, Ana Beatriz Solana, Carolin M. Pirkl, Benedikt Wiestler, Julia A. Schnabel, Cosmin I. Bercea Published: 2025-11-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.04720v1 Rare diseases represent the long tail of medical imaging, where AI models often fail due to the scarcity of representative training data. In clinical workflows, radiologists frequently consult case reports and literature when confronted with unfamiliar findings. Following this line of reasoning, we introduce RADAR, Retrieval Augmented Diagnostic Reasoning Agents, an agentic system for rare disease detection in brain MRI. Our approach uses AI agents with access to external medical knowledge by embedding both case reports and literature using sentence transformers and indexing them with FAISS to enable efficient similarity search. The agent retrieves clinically relevant evidence to guide diagnostic decision making on unseen diseases, without the need of additional training. Designed as a model-agnostic reasoning module, RADAR can be seamlessly integrated with diverse large language models, consistently improving their rare pathology recognition and interpretability. On the NOVA dataset comprising 280 distinct rare diseases, RADAR achieves up to a 10.2% performance gain, with the strongest improvements observed for open source models such as DeepSeek. Beyond accuracy, the retrieved examples provide interpretable, literature grounded explanations, highlighting retrieval-augmented reasoning as a powerful paradigm for low-prevalence conditions in medical imaging. --- ### Ada-FCN: Adaptive Frequency-Coupled Network for fMRI-Based Brain Disorder Classification Authors: Yue Xun, Jiaxing Xu, Wenbo Gao, Chen Yang, Shujun Wang Published: 2025-11-06 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.04718v2 Resting-state fMRI has become a valuable tool for classifying brain disorders and constructing brain functional connectivity networks by tracking BOLD signals across brain regions. However, existing mod els largely neglect the multi-frequency nature of neuronal oscillations, treating BOLD signals as monolithic time series. This overlooks the cru cial fact that neurological disorders often manifest as disruptions within specific frequency bands, limiting diagnostic sensitivity and specificity. While some methods have attempted to incorporate frequency informa tion, they often rely on predefined frequency bands, which may not be optimal for capturing individual variability or disease-specific alterations. To address this, we propose a novel framework featuring Adaptive Cas cade Decomposition to learn task-relevant frequency sub-bands for each brain region and Frequency-Coupled Connectivity Learning to capture both intra- and nuanced cross-band interactions in a unified functional network. This unified network informs a novel message-passing mecha nism within our Unified-GCN, generating refined node representations for diagnostic prediction. Experimental results on the ADNI and ABIDE datasets demonstrate superior performance over existing methods. The code is available at https://github.com/XXYY20221234/Ada-FCN. --- ### P-MIA: A Profiled-Based Membership Inference Attack on Cognitive Diagnosis Models Authors: Mingliang Hou, Yinuo Wang, Teng Guo, Zitao Liu, Wenzhou Dou, Jiaqi Zheng, Renqiang Luo, Mi Tian, Weiqi Luo Published: 2025-11-06 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.04716v1 Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While membership inference attacks (MIA) have been studied in various domains, their application to CDMs remains a critical research gap, leaving their privacy risks unquantified. This paper is the first to systematically investigate MIA against CDMs. We introduce a novel and realistic grey box threat model that exploits the explainability features of these platforms, where a model's internal knowledge state vectors are exposed to users through visualizations such as radar charts. We demonstrate that these vectors can be accurately reverse-engineered from such visualizations, creating a potent attack surface. Based on this threat model, we propose a profile-based MIA (P-MIA) framework that leverages both the model's final prediction probabilities and the exposed internal knowledge state vectors as features. Extensive experiments on three real-world datasets against mainstream CDMs show that our grey-box attack significantly outperforms standard black-box baselines. Furthermore, we showcase the utility of P-MIA as an auditing tool by successfully evaluating the efficacy of machine unlearning techniques and revealing their limitations. --- ### First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation Authors: Dmytro Vitel, Anshuman Chhabra Published: 2025-11-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.04715v2 Identifying how training samples influence/impact Large Language Model (LLM) decision-making is essential for effectively interpreting model decisions and auditing large-scale datasets. Current training sample influence estimation methods (also known as influence functions) undertake this goal by utilizing information flow through the model via its first-order and higher-order gradient terms. However, owing to the large model sizes of today consisting of billions of parameters, these influence computations are often restricted to some subset of model layers to ensure computational feasibility. Prior seminal work by Yeh et al. (2022) in assessing which layers are best suited for computing language data influence concluded that the first (embedding) layers are the most informative for this purpose, using a hypothesis based on influence scores canceling out (i.e., the cancellation effect). In this work, we propose theoretical and empirical evidence demonstrating how the cancellation effect is unreliable, and that middle attention layers are better estimators for influence. Furthermore, we address the broader challenge of aggregating influence scores across layers, and showcase how alternatives to standard averaging (such as ranking and vote-based methods) can lead to significantly improved performance. Finally, we propose better methods for evaluating influence score efficacy in LLMs without undertaking model retraining, and propose a new metric known as the Noise Detection Rate (NDR) that exhibits strong predictive capability compared to the cancellation effect. Through extensive experiments across LLMs of varying types and scales, we concretely determine that the first (layers) are not necessarily better than the last (layers) for LLM influence estimation, contrasting with prior knowledge in the field. --- ### Dark Energy Survey Year 3 results: Simulation-based $w$CDM inference from weak lensing and galaxy clustering maps with deep learning: Analysis design Authors: A. Thomsen, J. Bucko, T. Kacprzak, V. Ajani, J. Fluri, A. Refregier, D. Anbajagane, F. J. Castander, A. Ferté, M. Gatti, N. Jeffrey, A. Alarcon et al. Published: 2025-11-06 Categories: astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2511.04681v2 Data-driven approaches using deep learning are emerging as powerful techniques to extract non-Gaussian information from cosmological large-scale structure. This work presents the first simulation-based inference (SBI) pipeline that combines weak lensing and galaxy clustering maps in a realistic Dark Energy Survey Year 3 (DES Y3) configuration and serves as preparation for a forthcoming analysis of the survey data. We develop a scalable forward model based on the CosmoGridV1 suite of N-body simulations to generate over one million self-consistent mock realizations of DES Y3 at the map level. Leveraging this large dataset, we train deep graph convolutional neural networks on the full survey footprint in spherical geometry to learn low-dimensional features that approximately maximize mutual information with target parameters. These learned compressions enable neural density estimation of the implicit likelihood via normalizing flows in a ten-dimensional parameter space spanning cosmological $w$CDM, intrinsic alignment, and linear galaxy bias parameters, while marginalizing over baryonic, photometric redshift, and shear bias nuisances. To ensure robustness, we extensively validate our inference pipeline using synthetic observations derived from both systematic contaminations in our forward model and independent Buzzard galaxy catalogs. Our forecasts yield significant improvements in cosmological parameter constraints, achieving $2-3\times$ higher figures of merit in the $Ω_m - S_8$ plane relative to our implementation of baseline two-point statistics and effectively breaking parameter degeneracies through probe combination. These results demonstrate the potential of SBI analyses powered by deep learning for upcoming Stage-IV wide-field imaging surveys. --- ### Dark Energy Survey Year 3 results: Simulation-based $w$CDM inference from weak lensing and galaxy clustering maps with deep learning. I. Analysis design Authors: A. Thomsen, J. Bucko, T. Kacprzak, V. Ajani, J. Fluri, A. Refregier, D. Anbajagane, F. J. Castander, A. Ferté, M. Gatti, N. Jeffrey, A. Alarcon et al. Published: 2025-11-06 Categories: astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2511.04681v1 Data-driven approaches using deep learning are emerging as powerful techniques to extract non-Gaussian information from cosmological large-scale structure. This work presents the first simulation-based inference (SBI) pipeline that combines weak lensing and galaxy clustering maps in a realistic Dark Energy Survey Year 3 (DES Y3) configuration and serves as preparation for a forthcoming analysis of the survey data. We develop a scalable forward model based on the CosmoGridV1 suite of N-body simulations to