# Research Papers — 2025-12 · bundle page 92 of 175

> Full-text markdown of papers #4551–4600 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-12/page/92
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/91.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/93.md)

### DualHNIE: Dual-Channel Hypergraph Learning for Node Importance Estimation in Heterogeneous Knowledge Graphs

Authors: Jiawen Chen, Yanyan He, Qi Shao, Mengli Wei, Duxin Chen, Wenwu Yu, Yanlong Zhao
Published: 2025-12-13
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.12477v3

Estimating node importance in heterogeneous knowledge graphs is a fundamental problem underlying recommendation, search, and knowledge decision systems. However, most existing methods rely on pairwise message passing mechanisms that fail to capture higher-order interactions induced by meta-relational structures. Furthermore, structural topology and semantic attributes are typically entangled within a unified embedding space, which obscures their distinct inductive biases and limits the discriminative capacity of learned importance representations. To address these limitations, we propose DualHNIE, a principled dual-channel hypergraph learning framework for node importance estimation. DualHNIE first constructs a higher-order knowledge graph by forming typed hyperedges from meta-path sequences, enabling explicit modeling of higher-order relational patterns. It then introduces two complementary encoders: a structure-aware hypergraph attention network that performs locally normalized aggregation over meta-path--induced hyperedges to capture localized structural dependencies, and a sparse--chunked hypergraph transformer that captures global semantic interactions while maintaining scalable computation. We further design a contrastive alignment mechanism with auxiliary supervision, ensuring cross-view consistency while preserving modality-specific representation. Extensive experiments on multiple benchmark datasets demonstrate that DualHNIE outperforms state-of-the-art methods, validating the effectiveness of explicit high-order modeling and disentangled dual-channel representation learning for heterogeneous knowledge graphs. Code and datasets are available\footnote(1){https://github.com/jiawenchen10/DualHNIE}.

---

### AI-Driven Real-Time Kick Classification in Olympic Taekwondo Using Sensor Fusion

Authors: Jamsheed Mistri
Published: 2025-12-13
Categories: eess.SY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.12474v1

Olympic Taekwondo has faced challenges in spectator engagement due to static, defensive gameplay and contentious scoring. Current Protector and Scoring Systems (PSS) rely on impact sensors and simplistic logic, encouraging safe strategies that diminish the sport's dynamism. This paper proposes an AI-powered scoring system that integrates existing PSS sensors with additional accelerometers, gyroscopes, magnetic/RFID, and impact force sensors in a sensor fusion framework. The system classifies kicks in real-time to identify technique type, contact location, impact force, and even the part of the foot used. A machine learning pipeline employing sensor fusion and Support Vector Machines (SVMs) is detailed, enabling automatic kick technique recognition for scoring. We present a novel kick scoring rubric that awards points based on specific kick techniques (e.g., turning and spinning kicks) to incentivize dynamic attacks. Drawing on a 2024 study achieving 96-98% accuracy, we validate the feasibility of real-time kick classification and further propose enhancements to this methodology, such as ensemble SVM classifiers and expanded datasets, to achieve the high-stakes accuracy required by the sport. We analyze how the proposed system can improve scoring fairness, reduce rule exploitation and illegitimate tactics, encourage more dynamic techniques, and enhance spectator understanding and excitement. The paper includes system design illustrations, a kick scoring table from an AI-augmented rule set, and discusses anticipated impacts on Olympic Taekwondo.

---

### Sparse Concept Anchoring for Interpretable and Controllable Neural Representations

Authors: Sandy Fraser, Patryk Wielopolski
Published: 2025-12-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12469v3

We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing others to self-organize, using only minimal supervision (labels for <0.1% of examples per anchored concept). Training combines activation normalization, a separation regularizer, and anchor or subspace regularizers that attract rare labeled examples to predefined directions or axis-aligned subspaces. The anchored geometry enables two practical interventions: reversible behavioral steering that projects out a concept's latent component at inference, and permanent removal via targeted weight ablation of anchored dimensions. Experiments on structured autoencoders show selective attenuation of targeted concepts with negligible impact on orthogonal features, and complete elimination with reconstruction error approaching theoretical bounds. Sparse Concept Anchoring therefore provides a practical pathway to interpretable, steerable behavior in learned representations.

---

### Exploring the Design Space of Transition Matching

Authors: Uriel Singer, Yaron Lipman
Published: 2025-12-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.12465v1

Transition Matching (TM) is an emerging paradigm for generative modeling that generalizes diffusion and flow-matching models as well as continuous-state autoregressive models. TM, similar to previous paradigms, gradually transforms noise samples to data samples, however it uses a second ``internal'' generative model to implement the transition steps, making the transitions more expressive compared to diffusion and flow models. To make this paradigm tractable, TM employs a large backbone network and a smaller "head" module to efficiently execute the generative transition step. In this work, we present a large-scale, systematic investigation into the design, training and sampling of the head in TM frameworks, focusing on its time-continuous bidirectional variant. Through comprehensive ablations and experimentation involving training 56 different 1.7B text-to-image models (resulting in 549 unique evaluations) we evaluate the affect of the head module architecture and modeling during training as-well as a useful family of stochastic TM samplers. We analyze the impact on generation quality, training, and inference efficiency. We find that TM with an MLP head, trained with a particular time weighting and sampled with high frequency sampler provides best ranking across all metrics reaching state-of-the-art among all tested baselines, while Transformer head with sequence scaling and low frequency sampling is a runner up excelling at image aesthetics. Lastly, we believe the experiments presented highlight the design aspects that are likely to provide most quality and efficiency gains, while at the same time indicate what design choices are not likely to provide further gains.

---

### Understanding Overparametrization in Survival Models through Interpolation

Authors: Yin Liu, Jianwen Cai, Didong Li
Published: 2025-12-13
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2512.12463v3

Classical statistical learning theory predicts a U-shaped relationship between test loss and model capacity, driven by the bias-variance trade-off. Recent advances in modern machine learning have revealed a more complex pattern, double-descent, in which test loss, after peaking near the interpolation threshold, decreases again as model capacity continues to grow. While this behavior has been extensively analyzed in regression and classification, its manifestation in survival analysis remains unexplored. This study investigates overparametrization in four representative survival models: DeepSurv, PC-Hazard, Nnet-Survival, and N-MTLR. We rigorously define interpolation and finite-norm interpolation, two key characteristics of loss-based models to understand double-descent. We then show the existence (or absence) of (finite-norm) interpolation of all four models. Our findings clarify how likelihood-based losses and model implementation jointly determine the feasibility of interpolation and show that overparametrization should not be regarded as benign for survival models. All theoretical results are supported by numerical experiments that highlight the distinct generalization behaviors of survival models.

---

### Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference

Authors: Eray Erturk, Maryam M. Shanechi
Published: 2025-12-13
Categories: cs.LG, cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2512.12462v1

Real-time decoding of target variables from multiple simultaneously recorded neural time-series modalities, such as discrete spiking activity and continuous field potentials, is important across various neuroscience applications. However, a major challenge for doing so is that different neural modalities can have different timescales (i.e., sampling rates) and different probabilistic distributions, or can even be missing at some time-steps. Existing nonlinear models of multimodal neural activity do not address different timescales or missing samples across modalities. Further, some of these models do not allow for real-time decoding. Here, we develop a learning framework that can enable real-time recursive decoding while nonlinearly aggregating information across multiple modalities with different timescales and distributions and with missing samples. This framework consists of 1) a multiscale encoder that nonlinearly aggregates information after learning within-modality dynamics to handle different timescales and missing samples in real time, 2) a multiscale dynamical backbone that extracts multimodal temporal dynamics and enables real-time recursive decoding, and 3) modality-specific decoders to account for different probabilistic distributions across modalities. In both simulations and three distinct multiscale brain datasets, we show that our model can aggregate information across modalities with different timescales and distributions and missing samples to improve real-time target decoding. Further, our method outperforms various linear and nonlinear multimodal benchmarks in doing so.

