# Research Papers — 2025-11 · bundle page 52 of 197 > Full-text markdown of papers #2551–2600 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/52 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/51.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/53.md) ### CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning Authors: Mengdi Wang, Efe Bozkir, Enkelejda Kasneci Published: 2025-11-23 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2511.18611v1 Split learning emerges as a promising paradigm for collaborative distributed model training, akin to federated learning, by partitioning neural networks between clients and a server without raw data exchange. However, sequential split learning suffers from poor scalability, while parallel variants like parallel split learning and split federated learning often incur high server resource overhead due to model duplication and aggregation, and generally exhibit reduced model performance and convergence owing to factors like client drift and lag. To address these limitations, we introduce CycleSL, a novel aggregation-free split learning framework that enhances scalability and performance and can be seamlessly integrated with existing methods. Inspired by alternating block coordinate descent, CycleSL treats server-side training as an independent higher-level machine learning task, resampling client-extracted features (smashed data) to mitigate heterogeneity and drift. It then performs cyclical updates, namely optimizing the server model first, followed by client updates using the updated server for gradient computation. We integrate CycleSL into previous algorithms and benchmark them on five publicly available datasets with non-iid data distribution and partial client attendance. Our empirical findings highlight the effectiveness of CycleSL in enhancing model performance. Our source code is available at https://gitlab.lrz.de/hctl/CycleSL. --- ### Universality in Collective Intelligence on the Rubik's Cube Authors: David Krakauer, Gülce Kardeş, Joshua Grochow Published: 2025-11-23 Categories: cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2511.18609v1 Progress in understanding expert performance is limited by the scarcity of quantitative data on long-term knowledge acquisition and deployment. Here we use the Rubik's Cube as a cognitive model system existing at the intersection of puzzle solving, skill learning, expert knowledge, cultural transmission, and group theory. By studying competitive cube communities, we find evidence for universality in the collective learning of the Rubik's Cube in both sighted and blindfolded conditions: expert performance follows exponential progress curves whose parameters reflect the delayed acquisition of algorithms that shorten solution paths. Blindfold solves form a distinct problem class from sighted solves and are constrained not only by expert knowledge but also by the skill improvements required to overcome short-term memory bottlenecks, a constraint shared with blindfold chess. Cognitive artifacts such as the Rubik's Cube help solvers navigate an otherwise enormous mathematical state space. In doing so, they sustain collective intelligence by integrating communal knowledge stores with individual expertise and skill, illustrating how expertise can, in practice, continue to deepen over the course of a single lifetime. --- ### How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints Authors: Kensuke Nakamura, Arun L. Bishop, Steven Man, Aaron M. Johnson, Zachary Manchester, Andrea Bajcsy Published: 2025-11-23 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2511.18606v2 Latent safety filters extend Hamilton-Jacobi (HJ) reachability to operate on latent state representations and dynamics learned directly from high-dimensional observations, enabling safe visuomotor control under hard-to-model constraints. However, existing methods implement "least-restrictive" filtering that discretely switch between nominal and safety policies, potentially undermining the task performance that makes modern visuomotor policies valuable. While reachability value functions can, in principle, be adapted to be control barrier functions (CBFs) for smooth optimization-based filtering, we theoretically and empirically show that current latent-space learning methods produce fundamentally incompatible value functions. We identify two sources of incompatibility: First, in HJ reachability, failures are encoded via a "margin function" in latent space, whose sign indicates whether or not a latent is in the constraint set. However, representing the margin function as a classifier yields saturated value functions that exhibit discontinuous jumps. We prove that the value function's Lipschitz constant scales linearly with the margin function's Lipschitz constant, revealing that smooth CBFs require smooth margins. Second, reinforcement learning (RL) approximations trained solely on safety policy data yield inaccurate value estimates for nominal policy actions, precisely where CBF filtering needs them. We propose the LatentCBF, which addresses both challenges through gradient penalties that lead to smooth margin functions without additional labeling, and a value-training procedure that mixes data from both nominal and safety policy distributions. Experiments on simulated benchmarks and hardware with a vision-based manipulation policy demonstrate that LatentCBF enables smooth safety filtering while doubling the task-completion rate over prior switching methods. --- ### An Analysis of Constraint-Based Multi-Agent Pathfinding Algorithms Authors: Hannah Lee, James D. Motes, Marco Morales, Nancy M. Amato Published: 2025-11-23 Categories: cs.RO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.18604v1 This study informs the design of future multi-agent pathfinding (MAPF) and multi-robot motion planning (MRMP) algorithms by guiding choices based on constraint classification for constraint-based search algorithms. We categorize constraints as conservative or aggressive and provide insights into their search behavior, focusing specifically on vanilla Conflict-Based Search (CBS) and Conflict-Based Search with Priorities (CBSw/P). Under a hybrid grid-roadmap representation with varying resolution, we observe that aggressive (priority constraint) formulations tend to solve more instances as agent count or resolution increases, whereas conservative (motion constraint) formulations yield stronger solution quality when both succeed. Findings are synthesized in a decision flowchart, aiding users in selecting suitable constraints. Recommendations extend to Multi-Robot Motion Planning (MRMP), emphasizing the importance of considering topological features alongside problem, solution, and representation features. A comprehensive exploration of the study, including raw data and map performance, is available in our public GitHub Repository: https://GitHub.com/hannahjmlee/constraint-mapf-analysis --- ### RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data Authors: Wenchao Ma, Dario Kneubuehler, Maurice Chu, Ian Sachs, Haomiao Jiang, Sharon Xiaolei Huang Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18601v1 In this paper, we present RigAnyFace (RAF), a scalable neural auto-rigging framework for facial meshes of diverse topologies, including those with multiple disconnected components. RAF deforms a static neutral facial mesh into industry-standard FACS poses to form an expressive blendshape rig. Deformations are predicted by a triangulation-agnostic surface learning network augmented with our tailored architecture design to condition on FACS parameters and efficiently process disconnected components. For training, we curated a dataset of facial meshes, with a subset meticulously rigged by professional artists to serve as accurate 3D ground truth for deformation supervision. Due to the high cost of manual rigging, this subset is limited in size, constraining the generalization ability of models trained exclusively on it. To address this, we design a 2D supervision strategy for unlabeled neutral meshes without rigs. This strategy increases data diversity and allows for scaled training, thereby enhancing the generalization ability of models trained on this augmented data. Extensive experiments demonstrate that RAF is able to rig meshes of diverse topologies on not only our artist-crafted assets but also in-the-wild samples, outperforming previous works in accuracy and generalizability. Moreover, our method advances beyond prior work by supporting multiple disconnected components, such as eyeballs, for more detailed expression animation. Project page: https://wenchao-m.github.io/RigAnyFace.github.io --- ### NeAR: Coupled Neural Asset-Renderer Stack Authors: Hong Li, Chongjie Ye, Houyuan Chen, Weiqing Xiao, Ziyang Yan, Lixing Xiao, Zhaoxi Chen, Jianfeng Xiang, Shaocong Xu, Xuhui Liu, Yikai Wang, Baochang Zhang et al. Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18600v3 Neural asset authoring and neural rendering have traditionally evolved as disjoint paradigms: one generates digital assets for fixed graphics pipelines, while the other maps conventional assets to images. However, treating them as independent entities limits the potential for end-to-end optimization in fidelity and consistency. In this paper, we bridge this gap with NeAR, a Coupled Neural Asset--Renderer Stack. We argue that co-designing the asset representation and the renderer creates a robust "contract" for superior generation. On the asset side, we introduce the Lighting-Homogenized SLAT (LH-SLAT). Leveraging a rectified-flow model, NeAR lifts casually lit single images into a canonical, illumination-invariant latent space, effectively suppressing baked-in shadows and highlights. On the renderer side, we design a lighting-aware neural decoder tailored to interpret these homogenized latents. Conditioned on HDR environment maps and camera views, it synthesizes relightable 3D Gaussian splats in real-time without per-object optimization. We validate NeAR on four tasks: (1) G-buffer-based forward rendering, (2) random-lit reconstruction, (3) unknown-lit relighting, and (4) novel-view relighting. Extensive experiments demonstrate that our coupled stack outperforms state-of-the-art baselines in both quantitative metrics and perceptual quality. We hope this coupled asset-renderer perspective inspires future graphics stacks that view neural assets and renderers as co-designed components instead of independent entities. --- ### Toward Trustworthy Difficulty Assessments: Large Language Models as Judges in Programming and Synthetic Tasks Authors: H. M. Shadman Tabib, Jaber Ahmed Deedar Published: 2025-11-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18597v1 Large Language Models (LLMs) have demonstrated impressive capabilities in natural language and code generation, and are increasingly deployed as automatic judges of model outputs and learning activities. Yet, their behavior on structured tasks such as predicting the difficulty of competitive programming problems remains under-explored. We conduct a systematic comparison of GPT-4o, used purely as a natural-language difficulty assessor, against an interpretable Light-GBM ensemble trained on explicit numeric and textual features. On a dataset of 1,825 LeetCode problems labeled Easy, Medium, or Hard, LightGBM attains 86% accuracy, whereas GPT-4o reaches only 37.75%. Detailed analyses, including confusion matrices and SHAP-based interpretability, show that numeric constraints -- such as input size limits and acceptance rates -- play a crucial role in separating Hard problems from easier ones. By contrast, GPT-4o often overlooks these cues and exhibits a strong bias toward simpler categories. We further probe GPT-4o through a synthetic Hard-problem generation protocol. Surprisingly, GPT-4o labels almost all of its own synthetic Hard problems as Medium, contradicting its tendency to downgrade real Hard problems to Easy. Our findings connect to recent work on LLMs-as-judges and automatic difficulty estimation in programming and education, and highlight concrete failure modes that must be addressed before LLM-based judges can be considered trustworthy in competitive programming, educational platforms, or reinforcement-learning pipelines. --- ### Timepoint-Specific Benchmarking of Deep Learning Models for Glioblastoma Follow-Up MRI Authors: Wenhao Guo, Golrokh Mirzaei Published: 2025-11-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18595v2 Differentiating true tumor progression (TP) from treatment-related pseudoprogression (PsP) in glioblastoma remains challenging, especially at early follow-up. We present the first stage-specific, cross-sectional benchmarking of deep learning models for follow-up MRI using the Burdenko GBM Progression cohort (n = 180). We analyze different post-RT scans independently to test whether architecture performance depends on time-point. Eleven representative DL families (CNNs, LSTMs, hybrids, transformers, and selective state-space models) were trained under a unified, QC-driven pipeline with patient-level cross-validation. Across both stages, accuracies were comparable (~0.70-0.74), but discrimination improved at the second follow-up, with F1 and AUC increasing for several models, indicating richer separability later in the care pathway. A Mamba+CNN hybrid consistently offered the best accuracy-efficiency trade-off, while transformer variants delivered competitive AUCs at substantially higher computational cost and lightweight CNNs were efficient but less reliable. Performance also showed sensitivity to batch size, underscoring the need for standardized training protocols. Notably, absolute discrimination remained modest overall, reflecting the intrinsic difficulty of TP vs. PsP and the dataset's size imbalance. These results establish a stage-aware benchmark and motivate future work incorporating longitudinal modeling, multi-sequence MRI, and larger multi-center cohorts. --- ### Autoencoder for Position-Assisted Beam Prediction in mmWave ISAC Systems Authors: Ahmad A. Aziz El-Banna, Octavia A. Dobre Published: 2025-11-23 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2511.18594v1 Integrated sensing and communication and millimeter wave (mmWave) have emerged as pivotal technologies for 6G networks. However, the narrow nature of mmWave beams requires precise alignments that typically necessitate large training overhead. This overhead can be reduced by incorporating the position information with beam adjustments. This letter proposes a lightweight autorencoder (LAE) model that addresses the position-assisted beam prediction problem while significantly reducing computational complexity compared to the conventional baseline method, i.e., deep fully connected neural network. The proposed LAE is designed as a three-layer undercomplete network to exploit its dimensionality reduction capabilities and thereby mitigate the computational requirements of the trained model. Simulation results show that the proposed model achieves a similar beam prediction accuracy to the baseline with an 83% complexity reduction. --- ### Generative Myopia: Why Diffusion Models Fail at Structure Authors: Milad Siami Published: 2025-11-23 Categories: cs.LG, eess.SY, math.SP arXiv: https://arxiv.org/abs/2511.18593v1 Graph Diffusion Models (GDMs) optimize for statistical likelihood, implicitly acting as \textbf{frequency filters} that favor abundant substructures over spectrally critical ones. We term this phenomenon \textbf{Generative Myopia}. In combinatorial tasks like graph sparsification, this leads to the catastrophic removal of ``rare bridges,'' edges that are structurally mandatory ($R_{\text{eff}} \approx 1$) but statistically scarce. We prove theoretically and empirically that this failure is driven by \textbf{Gradient Starvation}: the optimization landscape itself suppresses rare structural signals, rendering them unlearnable regardless of model capacity. To resolve this, we introduce \textbf{Spectrally-Weighted Diffusion}, which re-aligns the variational objective using Effective Resistance. We demonstrate that spectral priors can be amortized into the training phase with zero inference overhead. Our method eliminates myopia, matching the performance of an optimal Spectral Oracle and achieving \textbf{100\% connectivity} on adversarial benchmarks where standard diffusion fails completely (0\%). --- ### Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation Authors: Wei Dong, Han Zhou, Junwei Lin, Jun Chen Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18591v1 Real-world dark images commonly exhibit not only low visibility and contrast but also complex noise and blur, posing significant restoration challenges. Existing methods often rely on paired data or fail to model dynamic illumination and blur characteristics, leading to poor generalization. To tackle this, we propose a generative framework based on visual autoregressive (VAR) modeling, guided by perceptual priors from the vision-language model (VLM). Specifically, to supply informative conditioning cues for VAR models, we deploy an adaptive curve estimation scheme to modulate the diverse illumination based on VLM-derived visibility scores. In addition, we integrate dynamic and spatial-frequency-aware Rotary Positional Encodings (SF-RoPE) into VAR to enhance its ability to model structures degraded by blur. Furthermore, we propose a recursive phase-domain modulation strategy that mitigates blur-induced artifacts in the phase domain via bounded iterative refinement guided by VLM-assessed blur scores. Our framework is fully unsupervised and achieves state-of-the-art performance on benchmark datasets. --- ### From Simulations to Surveys: Domain Adaptation for Galaxy Observations Authors: Kaley Brauer, Aditya Prasad Dash, Meet J. Vyas, Ahmed Salim, Stiven Briand Massala Published: 2025-11-23 Categories: astro-ph.GA, cs.LG, hep-th arXiv: https://arxiv.org/abs/2511.18590v1 Large photometric surveys will image billions of galaxies, but we currently lack quick, reliable automated ways to infer their physical properties like morphology, stellar mass, and star formation rates. Simulations provide galaxy images with ground-truth physical labels, but domain shifts in PSF, noise, backgrounds, selection, and label priors degrade transfer to real surveys. We present a preliminary domain adaptation pipeline that trains on simulated TNG50 galaxies and evaluates on real SDSS galaxies with morphology labels (elliptical/spiral/irregular). We train three backbones (CNN, $E(2)$-steerable CNN, ResNet-18) with focal loss and effective-number class weighting, and a feature-level domain loss $L_D$ built from GeomLoss (entropic Sinkhorn OT, energy distance, Gaussian MMD, and related metrics). We show that a combination of these losses with an OT-based "top_$k$ soft matching" loss that focuses $L_D$ on the worst-matched source-target pairs can further enhance domain alignment. With Euclidean distance, scheduled alignment weights, and top-$k$ matching, target accuracy (macro F1) rises from $\sim$46% ($\sim$30%) at no adaptation to $\sim$87% ($\sim$62.6%), with a domain AUC near 0.5, indicating strong latent-space mixing. --- ### Strategic Decision Framework for Enterprise LLM Adoption Authors: Michael Trusov, Minha Hwang, Zainab Jamal, Swarup Chandra Published: 2025-11-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.18589v1 Organizations are rapidly adopting Large Language Models (LLMs) to transform their operations, yet they lack clear guidance on key decisions for adoption and implementation. While LLMs offer powerful capabilities in content generation, assisted coding, and process automation, businesses face critical challenges in data security, LLM solution development approach, infrastructure requirements, and deployment strategies. Healthcare providers must protect patient data while leveraging LLMs for