generate over one million self-consistent mock realizations of DES Y3 at the map level. Leveraging this large dataset, we train deep graph convolutional neural networks on the full survey footprint in spherical geometry to learn low-dimensional features that approximately maximize mutual information with target parameters. These learned compressions enable neural density estimation of the implicit likelihood via normalizing flows in a ten-dimensional parameter space spanning cosmological $w$CDM, intrinsic alignment, and linear galaxy bias parameters, while marginalizing over baryonic, photometric redshift, and shear bias nuisances. To ensure robustness, we extensively validate our inference pipeline using synthetic observations derived from both systematic contaminations in our forward model and independent Buzzard galaxy catalogs. Our forecasts yield significant improvements in cosmological parameter constraints, achieving $2-3\times$ higher figures of merit in the $\Omega_m - S_8$ plane relative to our implementation of baseline two-point statistics and effectively breaking parameter degeneracies through probe combination. These results demonstrate the potential of SBI analyses powered by deep learning for upcoming Stage-IV wide-field imaging surveys. --- ### Carousel: A High-Resolution Dataset for Multi-Target Automatic Image Cropping Authors: Rafe Loya, Andrew Hamara, Benjamin Estell, Benjamin Kilpatrick, Andrew C. Freeman Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04680v1 Automatic image cropping is a method for maximizing the human-perceived quality of cropped regions in photographs. Although several works have proposed techniques for producing singular crops, little work has addressed the problem of producing multiple, distinct crops with aesthetic appeal. In this paper, we motivate the problem with a discussion on modern social media applications, introduce a dataset of 277 relevant images and human labels, and evaluate the efficacy of several single-crop models with an image partitioning algorithm as a pre-processing step. The dataset is available at https://github.com/RafeLoya/carousel. --- ### GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction Authors: Qingzhou Lu, Yao Feng, Baiyu Shi, Michael Piseno, Zhenan Bao, C. Karen Liu Published: 2025-11-06 Categories: cs.RO, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2511.04679v1 Humanoid robots are expected to operate in human-centered environments where safe and natural physical interaction is essential. However, most recent reinforcement learning (RL) policies emphasize rigid tracking and suppress external forces. Existing impedance-augmented approaches are typically restricted to base or end-effector control and focus on resisting extreme forces rather than enabling compliance. We introduce GentleHumanoid, a framework that integrates impedance control into a whole-body motion tracking policy to achieve upper-body compliance. At its core is a unified spring-based formulation that models both resistive contacts (restoring forces when pressing against surfaces) and guiding contacts (pushes or pulls sampled from human motion data). This formulation ensures kinematically consistent forces across the shoulder, elbow, and wrist, while exposing the policy to diverse interaction scenarios. Safety is further supported through task-adjustable force thresholds. We evaluate our approach in both simulation and on the Unitree G1 humanoid across tasks requiring different levels of compliance, including gentle hugging, sit-to-stand assistance, and safe object manipulation. Compared to baselines, our policy consistently reduces peak contact forces while maintaining task success, resulting in smoother and more natural interactions. These results highlight a step toward humanoid robots that can safely and effectively collaborate with humans and handle objects in real-world environments. --- ### Tracking and Understanding Object Transformations Authors: Yihong Sun, Xinyu Yang, Jennifer J. Sun, Bharath Hariharan Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04678v2 Real-world objects frequently undergo state transformations. From an apple being cut into pieces to a butterfly emerging from its cocoon, tracking through these changes is important for understanding real-world objects and dynamics. However, existing methods often lose track of the target object after transformation, due to significant changes in object appearance. To address this limitation, we introduce the task of Track Any State: tracking objects through transformations while detecting and describing state changes, accompanied by a new benchmark dataset, VOST-TAS. To tackle this problem, we present TubeletGraph, a zero-shot system that recovers missing objects after transformation and maps out how object states are evolving over time. TubeletGraph first identifies potentially