---

### Cross-Modal Representational Knowledge Distillation for Enhanced Spike-Informed LFP Modeling

Authors: Eray Erturk, Saba Hashemi, Maryam M. Shanechi
Published: 2025-12-13
Categories: cs.LG, cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2512.12461v1

Local field potentials (LFPs) can be routinely recorded alongside spiking activity in intracortical neural experiments, measure a larger complementary spatiotemporal scale of brain activity for scientific inquiry, and can offer practical advantages over spikes, including greater long-term stability, robustness to electrode degradation, and lower power requirements. Despite these advantages, recent neural modeling frameworks have largely focused on spiking activity since LFP signals pose inherent modeling challenges due to their aggregate, population-level nature, often leading to lower predictive power for downstream task variables such as motor behavior. To address this challenge, we introduce a cross-modal knowledge distillation framework that transfers high-fidelity representational knowledge from pretrained multi-session spike transformer models to LFP transformer models. Specifically, we first train a teacher spike model across multiple recording sessions using a masked autoencoding objective with a session-specific neural tokenization strategy. We then align the latent representations of the student LFP model to those of the teacher spike model. Our results show that the Distilled LFP models consistently outperform single- and multi-session LFP baselines in both fully unsupervised and supervised settings, and can generalize to other sessions without additional distillation while maintaining superior performance. These findings demonstrate that cross-modal knowledge distillation is a powerful and scalable approach for leveraging high-performing spike models to develop more accurate LFP models.

---

### From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fields

Authors: Jiachen Tao, Benjamin Planche, Van Nguyen Nguyen, Junyi Wu, Yuchun Liu, Haoxuan Wang, Zhongpai Gao, Gengyu Zhang, Meng Zheng, Feiran Wang, Anwesa Choudhuri, Zhenghao Zhao et al.
Published: 2025-12-13
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2512.12459v2

Accurately modeling light transport is essential for realistic image synthesis. Photon mapping provides physically grounded estimates of complex global illumination effects such as caustics and specular-diffuse interactions, yet its per-view radiance estimation remains computationally inefficient when rendering multiple views of the same scene. The inefficiency arises from independent photon tracing and stochastic kernel estimation at each viewpoint, leading to inevitable redundant computation. To accelerate multi-view rendering, we reformulate photon mapping as a continuous and reusable radiance function. Specifically, we introduce the Gaussian Photon Field (GPF), a learnable representation that encodes photon distributions as anisotropic 3D Gaussian primitives parameterized by position, rotation, scale, and spectrum. GPF is initialized from physically traced photons in the first SPPM iteration and optimized using multi-view supervision of final radiance, distilling photon-based light transport into a continuous field. Once trained, the field enables differentiable radiance evaluation along camera rays without repeated photon tracing or iterative refinement. Extensive experiments on scenes with complex light transport, such as caustics and specular-diffuse interactions, demonstrate that GPF attains photon-level accuracy while reducing computation by orders of magnitude, unifying the physical rigor of photon-based rendering with the efficiency of neural scene representations.

---

### Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval

Authors: Vihan Lakshman, Blaise Munyampirwa, Julian Shun, Benjamin Coleman
Published: 2025-12-13
Categories: cs.IR, cs.CG, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2512.12458v2

Modern vector databases enable efficient retrieval over high-dimensional neural embeddings, powering applications from web search to retrieval-augmented generation. However, classical theory predicts such tasks should suffer from the curse of dimensionality, where distances between points become nearly indistinguishable, thereby crippling efficient nearest-neighbor search. We revisit this paradox through the lens of stability, the property that small perturbations to a query do not radically alter its nearest neighbors. Building on foundational results, we extend stability theory to three key retrieval settings widely used in practice: (i) multi-vector search, where we prove that the popular Chamfer distance metric preserves single-vector stability, while average pooling aggregation may destroy it; (ii) filtered vector search, where we show that sufficiently large penalties for mismatched filters can induce stability even when the underlying search is unstable; and (iii) sparse vector search, where we formalize and prove novel sufficient stability conditions. Across synthetic and real datasets, our experimental results match our theoretical predictions, offering concrete guidance for model and system design to avoid the curse of dimensionality.

---

### Optimized Architectures for Kolmogorov-Arnold Networks

Authors: James Bagrow, Josh Bongard
Published: 2025-12-13
Categories: cs.LG, cs.NE, physics.data-an, stat.ML
arXiv: https://arxiv.org/abs/2512.12448v2

Efforts to improve Kolmogorov--Arnold networks (KANs) with architectural enhancements have been stymied by the complexity those enhancements bring, undermining the interpretability that makes KANs attractive in the first place. Here we study overprovisioned architectures combined with sparsification, deep supervision, and depth selection, to learn compact, interpretable KANs without sacrificing accuracy. Crucially, we focus on differentiable mechanisms under a principled minimum description length objective, jointly optimizing activations, structure, and depth end-to-end. Experiments across function approximation benchmarks, dynamical systems forecasting, and real-world prediction tasks demonstrate that sparsification alone is insufficient, but the combination with depth selection achieves competitive or superior accuracy while discovering substantially smaller models. The result is a principled path toward models that are both more expressive and more interpretable, addressing a key tension in scientific machine learning.

---

### Large language models have learned to use language

Authors: Gary Lupyan
Published: 2025-12-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.12447v1

Acknowledging that large language models have learned to use language can open doors to breakthrough language science. Achieving these breakthroughs may require abandoning some long-held ideas about how language knowledge is evaluated and reckoning with the difficult fact that we have entered a post-Turing test era.

---

### Knowledge-Guided Masked Autoencoder with Linear Spectral Mixing and Spectral-Angle-Aware Reconstruction

Authors: Abdul Matin, Rupasree Dey, Tanjim Bin Faruk, Shrideep Pallickara, Sangmi Lee Pallickara
Published: 2025-12-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12445v2

Integrating domain knowledge into deep learning has emerged as a promising direction for improving model interpretability, generalization, and data efficiency. In this work, we present a novel knowledge-guided ViT-based Masked Autoencoder that embeds scientific domain knowledge within the self-supervised reconstruction process. Instead of relying solely on data-driven optimization, our proposed approach incorporates the Linear Spectral Mixing Model (LSMM) as a physical constraint and physically-based Spectral Angle Mapper (SAM), ensuring that learned representations adhere to known structural relationships between observed signals and their latent components. The framework jointly optimizes LSMM and SAM loss with a conventional Huber loss objective, promoting both numerical accuracy and geometric consistency in the feature space. This knowledge-guided design enhances reconstruction fidelity, stabilizes training under limited supervision, and yields interpretable latent representations grounded in physical principles. The experimental findings indicate that the proposed model substantially enhances reconstruction quality and improves downstream task performance, highlighting the promise of embedding physics-informed inductive biases within transformer-based self-supervised learning.

---

### Can GPT replace human raters? Validity and reliability of machine-generated norms for metaphors

Authors: Veronica Mangiaterra, Hamad Al-Azary, Chiara Barattieri di San Pietro, Paolo Canal, Valentina Bambini
Published: 2025-12-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.12444v1

As Large Language Models (LLMs) are increasingly being used in scientific research, the issue of their trustworthiness becomes crucial. In psycholinguistics, LLMs have been recently employed in automatically augmenting human-rated datasets, with promising results obtained by generating ratings for single words. Yet, performance for ratings of complex items, i.e., metaphors, is still unexplored. Here, we present the first assessment of the validity and reliability of ratings of metaphors on familiarity, comprehensibility, and imageability, generated by three GPT models for a total of 687 items gathered from the Italian Figurative Archive and three English studies. We performed a thorough validation in terms of both alignment with human data and ability to predict behavioral and electrophysiological responses. We found that machine-generated ratings positively correlated with human-generated ones. Familiarity ratings reached moderate-to-strong correlations for both English and Italian metaphors, although correlations weakened for metaphors with high sensorimotor load. Imageability showed moderate correlations in English and moderate-to-strong in Italian. Comprehensibility for English metaphors exhibited the strongest correlations. Overall, larger models outperformed smaller ones and greater human-model misalignment emerged with familiarity and imageability. Machine-generated ratings significantly predicted response times and the EEG amplitude, with a strength comparable to human ratings. Moreover, GPT ratings obtained across independent sessions were highly stable. We conclude that GPT, especially larger models, can validly and reliably replace - or augment - human subjects in rating metaphor properties. Yet, LLMs align worse with humans when dealing with conventionality and multimodal aspects of metaphorical meaning, calling for careful consideration of the nature of stimuli.

