# Research Papers — 2025-12 · bundle page 93 of 175 > Full-text markdown of papers #4601–4650 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/93 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/92.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/94.md) ### WeDetect: Fast Open-Vocabulary Object Detection as Retrieval Authors: Shenghao Fu, Yukun Su, Fengyun Rao, Jing Lyu, Xiaohua Xie, Wei-Shi Zheng Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12309v1 Open-vocabulary object detection aims to detect arbitrary classes via text prompts. Methods without cross-modal fusion layers (non-fusion) offer faster inference by treating recognition as a retrieval problem, \ie, matching regions to text queries in a shared embedding space. In this work, we fully explore this retrieval philosophy and demonstrate its unique advantages in efficiency and versatility through a model family named WeDetect: (1) State-of-the-art performance. WeDetect is a real-time detector with a dual-tower architecture. We show that, with well-curated data and full training, the non-fusion WeDetect surpasses other fusion models and establishes a strong open-vocabulary foundation. (2) Fast backtrack of historical data. WeDetect-Uni is a universal proposal generator based on WeDetect. We freeze the entire detector and only finetune an objectness prompt to retrieve generic object proposals across categories. Importantly, the proposal embeddings are class-specific and enable a new application, object retrieval, supporting retrieval objects in historical data. (3) Integration with LMMs for referring expression comprehension (REC). We further propose WeDetect-Ref, an LMM-based object classifier to handle complex referring expressions, which retrieves target objects from the proposal list extracted by WeDetect-Uni. It discards next-token prediction and classifies objects in a single forward pass. Together, the WeDetect family unifies detection, proposal generation, object retrieval, and REC under a coherent retrieval framework, achieving state-of-the-art performance across 15 benchmarks with high inference efficiency. --- ### MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding Authors: Benjamin Beilharz, Thomas S. A. Wallis Published: 2025-12-13 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2512.12307v5 While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D inputs, they are often assumed to develop an implicit representation of the underlying 3D scene (for example, showing tolerance to partial occlusion, or the ability to reason about relative depth). Here, we introduce MRD (metamers rendered differentiably), an approach that uses physically based differentiable rendering to probe vision models' implicit understanding of generative 3D scene properties, by finding 3D scene parameters that are physically different but produce the same model activation (i.e. are model metamers). Unlike previous pixel-based methods for evaluating model representations, these reconstruction results are always grounded in physical scene descriptions. This means we can, for example, probe a model's sensitivity to object shape while holding material and lighting constant. As a proof-of-principle, we assess multiple models in their ability to recover scene parameters of geometry (shape) and bidirectional reflectance distribution function (material). The results show high similarity in model activation between target and optimized scenes, with varying visual results. Qualitatively, these reconstructions help investigate the physical scene attributes to which models are sensitive or invariant. MRD holds promise for advancing our understanding of both computer and human vision by enabling analysis of how physical scene parameters drive changes in model responses. --- ### OMUDA: Omni-level Masking for Unsupervised Domain Adaptation in Semantic Segmentation Authors: Yang Ou, Xiongwei Zhao, Xinye Yang, Yihan Wang, Yicheng Di, Rong Yuan, Xieyuanli Chen, Xu Zhu Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12303v1 Unsupervised domain adaptation (UDA) enables semantic segmentation models to generalize from a labeled source domain to an unlabeled target domain. However, existing UDA methods still struggle to bridge the domain gap due to cross-domain contextual ambiguity, inconsistent feature representations, and class-wise pseudo-label noise. To address these challenges, we propose Omni-level Masking for Unsupervised Domain Adaptation (OMUDA), a unified framework that introduces hierarchical masking strategies across distinct representation levels. Specifically, OMUDA comprises: 1) a Context-Aware Masking (CAM) strategy that adaptively distinguishes foreground from background to balance global context and local details; 2) a Feature Distillation Masking (FDM) strategy that enhances robust and consistent feature learning through knowledge transfer from pre-trained models; and 3) a Class Decoupling Masking (CDM) strategy that mitigates the impact of noisy pseudo-labels by explicitly modeling class-wise uncertainty. This hierarchical masking paradigm effectively reduces the domain shift at the contextual, representational, and categorical levels, providing a unified solution beyond existing approaches. Extensive experiments on multiple challenging cross-domain semantic segmentation benchmarks validate the effectiveness of OMUDA. Notably, on the SYNTHIA->Cityscapes and GTA5->Cityscapes tasks, OMUDA can be seamlessly integrated into existing UDA methods and consistently achieving state-of-the-art results with an average improvement of 7%. --- ### From Human Intention to Action Prediction: Intention-Driven End-to-End Autonomous Driving Authors: Huan Zheng, Yucheng Zhou, Tianyi Yan, Jiayi Su, Hongjun Chen, Dubing Chen, Xingtai Gui, Wencheng Han, Runzhou Tao, Zhongying Qiu, Jianfei Yang, Jianbing Shen Published: 2025-12-13 Categories: cs.CV, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2512.12302v2 While end-to-end autonomous driving has achieved remarkable progress in geometric control, current systems remain constrained by a command-following paradigm that relies on simple navigational instructions. Transitioning to genuinely intelligent agents requires the capability to interpret and fulfill high-level, abstract human intentions. However, this advancement is hindered by the lack of dedicated benchmarks and semantic-aware evaluation metrics. In this paper, we formally define the task of Intention-Driven End-to-End Autonomous Driving and present Intention-Drive, a comprehensive benchmark designed to bridge this gap. We construct a large-scale dataset featuring complex natural language intentions paired with high-fidelity sensor data. To overcome the limitations of conventional trajectory-based metrics, we introduce the Imagined Future Alignment (IFA), a novel evaluation protocol leveraging generative world models to assess the semantic fulfillment of human goals beyond mere geometric accuracy. Furthermore, we explore the solution space by proposing two distinct paradigms: an end-to-end vision-language planner and a hierarchical agent-based framework. The experiments reveal a critical dichotomy where existing models exhibit satisfactory driving stability but struggle significantly with intention fulfillment. Notably, the proposed frameworks demonstrate superior alignment with human intentions. --- ### TwinFormer: A Dual-Level Transformer for Long-Sequence Time-Series Forecasting Authors: Mahima Kumavat, Aditya Maheshwari Published: 2025-12-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.12301v1 TwinFormer is a hierarchical Transformer for long-sequence time-series forecasting. It divides the input into non-overlapping temporal patches and processes them in two stages: (1) a Local Informer with top-$k$ Sparse Attention models intra-patch dynamics, followed by mean pooling; (2) a Global Informer captures long-range inter-patch dependencies using the same top-$k$ attention. A lightweight GRU aggregates