medical analysis, financial institutions need to balance automated customer service with regulatory compliance, and software companies seek to enhance development productivity while maintaining code security. This article presents a systematic six-step decision framework for LLM adoption, helping organizations navigate from initial application selection to final deployment. Based on extensive interviews and analysis of successful and failed implementations, our framework provides practical guidance for business leaders to align technological capabilities with business objectives. Through key decision points and real-world examples from both B2B and B2C contexts, organizations can make informed decisions about LLM adoption while ensuring secure and efficient integration across various use cases, from customer service automation to content creation and advanced analytics. --- ### Differential privacy with dependent data Authors: Valentin Roth, Marco Avella-Medina Published: 2025-11-23 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2511.18583v2 Dependent data underlies many statistical studies in the social and health sciences, which often involve sensitive or private information. Differential privacy (DP) and in particular \textit{user-level} DP provide a natural formalization of privacy requirements for processing dependent data where each individual provides multiple observations to the dataset. However, dependence introduced, e.g., through repeated measurements challenges the existing statistical theory under DP-constraints. In \iid{} settings, noisy Winsorized mean estimators have been shown to be minimax optimal for standard (\textit{item-level}) and \textit{user-level} DP estimation of a mean $μ\in \R^d$. Yet, their behavior on potentially dependent observations has not previously been studied. We fill this gap and show that Winsorized mean estimators can also be used under dependence for bounded and unbounded data, and can lead to asymptotic and finite sample guarantees that resemble their \iid{} counterparts under a weak notion of dependence. For this, we formalize dependence via log-Sobolev inequalities on the joint distribution of observations. This enables us to adapt the stable histogram by Karwa and Vadhan (2018) to a non-\iid{} setting, which we then use to estimate the private projection intervals of the Winsorized estimator. The resulting guarantees for our item-level mean estimator extend to \textit{user-level} mean estimation and transfer to the local model via a randomized response histogram. Using the mean estimators as building blocks, we provide extensions to random effects models, longitudinal linear regression and nonparametric regression. Therefore, our work constitutes a first step towards a systematic study of DP for dependent data. --- ### Barriers to AI Adoption: Image Concerns at Work Authors: David Almog Published: 2025-11-23 Categories: econ.GN, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.18582v1 Concerns about how workers are perceived can deter effective collaboration with artificial intelligence (AI). In a field experiment on a large online labor market, I hired 450 U.S.-based remote workers to complete an image-categorization job assisted by AI recommendations. Workers were incentivized by the prospect of a contract extension based on an HR evaluator's feedback. I find that workers adopt AI recommendations at lower rates when their reliance on AI is visible to the evaluator, resulting in a measurable decline in task performance. The effects are present despite a conservative design in which workers know that the evaluator is explicitly instructed to assess expected accuracy on the same AI-assisted task. This reduction in AI reliance persists even when the evaluator is reassured about workers' strong performance history on the platform, underscoring how difficult these concerns are to alleviate. Leveraging the platform's public feedback feature, I introduce a novel incentive-compatible elicitation method showing that workers fear heavy reliance on AI signals a lack of confidence in their own judgment, a trait they view as essential when collaborating with AI. --- ### Re(Visiting) Time Series Foundation Models in Finance Authors: Eghbal Rahimikia, Hao Ni, Weiguan Wang Published: 2025-11-23 Categories: q-fin.CP, cs.AI, cs.LG, q-fin.PM, q-fin.PR arXiv: https://arxiv.org/abs/2511.18578v1 Financial time series forecasting is central to trading, portfolio optimization, and risk management, yet it remains challenging due to noisy, non-stationary, and heterogeneous data. Recent advances in time series foundation models (TSFMs), inspired by large language models, offer a new paradigm for learning generalizable temporal representations from large and diverse datasets. This paper presents the first comprehensive empirical study of TSFMs in global financial markets. Using a large-scale dataset of daily excess returns across diverse markets, we evaluate zero-shot inference, fine-tuning, and pre-training from scratch against strong benchmark models. We find that off-the-shelf pre-trained TSFMs perform poorly in zero-shot and fine-tuning settings, whereas models pre-trained from scratch on financial data achieve substantial forecasting and economic improvements, underscoring the value of domain-specific adaptation. Increasing the dataset size, incorporating synthetic data augmentation, and applying hyperparameter tuning further enhance performance. --- ### SAMBA: Toward a Long-Context EEG Foundation Model via Spatial Embedding and Differential Mamba Authors: Jiazhen Hong, Geoffrey Mackellar, Soheila Ghane Published: 2025-11-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18571v1 Long-sequence electroencephalogram (EEG) modeling is essential for developing generalizable EEG representation models. This need arises from the high sampling rate of EEG data and the long recording durations required to capture extended neurological patterns in brain activity. Transformer-based models have shown promise in modeling short sequences of a few seconds; however, their quadratic complexity limits scalability to longer contexts. Moreover, variability in electrode montage across available datasets, along with inter-subject differences in brain signals, pose significant challenges to developing a generalizable and robust foundation model. We propose \textit{SAMBA}, a self-supervised learning framework with a Mamba-based U-shaped encoder-decoder architecture, which effectively captures long-range temporal dependencies and spatial variability in EEG data. Leveraging the inherent ability of Mamba in processing long context sizes, we introduce: (1) \textit{Temporal Semantic Random Masking} for semantic-level sequence reconstruction, (2) a \textit{Multi-Head Differential Mamba} module to suppress redundancy and emphasize salient temporal structures, and (3) a \textit{Spatial-Adaptive Input Embedding} that learns unified embeddings in a three-dimensional Euclidean space, enabling robustness across devices. Experiments on thirteen EEG datasets across diverse tasks, electrode configurations, and sequence durations demonstrate that SAMBA consistently outperforms state-of-the-art methods while maintaining low memory consumption and inference time. We also show the learned spatial weight maps from our embedding module align closely with task-relevant neurophysiological regions, demonstrating the learnability and interpretability of SAMBA. These results highlight SAMBA's scalability and practical potential as a foundation model for real-time brain-computer interface applications. --- ### PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation Authors: Samarth Chopra, Jing Liang, Gershom Seneviratne, Dinesh Manocha Published: 2025-11-23 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.18570v1 Understanding physical properties such as friction, stiffness, hardness, and material composition is essential for enabling robots to interact safely and effectively with their surroundings. However, existing 3D reconstruction methods focus on geometry and appearance and cannot infer these underlying physical properties. We present PhysGS, a Bayesian-inferred extension of 3D Gaussian Splatting that estimates dense, per-point physical properties from visual cues and vision--language priors. We formulate property estimation as Bayesian inference over Gaussian splats, where material and property beliefs are iteratively refined as new observations arrive. PhysGS also models aleatoric and epistemic uncertainties, enabling uncertainty-aware object and scene interpretation. Across object-scale (ABO-500), indoor, and outdoor real-world datasets, PhysGS improves accuracy of the mass estimation by up to 22.8%, reduces Shore hardness error by up to 61.2%, and lowers kinetic friction error by up to 18.1% compared to deterministic baselines. Our results demonstrate that PhysGS unifies 3D reconstruction, uncertainty modeling, and physical reasoning in a single, spatially continuous framework for dense physical property estimation. Additional results are available at https://samchopra2003.github.io/physgs. --- ### In Search of Goodness: Large Scale Benchmarking of Goodness Functions for the Forward-Forward Algorithm Authors: Arya Shah, Vaibhav Tripathi Published: 2025-11-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18567v1 The Forward-Forward (FF) algorithm offers a biologically plausible alternative to backpropagation, enabling neural networks to learn through local updates. However, FF's efficacy relies heavily on the definition of "goodness", which is a scalar measure of neural activity. While current implementations predominantly utilize a simple sum-of-squares metric, it remains unclear if this default choice is optimal. To address this, we benchmarked 21 distinct goodness functions across four standard image datasets (MNIST, FashionMNIST, CIFAR-10, STL-10), evaluating classification accuracy, energy consumption, and