---

### AI Transparency Atlas: Framework, Scoring, and Real-Time Model Card Evaluation Pipeline

Authors: Akhmadillo Mamirov, Faiaz Azmain, Hanyu Wang
Published: 2025-12-13
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2512.12443v1

AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation from five frontier models (Gemini 3, Grok 4.1, Llama 4, GPT-5, and Claude 4.5) and 100 Hugging Face model cards, identifying 947 unique section names with extreme naming variation. Usage information alone appeared under 97 distinct labels. Using the EU AI Act Annex IV and the Stanford Transparency Index as baselines, we developed a weighted transparency framework with 8 sections and 23 subsections that prioritizes safety-critical disclosures (Safety Evaluation: 25%, Critical Risk: 20%) over technical specifications. We implemented an automated multi-agent pipeline that extracts documentation from public sources and scores completeness through LLM-based consensus. Evaluating 50 models across vision, multimodal, open-source, and closed-source systems cost less than $3 in total and revealed systematic gaps. Frontier labs (xAI, Microsoft, Anthropic) achieve approximately 80% compliance, while most providers fall below 60%. Safety-critical categories show the largest deficits: deception behaviors, hallucinations, and child safety evaluations account for 148, 124, and 116 aggregate points lost, respectively, across all evaluated models.

---

### Efficient Level-Crossing Probability Calculation for Gaussian Process Modeled Data

Authors: Haoyu Li, Isaac J Michaud, Ayan Biswas, Han-Wei Shen
Published: 2025-12-13
Categories: stat.ML, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2512.12442v1

Almost all scientific data have uncertainties originating from different sources. Gaussian process regression (GPR) models are a natural way to model data with Gaussian-distributed uncertainties. GPR also has the benefit of reducing I/O bandwidth and storage requirements for large scientific simulations. However, the reconstruction from the GPR models suffers from high computation complexity. To make the situation worse, classic approaches for visualizing the data uncertainties, like probabilistic marching cubes, are also computationally very expensive, especially for data of high resolutions. In this paper, we accelerate the level-crossing probability calculation efficiency on GPR models by subdividing the data spatially into a hierarchical data structure and only reconstructing values adaptively in the regions that have a non-zero probability. For each region, leveraging the known GPR kernel and the saved data observations, we propose a novel approach to efficiently calculate an upper bound for the level-crossing probability inside the region and use this upper bound to make the subdivision and reconstruction decisions. We demonstrate that our value occurrence probability estimation is accurate with a low computation cost by experiments that calculate the level-crossing probability fields on different datasets.

---

### Sim2Real Reinforcement Learning for Soccer skills

Authors: Jonathan Spraggett
Published: 2025-12-13
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2512.12437v1

This thesis work presents a more efficient and effective approach to training control-related tasks for humanoid robots using Reinforcement Learning (RL). The traditional RL methods are limited in adapting to real-world environments, complexity, and natural motions, but the proposed approach overcomes these limitations by using curriculum training and Adversarial Motion Priors (AMP) technique. The results show that the developed RL policies for kicking, walking, and jumping are more dynamic, and adaptive, and outperformed previous methods. However, the transfer of the learned policy from simulation to the real world was unsuccessful, highlighting the limitations of current RL methods in fully adapting to real-world scenarios.

---

### Rough Sets for Explainability of Spectral Graph Clustering

Authors: Bartłomiej Starosta, Sławomir T. Wierzchoń, Piotr Borkowski, Dariusz Czerski, Marcin Sydow, Eryk Laskowski, Mieczysław A. Kłopotek
Published: 2025-12-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.12436v3

Graph Spectral Clustering methods (GSC) allow representing clusters of diverse shapes, densities, etc. However, the results of such algorithms, when applied e.g. to text documents, are hard to explain to the user, especially due to embedding in the spectral space which has no obvious relation to document contents. Furthermore, the presence of documents without clear content meaning and the stochastic nature of the clustering algorithms deteriorate explainability. This paper proposes an enhancement to the explanation methodology, proposed in an earlier research of our team. It allows us to overcome the latter problems by taking inspiration from rough set theory.

---

### Co-Hub Node Based Multiview Graph Learning with Theoretical Guarantees

Authors: Bisakh Banerjee, Mohammad Alwardat, Tapabrata Maiti, Selin Aviyente
Published: 2025-12-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.12435v1

Identifying the graphical structure underlying the observed multivariate data is essential in numerous applications. Current methodologies are predominantly confined to deducing a singular graph under the presumption that the observed data are uniform. However, many contexts involve heterogeneous datasets that feature multiple closely related graphs, typically referred to as multiview graphs. Previous research on multiview graph learning promotes edge-based similarity across layers using pairwise or consensus-based regularizers. However, multiview graphs frequently exhibit a shared node-based architecture across different views, such as common hub nodes. Such commonalities can enhance the precision of learning and provide interpretive insight. In this paper, we propose a co-hub node model, positing that different views share a common group of hub nodes. The associated optimization framework is developed by enforcing structured sparsity on the connections of these co-hub nodes. Moreover, we present a theoretical examination of layer identifiability and determine bounds on estimation error. The proposed methodology is validated using both synthetic graph data and fMRI time series data from multiple subjects to discern several closely related graphs.

---

### Data-driven modelling of autonomous and forced dynamical systems

Authors: Robert Szalai
Published: 2025-12-13
Categories: math.DS, cs.LG, physics.data-an
arXiv: https://arxiv.org/abs/2512.12432v1

The paper demonstrates that invariant foliations are accurate, data-efficient and practical tools for data-driven modelling of physical systems. Invariant foliations can be fitted to data that either fill the phase space or cluster about an invariant manifold. Invariant foliations can be fitted to a single trajectory or multiple trajectories. Over and underfitting are eliminated by appropriately choosing a function representation and its hyperparameters, such as polynomial orders. The paper extends invariant foliations to forced and parameter dependent systems. It is assumed that forcing is provided by a volume preserving map, and therefore the forcing can be periodic, quasi-periodic or even chaotic. The method utilises full trajectories, hence it is able to predict long-term dynamics accurately. We take into account if a forced system is reducible to an autonomous system about a steady state, similar to how Floquet theory guarantees reducibility for periodically forced systems. In order to find an invariant manifold, multiple invariant foliations are calculated in the neighbourhood of the invariant manifold. Some of the invariant foliations can be linear, while others nonlinear but only defined in a small neighbourhood of an invariant manifold, which reduces the number of parameters to be identified. An invariant manifold is recovered as the zero level set of one or more of the foliations. To interpret the results, the identified mathematical models are transformed to a canonical form and instantaneous frequency and damping information are calculated.