the globally contextualized patch tokens for direct multi-horizon prediction. The resulting architecture achieves linear $O(kLd)$ time and memory complexity. On eight real-world benchmarking datasets from six different domains, including weather, stock price, temperature, power consumption, electricity, and disease, and forecasting horizons $96-720$, TwinFormer secures $27$ positions in the top two out of $34$. Out of the $27$, it achieves the best performance on MAE and RMSE at $17$ places and $10$ at the second-best place on MAE and RMSE. This consistently outperforms PatchTST, iTransformer, FEDformer, Informer, and vanilla Transformers. Ablations confirm the superiority of top-$k$ Sparse Attention over ProbSparse and the effectiveness of GRU-based aggregation. Code is available at this repository: https://github.com/Mahimakumavat1205/TwinFormer. --- ### F5-TTS-RO: Extending F5-TTS to Romanian TTS via Lightweight Input Adaptation Authors: Radu-Gabriel Chivereanu, Tiberiu Boros Published: 2025-12-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.12297v1 This work introduces a lightweight input-level adapter for the F5-TTS model that enables Romanian Language support. To preserve the existing capabilities of the model (voice cloning, English and Chinese support), we keep the original weights frozen, append a sub-network to the model and train it as an extension for the textual embedding matrix of the text encoder. For simplicity, we rely on ConvNeXt module implemented in F5-TTS to also model the co-dependencies between the new character-level embeddings. The module serves as a ``soft`` letter-to-sound layer, converting Romanian text into a continuous representation that the F5-TTS model uses to produce naturally sounding Romanian utterances. We evaluate the model with a pool of 20 human listeners across three tasks: (a) audio similarity between reference and generated speech, (b) pronunciation and naturalness and (c) Romanian-English code-switching. The results indicate that our approach maintains voice cloning capabilities and enables, to a certain extent, code-switching within the same utterance; however, residual English accent characteristics remain. We open-source our code and provide example audio samples at https://github.com/racai-ro/Ro-F5TTS. --- ### GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search Authors: Hyunju Lee, Youngmin Oh, Jeimin Jeon, Donghyeon Baek, Bumsub Ham Published: 2025-12-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.12296v1 Transformer architecture search (TAS) aims to automatically discover efficient vision transformers (ViTs), reducing the need for manual design. Existing TAS methods typically train an over-parameterized network (i.e., a supernet) that encompasses all candidate architectures (i.e., subnets). However, all subnets share the same set of weights, which leads to interference that degrades the smaller subnets severely. We have found that well-trained small subnets can serve as a good foundation for training larger ones. Motivated by this, we propose a progressive training framework, dubbed GrowTAS, that begins with training small subnets and incorporate larger ones gradually. This enables reducing the interference and stabilizing a training process. We also introduce GrowTAS+ that fine-tunes a subset of weights only to further enhance the performance of large subnets. Extensive experiments on ImageNet and several transfer learning benchmarks, including CIFAR-10/100, Flowers, CARS, and INAT-19, demonstrate the effectiveness of our approach over current TAS methods --- ### Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updates Authors: Wenjun Yu, Sitian Chen, Cheng Chen, Amelie Chi Zhou Published: 2025-12-13 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2512.12295v2 Deep Learning Recommendation Models (DLRMs) underpin personalized services but face a critical freshness-accuracy tradeoff due to massive parameter synchronization overheads. Production DLRMs deploy decoupled training/inference clusters, where synchronizing petabyte-scale embedding tables (EMTs) causes multi-minute staleness, degrading recommendation quality and revenue. We observe that (1) inference nodes exhibit sustained CPU underutilization (peak <= 20%), and (2) EMT gradients possess intrinsic low-rank structure, enabling compact update representation. We present LiveUpdate, a system that eliminates inter-cluster synchronization by colocating Low-Rank Adaptation (LoRA) trainers within inference nodes. LiveUpdate addresses two core challenges: (1) dynamic rank adaptation via singular value monitoring to constrain memory overhead (<2% of EMTs), and (2) NUMA-aware resource scheduling with hardware-enforced QoS to eliminate update inference contention (P99 latency impact <20ms). Evaluations show LiveUpdate reduces update costs by 2x versus delta-update baselines while achieving higher accuracy within 1-hour windows. By transforming idle inference resources into freshness engines, LiveUpdate delivers online model updates while outperforming state-of-the-art delta-update methods by 0.04% to 0.24% in accuracy. --- ### Robust Outlier Detection and Low-Latency Concept Drift Adaptation for Data Stream Regression: A Dual-Channel Architecture Authors: Bingbing Wang, Shengyan Sun, Jiaqi Wang, Yu Tang Published: 2025-12-13 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2512.12289v1 Outlier detection and concept drift detection represent two challenges in data analysis. Most studies address these issues separately. However, joint detection mechanisms in regression remain underexplored, where the continuous nature of output spaces makes distinguishing drifts from outliers inherently challenging. To address this, we propose a novel robust regression framework for joint outlier and concept drift detection. Specifically, we introduce a dual-channel decision process that orchestrates prediction residuals into two coupled logic flows: a rapid response channel for filtering point outliers and a deep analysis channel for diagnosing drifts. We further develop the Exponentially Weighted Moving Absolute Deviation with Distinguishable Types (EWMAD-DT) detector to autonomously differentiate between abrupt and incremental drifts via dynamic thresholding. Comprehensive experiments on both synthetic and real-world datasets demonstrate that our unified framework, enhanced by EWMAD-DT, exhibits superior detection performance even when point outliers and concept drifts coexist. --- ### Quantum-Aware Generative AI for Materials Discovery: A Framework for Robust Exploration Beyond DFT Biases Authors: Mahule Roy Published: 2025-12-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.12288v1 Conventional generative models for materials discovery are predominantly trained and validated using data from Density Functional Theory (DFT) with approximate exchange-correlation functionals. This creates a fundamental bottleneck: these models inherit DFT's systematic failures for strongly correlated systems, leading to exploration biases and an inability to discover materials where DFT predictions are qualitatively incorrect. We introduce a quantum-aware generative AI framework that systematically addresses this limitation through tight integration of multi-fidelity learning and active validation. Our approach employs a diffusion-based generator conditioned on quantum-mechanical descriptors and a validator using an equivariant neural network potential trained on a hierarchical dataset spanning multiple levels of theory (PBE, SCAN, HSE06, CCSD(T)). Crucially, we implement a robust active learning loop that quantifies and targets the divergence between low- and high-fidelity predictions. We conduct comprehensive ablation studies to deconstruct the contribution of each component, perform detailed failure mode analysis, and benchmark our framework against state-of-the-art generative models (CDVAE, GNoME, DiffCSP) across several challenging material classes. Our