overlooked tracks, and determines whether they should be integrated based on semantic and proximity priors. Then, it reasons about the added tracks and generates a state graph describing each observed transformation. TubeletGraph achieves state-of-the-art tracking performance under transformations, while demonstrating deeper understanding of object transformations and promising capabilities in temporal grounding and semantic reasoning for complex object transformations. Code, additional results, and the benchmark dataset are available at https://tubelet-graph.github.io. --- ### Tracking and Understanding Object Transformations Authors: Yihong Sun, Xinyu Yang, Jennifer J. Sun, Bharath Hariharan Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04678v1 Real-world objects frequently undergo state transformations. From an apple being cut into pieces to a butterfly emerging from its cocoon, tracking through these changes is important for understanding real-world objects and dynamics. However, existing methods often lose track of the target object after transformation, due to significant changes in object appearance. To address this limitation, we introduce the task of Track Any State: tracking objects through transformations while detecting and describing state changes, accompanied by a new benchmark dataset, VOST-TAS. To tackle this problem, we present TubeletGraph, a zero-shot system that recovers missing objects after transformation and maps out how object states are evolving over time. TubeletGraph first identifies potentially overlooked tracks, and determines whether they should be integrated based on semantic and proximity priors. Then, it reasons about the added tracks and generates a state graph describing each observed transformation. TubeletGraph achieves state-of-the-art tracking performance under transformations, while demonstrating deeper understanding of object transformations and promising capabilities in temporal grounding and semantic reasoning for complex object transformations. Code, additional results, and the benchmark dataset are available at https://tubelet-graph.github.io. --- ### InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation Authors: Jinlai Liu, Jian Han, Bin Yan, Hui Wu, Fengda Zhu, Xing Wang, Yi Jiang, Bingyue Peng, Zehuan Yuan Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04675v2 We introduce InfinityStar, a unified spacetime autoregressive framework for high-resolution image and dynamic video synthesis. Building on the recent success of autoregressive modeling in both vision and language, our purely discrete approach jointly captures spatial and temporal dependencies within a single architecture. This unified design naturally supports a variety of generation tasks such as text-to-image, text-to-video, image-to-video, and long interactive video synthesis via straightforward temporal autoregression. Extensive experiments demonstrate that InfinityStar scores 83.74 on VBench, outperforming all autoregressive models by large margins, even surpassing some diffusion competitors like HunyuanVideo. Without extra optimizations, our model generates a 5s, 720p video approximately 10x faster than leading diffusion-based methods. To our knowledge, InfinityStar is the first discrete autoregressive video generator capable of producing industrial level 720p videos. We release all code and models to foster further research in efficient, high-quality video generation. --- ### InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation Authors: Jinlai Liu, Jian Han, Bin Yan, Hui Wu, Fengda Zhu, Xing Wang, Yi Jiang, Bingyue Peng, Zehuan Yuan Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04675v1 We introduce InfinityStar, a unified spacetime autoregressive framework for high-resolution image and dynamic video synthesis. Building on the recent success of autoregressive modeling in both vision and language, our purely discrete approach jointly captures spatial and temporal dependencies within a single architecture. This unified design naturally supports a variety of generation tasks such as text-to-image, text-to-video, image-to-video, and long interactive video synthesis via straightforward temporal autoregression. Extensive experiments demonstrate that InfinityStar scores 83.74 on VBench, outperforming all autoregressive models by large margins, even surpassing some diffusion competitors like HunyuanVideo. Without extra optimizations, our model generates a 5s, 720p video approximately 10x faster than leading diffusion-based methods. To our knowledge, InfinityStar is the first discrete autoregressive video generator capable of producing industrial level 720p videos. We release all code and models to foster further research in efficient, high-quality video generation. --- ### X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations Authors: Maximus A. Pace, Prithwish