---

### Endless World: Real-Time 3D-Aware Long Video Generation

Authors: Ke Zhang, Yiqun Mei, Jiacong Xu, Vishal M. Patel
Published: 2025-12-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12430v1

Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a real-time framework for infinite, 3D-consistent video generation.To support infinite video generation, we introduce a conditional autoregressive training strategy that aligns newly generated content with existing video frames. This design preserves long-range dependencies while remaining computationally efficient, enabling real-time inference on a single GPU without additional training overhead.Moreover, our Endless World integrates global 3D-aware attention to provide continuous geometric guidance across time. Our 3D injection mechanism enforces physical plausibility and geometric consistency throughout extended sequences, addressing key challenges in long-horizon and dynamic scene synthesis.Extensive experiments demonstrate that Endless World produces long, stable, and visually coherent videos, achieving competitive or superior performance to existing methods in both visual fidelity and spatial consistency. Our project has been available on https://bwgzk-keke.github.io/EndlessWorld/.

---

### Learning Dynamics in Memristor-Based Equilibrium Propagation

Authors: Michael Döll, Andreas Müller, Bernd Ulmann
Published: 2025-12-13
Categories: cs.LG, cs.ET, cs.NE
arXiv: https://arxiv.org/abs/2512.12428v1

Memristor-based in-memory computing has emerged as a promising paradigm to overcome the constraints of the von Neumann bottleneck and the memory wall by enabling fully parallelisable and energy-efficient vector-matrix multiplications. We investigate the effect of nonlinear, memristor-driven weight updates on the convergence behaviour of neural networks trained with equilibrium propagation (EqProp). Six memristor models were characterised by their voltage-current hysteresis and integrated into the EBANA framework for evaluation on two benchmark classification tasks. EqProp can achieve robust convergence under nonlinear weight updates, provided that memristors exhibit a sufficiently wide resistance range of at least an order of magnitude.

---

### Boosting Monocular Metric Depth Estimation via Bokeh Rendering

Authors: Hangwei Zhang, Armando Fortes, Tianyi Wei, Xingang Pan
Published: 2025-12-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12425v2

Bokeh rendering and depth estimation share a fundamental optical connection, yet existing methods fail to fully exploit this reciprocity. Conventional bokeh pipelines rely heavily on noisy depth maps that inevitably introduce visual artifacts. Conversely, existing monocular depth models typically follow two flawed paradigms. Generative diffusion-based frameworks often lack consistent metric scale. Meanwhile, feed-forward metric depth models frequently fail in textureless or distant regions where defocus blur can provide geometric information. We propose BokehDepth, a two-stage framework that treats synthetic defocus as a supervision-free geometric signal. In the first stage, a physically grounded generative model produces calibrated bokeh stacks from a single sharp input without requiring prior depth input. Subsequently, a lightweight defocus-aware aggregation module integrates these stacks into the encoder of a depth estimation framework. This mechanism allows the model to extract consistent geometric features from the defocus dimension while keeping the decoder architecture unchanged. Experiments demonstrate that BokehDepth achieves superior visual bokeh fidelity compared to depth-dependent rendering baselines and consistently enhances the metric accuracy of state-of-the-art monocular depth models.

---

### ViInfographicVQA: A Benchmark for Single and Multi-image Visual Question Answering on Vietnamese Infographics

Authors: Tue-Thu Van-Dinh, Hoang-Duy Tran, Truong-Binh Duong, Mai-Hanh Pham, Binh-Nam Le-Nguyen, Quoc-Thai Nguyen
Published: 2025-12-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.12424v1

Infographic Visual Question Answering (InfographicVQA) evaluates a model's ability to read and reason over data-rich, layout-heavy visuals that combine text, charts, icons, and design elements. Compared with scene-text or natural-image VQA, infographics require stronger integration of OCR, layout understanding, and numerical and semantic reasoning. We introduce ViInfographicVQA, the first benchmark for Vietnamese InfographicVQA, comprising over 6747 real-world infographics and 20409 human-verified question-answer pairs across economics, healthcare, education, and more. The benchmark includes two evaluation settings. The Single-image task follows the traditional setup in which each question is answered using a single infographic. The Multi-image task requires synthesizing evidence across multiple semantically related infographics and is, to our knowledge, the first Vietnamese evaluation of cross-image reasoning in VQA. We evaluate a range of recent vision-language models on this benchmark, revealing substantial performance disparities, with the most significant errors occurring on Multi-image questions that involve cross-image integration and non-span reasoning. ViInfographicVQA contributes benchmark results for Vietnamese InfographicVQA and sheds light on the limitations of current multimodal models in low-resource contexts, encouraging future exploration of layout-aware and cross-image reasoning methods.

---

### Understanding Critical Thinking in Generative Artificial Intelligence Use: Development, Validation, and Correlates of the Critical Thinking in AI Use Scale

Authors: Gabriel R. Lau, Wei Yan Low, Louis Tay, Ysabel Guevarra, Dragan Gašević, Andree Hartanto
Published: 2025-12-13
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2512.12413v2

Generative AI tools are increasingly embedded in everyday work and learning, yet their fluency, opacity, and propensity to hallucinate mean that users must critically evaluate AI outputs rather than accept them at face value. The present research conceptualises critical thinking in AI use as a dispositional tendency to verify the source and content of AI-generated information, to understand how models work and where they fail, and to reflect on the broader implications of relying on AI. Across six studies (N = 1341), we developed and validated the 13-item critical thinking in AI use scale and mapped its nomological network. Study 1 generated and content-validated scale items. Study 2 supported a three-factor structure (Verification, Motivation, and Reflection). Studies 3 and 4 confirmed the higher-order model, demonstrated strong factor loadings, internal consistency, sex invariance, convergent and discriminant evidence for validity, and showed that critical thinking in AI use was positively associated with openness, extraversion, positive trait affect, and frequency of AI use. Study 5 supported the scale's test-retest reliability. Lastly, Study 6 demonstrated criterion evidence of validity for the scale, with higher critical thinking in AI use scores predicting more frequent and diverse verification strategies, greater veracity judgement accuracy in a novel and naturalistic GPT-powered AI chatbot fact-checking task, and deeper reflection about responsible AI. The current work clarifies why and how people exercise oversight over generative AI outputs and provides a validated scale and ecologically grounded paradigm to support theory testing, cross-group, and longitudinal research on critical thinking in AI use.

---

### Detecting the Disturbance: A Nuanced View of Introspective Abilities in LLMs

Authors: Ely Hahami, Ishaan Sinha, Lavik Jain, Josh Kaplan, Jon Hahami
Published: 2025-12-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.12411v2

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary detection paradigm used in prior work conflates introspection with a methodological artifact: apparent detection accuracy is entirely explained by global logit shifts that bias models toward affirmative responses regardless of question content. However, on tasks requiring differential sensitivity, we find robust evidence for partial introspection: models localize which of 10 sentences received an injection at up to 88\% accuracy (vs.\ 10\% chance) and discriminate relative injection strengths at 83\% accuracy (vs.\ 50\% chance). These capabilities are confined to early-layer injections and collapse to chance thereafter -- a pattern we explain mechanistically through attention-based signal routing and residual stream recovery dynamics. Our findings demonstrate that LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenon that merits further investigation. Our code is open-sourced here: https://github.com/elyhahami18/llama-introspection-new

---

### A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams

Authors: Khalfalla Awedat, Mohamed Abidalrekab, Mohammad El-Yabroudi
Published: 2025-12-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.12410v1

Vertical beam dropout in spinning LiDAR sensors triggered by hardware aging, dust, snow, fog, or bright reflections removes entire vertical slices from the point cloud and severely degrades 3D perception in autonomous vehicles. This paper proposes a Graph Attention Network (GAT)-based framework that reconstructs these missing vertical channels using only the current LiDAR frame, with no camera images or temporal information required. Each LiDAR sweep is represented as an unstructured spatial graph: points are nodes and edges connect nearby points while preserving the original beam-index ordering. A multi-layer GAT learns adaptive attention weights over local geometric neighborhoods and directly regresses the missing elevation (z) values at dropout locations. Trained and evaluated on 1,065 raw KITTI sequences with simulated channel dropout, the method achieves an average height RMSE of 11.67 cm, with 87.98% of reconstructed points falling within a 10 cm error threshold. Inference takes 14.65 seconds per frame on a single GPU, and reconstruction quality remains stable for different neighborhood sizes k. These results show that a pure graph attention model operating solely on raw point-cloud geometry can effectively recover dropped vertical beams under realistic sensor degradation.