results demonstrate significant practical gains: a 3-5x improvement in successfully identifying potentially stable candidates in high-divergence regions (e.g., correlated oxides) compared to DFT-only baselines, while maintaining computational feasibility. This work provides a rigorous, transparent framework for extending the effective search space of computational materials discovery beyond the limitations of single-fidelity models. --- ### RealDrag: The First Dragging Benchmark with Real Target Image Authors: Ahmad Zafarani, Zahra Dehghanian, Mohammadreza Davoodi, Mohsen Shadroo, MohammadAmin Fazli, Hamid R. Rabiee Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12287v1 The evaluation of drag based image editing models is unreliable due to a lack of standardized benchmarks and metrics. This ambiguity stems from inconsistent evaluation protocols and, critically, the absence of datasets containing ground truth target images, making objective comparisons between competing methods difficult. To address this, we introduce \textbf{RealDrag}, the first comprehensive benchmark for point based image editing that includes paired ground truth target images. Our dataset contains over 400 human annotated samples from diverse video sources, providing source/target images, handle/target points, editable region masks, and descriptive captions for both the image and the editing action. We also propose four novel, task specific metrics: Semantical Distance (SeD), Outer Mask Preserving Score (OMPS), Inner Patch Preserving Score (IPPS), and Directional Similarity (DiS). These metrics are designed to quantify pixel level matching fidelity, check preservation of non edited (out of mask) regions, and measure semantic alignment with the desired task. Using this benchmark, we conduct the first large scale systematic analysis of the field, evaluating 17 SOTA models. Our results reveal clear trade offs among current approaches and establish a robust, reproducible baseline to guide future research. Our dataset and evaluation toolkit will be made publicly available. --- ### Fractional Differential Equation Physics-Informed Neural Network and Its Application in Battery State Estimation Authors: Lujuan Dang, Zilai Wang Published: 2025-12-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.12285v1 Accurate estimation of the State of Charge (SOC) is critical for ensuring the safety, reliability, and performance optimization of lithium-ion battery systems. Conventional data-driven neural network models often struggle to fully characterize the inherent complex nonlinearities and memory-dependent dynamics of electrochemical processes, significantly limiting their predictive accuracy and physical interpretability under dynamic operating conditions. To address this challenge, this study proposes a novel neural architecture termed the Fractional Differential Equation Physics-Informed Neural Network (FDIFF-PINN), which integrates fractional calculus with deep learning. The main contributions of this paper include: (1) Based on a fractional-order equivalent circuit model, a discretized fractional-order partial differential equation is constructed. (2) Comparative experiments were conducted using a dynamic charge/discharge dataset of Panasonic 18650PF batteries under multi-temperature conditions (from -10$^{\circ}$C to 20$^{\circ}$C). --- ### V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval Authors: Donghyuk Kim, Sejeong Yang, Wonjin Shin, Joo-Young Kim Published: 2025-12-13 Categories: eess.IV, cs.AI, cs.AR, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2512.12284v3 Streaming video large language models (LLMs) are increasingly used for real-time multimodal tasks such as video captioning, question answering, conversational agents, and augmented reality. However, these models face fundamental memory and computational challenges because their key-value (KV) caches grow substantially with continuous streaming video input. This process requires an iterative prefill stage, which is a unique feature of streaming video LLMs. Due to its iterative prefill stage, it suffers from significant limitations, including extensive computation, substantial data transfer, and degradation in accuracy. Crucially, this issue is exacerbated for edge deployment, which is the primary target for these models. In this work, we propose V-Rex, the first software-hardware co-designed accelerator that comprehensively addresses both algorithmic and hardware bottlenecks in streaming video LLM inference. At its core, V-Rex introduces ReSV, a training-free dynamic KV cache retrieval algorithm. ReSV exploits temporal and spatial similarity-based token clustering to reduce excessive KV cache memory across video frames. To fully realize these algorithmic benefits, V-Rex offers a compact, low-latency hardware accelerator with a dynamic KV cache retrieval engine (DRE), featuring bit-level and early-exit based computing units. V-Rex achieves unprecedented real-time of 3.9-8.3 FPS and energy-efficient streaming video LLM inference on edge deployment with negligible accuracy loss. While DRE only accounts for 2.2% power and 2.0% area, the system delivers 1.9-19.7x speedup and 3.1-18.5x energy efficiency improvements over AGX Orin GPU. This work is the first to comprehensively tackle KV cache retrieval across algorithms and hardware, enabling real-time streaming video LLM inference on resource-constrained edge devices. --- ### Cognitive-YOLO: LLM-Driven Architecture Synthesis from First Principles of Data for Object Detection Authors: Jiahao Zhao Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12281v2 General-purpose object detection algorithms face a domain-shift bottleneck when deployed in vertical scenarios, and manually customizing a network architecture relies heavily on expert experience with high trial-and-error cost. To address these problems, we present \textbf{Cognitive-YOLO}, an adaptive object-detection model synthesis system driven by a large language model (LLM) collaborating with an autonomous agent. Cognitive-YOLO builds a fully automated \emph{Analyze--Synthesize--Compile} pipeline. First, a data-profiling module quantitatively extracts dataset features, guiding a ReAct-paradigm agent to autonomously retrieve matching network modules from a curated component library. Second, the LLM performs logical reasoning and topological assembly conditioned on the data features, producing a specification-compliant neural architecture description. Finally, a backend hybrid compiler dynamically instantiates the model, closing the loop with end-to-end training and evaluation scheduling. Cross-validation on datasets including rail-surface defects and rice diseases shows that the lightweight models synthesized by Cognitive-YOLO markedly compress the parameter count (down to 1.9M) while matching or surpassing mainstream baselines such as YOLOv11n in mAP@0.5:0.95, effectively balancing model compactness and feature-representation capability. --- ### Feature Aggregation for Efficient Continual Learning of Complex Facial Expressions Authors: Thibault Geoffroy, Myriam Maumy, Lionel Prevost Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12277v1 As artificial intelligence (AI) systems become increasingly embedded in our daily life, the ability to recognize and adapt to human emotions is essential for effective human-computer interaction. Facial expression recognition (FER) provides a primary channel for inferring affective states, but the dynamic and culturally nuanced nature of emotions requires models that can learn continuously without forgetting prior knowledge. In this work, we propose a hybrid framework for FER in a continual learning setting that mitigates catastrophic forgetting. Our approach integrates two complementary modalities: deep convolutional features and facial Action Units (AUs) derived from the Facial Action Coding System (FACS). The combined representation is modelled through Bayesian Gaussian Mixture