carbon footprint. We found that certain alternative goodness functions inspired from various domains significantly outperform the standard baseline. Specifically, \texttt{game\_theoretic\_local} achieved 97.15\% accuracy on MNIST, \texttt{softmax\_energy\_margin\_local} reached 82.84\% on FashionMNIST, and \texttt{triplet\_margin\_local} attained 37.69\% on STL-10. Furthermore, we observed substantial variability in computational efficiency, highlighting a critical trade-off between predictive performance and environmental cost. These findings demonstrate that the goodness function is a pivotal hyperparameter in FF design. We release our code on \href{https://github.com/aryashah2k/In-Search-of-Goodness}{Github} for reference and reproducibility. --- ### Ensuring Calibration Robustness in Split Conformal Prediction Under Adversarial Attacks Authors: Xunlei Qian, Yue Xing Published: 2025-11-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.18562v2 Conformal prediction (CP) provides distribution-free, finite-sample coverage guarantees but critically relies on exchangeability, a condition often violated under distribution shift. We study the robustness of split conformal prediction under adversarial perturbations at test time, focusing on both coverage validity and the resulting prediction set size. Our theoretical analysis characterizes how the strength of adversarial perturbations during calibration affects coverage guarantees under adversarial test conditions. We further examine the impact of adversarial training at the model-training stage. Extensive experiments support our theory: (i) Prediction coverage varies monotonically with the calibration-time attack strength, enabling the use of nonzero calibration-time attack to predictably control coverage under adversarial tests; (ii) target coverage can hold over a range of test-time attacks: with a suitable calibration attack, coverage stays within any chosen tolerance band across a contiguous set of perturbation levels; and (iii) adversarial training at the training stage produces tighter prediction sets that retain high informativeness. --- ### C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction Authors: Kuan Wei Huang, Brandon Li, Bharath Hariharan, Noah Snavely Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18559v2 Geometric models like DUSt3R have shown great advances in understanding the geometry of a scene from pairs of photos. However, they fail when the inputs are from vastly different viewpoints (e.g., aerial vs. ground) or modalities (e.g., photos vs. abstract drawings) compared to what was observed during training. This paper addresses a challenging version of this problem: predicting correspondences between ground-level photos and floor plans. Current datasets for joint photo-floor plan reasoning are limited, either lacking in varying modalities (VIGOR) or lacking in correspondences (WAFFLE). To address these limitations, we introduce a new dataset, C3, created by first reconstructing a number of scenes in 3D from Internet photo collections via structure-from-motion, then manually registering the reconstructions to floor plans gathered from the Internet, from which we can derive correspondences between images and floor plans. C3 contains 90K paired floor plans and photos across 597 scenes with 153M pixel-level correspondences and 85K camera poses. We find that state-of-the-art correspondence models struggle on this task. By training on our new data, we can improve on the best performing method by 34% in RMSE. We also use the predicted correspondences to estimate camera poses and evaluate performance using recall metrics. Lastly, we identify open challenges in cross-modal geometric reasoning that our dataset aims to help address. --- ### Dealing with the Hard Facts of Low-Resource African NLP Authors: Yacouba Diarra, Nouhoum Souleymane Coulibaly, Panga Azazia Kamaté, Madani Amadou Tall, Emmanuel Élisé Koné, Aymane Dembélé, Michael Leventhal Published: 2025-11-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18557v1 Creating speech datasets, models, and evaluation frameworks for low-resource languages remains challenging given the lack of a broad base of pertinent experience to draw from. This paper reports on the field collection of 612 hours of spontaneous speech in Bambara, a low-resource West African language; the semi-automated annotation of that dataset with transcriptions; the creation of several monolingual ultra-compact and small models using the dataset; and the automatic and human evaluation of their output. We offer practical suggestions for data collection protocols, annotation, and model design, as well as evidence for the importance of performing human evaluation. In addition to the main dataset, multiple evaluation datasets, models, and code are made publicly available. --- ### A joint optimization approach to identifying sparse dynamics using least squares kernel collocation Authors: Alexander W. Hsu, Ike Griss Salas, Jacob M. Stevens-Haas, J. Nathan Kutz, Aleksandr Aravkin, Bamdad Hosseini Published: 2025-11-23 Categories: stat.ME, cs.LG, math.DS, stat.ML arXiv: https://arxiv.org/abs/2511.18555v2 We develop an all-at-once modeling framework for learning systems of ordinary differential equations (ODE) from scarce, partial, and noisy observations of the states. The proposed methodology amounts to a combination of sparse recovery strategies for the ODE over a function library combined with techniques from reproducing kernel Hilbert space (RKHS) theory for estimating the state and discretizing the ODE. Our numerical experiments reveal that the proposed strategy leads to significant gains in terms of accuracy, sample efficiency, and robustness to noise, both in terms of learning the equation and estimating the unknown states. This work demonstrates capabilities well beyond existing and widely used algorithms while extending the modeling flexibility of other recent developments in equation discovery. --- ### Online Smoothed Demand Management Authors: Adam Lechowicz, Nicolas Christianson, Mohammad Hajiesmaili, Adam Wierman, Prashant Shenoy Published: 2025-11-23 Categories: cs.DS, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2511.18554v2 We introduce and study a class of online problems called online smoothed demand management $(\texttt{OSDM})$, motivated by paradigm shifts in grid integration and energy storage for large energy consumers such as data centers. In $\texttt{OSDM}$, an operator makes two decisions at each time step: an amount of energy to be purchased, and an amount of energy to be delivered (i.e., used for computation). The difference between these decisions charges (or discharges) the operator's energy storage (e.g., a battery). Two types of demand arrive online: base demand, which must be covered at the current time, and flexible demand, which can be satisfied at any time before a demand-specific deadline $Δ_t$. The operator's goal is to minimize a cost (subject to above constraints) that combines a cost of purchasing energy, a cost for delivering energy (if applicable), and smoothness penalties on the purchasing and delivery rates to discourage fluctuations and encourage ``grid healthy'' decisions. $\texttt{OSDM}$ generalizes several problems in the online algorithms literature while being the first to fully model applications of interest. We propose a competitive algorithm for $\texttt{OSDM}$ called $\texttt{PAAD}$ (partitioned accounting & aggregated decisions) and show it achieves the optimal competitive ratio. To overcome the pessimism typical of worst-case analysis, we also propose a novel learning framework that provides guarantees on the worst-case competitive ratio (i.e., to provide robustness against nonstationarity) while allowing end-to-end differentiable learning of the best algorithm on historical instances of the problem. We evaluate our algorithms in a case study of a grid-integrated data center with battery storage, showing that $\texttt{PAAD}$ effectively solves the problem and end-to-end learning achieves substantial performance improvements compared to $\texttt{PAAD}$. --- ### Matching correlated VAR time series Authors: Ernesto Araya, Hemant Tyagi Published: 2025-11-23 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2511.18553v2 We study the problem of matching correlated VAR time series databases, where a multivariate time series is observed along with a perturbed and permuted version, and the goal is to recover the unknown matching between them. To model this, we introduce a probabilistic framework in which two time series $(x_t)_{t\in(T)},(x^\#_t)_{t\in(T)}$ are jointly generated, such that $x^\#_t=x_{π^*(t)}+σ\tilde{x}_{π^*(t)}$, where $(x_t)_{t\in(T)},(\tilde{x}_t)_{t\in(T)}$ are independent and identically distributed vector autoregressive (VAR) time series of order $1$ with Gaussian increments, for a hidden $π^*$. The objective is to recover $π^*$, from the observation of $(x_t)_{t\in(T)},(x^\#_t)_{t\in(T)}$. This generalizes the classical problem of matching independent point clouds to the time series setting. We derive the maximum likelihood estimator (MLE), leading to a quadratic optimization over permutations, and theoretically analyze an estimator based on linear assignment. For the latter approach, we establish recovery guarantees, identifying thresholds for $σ$ that allow for perfect or partial recovery. Additionally, we propose solving the MLE by considering convex relaxations of the set of permutation matrices (e.g., over the Birkhoff polytope). This allows for efficient estimation of $π^*$ and the VAR parameters via alternating minimization. Empirically, we find that linear assignment often matches or outperforms MLE relaxation based approaches. --- ### Robust Inference Methods for Latent Group Panel Models under Possible Group Non-Separation Authors: Oguzhan Akgun, Ryo Okui Published: 2025-11-23 Categories: econ.EM, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2511.18550v2 