---

### Can Graphs Improve Tabular Foundation Models?

Authors: Franck Le, Keith Grueneberg, Erich Nahum, Vadim Sheinin
Published: 2025-12-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12405v1

Tabular data are central to many real-world systems. While recent tabular transformers and in-context learners such as SAINT, TP-BERTa, TabPFN, TabICL, and MITRA incorporate limited inter-row reasoning, most approaches still lack an explicit mechanism to model relationships among instances, even though similar samples often share related outcomes. We investigate whether introducing \emph{simple graph priors} can enhance \emph{pretrained tabular transformers}. Concretely, we introduce {BOLERO}, a lightweight, static bipartite graph head that augments {RoBERTa-Tab} (a RoBERTa-style tabular backbone pretrained with masked-token prediction.) Each instance connects to feature/value anchors; a small GNN refines row representations, while the backbone remains frozen. We evaluate on 80 classification and 64 regression datasets from the TP-BERTa benchmark suites, comparing against strong baselines including XGBoost, CatBoost, TabPFN-v2, MITRA, TabICL, TP-BERTa, and RoBERTa-Tab. To ensure statistically sound conclusions, we follow best practices for multi-dataset evaluation: pairwise Wilcoxon signed-rank tests on per-dataset score differences and effect sizes (median improvement with confidence intervals), rather than mean-rank post-hoc tests that depend on the competitor pool. BOLERO achieves the highest number of statistically significant wins across both classification and regression, demonstrating that lightweight graph priors meaningfully improve pretrained tabular transformers.

---

### DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields

Authors: Vladimer Khasia
Published: 2025-12-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12402v1

We present DeepVekua, a hybrid architecture that unifies geometric deep learning with spectral analysis to solve partial differential equations (PDEs) in sparse data regimes. By learning a diffeomorphic coordinate transformation that maps complex geometries to a latent harmonic space, our method outperforms state-of-the-art implicit representations on advection-diffusion systems. Unlike standard coordinate-based networks which struggle with spectral bias, DeepVekua separates the learning of geometry from the learning of physics, solving for optimal spectral weights in closed form. We demonstrate a 100x improvement over spectral baselines. The code is available at https://github.com/VladimerKhasia/vekuanet.

---

### ArtGen: Conditional Generative Modeling of Articulated Objects in Arbitrary Part-Level States

Authors: Haowen Wang, Xiaoping Yuan, Fugang Zhang, Rui Jian, Yuanwei Zhu, Xiuquan Qiao, Yakun Huang
Published: 2025-12-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12395v1

Generating articulated assets is crucial for robotics, digital twins, and embodied intelligence. Existing generative models often rely on single-view inputs representing closed states, resulting in ambiguous or unrealistic kinematic structures due to the entanglement between geometric shape and joint dynamics. To address these challenges, we introduce ArtGen, a conditional diffusion-based framework capable of generating articulated 3D objects with accurate geometry and coherent kinematics from single-view images or text descriptions at arbitrary part-level states. Specifically, ArtGen employs cross-state Monte Carlo sampling to explicitly enforce global kinematic consistency, reducing structural-motion entanglement. Additionally, we integrate a Chain-of-Thought reasoning module to infer robust structural priors, such as part semantics, joint types, and connectivity, guiding a sparse-expert Diffusion Transformer to specialize in diverse kinematic interactions. Furthermore, a compositional 3D-VAE latent prior enhanced with local-global attention effectively captures fine-grained geometry and global part-level relationships. Extensive experiments on the PartNet-Mobility benchmark demonstrate that ArtGen significantly outperforms state-of-the-art methods.

---

### The Morphemic Origin of Zipf's Law: A Factorized Combinatorial Framework

Authors: Vladimir Berman
Published: 2025-12-13
Categories: stat.ME, cs.CL, physics.soc-ph, stat.AP
arXiv: https://arxiv.org/abs/2512.12394v1

We present a simple structure based model of how words are formed from morphemes. The model explains two major empirical facts: the typical distribution of word lengths and the appearance of Zipf like rank frequency curves. In contrast to classical explanations based on random text or communication efficiency, our approach uses only the combinatorial organization of prefixes, roots, suffixes and inflections. In this Morphemic Combinatorial Word Model, a word is created by activating several positional slots. Each slot turns on with a certain probability and selects one morpheme from its inventory. Morphemes are treated as stable building blocks that regularly appear in word formation and have characteristic positions. This mechanism produces realistic word length patterns with a concentrated middle zone and a thin long tail, closely matching real languages. Simulations with synthetic morpheme inventories also generate rank frequency curves with Zipf like exponents around 1.1-1.4, similar to English, Russian and Romance languages. The key result is that Zipf like behavior can emerge without meaning, communication pressure or optimization principles. The internal structure of morphology alone, combined with probabilistic activation of slots, is sufficient to create the robust statistical patterns observed across languages.

---

### Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment

Authors: Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu, Wei Zhai, Yang Cao, Zheng-Jun Zha
Published: 2025-12-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12387v1

Group Relative Policy Optimization (GRPO) has proven highly effective in enhancing the alignment capabilities of Large Language Models (LLMs). However, current adaptations of GRPO for the flow matching-based image generation neglect a foundational conflict between its core principles and the distinct dynamics of the visual synthesis process. This mismatch leads to two key limitations: (i) Uniformly applying a sparse terminal reward across all timesteps impairs temporal credit assignment, ignoring the differing criticality of generation phases from early structure formation to late-stage tuning. (ii) Exclusive reliance on relative, intra-group rewards causes the optimization signal to fade as training converges, leading to the optimization stagnation when reward diversity is entirely depleted. To address these limitations, we propose Value-Anchored Group Policy Optimization (VGPO), a framework that redefines value estimation across both temporal and group dimensions. Specifically, VGPO transforms the sparse terminal reward into dense, process-aware value estimates, enabling precise credit assignment by modeling the expected cumulative reward at each generative stage. Furthermore, VGPO replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal even as reward diversity declines. Extensive experiments on three benchmarks demonstrate that VGPO achieves state-of-the-art image quality while simultaneously improving task-specific accuracy, effectively mitigating reward hacking. Project webpage: https://yawen-shao.github.io/VGPO/.

---

### Speedrunning ImageNet Diffusion

Authors: Swayam Bhanded
Published: 2025-12-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12386v1

Recent advances have significantly improved the training efficiency of diffusion transformers. However, these techniques have largely been studied in isolation, leaving unexplored the potential synergies from combining multiple approaches. We present SR-DiT (Speedrun Diffusion Transformer), a framework that systematically integrates token routing, architectural improvements, and training modifications on top of representation alignment. Our approach achieves FID 3.49 and KDD 0.319 on ImageNet-256 using only a 140M parameter model at 400K iterations without classifier-free guidance - comparable to results from 685M parameter models trained significantly longer. To our knowledge, this is a state-of the-art result at this model size. Through extensive ablation studies, we identify which technique combinations are most effective and document both synergies and incompatibilities. We release our framework as a computationally accessible baseline for future research.

---

### The Data Efficiency Frontier of Financial Foundation Models: Scaling Laws from Continued Pretraining

Authors: Jesse Ponnock
Published: 2025-12-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2512.12384v1

Domain-adaptive pretraining (DAPT) offers a practical path to specializing large language models for high-value domains without full retraining. We conduct an early-stage scaling-law analysis of continued pretraining on U.S. SEC filings, training 1B and 3B-parameter Llama-3.2 models on a 400M-token financial corpus with validation checkpoints at 50M, 100M, 200M, and 400M tokens. Results show consistent improvements in SEC-domain validation loss for both models, with the largest gains occurring within the first 200M tokens and diminishing returns thereafter. Power-law fits reveal shallow exponents, indicating that financial language is highly regular and efficiently learnable under continued pretraining. General-domain validation loss remains effectively unchanged across all token budgets, suggesting minimal drift and no signs of catastrophic forgetting. A data-efficiency frontier further shows that both models move toward improved specialization with negligible mixed-domain degradation. Together, these findings provide early empirical guidance for scaling financial foundation models, suggesting that meaningful domain adaptation can be achieved with comparatively modest token budgets and that larger model scales (7B-70B) remain tractable under projected data requirements.