Models (BGMMs), which provide a lightweight, probabilistic solution that avoids retraining while offering strong discriminative power. Using the Compound Facial Expression of Emotion (CFEE) dataset, we show that our model can first learn basic expressions and then progressively recognize compound expressions. Experiments demonstrate improved accuracy, stronger knowledge retention, and reduced forgetting. This framework contributes to the development of emotionally intelligent AI systems with applications in education, healthcare, and adaptive user interfaces. --- ### Balancing Accuracy and Speed: A Multi-Fidelity Ensemble Kalman Filter with a Machine Learning Surrogate Model Authors: Jeffrey van der Voort, Martin Verlaan, Hanne Kekkonen Published: 2025-12-13 Categories: cs.LG, math.ST, physics.ao-ph arXiv: https://arxiv.org/abs/2512.12276v1 Currently, more and more machine learning (ML) surrogates are being developed for computationally expensive physical models. In this work we investigate the use of a Multi-Fidelity Ensemble Kalman Filter (MF-EnKF) in which the low-fidelity model is such a machine learning surrogate model, instead of a traditional low-resolution or reduced-order model. The idea behind this is to use an ensemble of a few expensive full model runs, together with an ensemble of many cheap but less accurate ML model runs. In this way we hope to reach increased accuracy within the same computational budget. We investigate the performance by testing the approach on two common test problems, namely the Lorenz-2005 model and the Quasi-Geostrophic model. By keeping the original physical model in place, we obtain a higher accuracy than when we completely replace it by the ML model. Furthermore, the MF-EnKF reaches improved accuracy within the same computational budget. The ML surrogate has similar or improved accuracy compared to the low-resolution one, but it can provide a larger speed-up. Our method contributes to increasing the effective ensemble size in the EnKF, which improves the estimation of the initial condition and hence accuracy of the predictions in fields such as meteorology and oceanography. --- ### GRC-Net: Gram Residual Co-attention Net for epilepsy prediction Authors: Bihao You, Jiping Cui Published: 2025-12-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.12273v1 Prediction of epilepsy based on electroencephalogram (EEG) signals is a rapidly evolving field. Previous studies have traditionally applied 1D processing to the entire EEG signal. However, we have adopted the Gram Matrix method to transform the signals into a 3D representation, enabling modeling of signal relationships across dimensions while preserving the temporal dependencies of the one-dimensional signals. Additionally, we observed an imbalance between local and global signals within the EEG data. Therefore, we introduced multi-level feature extraction, utilizing coattention for capturing global signal characteristics and an inception structure for processing local signals, achieving multi-granular feature extraction. Our experiments on the BONN dataset demonstrate that for the most challenging five-class classification task, GRC-Net achieved an accuracy of 93.66%, outperforming existing methods. --- ### Accurate de novo sequencing of the modified proteome with OmniNovo Authors: Yuhan Chen, Shang Qu, Zhiqiang Gao, Yuejin Yang, Xiang Zhang, Sheng Xu, Xinjie Mao, Liujia Qian, Jiaqi Wei, Zijie Qiu, Chenyu You, Lei Bai et al. Published: 2025-12-13 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2512.12272v1 Post-translational modifications (PTMs) serve as a dynamic chemical language regulating protein function, yet current proteomic methods remain blind to a vast portion of the modified proteome. Standard database search algorithms suffer from a combinatorial explosion of search spaces, limiting the identification of uncharacterized or complex modifications. Here we introduce OmniNovo, a unified deep learning framework for reference-free sequencing of unmodified and modified peptides directly from tandem mass spectra. Unlike existing tools restricted to specific modification types, OmniNovo learns universal fragmentation rules to decipher diverse PTMs within a single coherent model. By integrating a mass-constrained decoding algorithm with rigorous false discovery rate estimation, OmniNovo achieves state-of-the-art accuracy, identifying 51\% more peptides than standard approaches at a 1\% false discovery rate. Crucially, the model generalizes to biological sites unseen during training, illuminating the dark matter of the proteome and enabling unbiased comprehensive analysis of cellular regulation. --- ### MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models Authors: Yuqing Lei, Yingjun Du, Yawen Huang, Xiantong Zhen, Ling Shao Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12268v1 Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this issue by adapting prompts with fixed augmentations, which may falter in more challenging settings. In this work, we propose Meta Test-Time Prompt Tuning (MetaTPT), a meta-learning framework that learns a self-supervised auxiliary task to guide test-time prompt tuning. The auxiliary task dynamically learns parameterized augmentations for each sample, enabling more expressive transformations that capture essential features in target domains. MetaTPT adopts a dual-loop optimization paradigm: an inner loop learns a self-supervised task that generates informative views, while the outer loop performs prompt tuning by enforcing consistency across these views. By coupling augmentation learning with prompt tuning, MetaTPT improves test-time adaptation under domain shifts. Extensive experiments demonstrate that MetaTPT achieves state-of-the-art performance on domain generalization and cross-dataset benchmarks. --- ### Hellinger loss function for Generative Adversarial Networks Authors: Giovanni Saraceno, Anand N. Vidyashankar, Claudio Agostinelli Published: 2025-12-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.12267v1 We propose Hellinger-type loss functions for training Generative Adversarial Networks (GANs), motivated by the boundedness, symmetry, and robustness properties of the Hellinger distance. We define an adversarial objective based on this divergence and study its statistical properties within a general parametric framework. We establish the existence, uniqueness, consistency, and joint asymptotic normality of the estimators obtained from the adversarial training procedure. In particular, we analyze the joint estimation of both generator and discriminator parameters, offering a comprehensive asymptotic characterization of the resulting estimators. We introduce two implementations of the Hellinger-type loss and we evaluate their empirical behavior in comparison with the classic (Maximum Likelihood-type) GAN loss. Through a controlled simulation study, we demonstrate that both proposed losses yield improved estimation accuracy and robustness under increasing levels of data contamination. --- ### Market-Bench: Evaluating Large Language Models on Introductory Quantitative Trading and Market Dynamics Authors: Abhay Srivastava, Sam Jung, Spencer Mateega Published: 2025-12-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.12264v2 We introduce MARKET-BENCH, a benchmark that evaluates large language models (LLMs) on introductory quantitative trading tasks by asking them to construct executable backtesters from natural language strategy descriptions and market assumptions. Each instance specifies one of three canonical strategies: scheduled trading on Microsoft (NASDAQ: MSFT), pairs trading on Coca-Cola (NASDAQ: KO) and Pepsi (NASDAQ: PEP), or delta hedging on MSFT. Models must produce code whose profit and loss (P and L), drawdown, and position paths match a verifiable reference implementation. We assess thirteen state-of-the-art models using a multi-round evaluation that separates structural reliability (whether the