We develop robust inference methods for general linear hypotheses in linear panel data models with latent group structure in the coefficients. We employ a selective conditional inference approach based on the conditional distribution of coefficient estimates given the group structure estimated from the data. The resulting inference procedures remain valid even when group separation fails (i.e., when the distributional properties of the group-specific coefficients are not established) and, because they account for uncertainty in estimating the group structure, they also improve on conventional asymptotic procedures in finite samples when separation does hold. Our tests are exactly valid under Gaussian errors with known variances and asymptotically valid under general error distributions. Unlike much of the post-clustering inference literature, which focuses on testing group homogeneity, our framework accommodates arbitrary linear restrictions on the group-specific coefficients. Inverting the conditional tests yields selective confidence sets with valid coverage conditional on the estimated group structure. We illustrate the methods through Monte Carlo simulations and an application to growth convergence clubs. Simulations demonstrate accurate size control and good power in finite samples, including in the presence of serial correlation and cross-sectional dependence. The applications show sharp differences between the traditional inference methods and robust methods proposed in this paper, illustrating the importance of taking the estimated group structure into account. --- ### TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting Authors: Lingyu Jiang, Lingyu Xu, Peiran Li, Dengzhe Hou, Qianwen Ge, Dingyi Zhuang, Shuo Xing, Wenjing Chen, Xiangbo Gao, Ting-Hsuan Chen, Xueying Zhan, Xin Zhang et al. Published: 2025-11-23 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.18539v3 We propose TimePre, a simple framework that unifies the efficiency of Multilayer Perceptron (MLP)-based models with the distributional flexibility of Multiple Choice Learning (MCL) for Probabilistic Time-Series Forecasting (PTSF). Stabilized Instance Normalization (SIN), the core of TimePre, is a normalization layer that explicitly addresses the trade-off among accuracy, efficiency, and stability. SIN stabilizes the hybrid architecture by correcting channel-wise statistical shifts, thereby resolving the catastrophic hypothesis collapse. Extensive experiments on six benchmark datasets demonstrate that TimePre achieves state-of-the-art (SOTA) accuracy on key probabilistic metrics. Critically, TimePre achieves inference speeds that are orders of magnitude faster than sampling-based models, and is more stable than prior MCL approaches. --- ### From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence Authors: Jian Yang, Xianglong Liu, Weifeng Lv, Ken Deng, Shawn Guo, Lin Jing, Yizhi Li, Shark Liu, Xianzhen Luo, Yuyu Luo, Changzai Pan, Ensheng Shi et al. Published: 2025-11-23 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2511.18538v5 Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, driving commercial adoption through tools like Github Copilot (Microsoft), Cursor (Anysphere), Trae (ByteDance), and Claude Code (Anthropic). While the field has evolved dramatically from rule-based systems to Transformer-based architectures, achieving performance improvements from single-digit to over 95\% success rates on benchmarks like HumanEval. In this work, we provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs, systematically examining the complete model life cycle from data curation to post-training through advanced prompting paradigms, code pre-training, supervised fine-tuning, reinforcement learning, and autonomous coding agents. We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder), critically examining the techniques, design decisions, and trade-offs. Further, we articulate the research-practice gap between academic research (e.g., benchmarks and tasks) and real-world deployment (e.g., software-related code tasks), including code correctness, security, contextual awareness of large codebases, and integration with development workflows, and map promising research directions to practical needs. Last, we conduct a series of experiments to provide a comprehensive analysis of code pre-training, supervised fine-tuning, and reinforcement learning, covering scaling law, framework selection, hyperparameter sensitivity, model architectures, and dataset comparisons. --- ### Zero-Shot Video Deraining with Video Diffusion Models Authors: Tuomas Varanka, Juan Luis Gonzalez, Hyeongwoo Kim, Pablo Garrido, Xu Yao Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18537v2 Existing video deraining methods are often trained on paired datasets, either synthetic, which limits their ability to generalize to real-world rain, or captured by static cameras, which restricts their effectiveness in dynamic scenes with background and camera motion. Furthermore, recent works in fine-tuning diffusion models have shown promising results, but the fine-tuning tends to weaken the generative prior, limiting generalization to unseen cases. In this paper, we introduce the first zero-shot video deraining method for complex dynamic scenes that does not require synthetic data nor model fine-tuning, by leveraging a pretrained text-to-video diffusion model that demonstrates strong generalization capabilities. By inverting an input video into the latent space of diffusion models, its reconstruction process can be intervened and pushed away from the model's concept of rain using negative prompting. At the core of our approach is an attention switching mechanism that we found is crucial for maintaining dynamic backgrounds as well as structural consistency between the input and the derained video, mitigating artifacts introduced by naive negative prompting. Our approach is validated through extensive experiments on real-world rain datasets, demonstrating substantial improvements over prior methods and showcasing robust generalization without the need for supervised training. --- ### HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction Authors: Pengcheng Fang, Hongli Chen, Guangzhen Yao, Jian Shi, Fangfang Tang, Xiaohao Cai, Shanshan Shan, Feng Liu Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18534v1 Reconstructing high-fidelity MR images from undersampled k-space data requires recovering high-frequency details while maintaining anatomical coherence. We present HiFi-MambaV2, a hierarchical shared-routed Mixture-of-Experts (MoE) Mamba architecture that couples frequency decomposition with content-adaptive computation. The model comprises two core components: (i) a separable frequency-consistent Laplacian pyramid (SF-Lap) that delivers alias-resistant, stable low- and high-frequency streams; and (ii) a hierarchical shared-routed MoE that performs per-pixel top-1 sparse dispatch to shared experts and local routers, enabling effective specialization with stable cross-depth behavior. A lightweight global context path is fused into an unrolled, data-consistency-regularized backbone to reinforce long-range reasoning and preserve anatomical coherence. Evaluated on fastMRI, CC359, ACDC, M4Raw, and Prostate158, HiFi-MambaV2 consistently outperforms CNN-, Transformer-, and prior Mamba-based baselines in PSNR, SSIM, and NMSE across single- and multi-coil settings and multiple acceleration factors, consistently surpassing consistent improvements in high-frequency detail and overall structural fidelity. These results demonstrate that HiFi-MambaV2 enables reliable and robust MRI reconstruction. --- ### DE-KAN: A Kolmogorov Arnold Network with Dual Encoder for accurate 2D Teeth Segmentation Authors: Md Mizanur Rahman Mustakim, Jianwu Li, Sumya Bhuiyan, Mohammad Mehedi Hasan, Bing Han Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18533v2 Accurate segmentation of individual teeth from panoramic radiographs remains a challenging task due to anatomical variations, irregular tooth shapes, and overlapping structures. These complexities often limit the performance of conventional deep learning models. To address this, we propose DE-KAN, a novel Dual Encoder Kolmogorov Arnold Network, which enhances feature representation and segmentation precision. The framework employs a ResNet-18 encoder for augmented inputs and a customized CNN encoder for original inputs, enabling the complementary extraction of global and local spatial features. These features are fused through KAN-based bottleneck layers, incorporating nonlinear learnable activation functions derived from the Kolmogorov Arnold representation theorem to improve learning capacity and interpretability. Extensive experiments on two benchmark dental X-ray datasets demonstrate that DE-KAN outperforms state-of-the-art segmentation models, achieving mIoU of 94.5%, Dice coefficient of 97.1%, accuracy of 98.91%, and recall of 97.36%, representing up to +4.7% improvement in Dice compared to existing methods. --- ### Transforming Conditional Density Estimation Into a Single Nonparametric Regression Task Authors: Alexander G. Reisach, Olivier Collier, Alex Luedtke, Antoine Chambaz Published: 2025-11-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.18530v1 We propose a way of transforming the problem of conditional density estimation into a single nonparametric regression task via the introduction of auxiliary samples. This allows leveraging regression methods that work well in high dimensions, such as neural networks and decision trees. Our main theoretical result characterizes and establishes the convergence of our estimator to the true conditional density in the data limit. We develop condensité, a method that implements this approach. We demonstrate the benefit of the auxiliary samples on synthetic data and showcase that condensité can achieve good out-of-the-box results. We evaluate our method on a large population