Dan, Chuanruo Ning, Atiksh Bhardwaj, Audrey Du, Edward W. Duan, Wei-Chiu Ma, Kushal Kedia Published: 2025-11-06 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.04671v2 Human videos are a scalable source of training data for robot learning. However, humans and robots significantly differ in embodiment, making many human actions infeasible for direct execution on a robot. Still, these demonstrations convey rich object-interaction cues and task intent. Our goal is to learn from this coarse guidance without transferring embodiment-specific, infeasible execution strategies. Recent advances in generative modeling tackle a related problem of learning from low-quality data. In particular, Ambient Diffusion is a recent method for diffusion modeling that incorporates low-quality data only at high-noise timesteps of the forward diffusion process. Our key insight is to view human actions as noisy counterparts of robot actions. As noise increases along the forward diffusion process, embodiment-specific differences fade away while task-relevant guidance is preserved. Based on these observations, we present X-Diffusion, a cross-embodiment learning framework based on Ambient Diffusion that selectively trains diffusion policies on noised human actions. This enables effective use of easy-to-collect human videos without sacrificing robot feasibility. Across five real-world manipulation tasks, we show that X-Diffusion improves average success rates by 16% over naive co-training and manual data filtering. The project website is available at https://portal-cornell.github.io/X-Diffusion/. --- ### X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations Authors: Maximus A. Pace, Prithwish Dan, Chuanruo Ning, Atiksh Bhardwaj, Audrey Du, Edward W. Duan, Wei-Chiu Ma, Kushal Kedia Published: 2025-11-06 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.04671v1 Human videos can be recorded quickly and at scale, making them an appealing source of training data for robot learning. However, humans and robots differ fundamentally in embodiment, resulting in mismatched action execution. Direct kinematic retargeting of human hand motion can therefore produce actions that are physically infeasible for robots. Despite these low-level differences, human demonstrations provide valuable motion cues about how to manipulate and interact with objects. Our key idea is to exploit the forward diffusion process: as noise is added to actions, low-level execution differences fade while high-level task guidance is preserved. We present X-Diffusion, a principled framework for training diffusion policies that maximally leverages human data without learning dynamically infeasible motions. X-Diffusion first trains a classifier to predict whether a noisy action is executed by a human or robot. Then, a human action is incorporated into policy training only after adding sufficient noise such that the classifier cannot discern its embodiment. Actions consistent with robot execution supervise fine-grained denoising at low noise levels, while mismatched human actions provide only coarse guidance at higher noise levels. Our experiments show that naive co-training under execution mismatches degrades policy performance, while X-Diffusion consistently improves it. Across five manipulation tasks, X-Diffusion achieves a 16% higher average success rate than the best baseline. The project website is available at https://portal-cornell.github.io/X-Diffusion/. --- ### Cambrian-S: Towards Spatial Supersensing in Video Authors: Shusheng Yang, Jihan Yang, Pinzhi Huang, Ellis Brown, Zihao Yang, Yue Yu, Shengbang Tong, Zihan Zheng, Yifan Xu, Muhan Wang, Daohan Lu, Rob Fergus et al. Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04670v1 We argue that progress in true multimodal intelligence calls for a shift from reactive, task-driven systems and brute-force long context towards a broader paradigm of supersensing. We frame spatial supersensing as four stages beyond linguistic-only understanding: semantic perception (naming what is seen), streaming event cognition (maintaining memory across continuous experiences), implicit 3D spatial cognition (inferring the world behind pixels), and predictive world modeling (creating internal models that filter and organize information). Current benchmarks largely test only the early stages, offering narrow coverage of spatial cognition and rarely challenging models in ways that require true world modeling. To drive progress in spatial supersensing, we present VSI-SUPER, a two-part benchmark: VSR (long-horizon visual spatial recall) and VSC (continual visual spatial counting). These tasks require arbitrarily long video inputs yet are resistant to brute-force context expansion. We then test data scaling limits by curating VSI-590K and training Cambrian-S, achieving +30% absolute improvement on VSI-Bench without sacrificing