backtest runs) from numerical accuracy (mean absolute error of the backtest metrics), assigning failed outputs a duplicated-metrics baseline MAE. While most models reliably execute the simplest strategy (average executable passes of 4.08 out of 5 rounds), errors vary by orders of magnitude across models and tasks. Gemini 3 Pro and Claude 4.5 Sonnet combine strong reliability with low error on simpler strategies. GPT-5.2 achieves strong overall performance with perfect executability. GPT-5.1 Codex-Max achieves the lowest best-run error on the easiest task. Qwen3 Max attains perfect executability yet sometimes produces inaccurate profit and loss paths. These results show that current LLMs can scaffold basic trading infrastructure but still struggle to reason robustly about prices, inventory, and risk. We release MARKET-BENCH and a public leaderboard at https://marketbench.ai. --- ### A Multi-Axial Mindset for Ontology Design Lessons from Wikidata's Polyhierarchical Structure Authors: Ege Atacan Doğan, Peter F. Patel-Schneider Published: 2025-12-13 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2512.12260v1 Traditional ontology design emphasizes disjoint and exhaustive top-level distinctions such as continuant vs. occurrent, abstract vs. concrete, or type vs. instance. These distinctions are used to structure unified hierarchies where every entity is classified under a single upper-level category. Wikidata, by contrast, does not enforce a singular foundational taxonomy. Instead, it accommodates multiple classification axes simultaneously under the shared root class entity. This paper analyzes the structural implications of Wikidata's polyhierarchical and multi-axial design. The Wikidata architecture enables a scalable and modular approach to ontology construction, especially suited to collaborative and evolving knowledge graphs. --- ### Optimized Learned Count-Min Sketch Authors: Kyosuke Nishishita, Atsuki Sato, Yusuke Matsui Published: 2025-12-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.12252v1 Count-Min Sketch (CMS) is a memory-efficient data structure for estimating the frequency of elements in a multiset. Learned Count-Min Sketch (LCMS) enhances CMS with a machine learning model to reduce estimation error under the same memory usage, but suffers from slow construction due to empirical parameter tuning and lacks theoretical guarantees on intolerable error probability. We propose Optimized Learned Count-Min Sketch (OptLCMS), which partitions the input domain and assigns each partition to its own CMS instance, with CMS parameters analytically derived for fixed thresholds, and thresholds optimized via dynamic programming with approximate feasibility checks. This reduces the need for empirical validation, enabling faster construction while providing theoretical guarantees under these assumptions. OptLCMS also allows explicit control of the allowable error threshold, improving flexibility in practice. Experiments show that OptLCMS builds faster, achieves lower intolerable error probability, and matches the estimation accuracy of LCMS. --- ### Stochastic Volatility Modelling with LSTM Networks: A Hybrid Approach for S&P 500 Index Volatility Forecasting Authors: Anna Perekhodko, Robert Ślepaczuk Published: 2025-12-13 Categories: q-fin.TR, cs.AI, cs.LG, cs.NE, q-fin.PM arXiv: https://arxiv.org/abs/2512.12250v1 Accurate volatility forecasting is essential in banking, investment, and risk management, because expectations about future market movements directly influence current decisions. This study proposes a hybrid modelling framework that integrates a Stochastic Volatility model with a Long Short Term Memory neural network. The SV model improves statistical precision and captures latent volatility dynamics, especially in response to unforeseen events, while the LSTM network enhances the model's ability to detect complex nonlinear patterns in financial time series. The forecasting is conducted using daily data from the S and P 500 index, covering the period from January 1 1998 to December 31 2024. A rolling window approach is employed to train the model and generate one step ahead volatility forecasts. The performance of the hybrid SV-LSTM model is evaluated through both statistical testing and investment simulations. The results show that the hybrid approach outperforms both the standalone SV and LSTM models and contributes to the development of volatility modelling techniques, providing a foundation for improving risk assessment and strategic investment planning in the context of the S and P 500. --- ### Moment and Highlight Detection via MLLM Frame Segmentation Authors: I Putu Andika Bagas Jiwanta, Ayu Purwarianti Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12246v1 Detecting video moments and highlights from natural-language queries have been unified by transformer-based methods. Other works use generative Multimodal LLM (MLLM) to predict moments and/or highlights as text timestamps, utilizing its reasoning capability. While effective, text-based generation cannot provide direct gradients for frame-level predictions because the model only emits language tokens. Although recent Reinforcement Learning (RL) methods attempt to address the issue, we propose a novel approach by applying segmentation objectives directly on the LLM's output tokens. The LLM is fed with a fixed number of frames alongside a prompt that enforces it to output a sequence of continuous "0" and/or "1" characters, with one character per frame. The "0"/"1" characters benefit from the LLM's inherent language capability while also acting as background and foreground probabilities, respectively. Training employs segmentation losses on the probabilities alongside a normal causal LM loss. At inference, beam search generates sequence and logits, acting as moments and saliency scores, respectively. Despite sampling only 25 frames -- less than half of comparable methods -- our method achieved strong highlight detection (56.74 HIT@1) on QVHighlights. Additionally, our efficient method scores above the baseline (35.28 MAP) for moment retrieval. Empirically, segmentation losses provide a stable complementary learning signal even when the causal LM loss plateaus. --- ### Adversarially Probing Cross-Family Sound Symbolism in 27 Languages Authors: Anika Sharma, Tianyi Niu, Emma Wrenn, Shashank Srivastava Published: 2025-12-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.12245v1 The phenomenon of sound symbolism, the non-arbitrary mapping between word sounds and meanings, has long been demonstrated through anecdotal experiments like Bouba Kiki, but rarely tested at scale. We present the first computational cross-linguistic analysis of sound symbolism in the semantic domain of size. We compile a typologically broad dataset of 810 adjectives (27 languages, 30 words each), each phonemically transcribed and validated with native-speaker audio. Using interpretable classifiers over bag-of-segment features, we find that phonological form predicts size semantics above chance even across unrelated languages, with both vowels and consonants contributing. To probe universality beyond genealogy, we train an adversarial scrubber that suppresses language identity while preserving size signal (also at family granularity). Language prediction averaged across languages and settings falls below chance while size prediction remains significantly above chance, indicating cross-family sound-symbolic bias. We release data, code, and diagnostic tools for future large-scale studies of iconicity. --- ### Semantic Distance Measurement based on Multi-Kernel Gaussian Processes Authors: Yinzhu Cheng, Haihua Xie, Yaqing Wang, Miao He, Mingming Sun Published: 2025-12-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.12238v1 Semantic distance measurement is a fundamental problem in computational linguistics, providing a quantitative characterization of similarity or relatedness between text segments, and underpinning