survey dataset and on a satellite imaging dataset. In both cases, we find that condensité matches or outperforms the state of the art and yields conditional densities in line with established findings in the literature on each dataset. Our contribution opens up new possibilities for regression-based conditional density estimation and the empirical results indicate strong promise for applied research. --- ### Splatblox: Traversability-Aware Gaussian Splatting for Outdoor Robot Navigation Authors: Samarth Chopra, Jing Liang, Gershom Seneviratne, Yonghan Lee, Jaehoon Choi, Jianyu An, Stephen Cheng, Dinesh Manocha Published: 2025-11-23 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.18525v2 We present Splatblox, a real-time system for autonomous navigation in outdoor environments with dense vegetation, irregular obstacles, and complex terrain. Our method fuses segmented RGB images and LiDAR point clouds using Gaussian Splatting to construct a traversability-aware Euclidean Signed Distance Field (ESDF) that jointly encodes geometry and semantics. Updated online, this field enables semantic reasoning to distinguish traversable vegetation (e.g., tall grass) from rigid obstacles (e.g., trees), while LiDAR ensures 360-degree geometric coverage for extended planning horizons. We validate Splatblox on a quadruped robot and demonstrate transfer to a wheeled platform. In field trials across vegetation-rich scenarios, it outperforms state-of-the-art methods with over 50% higher success rate, 40% fewer freezing incidents, 5% shorter paths, and up to 13% faster time to goal, while supporting long-range missions up to 100 meters. Experiment videos and more details can be found on our project page: https://splatblox.github.io --- ### Hyperspectral Variational Autoencoders for Joint Data Compression and Component Extraction Authors: Core Francisco Park, Manuel Perez-Carrasco, Caroline Nowlan, Cecilia Garraffo Published: 2025-11-23 Categories: cs.LG, astro-ph.EP, astro-ph.IM arXiv: https://arxiv.org/abs/2511.18521v1 Geostationary hyperspectral satellites generate terabytes of data daily, creating critical challenges for storage, transmission, and distribution to the scientific community. We present a variational autoencoder (VAE) approach that achieves x514 compression of NASA's TEMPO satellite hyperspectral observations (1028 channels, 290-490nm) with reconstruction errors 1-2 orders of magnitude below the signal across all wavelengths. This dramatic data volume reduction enables efficient archival and sharing of satellite observations while preserving spectral fidelity. Beyond compression, we investigate to what extent atmospheric information is retained in the compressed latent space by training linear and nonlinear probes to extract Level-2 products (NO2, O3, HCHO, cloud fraction). Cloud fraction and total ozone achieve strong extraction performance (R^2 = 0.93 and 0.81 respectively), though these represent relatively straightforward retrievals given their distinct spectral signatures. In contrast, tropospheric trace gases pose genuine challenges for extraction (NO2 R^2 = 0.20, HCHO R^2 = 0.51) reflecting their weaker signals and complex atmospheric interactions. Critically, we find the VAE encodes atmospheric information in a semi-linear manner - nonlinear probes substantially outperform linear ones - and that explicit latent supervision during training provides minimal improvement, revealing fundamental encoding challenges for certain products. This work demonstrates that neural compression can dramatically reduce hyperspectral data volumes while preserving key atmospheric signals, addressing a critical bottleneck for next-generation Earth observation systems. Code - https://github.com/cfpark00/Hyperspectral-VAE --- ### CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection Authors: Xinlin Zhuang, Yichen Li, Xiwei Liu, Haolin Yang, Yifan Lu, Ziyun Zou, Yulong Li, Huifa Li, Dongliang Chen, Qinglei Wang, Weiyang Liu, Ying Qian et al. Published: 2025-11-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18519v2 Adapting CLIP to vertical domains is typically approached by novel fine-tuning strategies or by continual pre-training (CPT) on large domain-specific datasets. Yet, data itself remains an underexplored factor in this process. We revisit this task from a data-centric perspective: Can effective data selection substitute for large-scale datasets in CPT? We introduce CHIPS (Curvature-aware Hybrid Influence in Projection Subspace), which assigns each image-text pair a utility score that integrates three complementary factors aligned with three goals: faithfulness via a curvature-aware and Newton-style alignment computed in CLIP's end-point subspace; scalability via an InfoNCE-aware curvature estimator with Johnson-Lindenstrauss (JL) sketching; and retention via a selection-aware relevance weight combined with learnability to balance target adaptation against general-domain preservation. We justify this design theoretically by proving a lower-bound guarantee on the proxy's correlation with full-parameter alignment and by characterizing the bias-variance trade-offs introduced by curvature mixing and JL sketching. We evaluate CHIPS empirically across various settings: 1) CHIPS attains state-of-the-art performance among selection baselines on 17 medical benchmarks, matches full-dataset CPT with 30% of the data, and outperforms half-dataset CPT using only 10%; 2) on 31 general-domain benchmarks, CHIPS yields the least performance drop under all retention ratios. --- ### Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI Authors: Khanh Gia Bui Published: 2025-11-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18517v1 Within the limited scope of this paper, we argue that artificial general intelligence cannot emerge from current neural network paradigms regardless of scale, nor is such an approach healthy for the field at present. Drawing on various notions, discussions, present-day developments and observations, current debates and critiques, experiments, and so on in between philosophy, including the Chinese Room Argument and Gödelian argument, neuroscientific ideas, computer science, the theoretical consideration of artificial intelligence, and learning theory, we address conceptually that neural networks are architecturally insufficient for genuine understanding. They operate as static function approximators of a limited encoding framework - a 'sophisticated sponge' exhibiting complex behaviours without structural richness that constitute intelligence. We critique the theoretical foundations the field relies on and created of recent times; for example, an interesting heuristic as neural scaling law (as an example, arXiv:2001.08361 ) made prominent in a wrong way of interpretation, The Universal Approximation Theorem addresses the wrong level of abstraction and, in parts, partially, the question of current architectures lacking dynamic restructuring capabilities. We propose a framework distinguishing existential facilities (computational substrate) from architectural organization (interpretive structures), and outline principles for what genuine machine intelligence would require, and furthermore, a conceptual method of structuralizing the richer framework on which the principle of neural network system takes hold. --- ### Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusion Authors: Haidong Kang, Ketong Qian, Yi Lu Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18516v1 Efforts to overcome catastrophic forgetting in Few-Shot Class-Incremental Learning (FSCIL) have primarily focused on developing more effective gradient-based optimization strategies. In contrast, little attention has been paid to the training cost explosion that inevitably arises as the number of novel classes increases, a consequence of relying on gradient learning even under extreme data scarcity. More critically, since FSCIL typically provides only a few samples for each new class, gradient-based updates not only induce severe catastrophic forgetting on base classes but also hinder adaptation to novel ones. This paper seeks to break this long-standing limitation by asking: Can we design a training-free FSCIL paradigm that entirely removes gradient optimization? We provide an affirmative answer by uncovering an intriguing connection between gradient-based optimization and the Conditional Diffusion process. Building on this observation, we propose a Conditional Diffusion-driven FSCIL (CD-FSCIL) framework that substitutes the conventional gradient update process with a diffusion-based generative transition, enabling training-free incremental adaptation while effectively mitigating forgetting. Furthermore, to enhance representation under few-shot constraints, we introduce a multimodal learning strategy that integrates visual features with natural language descriptions automatically generated by Large Language Models (LLMs). This synergy substantially alleviates the sample scarcity issue and improves generalization across novel classes. Extensive experiments on mainstream FSCIL benchmarks demonstrate that our method not only achieves state-of-the-art performance but also drastically reduces computational and memory overhead, marking a paradigm shift toward training-free continual adaptation. --- ### RRaPINNs: Residual Risk-Aware Physics Informed Neural Networks Authors: Ange-Clément Akazan, Issa Karambal, Jean Medard Ngnotchouye, Abebe Geletu Selassie. W Published: 2025-11-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18515v1 Physics-informed neural networks (PINNs) typically minimize average residuals, which can conceal large, localized errors. We propose Residual Risk-Aware Physics-Informed Neural Networks PINNs (RRaPINNs), a single-network framework that optimizes tail-focused objectives using Conditional Value-at-Risk (CVaR), we also introduced a Mean-Excess (ME) surrogate penalty to directly control worst-case PDE residuals. This