general capabilities. Yet performance on VSI-SUPER remains limited, indicating that scale alone is insufficient for spatial supersensing. We propose predictive sensing as a path forward, presenting a proof-of-concept in which a self-supervised next-latent-frame predictor leverages surprise (prediction error) to drive memory and event segmentation. On VSI-SUPER, this approach substantially outperforms leading proprietary baselines, showing that spatial supersensing requires models that not only see but also anticipate, select, and organize experience. --- ### SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding Authors: Ellis Brown, Arijit Ray, Ranjay Krishna, Ross Girshick, Rob Fergus, Saining Xie Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04668v2 Despite impressive high-level video comprehension, multimodal language models struggle with spatial reasoning across time and space. While current spatial training approaches rely on real-world video data, obtaining diverse footage with precise spatial annotations remains a bottleneck. To alleviate this bottleneck, we present SIMS-V -- a systematic data-generation framework that leverages the privileged information of 3D simulators to create spatially-rich video training data for multimodal language models. Using this framework, we investigate which properties of simulated data drive effective real-world transfer through systematic ablations of question types, mixes, and scales. We identify a minimal set of three question categories (metric measurement, perspective-dependent reasoning, and temporal tracking) that prove most effective for developing transferable spatial intelligence, outperforming comprehensive coverage despite using fewer question types. These insights enable highly efficient training: our 7B-parameter video LLM fine-tuned on just 25K simulated examples outperforms the larger 72B baseline and achieves competitive performance with proprietary models on rigorous real-world spatial reasoning benchmarks. Our approach demonstrates robust generalization, maintaining performance on general video understanding while showing substantial improvements on embodied and real-world spatial tasks. --- ### SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding Authors: Ellis Brown, Arijit Ray, Ranjay Krishna, Ross Girshick, Rob Fergus, Saining Xie Published: 2025-11-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.04668v1 Despite impressive high-level video comprehension, multimodal language models struggle with spatial reasoning across time and space. While current spatial training approaches rely on real-world video data, obtaining diverse footage with precise spatial annotations remains a bottleneck. To alleviate this bottleneck, we present SIMS-V -- a systematic data-generation framework that leverages the privileged information of 3D simulators to create spatially-rich video training data for multimodal language models. Using this framework, we investigate which properties of simulated data drive effective real-world transfer through systematic ablations of question types, mixes, and scales. We identify a minimal set of three question categories (metric measurement, perspective-dependent reasoning, and temporal tracking) that prove most effective for developing transferable spatial intelligence, outperforming comprehensive coverage despite using fewer question types. These insights enable highly efficient training: our 7B-parameter video LLM fine-tuned on just 25K simulated examples outperforms the larger 72B baseline and achieves competitive performance with proprietary models on rigorous real-world spatial reasoning benchmarks. Our approach demonstrates robust generalization, maintaining performance on general video understanding while showing substantial improvements on embodied and real-world spatial tasks. --- ### Multi-Method Analysis of Mathematics Placement Assessments: Classical, Machine Learning, and Clustering Approaches Authors: Julian D. Allagan, Dasia A. Singleton, Shanae N. Perry, Gabrielle C. Morgan, Essence A. Morgan Published: 2025-11-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.04667v1 This study evaluates a 40-item mathematics placement examination administered to 198 students using a multi-method framework combining Classical Test Theory, machine learning, and unsupervised clustering. Classical Test Theory analysis reveals that 55\% of items achieve excellent discrimination ($D \geq 0.40$) while 30\% demonstrate poor discrimination ($D < 0.20$) requiring replacement. Question 6 (Graph Interpretation) emerges as the examination's most powerful discriminator, achieving perfect discrimination ($D = 1.000$), highest ANOVA F-statistic ($F = 4609.1$), and maximum Random Forest feature importance (0.206), accounting for 20.6\% of predictive power. Machine learning algorithms demonstrate exceptional performance, with