tasks such as text retrieval and text classification. From a mathematical perspective, a semantic distance can be viewed as a metric defined on a space of texts or on a representation space derived from them. However, most classical semantic distance methods are essentially fixed, making them difficult to adapt to specific data distributions and task requirements. In this paper, a semantic distance measure based on multi-kernel Gaussian processes (MK-GP) was proposed. The latent semantic function associated with texts was modeled as a Gaussian process, with its covariance function given by a combined kernel combining Matérn and polynomial components. The kernel parameters were learned automatically from data under supervision, rather than being hand-crafted. This semantic distance was instantiated and evaluated in the context of fine-grained sentiment classification with large language models under an in-context learning (ICL) setup. The experimental results demonstrated the effectiveness of the proposed measure. --- ### Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT Authors: Aujasvit Datta, Jiayun Wang, Asad Aali, Anima Anandkumar Published: 2025-12-13 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.12236v2 Sparse-view Computed Tomography (CT) reconstructs images from a limited number of X-ray projections to reduce radiation and scanning time, which is an ill-posed inverse problem. Existing methods achieve high-fidelity reconstructions but overfit to a fixed acquisition setup, failing to generalize well across sampling rates. For example, convolutional neural networks (CNNs) use the same kernels across resolutions, leading to artifacts when data resolution changes. This is a critical limitation in clinical practice, where acquisition sampling settings vary across organs and diagnostic protocols. We propose Computed Tomography neural Operator (CTO), the first neural operator (NO) framework for CT reconstruction. CTO extends learning from fixed discretized grids to continuous function space, enabling a single model to generalize across measurement sampling rates without retraining. We also propose new NO architectural designs for CT: (i) a dual-domain NO architecture in both sinogram and image spaces, capturing complementary spatial-frequency information, and (ii) rotation-equivariant DIScrete-COntinuous convolutions (DISCO) that exploit the rotational structure inherent in tomographic acquisition. Empirically, CTO outperforms CNNs (> 3.4dB PSNR gain) and other baselines in multi-resolution settings across multiple CT datasets. Compared to state-of-the-art diffusion methods, CTO has 500x faster inference with an average 3dB gain. CTO further demonstrates strong out-of-distribution robustness, maintaining gains under cross-dataset transfer and noisy sinogram conditions. Ablation studies also validate each design choice. CTO establishes neural operators as a principled and practical paradigm for flexible, discretization-agnostic CT reconstruction. Our code is available at https://github.com/neuraloperator/sparse_ct. --- ### Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy Authors: Jonathan Spraggett Published: 2025-12-13 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.12230v1 Fall recovery is a critical skill for humanoid robots in dynamic environments such as RoboCup, where prolonged downtime often decides the match. Recent techniques using deep reinforcement learning (DRL) have produced robust get-up behaviors, yet existing methods require training of separate policies for each robot morphology. This paper presents a single DRL policy capable of recovering from falls across seven humanoid robots with diverse heights (0.48 - 0.81 m), weights (2.8 - 7.9 kg), and dynamics. Trained with CrossQ, the unified policy transfers zero-shot up to 86 +/- 7% (95% CI (81, 89)) on unseen morphologies, eliminating the need for robot-specific training. Comprehensive leave-one-out experiments, morph scaling analysis, and diversity ablations show that targeted morphological coverage improves zero-shot generalization. In some cases, the shared policy even surpasses the specialist baselines. These findings illustrate the practicality of morphology-agnostic control for fall recovery, laying the foundation for generalist humanoid control. The software is open-source and available at: https://github.com/utra-robosoccer/unified-humanoid-getup --- ### Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder Authors: Tianyu Zhang, Dong Liu, Chang Wen Chen Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12229v2 Ultra-low bitrate image compression (below 0.05 bits per pixel) is increasingly critical for bandwidth-constrained and computation-limited encoding scenarios such as edge devices. Existing frameworks typically rely on large pretrained encoders (e.g., VAEs or tokenizer-based models) and perform transform coding within their generative latent space. While these approaches achieve impressive perceptual fidelity, their reliance on heavy encoder networks makes them unsuitable for deployment on weak sender devices. In this work, we explore the feasibility of applying shallow encoders for ultra-low bitrate compression and propose a novel Asymmetric Extreme Image Compression (AEIC) framework that pursues simultaneously encoding simplicity and decoding quality. Specifically, AEIC employs moderate or even shallow encoder networks, while leveraging an one-step diffusion decoder to maintain high-fidelity and high-realism reconstructions under extreme bitrates. To further enhance the efficiency of shallow encoders, we design a dual-side feature distillation scheme that transfers knowledge from AEIC with moderate encoders to its shallow encoder variants. Experiments show that AEIC not only outperforms existing methods on rate-distortion-perception performance at ultra-low bitrates, but also delivers exceptional encoding efficiency for 35.8 FPS on 1080P images, while maintaining competitive decoding speed compared to existing methods. Code is available at https://github.com/LuizScarlet/AEIC. --- ### A Geometric Theory of Cognition for Machine Intelligence Authors: Laha Ale Published: 2025-12-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.12225v3 Developing artificial agents that unify representation, memory, adaptation, and prediction remains a fundamental challenge in artificial intelligence. Here we introduce a geometric framework in which cognitive computation emerges from Riemannian gradient flow on a learned latent manifold. The learned metric encodes representational constraints and computational preferences, while anisotropies in the geometry naturally generate multiple timescales of behaviour, yielding both rapid reactive responses and slower adaptive dynamics without explicit memory modules or recurrent mechanisms. We instantiate this framework through Riemannian representation and dynamics models and evaluate them in partially observable reinforcement-learning environments. Across observation masking, sensory blackouts, dynamics perturbations, and predictive latent-modelling tasks, the proposed approach consistently outperforms feedforward baselines, achieves robustness comparable to recurrent architectures, and produces highly predictable latent trajectories with low long-horizon rollout error. These results suggest that learned latent geometry can serve simultaneously as a substrate for representation, memory, adaptation, and prediction. More broadly, the framework provides a principled connection between dynamical systems, representation learning, and world-model-based intelligence. --- ### Comparison of different segmentation algorithms on brain volume and fractal dimension in infant brain MRIs Authors: Nathalie Alexander, Arnaud Gucciardi, Umberto Michelucci Published: 2025-12-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.12222v1 Accurate segmentation of infant brain MRI is essential for quantifying developmental changes in structure and