casts PINN training as risk-sensitive optimization and links it to chance-constrained formulations. The method is effective and simple to implement. Across several partial differential equations (PDEs) such as Burgers, Heat, Korteweg-de-Vries, and Poisson (including a Poisson interface problem with a source jump at x=0.5) equations, RRaPINNs reduce tail residuals while maintaining or improving mean errors compared to vanilla PINNs, Residual-Based Attention and its variant using convolution weighting; the ME surrogate yields smoother optimization than a direct CVaR hinge. The chance constraint reliability level $α$ acts as a transparent knob trading bulk accuracy (lower $α$ ) for stricter tail control (higher $α$ ). We discuss the framework limitations, including memoryless sampling, global-only tail budgeting, and residual-centric risk, and outline remedies via persistent hard-point replay, local risk budgets, and multi-objective risk over BC/IC terms. RRaPINNs offer a practical path to reliability-aware scientific ML for both smooth and discontinuous PDEs. --- ### Unified Deep Learning Platform for Dust and Fault Diagnosis in Solar Panels Using Thermal and Visual Imaging Authors: Abishek Karthik, Sreya Mynampati, Pandiyaraju V Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18514v1 Solar energy is one of the most abundant and tapped sources of renewable energies with enormous future potential. Solar panel output can vary widely with factors like intensity, temperature, dirt, debris and so on affecting it. We have implemented a model on detecting dust and fault on solar panels. These two applications are centralized as a single-platform and can be utilized for routine-maintenance and any other checks. These are checked against various parameters such as power output, sinusoidal wave (I-V component of solar cell), voltage across each solar cell and others. Firstly, we filter and preprocess the obtained images using gamma removal and Gaussian filtering methods alongside some predefined processes like normalization. The first application is to detect whether a solar cell is dusty or not based on various pre-determined metrics like shadowing, leaf, droppings, air pollution and from other human activities to extent of fine-granular solar modules. The other one is detecting faults and other such occurrences on solar panels like faults, cracks, cell malfunction using thermal imaging application. This centralized platform can be vital since solar panels have different efficiency across different geography (air and heat affect) and can also be utilized for small-scale house requirements to large-scale solar farm sustentation effectively. It incorporates CNN, ResNet models that with self-attention mechanisms-KerNet model which are used for classification and results in a fine-tuned system that detects dust or any fault occurring. Thus, this multi-application model proves to be efficient and optimized in detecting dust and faults on solar panels. We have performed various comparisons and findings that demonstrates that our model has better efficiency and accuracy results overall than existing models. --- ### LRDUN: A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive Imaging Authors: He Huang, Yujun Guo, Wei He Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18513v2 Deep unfolding networks (DUNs) have achieved remarkable success and become the mainstream paradigm for spectral compressive imaging (SCI) reconstruction. Existing DUNs are derived from full-HSI imaging models, where each stage operates directly on the high-dimensional HSI, refining the entire data cube based on the single 2D coded measurement. However, this paradigm leads to computational redundancy and suffers from the ill-posed nature of mapping 2D residuals back to 3D space of HSI. In this paper, we propose two novel imaging models corresponding to the spectral basis and subspace image by explicitly integrating low-rank (LR) decomposition with the sensing model. Compared to recovering the full HSI, estimating these compact low-dimensional components significantly mitigates the ill-posedness. Building upon these novel models, we develop the Low-Rank Deep Unfolding Network (LRDUN), which jointly solves the two subproblems within an unfolded proximal gradient descent (PGD) framework. Furthermore, we introduce a Generalized Feature Unfolding Mechanism (GFUM) that decouples the physical rank in the data-fidelity term from the feature dimensionality in the prior module, enhancing the representational capacity and flexibility of the network. Extensive experiments on simulated and real datasets demonstrate that the proposed LRDUN achieves state-of-the-art (SOTA) reconstruction quality with significantly reduced computational cost. --- ### Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives Authors: Kai Jiang, Siqi Huang, Xiangyu Chen, Jiawei Shao, Hongyuan Zhang, Ping Luo, Xuelong Li Published: 2025-11-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18507v3 Multimodal large language models (MLLMs) deployed on devices must adapt to continuously changing visual scenarios such as variations in background and perspective, to effectively perform complex visual tasks. To investigate catastrophic forgetting under real-world scenario shifts, we construct a multimodal visual understanding dataset (MSVQA), covering four distinct scenarios and perspectives: high-altitude, underwater, low-altitude, and indoor environments. Furthermore, we propose UNIFIER (mUltimodal coNtInual learning with MLLMs From multi-scenarIo pERspectives), a continual learning (CL) framework designed to address visual discrepancies while learning different scenarios. Compared to existing CL methods, UNIFIER enables knowledge accumulation within the same scenario and mutual enhancement across different scenarios via Vision Representation Expansion (VRE) and Vision Consistency Constraint (VCC). Experimental results show that UNIFIER improves the last-step VQA scores by 2.70%~10.62% and the last-step F1 scores by 3.40%~7.69% compared to the state-of-the-art method, QUAD, in 20-step cross-scenario continual learning tasks. MSVQA dataset is available at https://huggingface.co/datasets/Kaij00/MSVQA. --- ### Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives Authors: Kai Jiang, Siqi Huang, Xiangyu Chen, Jiawei Shao, Hongyuan Zhang, Xuelong Li Published: 2025-11-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18507v1 Continual learning in visual understanding aims to deal with catastrophic forgetting in Multimodal Large Language Models (MLLMs). MLLMs deployed on devices have to continuously adapt to dynamic scenarios in downstream tasks, such as variations in background and perspective, to effectively perform complex visual tasks. To this end, we construct a multimodal visual understanding dataset (MSVQA) encompassing four different scenarios and perspectives including high altitude, underwater, low altitude and indoor, to investigate the catastrophic forgetting in MLLMs under the dynamics of scenario shifts in real-world data streams. Furthermore, we propose mUltimodal coNtInual learning with MLLMs From multi-scenarIo pERspectives (UNIFIER) to address visual discrepancies while learning different scenarios. Specifically, it decouples the visual information from different scenarios into distinct branches within each vision block and projects them into the same feature space. A consistency constraint is imposed on the features of each branch to maintain the stability of visual representations across scenarios. Extensive experiments on the MSVQA dataset demonstrate that UNIFIER effectively alleviates forgetting of cross-scenario tasks and achieves knowledge accumulation within the same scenario. --- ### Extreme Model Compression for Edge Vision-Language Models: Sparse Temporal Token Fusion and Adaptive Neural Compression Authors: Md Tasnin Tanvir, Soumitra Das, Sk Md Abidar Rahaman, Ali Shiri Sichani Published: 2025-11-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18504v1 The demand for edge AI in vision-language tasks requires models that achieve real-time performance on resource-constrained devices with limited power and memory. This paper proposes two adaptive compression techniques -- Sparse Temporal Token Fusion (STTF) and Adaptive Neural Compression (ANC) -- that integrate algorithmic innovations with hardware-aware optimizations. Unlike previous approaches relying on static pruning or uniform scaling, STTF dynamically reuses visual tokens through event-driven change detection, while ANC conditionally activates encoder branches via a learned router, enabling fine-grained adaptation to scene complexity. Our 3B-parameter TinyGPT-STTF achieves CIDEr 131.2, BLEU-4 0.38, METEOR 0.31, and ROUGE-L 0.56 on the COCO 2017 test set, surpassing LLaVA-1.5 7B by 17.6 CIDEr points while using 2.3x fewer parameters and 62x fewer on-device FLOPs. TinyGPT-ANC reaches CIDEr 128.5. On event-based vision tasks, STTF reduces average token count by 84% (from 196 to 31 tokens) while preserving 95.6% accuracy on the DVS128 Gesture dataset, and ANC cuts FLOPs by up to 90% in low-motion scenes. Compared to strong baselines, our models improve accuracy by up to 4.4% and reduce latency by up to 13x. These results enable efficient deployment of capable vision-language models on real-world edge devices. --- ### For Those Who May Find Themselves on the Red Team Authors: Tyler Shoemaker Published: 2025-11-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18499v1 This position paper argues that literary scholars must engage with large language model (LLM) interpretability research. While doing so will involve ideological struggle, if not out-right complicity, the necessity of this engagement is clear: the abiding instrumentality of current approaches to interpretability cannot be the only standard by which we measure interpretation with LLMs. One site at which this struggle could take place, I suggest, is the