---

### Entropy Collapse: A Universal Failure Mode of Intelligent Systems

Authors: Truong Xuan Khanh, Truong Quynh Hoa
Published: 2025-12-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.12381v2

A foundational assumption in complex-system collapse studies is that critical transitions are second-order, preceded by early-warning signals like rising autocorrelation, variance, and critical slowing down (Scheffer, 2009). We show this fails for feedback-amplified adaptive systems. We prove entropy collapse - the irreversible contraction of effective state space when feedback amplification alpha exceeds novelty regeneration beta - is a first-order (discontinuous) phase transition. Four exact results: (1) Threshold alpha_c(beta) = 1/(1-beta), from Jacobian spectrum of Multiplicative-Weights operator. (2) Discontinuity: entropy order parameter m = 1 - H_ss/H_max jumps Delta m_0 = 0.698 at alpha_c, with hysteresis Delta H_hyst approx 2.73 nats (lower bound; up to 3.9 nats in simulations); no pre-transition warnings as autocorrelation and variance stay finite. (3) Relaxation exponent nu = 1, from transcritical bifurcation (R^2 = 0.9997 vs. simulation); universality across update mechanisms. (4) Two classes: feedback curvature kappa = f''(1/N) determines order - Class 1 (kappa > 0, convex, e.g., power-law) irreversible with nu = 1; Class 2 (kappa = 0, linear) reversible with nu = 1/2. Theorems validated in neural experiments on two-layer autoregressive transformer (SmallGPT, N=50 vocab, 92 conditions, 8 seeds/condition): Delta H_hyst^NN = 2.92 nats > 2.73 (Theorem 2); nu^NN = 1.14 +/- 0.13, R^2 = 0.977 (Theorem 3). This unifies AI model collapse (Shumailov et al., 2023), economic institutional sclerosis, and evolutionary genetic bottlenecks as first-order entropy-driven processes, evading standard early-warning monitoring.

---

### M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction

Authors: Junqiao Fan, Yunjiao Zhou, Yizhuo Yang, Xinyuan Cui, Jiarui Zhang, Lihua Xie, Jianfei Yang, Chris Xiaoxuan Lu, Fangqiang Ding
Published: 2025-12-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12378v3

Human mesh reconstruction (HMR) provides direct insights into body-environment interaction, which enables various immersive applications. While existing large-scale HMR datasets rely heavily on line-of-sight RGB input, vision-based sensing is limited by occlusion, lighting variation, and privacy concerns. To overcome these limitations, recent efforts have explored radio-frequency (RF) mmWave radar for privacy-preserving indoor human sensing. However, current radar datasets are constrained by sparse skeleton labels, limited scale, and simple in-place actions. To advance the HMR research community, we introduce M4Human, the current largest-scale (661K-frame) ($9\times$ prior largest) multimodal benchmark, featuring high-resolution mmWave radar, RGB, and depth data. M4Human provides both raw radar tensors (RT) and processed radar point clouds (RPC) to enable research across different levels of RF signal granularity. M4Human includes high-quality motion capture (MoCap) annotations with 3D meshes and global trajectories, and spans 20 subjects and 50 diverse actions, including in-place, sit-in-place, and free-space sports or rehabilitation movements. We establish benchmarks on both RT and RPC modalities, as well as multimodal fusion with RGB-D modalities. Extensive results highlight the significance of M4Human for radar-based human modeling while revealing persistent challenges under fast, unconstrained motion. The dataset and code will be released after the paper publication.

---

### V-Warper: Appearance-Consistent Video Diffusion Personalization via Value Warping

Authors: Hyunkoo Lee, Wooseok Jang, Jini Yang, Taehwan Kim, Sangoh Kim, Sangwon Jung, Seungryong Kim
Published: 2025-12-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12375v1

Video personalization aims to generate videos that faithfully reflect a user-provided subject while following a text prompt. However, existing approaches often rely on heavy video-based finetuning or large-scale video datasets, which impose substantial computational cost and are difficult to scale. Furthermore, they still struggle to maintain fine-grained appearance consistency across frames. To address these limitations, we introduce V-Warper, a training-free coarse-to-fine personalization framework for transformer-based video diffusion models. The framework enhances fine-grained identity fidelity without requiring any additional video training. (1) A lightweight coarse appearance adaptation stage leverages only a small set of reference images, which are already required for the task. This step encodes global subject identity through image-only LoRA and subject-embedding adaptation. (2) A inference-time fine appearance injection stage refines visual fidelity by computing semantic correspondences from RoPE-free mid-layer query--key features. These correspondences guide the warping of appearance-rich value representations into semantically aligned regions of the generation process, with masking ensuring spatial reliability. V-Warper significantly improves appearance fidelity while preserving prompt alignment and motion dynamics, and it achieves these gains efficiently without large-scale video finetuning.

---

### STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative

Authors: Peixuan Zhang, Zijian Jia, Kaiqi Liu, Shuchen Weng, Si Li, Boxin Shi
Published: 2025-12-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12372v2

While recent advancements in generative models have achieved remarkable visual fidelity in video synthesis, creating coherent multi-shot narratives remains a significant challenge. To address this, keyframe-based approaches have emerged as a promising alternative to computationally intensive end-to-end methods, offering the advantages of fine-grained control and greater efficiency. However, these methods often fail to maintain cross-shot consistency and capture cinematic language. In this paper, we introduce STAGE, a SToryboard-Anchored GEneration workflow to reformulate the keyframe-based multi-shot video generation task. Instead of using sparse keyframes, we propose STEP2 to predict a structural storyboard composed of start-end frame pairs for each shot. We introduce the multi-shot memory pack to ensure long-range entity consistency, the dual-encoding strategy for intra-shot coherence, and the two-stage training scheme to learn cinematic inter-shot transition. We also contribute the large-scale ConStoryBoard dataset, including high-quality movie clips with fine-grained annotations for story progression, cinematic attributes, and human preferences. Extensive experiments demonstrate that STAGE achieves superior performance in structured narrative control and cross-shot coherence. Our code will be available at this url.

---

### JPEG-Inspired Cloud-Edge Holography

Authors: Shuyang Xie, Jie Zhou, Jun Wang, Renjing Xu
Published: 2025-12-13
Categories: physics.optics, cs.CV
arXiv: https://arxiv.org/abs/2512.12367v1

Computer-generated holography (CGH) presents a transformative solution for near-eye displays in augmented and virtual reality. Recent advances in deep learning have greatly improved CGH in reconstructed quality and computational efficiency. However, deploying neural CGH pipelines directly on compact, eyeglass-style devices is hindered by stringent constraints on computation and energy consumption, while cloud offloading followed by transmission with natural image codecs often distorts phase information and requires high bandwidth to maintain reconstruction quality. Neural compression methods can reduce bandwidth but impose heavy neural decoders at the edge, increasing inference latency and hardware demand. In this work, we introduce JPEG-Inspired Cloud-Edge Holography, an efficient pipeline designed around a learnable transform codec that retains the block-structured and hardware-friendly nature of JPEG. Our system shifts all heavy neural processing to the cloud, while the edge device performs only lightweight decoding without any neural inference. To further improve throughput, we implement custom CUDA kernels for entropy coding on both cloud and edge. This design achieves a peak signal-to-noise ratio of 32.15 dB at $<$ 2 bits per pixel with decode latency as low as 4.2 ms. Both numerical simulations and optical experiments confirm the high reconstruction quality of the holograms. By aligning CGH with a codec that preserves JPEG's structural efficiency while extending it with learnable components, our framework enables low-latency, bandwidth-efficient hologram streaming on resource-constrained wearable devices-using only simple block-based decoding readily supported by modern system-on-chips, without requiring neural decoders or specialized hardware.