complexity. However, ongoing myelination and reduced tissue contrast make automated segmentation particularly challenging. This study systematically compared segmentation accuracy and its impact on volumetric and fractal dimension (FD) estimates in infant brain MRI using the Baby Open Brains (BOB) dataset (71 scans, 1-9 months). Two methods, SynthSeg and SamSeg, were evaluated against expert annotations using Dice, Intersection over Union, 95th-percentile Hausdorff distance, and Normalised Mutual Information. SynthSeg outperformed SamSeg across all quality metrics (mean Dice > 0.8 for major regions) and provided volumetric estimates closely matching the manual reference (mean +4% (-28% - 71%)). SamSeg systematically overestimated ventricular and whole-brain volumes (mean +76% (-12% - 190%)). Segmentation accuracy improved with age, consistent with increasing tissue contrast during myelination. Fractal dimension a(FD) nalyses revealed significant regional differences between SynthSeg and expert segmentations, and Bland-Altman limits of agreement indicated that segmentation-related FD variability exceeded most group differences reported in developmental cohorts. Volume and FD deviations were positively correlated across structures, indicating that segmentation bias directly affects FD estimation. Overall, SynthSeg provided the most reliable volumetric and FD results for paediatric MRI, yet small morphological differences in volume and FD should be interpreted with caution due to segmentation-related uncertainty. --- ### Scalable branch-and-bound model selection with non-monotonic criteria including AIC, BIC and Mallows's $\mathit{C_p}$ Authors: Jakob Vanhoefer, Antonia Körner, Domagoj Doresic, Jan Hasenauer, Dilan Pathirana Published: 2025-12-13 Categories: q-bio.QM, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.12221v1 Model selection is a pivotal process in the quantitative sciences, where researchers must navigate between numerous candidate models of varying complexity. Traditional information criteria, such as the corrected Akaike Information Criterion (AICc), Bayesian Information Criterion (BIC), and Mallows's $\mathit{C_p}$, are valuable tools for identifying optimal models. However, the exponential increase in candidate models with each additional model parameter renders the evaluation of these criteria for all models -- a strategy known as exhaustive, or brute-force, searches -- computationally prohibitive. Consequently, heuristic approaches like stepwise regression are commonly employed, albeit without guarantees of finding the globally-optimal model. In this study, we challenge the prevailing notion that non-monotonicity in information criteria precludes bounds on the search space. We introduce a simple but novel bound that enables the development of branch-and-bound algorithms tailored for these non-monotonic functions. We demonstrate that our approach guarantees identification of the optimal model(s) across diverse model classes, sizes, and applications, often with orders of magnitude computational speedups. For instance, in one previously-published model selection task involving $2^{32}$ (approximately 4 billion) candidate models, our method achieves a computational speedup exceeding 6,000. These findings have broad implications for the scalability and effectiveness of model selection in complex scientific domains. --- ### TechImage-Bench: Rubric-Based Evaluation for Technical Image Generation Authors: Minheng Ni, Zhengyuan Yang, Yaowen Zhang, Linjie Li, Chung-Ching Lin, Kevin Lin, Zhendong Wang, Xiaofei Wang, Shujie Liu, Lei Zhang, Wangmeng Zuo, Lijuan Wang Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12220v2 We study technical image generation, where a model must synthesize information-dense, scientifically precise illustrations from detailed descriptions rather than merely produce visually plausible pictures. To quantify the progress, we introduce TechImage-Bench, a rubric-based benchmark that targets biology schematics, engineering/patent drawings, and general technical illustrations. For 654 figures collected from real textbooks and technical reports, we construct detailed image instructions and a hierarchy of rubrics that decompose correctness into 6,076 criteria and 44,131 binary checks. Rubrics are derived from surrounding text and reference figures using large multimodal models, and are evaluated by an automated LMM-based judge with a principled penalty scheme that aggregates sub-question outcomes into interpretable criterion scores. We benchmark several representative text-to-image models on TechImage-Bench and find that, despite strong open-domain performance, the best base model reaches only 0.801 rubric accuracy and 0.576 criterion score overall, revealing substantial gaps in fine-grained scientific fidelity. Finally, we show that the same rubrics provide actionable supervision: feeding failed checks back into an editing model for iterative refinement boosts a strong generator from 0.660 to 0.865 in rubric accuracy and from 0.382 to 0.697 in criterion score. TechImage-Bench thus offers both a rigorous diagnostic for technical image generation and a scalable signal for improving specification-faithful scientific illustrations. --- ### Fine-Grained Zero-Shot Learning with Attribute-Centric Representations Authors: Zhi Chen, Jingcai Guo, Taotao Cai, Yuxiang Cai Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12219v1 Recognizing unseen fine-grained categories demands a model that can distinguish subtle visual differences. This is typically achieved by transferring visual-attribute relationships from seen classes to unseen classes. The core challenge is attribute entanglement, where conventional models collapse distinct attributes like color, shape, and texture into a single visual embedding. This causes interference that masks these critical distinctions. The post-hoc solutions of previous work are insufficient, as they operate on representations that are already mixed. We propose a zero-shot learning framework that learns AttributeCentric Representations (ACR) to tackle this problem by imposing attribute disentanglement during representation learning. ACR is achieved with two mixture-of-experts components, including Mixture of Patch Experts (MoPE) and Mixture of Attribute Experts (MoAE). First, MoPE is inserted into the transformer using a dual-level routing mechanism to conditionally dispatch image patches to specialized experts. This ensures coherent attribute families are processed by dedicated experts. Finally, the MoAE head projects these expert-refined features into sparse, partaware attribute maps for robust zero-shot classification. On zero-shot learning benchmark datasets CUB, AwA2, and SUN, our ACR achieves consistent state-of-the-art results. --- ### Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking Authors: Rheeya Uppaal, Phu Mon Htut, Min Bai, Nikolaos Pappas, Zheng Qi, Sandesh Swamy Published: 2025-12-13 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.12218v2 Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful intermediate steps, or reason faithfully yet fail on the final prediction. Standard evaluations that only measure final-answer accuracy cannot distinguish these behaviors. We introduce the visual faithfulness of reasoning chains as a distinct evaluation dimension, focusing on whether the perception steps of a reasoning chain are grounded in the image. We propose a training- and reference-free framework that decomposes chains into perception versus reasoning steps and uses off-the-shelf VLM judges for step-level faithfulness, additionally verifying this approach through a human meta-evaluation. Building on this metric, we present a lightweight self-reflection procedure that detects and locally regenerates unfaithful perception steps without any training. Across multiple reasoning-trained VLMs and perception-heavy benchmarks, our method reduces Unfaithful Perception Rate while preserving