Random Forest and Gradient Boosting achieving 97.5\% and 96.0\% cross-validation accuracy. K-means clustering identifies a natural binary competency structure with a boundary at 42.5\%, diverging from the institutional threshold of 55\% and suggesting potential overclassification into remedial categories. The two-cluster solution exhibits exceptional stability (bootstrap ARI = 0.855) with perfect lower-cluster purity. Convergent evidence across methods supports specific refinements: replace poorly discriminating items, implement a two-stage assessment, and integrate Random Forest predictions with transparency mechanisms. These findings demonstrate that multi-method integration provides a robust empirical foundation for evidence-based mathematics placement optimization. --- ### Forgetting is Everywhere Authors: Ben Sanati, Thomas L. Lee, Trevor McInroe, Aidan Scannell, Esmeralda S. Whitammer, David Abel, Amos Storkey Published: 2025-11-06 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.04666v4 A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge as they adapt to new data. Addressing this problem requires a principled understanding of forgetting. Yet, despite decades of study, no unified definition has emerged that offers insight into the underlying dynamics of learning. We propose an algorithm- and task-agnostic theory that characterises forgetting as a lack of self-consistency in a learner's predictive distribution, manifesting as a loss of predictive information. Our theory naturally yields a general measure of an algorithm's propensity to forget, proves that exact Bayesian inference allows for adaptation without forgetting, and provides a tautological explanation for why generative models forget when trained on their own synthetic outputs. To validate these claims, we design a comprehensive set of experiments that span classification, regression, generative modelling, and reinforcement learning. We demonstrate that forgetting is present across all deep learning settings and plays a significant role in determining learning efficiency. Together, these results establish a principled understanding of forgetting and lay the foundation for analysing and improving the information retention capabilities of general learning algorithms. --- ### Forgetting is Everywhere Authors: Ben Sanati, Thomas L. Lee, Trevor McInroe, Aidan Scannell, Nikolay Malkin, David Abel, Amos Storkey Published: 2025-11-06 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.04666v1 A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge when adapting to new data. Addressing this problem requires a principled understanding of forgetting; yet, despite decades of study, no unified definition has emerged that provides insights into the underlying dynamics of learning. We propose an algorithm- and task-agnostic theory that characterises forgetting as a lack of self-consistency in a learner's predictive distribution over future experiences, manifesting as a loss of predictive information. Our theory naturally yields a general measure of an algorithm's propensity to forget. To validate the theory, we design a comprehensive set of experiments that span classification, regression, generative modelling, and reinforcement learning. We empirically demonstrate how forgetting is present across all learning settings and plays a significant role in determining learning efficiency. Together, these results establish a principled understanding of forgetting and lay the foundation for analysing and improving the information retention capabilities of general learning algorithms. --- ### Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions Authors: Kaifeng Zhang, Shuo Sha, Hanxiao Jiang, Matthew Loper, Hyunjong Song, Guangyan Cai, Zhuo Xu, Xiaochen Hu, Changxi Zheng, Yunzhu Li Published: 2025-11-06 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.04665v2 Robotic manipulation policies are advancing rapidly, but their direct evaluation in the real world remains costly, time-consuming, and difficult to reproduce, particularly for tasks involving deformable objects. Simulation provides a scalable and systematic alternative, yet existing simulators often fail to capture the coupled visual and physical complexity of soft-body interactions. We present a real-to-sim policy evaluation framework that constructs soft-body digital twins from real-world videos and renders robots, objects, and environments with photorealistic fidelity using 3D Gaussian Splatting. We validate our approach on representative deformable manipulation tasks, including plush toy packing, rope routing, and T-block pushing, demonstrating that simulated rollouts correlate strongly with real-world execution performance and reveal key behavioral patterns of learned policies. Our results suggest that combining physics-informed reconstruction with high-quality rendering enables