---

### ElasticVR: Elastic Task Computing in Multi-User Multi-Connectivity Wireless Virtual Reality (VR) Systems

Authors: Babak Badnava, Jacob Chakareski, Morteza Hashemi
Published: 2025-12-13
Categories: cs.IT, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2512.12366v1

Diverse emerging VR applications integrate streaming of high fidelity 360 video content that requires ample amounts of computation and data rate. Scalable 360 video tiling enables having elastic VR computational tasks that can be scaled adaptively in computation and data rate based on the available user and system resources. We integrate scalable 360 video tiling in an edge-client wireless multi-connectivity architecture for joint elastic task computation offloading across multiple VR users called ElasticVR. To balance the trade-offs in communication, computation, energy consumption, and QoE that arise herein, we formulate a constrained QoE and energy optimization problem that integrates the multi-user/multi-connectivity action space with the elasticity of VR computational tasks. The ElasticVR framework introduces two multi-agent deep reinforcement learning solutions, namely CPPG and IPPG. CPPG adopts a centralized training and centralized execution approach to capture the coupling between users' communication and computational demands. This leads to globally coordinated decisions at the cost of increased computational overheads and limited scalability. To address the latter challenges, we also explore an alternative strategy denoted IPPG that adopts a centralized training with decentralized execution paradigm. IPPG leverages shared information and parameter sharing to learn robust policies; however, during execution, each user takes action independently based on its local state information only. The decentralized execution alleviates the communication and computation overhead of centralized decision-making and improves scalability. We show that the ElasticVR framework improves the PSNR by 43.21%, while reducing the response time and energy consumption by 42.35% and 56.83%, respectively, compared with a case where no elasticity is incorporated into VR computations.

---

### Synthetic Swarm Mosquito Dataset for Acoustic Classification: A Proof of Concept

Authors: Thai-Duy Dinh, Minh-Luan Vo, Cuong Tuan Nguyen, Bich-Hien Vo
Published: 2025-12-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12365v1

Mosquito-borne diseases pose a serious global health threat, causing over 700,000 deaths annually. This work introduces a proof-of-concept Synthetic Swarm Mosquito Dataset for Acoustic Classification, created to simulate realistic multi-species and noisy swarm conditions. Unlike conventional datasets that require labor-intensive recording of individual mosquitoes, the synthetic approach enables scalable data generation while reducing human resource demands. Using log-mel spectrograms, we evaluated lightweight deep learning architectures for the classification of mosquito species. Experiments show that these models can effectively identify six major mosquito vectors and are suitable for deployment on embedded low-power devices. The study demonstrates the potential of synthetic swarm audio datasets to accelerate acoustic mosquito research and enable scalable real-time surveillance solutions.

---

### VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding

Authors: Yufei Yin, Qianke Meng, Minghao Chen, Jiajun Ding, Zhenwei Shao, Zhou Yu
Published: 2025-12-13
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2512.12360v2

Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming video preprocessing to guide MLLMs in autonomous reasoning. To overcome these limitations, we introduce VideoARM, an Agentic Reasoning-over-hierarchical-Memory paradigm for long-form video understanding. Instead of static, exhaustive preprocessing, VideoARM performs adaptive, on-the-fly agentic reasoning and memory construction. Specifically, VideoARM performs an adaptive and continuous loop of observing, thinking, acting, and memorizing, where a controller autonomously invokes tools to interpret the video in a coarse-to-fine manner, thereby substantially reducing token consumption. In parallel, a hierarchical multimodal memory continuously captures and updates multi-level clues throughout the operation of the agent, providing precise contextual information to support the controller in decision-making. Experiments on prevalent benchmarks demonstrate that VideoARM outperforms the state-of-the-art method, DVD, while significantly reducing token consumption for long-form videos.

---

### Towards a pretrained deep learning estimator of the Linfoot informational correlation

Authors: Stéphanie M. van den Berg, Ulrich Halekoh, Sören Möller, Andreas Kryger Jensen, Jacob von Bornemann Hjelmborg
Published: 2025-12-13
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2512.12358v1

We develop a supervised deep-learning approach to estimate mutual information between two continuous random variables. As labels, we use the Linfoot informational correlation, a transformation of mutual information that has many important properties. Our method is based on ground truth labels for Gaussian and Clayton copulas. We compare our method with estimators based on kernel density, k-nearest neighbours and neural estimators. We show generally lower bias and lower variance. As a proof of principle, future research could look into training the model with a more diverse set of examples from other copulas for which ground truth labels are available.

---

### TCLeaf-Net: a transformer-convolution framework with global-local attention for robust in-field lesion-level plant leaf disease detection

Authors: Zishen Song, Yongjian Zhu, Dong Wang, Hongzhan Liu, Lingyu Jiang, Yongxing Duan, Zehua Zhang, Sihan Li, Jiarui Li
Published: 2025-12-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12357v1

Timely and accurate detection of foliar diseases is vital for safeguarding crop growth and reducing yield losses. Yet, in real-field conditions, cluttered backgrounds, domain shifts, and limited lesion-level datasets hinder robust modeling. To address these challenges, we release Daylily-Leaf, a paired lesion-level dataset comprising 1,746 RGB images and 7,839 lesions captured under both ideal and in-field conditions, and propose TCLeaf-Net, a transformer-convolution hybrid detector optimized for real-field use. TCLeaf-Net is designed to tackle three major challenges. To mitigate interference from complex backgrounds, the transformer-convolution module (TCM) couples global context with locality-preserving convolution to suppress non-leaf regions. To reduce information loss during downsampling, the raw-scale feature recalling and sampling (RSFRS) block combines bilinear resampling and convolution to preserve fine spatial detail. To handle variations in lesion scale and feature shifts, the deformable alignment block with FPN (DFPN) employs offset-based alignment and multi-receptive-field perception to strengthen multi-scale fusion. Experimental results show that on the in-field split of the Daylily-Leaf dataset, TCLeaf-Net improves mAP@50 by 5.4 percentage points over the baseline model, reaching 78.2\%, while reducing computation by 7.5 GFLOPs and GPU memory usage by 8.7\%. Moreover, the model outperforms recent YOLO and RT-DETR series in both precision and recall, and demonstrates strong performance on the PlantDoc, Tomato-Leaf, and Rice-Leaf datasets, validating its robustness and generalizability to other plant disease detection scenarios.

---

### Uncertainty Quantification for Machine Learning: One Size Does Not Fit All

Authors: Paul Hofman, Yusuf Sale, Eyke Hüllermeier
Published: 2025-12-13
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.12341v1

Proper quantification of predictive uncertainty is essential for the use of machine learning in safety-critical applications. Various uncertainty measures have been proposed for this purpose, typically claiming superiority over other measures. In this paper, we argue that there is no single best measure. Instead, uncertainty quantification should be tailored to the specific application. To this end, we use a flexible family of uncertainty measures that distinguishes between total, aleatoric, and epistemic uncertainty of second-order distributions. These measures can be instantiated with specific loss functions, so-called proper scoring rules, to control their characteristics, and we show that different characteristics are useful for different tasks. In particular, we show that, for the task of selective prediction, the scoring rule should ideally match the task loss. On the other hand, for out-of-distribution detection, our results confirm that mutual information, a widely used measure of epistemic uncertainty, performs best. Furthermore, in an active learning setting, epistemic uncertainty based on zero-one loss is shown to consistently outperform other uncertainty measures.