red team. --- ### SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation Authors: Gia Huy Thai, Hoang-Nguyen Vu, Anh-Minh Phan, Quang-Thinh Ly, Tram Dinh, Thi-Ngoc-Truc Nguyen, Nhat Ho Published: 2025-11-23 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.18493v5 The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity. Current CNN-Transformer hybrids use static computation graphs with fixed routing. This leads to extra computation and makes it harder to adapt to changes in input. We propose Shape-Adapting Gated Experts (SAGE), an input-adaptive framework that enables dynamic expert routing in heterogeneous visual networks. SAGE reconfigures static backbones into dynamically routed expert architectures via a dual-path design with hierarchical gating and a Shape-Adapting Hub (SA-Hub) that harmonizes feature representations across convolutional and transformer modules. Embodied as SAGE with ConvNeXt and Vision Transformer UNet (SAGE-ConvNeXt+ViT-UNet), our model achieves a Dice score of 95.23% on EBHI, DSC scores of 92.78% and 91.42% on GlaS Test A and Test B, respectively, and 91.26% DSC at the WSI level on DigestPath, while exhibiting robust generalization under distribution shifts by adaptively balancing local refinement and global context. SAGE establishes a scalable foundation for dynamic expert routing in visual networks, thereby facilitating flexible visual reasoning. Project page: https://oxyzgiahuy.github.io/sage/ --- ### Shape-Adapting Gated Experts: Dynamic Expert Routing for Colonoscopic Lesion Segmentation Authors: Gia Huy Thai, Hoang-Nguyen Vu, Anh-Minh Phan, Quang-Thinh Ly, Tram Dinh, Thi-Ngoc-Truc Nguyen, Nhat Ho Published: 2025-11-23 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.18493v1 The substantial diversity in cell scale and form remains a primary challenge in computer-aided cancer detection on gigapixel Whole Slide Images (WSIs), attributable to cellular heterogeneity. Existing CNN-Transformer hybrids rely on static computation graphs with fixed routing, which consequently causes redundant computation and limits their adaptability to input variability. We propose Shape-Adapting Gated Experts (SAGE), an input-adaptive framework that enables dynamic expert routing in heterogeneous visual networks. SAGE reconfigures static backbones into dynamically routed expert architectures. SAGE's dual-path design features a backbone stream that preserves representation and selectively activates an expert path through hierarchical gating. This gating mechanism operates at multiple hierarchical levels, performing a two-level, hierarchical selection between shared and specialized experts to modulate model logits for Top-K activation. Our Shape-Adapting Hub (SA-Hub) harmonizes structural and semantic representations across the CNN and the Transformer module, effectively bridging diverse modules. Embodied as SAGE-UNet, our model achieves superior segmentation on three medical benchmarks: EBHI, DigestPath, and GlaS, yielding state-of-the-art Dice Scores of 95.57%, 95.16%, and 94.17%, respectively, and robustly generalizes across domains by adaptively balancing local refinement and global context. SAGE provides a scalable foundation for dynamic expert routing, enabling flexible visual reasoning. --- ### MindEval: Benchmarking Language Models on Multi-turn Mental Health Support Authors: José Pombal, Maya D'Eon, Nuno M. Guerreiro, Pedro Henrique Martins, António Farinhas, Ricardo Rei Published: 2025-11-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.18491v3 Demand for mental health support through AI chatbots is surging, though current systems present several limitations, like sycophancy or overvalidation, and reinforcement of maladaptive beliefs. A core obstacle to the creation of better systems is the scarcity of benchmarks that capture the complexity of real therapeutic interactions. Most existing benchmarks either only test clinical knowledge through multiple-choice questions or assess single responses in isolation. To bridge this gap, we present MindEval, a framework designed in collaboration with Ph.D-level Licensed Clinical Psychologists for automatically evaluating language models in realistic, multi-turn mental health therapy conversations. Through patient simulation and automatic evaluation with LLMs, our framework balances resistance to gaming with reproducibility via its fully automated, model-agnostic design. We begin by quantitatively validating the realism of our simulated patients against human-generated text and by demonstrating strong correlations between automatic and human expert judgments. Then, we evaluate 12 state-of-the-art LLMs and show that all models struggle, scoring below 4 out of 6, on average, with particular weaknesses in problematic AI-specific patterns of communication. Notably, reasoning capabilities and model scale do not guarantee better performance, and systems deteriorate with longer interactions or when supporting patients with severe symptoms. We release all code, prompts, and human evaluation data. --- ### MindEval: Benchmarking Language Models on Multi-turn Mental Health Support Authors: José Pombal, Maya D'Eon, Nuno M. Guerreiro, Pedro Henrique Martins, António Farinhas, Ricardo Rei Published: 2025-11-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.18491v1 Demand for mental health support through AI chatbots is surging, though current systems present several limitations, like sycophancy or overvalidation, and reinforcement of maladaptive beliefs. A core obstacle to the creation of better systems is the scarcity of benchmarks that capture the complexity of real therapeutic interactions. Most existing benchmarks either only test clinical knowledge through multiple-choice questions or assess single responses in isolation. To bridge this gap, we present MindEval, a framework designed in collaboration with Ph.D-level Licensed Clinical Psychologists for automatically evaluating language models in realistic, multi-turn mental health therapy conversations. Through patient simulation and automatic evaluation with LLMs, our framework balances resistance to gaming with reproducibility via its fully automated, model-agnostic design. We begin by quantitatively validating the realism of our simulated patients against human-generated text and by demonstrating strong correlations between automatic and human expert judgments. Then, we evaluate 12 state-of-the-art LLMs and show that all models struggle, scoring below 4 out of 6, on average, with particular weaknesses in problematic AI-specific patterns of communication. Notably, reasoning capabilities and model scale do not guarantee better performance, and systems deteriorate with longer interactions or when supporting patients with severe symptoms. We release all code, prompts, and human evaluation data. --- ### Real-Time Personalized Content Adaptation through Matrix Factorization and Context-Aware Federated Learning Authors: Sai Puppala, Ismail Hossain, Md Jahangir Alam, Sajedul Talukder Published: 2025-11-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18489v1 Our study presents a multifaceted approach to enhancing user interaction and content relevance in social media platforms through a federated learning framework. We introduce personalized LLM Federated Learning and Context-based Social Media models. In our framework, multiple client entities receive a foundational GPT model, which is fine-tuned using locally collected social media data while ensuring data privacy through federated aggregation. Key modules focus on categorizing user-generated content, computing user persona scores, and identifying relevant posts from friends networks. By integrating a sophisticated social engagement quantification method with matrix factorization techniques, our system delivers real-time personalized content suggestions tailored to individual preferences. Furthermore, an adaptive feedback loop, alongside a robust readability scoring algorithm, significantly enhances the quality and relevance of the content presented to users. This comprehensive solution not only addresses the challenges of content filtering and recommendation but also fosters a more engaging social media experience while safeguarding user privacy, setting a new standard for personalized interactions in digital platforms. --- ### Evaluating perturbation robustness of generative systems that use COBOL code inputs Authors: Samuel Ackerman, Wesam Ibraheem, Orna Raz, Marcel Zalmanovici Published: 2025-11-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.18488v2 Systems incorporating large language models (LLMs) as a component are known to be sensitive (i.e., non-robust) to minor input variations that do not change the meaning of the input; such sensitivity may reduce the system's usefulness. Here, we present a framework to evaluate robustness of systems using COBOL code as input; our application is translation between COBOL and Java programming languages, but the approach extends to other tasks such as code generation or explanation. Targeting robustness of systems with COBOL as input is essential yet challenging. Many business-critical applications are written in COBOL, yet these are typically proprietary legacy applications and their code is unavailable to LLMs for training. We develop a library of COBOL paragraph and full-program perturbation methods, and create variant-expanded versions of a benchmark dataset of examples for a specific task. The robustness of the LLM-based system is evaluated by measuring changes in values of individual and aggregate metrics calculated on the system's outputs. Finally, we present a series of dynamic table and chart visualization dashboards that assist in debugging the system's outputs, and monitoring and understanding root causes of the system's sensitivity to input variation. These tools can be further used to improve the system by, for instance, indicating variations that should be handled by pre-processing steps. ---