reproducible, scalable, and accurate evaluation of robotic manipulation policies. Website: https://real2sim-eval.github.io/ --- ### Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions Authors: Kaifeng Zhang, Shuo Sha, Hanxiao Jiang, Matthew Loper, Hyunjong Song, Guangyan Cai, Zhuo Xu, Xiaochen Hu, Changxi Zheng, Yunzhu Li Published: 2025-11-06 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.04665v1 Robotic manipulation policies are advancing rapidly, but their direct evaluation in the real world remains costly, time-consuming, and difficult to reproduce, particularly for tasks involving deformable objects. Simulation provides a scalable and systematic alternative, yet existing simulators often fail to capture the coupled visual and physical complexity of soft-body interactions. We present a real-to-sim policy evaluation framework that constructs soft-body digital twins from real-world videos and renders robots, objects, and environments with photorealistic fidelity using 3D Gaussian Splatting. We validate our approach on representative deformable manipulation tasks, including plush toy packing, rope routing, and T-block pushing, demonstrating that simulated rollouts correlate strongly with real-world execution performance and reveal key behavioral patterns of learned policies. Our results suggest that combining physics-informed reconstruction with high-quality rendering enables reproducible, scalable, and accurate evaluation of robotic manipulation policies. Website: https://real2sim-eval.github.io/ --- ### VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks Authors: Yu Feng, Nathaniel Weir, Kaj Bostrom, Sam Bayless, Darion Cassel, Sapana Chaudhary, Benjamin Kiesl-Reiter, Huzefa Rangwala Published: 2025-11-06 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.04662v1 LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasoning may be flawed, undermining trust in high-stakes scenarios. To mitigate this issue, we introduce VeriCoT, a neuro-symbolic method that extracts and verifies formal logical arguments from CoT reasoning. VeriCoT formalizes each CoT reasoning step into first-order logic and identifies premises that ground the argument in source context, commonsense knowledge, or prior reasoning steps. The symbolic representation enables automated solvers to verify logical validity while the NL premises allow humans and systems to identify ungrounded or fallacious reasoning steps. Experiments on the ProofWriter, LegalBench, and BioASQ datasets show VeriCoT effectively identifies flawed reasoning, and serves as a strong predictor of final answer correctness. We also leverage VeriCoT's verification signal for (1) inference-time self-reflection, (2) supervised fine-tuning (SFT) on VeriCoT-distilled datasets and (3) preference fine-tuning (PFT) with direct preference optimization (DPO) using verification-based pairwise rewards, further improving reasoning validity and accuracy. --- ### Nowcast3D: Reliable precipitation nowcasting via gray-box learning Authors: Huaguan Chen, Wei Han, Haofei Sun, Ning Lin, Xingtao Song, Yunfan Yang, Jie Tian, Yang Liu, Ji-Rong Wen, Xiaoye Zhang, Xueshun Shen, Hao Sun Published: 2025-11-06 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2511.04659v4 Reliable nowcasting of extreme precipitation remains difficult because convective systems are strongly nonlinear, multiscale, and nonstationary in 3D. Radar is the backbone of nowcasting, yet existing methods struggle to predict extremes: physics-based extrapolation cannot capture growth and decay, deterministic learning tends to oversmooth and underestimate peaks, and purely generative models often lack physical consistency. Hybrid schemes help but are mostly limited to 2D composite reflectivity, collapsing the atmosphere into one layer and discarding vertical structure critical for height-dependent dynamics. We introduce Nowcast3D, a gray-box, fully 3D framework that works directly on volumetric radar reflectivity. The end-to-end model couples physically constrained neural operators (advection, local diffusion, and microphysics) with a conditional diffusion model to generate ensemble forecasts with quantified uncertainty. Trained on provincial-scale 3D volumes over a $10.24^\circ \times 10.24^\circ$ region and fine-tuned on a $2.56^\circ \times 2.56^\circ$ city region ($0.01^\circ \approx 1$ km), Nowcast3D provides near-real-time forecasts up to 3 h and outperforms competitive baselines in cross-region and temporal out-of-sample tests. It can also infer wind fields without labeled supervision, supporting physically plausible transport. In a nationwide blind evaluation by 160 meteorologists, Nowcast3D ranked first and was preferred in 57% of post-hoc assessments, surpassing the leading baseline (27%). These results highlight its reliability and operational value for extreme precipitation nowcasting. ---