---

### Unified Control for Inference-Time Guidance of Denoising Diffusion Models

Authors: Maurya Goyal, Anuj Singh, Hadi Jamali-Rad
Published: 2025-12-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.12339v1

Aligning diffusion model outputs with downstream objectives is essential for improving task-specific performance. Broadly, inference-time training-free approaches for aligning diffusion models can be categorized into two main strategies: sampling-based methods, which explore multiple candidate outputs and select those with higher reward signals, and gradient-guided methods, which use differentiable reward approximations to directly steer the generation process. In this work, we propose a universal algorithm, UniCoDe, which brings together the strengths of sampling and gradient-based guidance into a unified framework. UniCoDe integrates local gradient signals during sampling, thereby addressing the sampling inefficiency inherent in complex reward-based sampling approaches. By cohesively combining these two paradigms, UniCoDe enables more efficient sampling while offering better trade-offs between reward alignment and divergence from the diffusion unconditional prior. Empirical results demonstrate that UniCoDe remains competitive with state-of-the-art baselines across a range of tasks. The code is available at https://github.com/maurya-goyal10/UniCoDe

---

### SCIR: A Self-Correcting Iterative Refinement Framework for Enhanced Information Extraction Based on Schema

Authors: Yushen Fang, Jianjun Li, Mingqian Ding, Chang Liu, Xinchi Zou, Wenqi Yang
Published: 2025-12-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.12337v1

Although Large language Model (LLM)-powered information extraction (IE) systems have shown impressive capabilities, current fine-tuning paradigms face two major limitations: high training costs and difficulties in aligning with LLM preferences. To address these issues, we propose a novel universal IE paradigm, the Self-Correcting Iterative Refinement (SCIR) framework, along with a Multi-task Bilingual (Chinese-English) Self-Correcting (MBSC) dataset containing over 100,000 entries. The SCIR framework achieves plug-and-play compatibility with existing LLMs and IE systems through its Dual-Path Self-Correcting module and feedback-driven optimization, thereby significantly reducing training costs. Concurrently, the MBSC dataset tackles the challenge of preference alignment by indirectly distilling GPT-4's capabilities into IE result detection models. Experimental results demonstrate that SCIR outperforms state-of-the-art IE methods across three key tasks: named entity recognition, relation extraction, and event extraction, achieving a 5.27 percent average improvement in span-based Micro-F1 while reducing training costs by 87 percent compared to baseline approaches. These advancements not only enhance the flexibility and accuracy of IE systems but also pave the way for lightweight and efficient IE paradigms.

---

### Extending the application of dynamic Bayesian networks in calculating market risk: Standard and stressed expected shortfall

Authors: Eden Gross, Ryan Kruger, Francois Toerien
Published: 2025-12-13
Categories: q-fin.RM, cs.LG, q-fin.CP, q-fin.ST
arXiv: https://arxiv.org/abs/2512.12334v1

In the last five years, expected shortfall (ES) and stressed ES (SES) have become key required regulatory measures of market risk in the banking sector, especially following events such as the global financial crisis. Thus, finding ways to optimize their estimation is of great importance. We extend the application of dynamic Bayesian networks (DBNs) to the estimation of 10-day 97.5% ES and stressed ES, building on prior work applying DBNs to value at risk. Using the S&P 500 index as a proxy for the equities trading desk of a US bank, we compare the performance of three DBN structure-learning algorithms with several traditional market risk models, using either the normal or the skewed Student's t return distributions. Backtesting shows that all models fail to produce statistically accurate ES and SES forecasts at the 2.5% level, reflecting the difficulty of modeling extreme tail behavior. For ES, the EGARCH(1,1) model (normal) produces the most accurate forecasts, while, for SES, the GARCH(1,1) model (normal) performs best. All distribution-dependent models deteriorate substantially when using the skewed Student's t distribution. The DBNs perform comparably to the historical simulation model, but their contribution to tail prediction is limited by the small weight assigned to their one-day-ahead forecasts within the return distribution. Future research should examine weighting schemes that enhance the influence of forward-looking DBN forecasts on tail risk estimation.

---

### Dynamic Homophily with Imperfect Recall: Modeling Resilience in Adversarial Networks

Authors: Saad Alqithami
Published: 2025-12-13
Categories: cs.SI, cs.AI, cs.CR, cs.IT
arXiv: https://arxiv.org/abs/2512.12332v1

The purpose of this study is to investigate how homophily, memory constraints, and adversarial disruptions collectively shape the resilience and adaptability of complex networks. To achieve this, we develop a new framework that integrates explicit memory decay mechanisms into homophily-based models and systematically evaluate their performance across diverse graph structures and adversarial settings. Our methods involve extensive experimentation on synthetic datasets, where we vary decay functions, reconnection probabilities, and similarity measures, primarily comparing cosine similarity with traditional metrics such as Jaccard similarity and baseline edge weights. The results show that cosine similarity achieves up to a 30\% improvement in stability metrics in sparse, convex, and modular networks. Moreover, the refined value-of-recall metric demonstrates that strategic forgetting can bolster resilience by balancing network robustness and adaptability. The findings underscore the critical importance of aligning memory and similarity parameters with the structural and adversarial dynamics of the network. By quantifying the tangible benefits of incorporating memory constraints into homophily-based analyses, this study offers actionable insights for optimizing real-world applications, including social systems, collaborative platforms, and cybersecurity contexts.

---

### Eventually LIL Regret: Almost Sure $\ln\ln T$ Regret for a sub-Gaussian Mixture on Unbounded Data

Authors: Shubhada Agrawal, Aaditya Ramdas
Published: 2025-12-13
Categories: cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2512.12325v3

We prove that a classic sub-Gaussian mixture proposed by Robbins in a stochastic setting actually satisfies a path-wise (deterministic) regret bound. For every path in a natural ``Ville event'' $\mathcal E_α$, this regret till time $T$ is bounded by $\ln^2(1/α)/V_T + \ln (1/α) + \ln \ln V_T$ up to universal constants, where $V_T$ is a nonnegative, nondecreasing, cumulative variance process. (The bound reduces to $\ln(1/α) + \ln \ln V_T$ if $V_T \geq \ln(1/α)$.) If the data were stochastic, then one can show that $\mathcal E_α$ has probability at least $1-α$ under a wide class of distributions (eg: sub-Gaussian, symmetric, variance-bounded, etc.). In fact, we show that on the Ville event $\mathcal E_0$ of probability one, the regret on every path in $\mathcal E_0$ is eventually bounded by $\ln \ln V_T$ (up to constants). We explain how this work helps bridge the world of adversarial online learning (which usually deals with regret bounds for bounded data), with game-theoretic statistics (which can handle unbounded data, albeit using stochastic assumptions). In short, conditional regret bounds serve as a bridge between stochastic and adversarial betting.

---

### UniMark: Artificial Intelligence Generated Content Identification Toolkit

Authors: Meilin Li, Ji He, Yi Yu, Jia Xu, Shanzhe Lei, Yan Teng, Yingchun Wang, Xuhong Wang
Published: 2025-12-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.12324v3

The rapid proliferation of Artificial Intelligence Generated Content has precipitated a crisis of trust and urgent regulatory demands. However, existing identification tools suffer from fragmentation and a lack of support for visible compliance marking. To address these gaps, we introduce the \textbf{UniMark}, an open-source, unified framework for multimodal content governance. Our system features a modular unified engine that abstracts complexities across text, image, audio, and video modalities. Crucially, we propose a novel dual-operation strategy, natively supporting both \emph{Hidden Watermarking} for copyright protection and \emph{Visible Marking} for regulatory compliance. Furthermore, we establish a standardized evaluation framework with three specialized benchmarks (Image/Video/Audio-Bench) to ensure rigorous performance assessment. This toolkit bridges the gap between advanced algorithms and engineering implementation, fostering a more transparent and secure digital ecosystem.

---