final-answer accuracy, improving the reliability of multimodal reasoning. --- ### Training Versatile Coding Agents in Synthetic Environments Authors: Yiqi Zhu, Apurva Gandhi, Graham Neubig Published: 2025-12-13 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.12216v2 Prior works on training software engineering agents have explored utilizing existing resources such as issues on GitHub repositories to construct software engineering tasks and corresponding test suites. These approaches face two key limitations: (1) their reliance on pre-existing GitHub repositories offers limited flexibility, and (2) their primary focus on issue resolution tasks restricts their applicability to the much wider variety of tasks a software engineer must handle. To overcome these challenges, we introduce SWE-Playground, a novel pipeline for generating environments and trajectories which supports the training of versatile coding agents. Unlike prior efforts, SWE-Playground synthetically generates projects and tasks from scratch with strong language models and agents, eliminating reliance on external data sources. This allows us to tackle a much wider variety of coding tasks, such as reproducing issues by generating unit tests and implementing libraries from scratch. We demonstrate the effectiveness of this approach on three distinct benchmarks, and results indicate that SWE-Playground produces trajectories with dense training signal, enabling agents to reach comparable performance with significantly fewer trajectories than previous works. --- ### Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving Authors: Longchao Da, David Isele, Hua Wei, Manish Saroya Published: 2025-12-13 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2512.12211v1 Being able to anticipate the motion of surrounding agents is essential for the safe operation of autonomous driving systems in dynamic situations. While various methods have been proposed for trajectory prediction, the current evaluation practices still rely on error-based metrics (e.g., ADE, FDE), which reveal the accuracy from a post-hoc view but ignore the actual effect the predictor brings to the self-driving vehicles (SDVs), especially in complex interactive scenarios: a high-quality predictor not only chases accuracy, but should also captures all possible directions a neighbor agent might move, to support the SDVs' cautious decision-making. Given that the existing metrics hardly account for this standard, in our work, we propose a comprehensive pipeline that adaptively evaluates the predictor's performance by two dimensions: accuracy and diversity. Based on the criticality of the driving scenario, these two dimensions are dynamically combined and result in a final score for the predictor's performance. Extensive experiments on a closed-loop benchmark using real-world datasets show that our pipeline yields a more reasonable evaluation than traditional metrics by better reflecting the correlation of the predictors' evaluation with the autonomous vehicles' driving performance. This evaluation pipeline shows a robust way to select a predictor that potentially contributes most to the SDV's driving performance. --- ### EEG-DLite: Dataset Distillation for Efficient Large EEG Model Training Authors: Yuting Tang, Weibang Jiang, Shanglin Li, Yong Li, Chenyu Liu, Xinliang Zhou, Yi Ding, Cuntai Guan Published: 2025-12-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.12210v2 Large-scale EEG foundation models have shown strong generalization across a range of downstream tasks, but their training remains resource-intensive due to the volume and variable quality of EEG data. In this work, we introduce EEG-DLite, a data distillation framework that enables more efficient pre-training by selectively removing noisy and redundant samples from large EEG datasets. EEG-DLite begins by encoding EEG segments into compact latent representations using a self-supervised autoencoder, allowing sample selection to be performed efficiently and with reduced sensitivity to noise. Based on these representations, EEG-DLite filters out outliers and minimizes redundancy, resulting in a smaller yet informative subset that retains the diversity essential for effective foundation model training. Through extensive experiments, we demonstrate that training on only 5 percent of a 2,500-hour dataset curated with EEG-DLite yields performance comparable to, and in some cases better than, training on the full dataset across multiple downstream tasks. To our knowledge, this is the first systematic study of pre-training data distillation in the context of EEG foundation models. EEG-DLite provides a scalable and practical path toward more effective and efficient physiological foundation modeling. The code is available at https://github.com/t170815518/EEG-DLite. --- ### CineLOG: A Training Free Approach for Cinematic Long Video Generation Authors: Zahra Dehghanian, Morteza Abolghasemi, Hamid Beigy, Hamid R. Rabiee Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12209v1 Controllable video synthesis is a central challenge in computer vision, yet current models struggle with fine grained control beyond textual prompts, particularly for cinematic attributes like camera trajectory and genre. Existing datasets often suffer from severe data imbalance, noisy labels, or a significant simulation to real gap. To address this, we introduce CineLOG, a new dataset of 5,000 high quality, balanced, and uncut video clips. Each entry is annotated with a detailed scene description, explicit camera instructions based on a standard cinematic taxonomy, and genre label, ensuring balanced coverage across 17 diverse camera movements and 15 film genres. We also present our novel pipeline designed to create this dataset, which decouples the complex text to video (T2V) generation task into four easier stages with more mature technology. To enable coherent, multi shot sequences, we introduce a novel Trajectory Guided Transition Module that generates smooth spatio-temporal interpolation. Extensive human evaluations show that our pipeline significantly outperforms SOTA end to end T2V models in adhering to specific camera and screenplay instructions, while maintaining professional visual quality. All codes and data are available at https://cine-log.pages.dev. --- ### A Hybrid Deep Learning Framework for Emotion Recognition in Children with Autism During NAO Robot-Mediated Interaction Authors: Indranil Bhattacharjee, Vartika Narayani Srinet, Anirudha Bhattacharjee, Braj Bhushan, Bishakh Bhattacharya Published: 2025-12-13 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.12208v1 Understanding emotional responses in children with Autism Spectrum Disorder (ASD) during social interaction remains a critical challenge in both developmental psychology and human-robot interaction. This study presents a novel deep learning pipeline for emotion recognition in autistic children in response to a name-calling event by a humanoid robot (NAO), under controlled experimental settings. The dataset comprises of around 50,000 facial frames extracted from video recordings of 15 children with ASD. A hybrid model combining a fine-tuned ResNet-50-based Convolutional Neural Network (CNN) and a three-layer Graph Convolutional Network (GCN) trained on both visual and geometric features extracted from MediaPipe FaceMesh landmarks. Emotions were probabilistically labeled using a weighted ensemble of two models: DeepFace's and FER, each contributing to soft-label generation across seven emotion classes. Final classification leveraged a fused embedding optimized via Kullback-Leibler divergence. The proposed method demonstrates robust performance in modeling subtle affective responses and offers significant promise for affective profiling of ASD children in clinical and therapeutic human-robot interaction contexts, as the pipeline effectively captures micro emotional cues in neurodivergent children, addressing a major gap in autism-specific HRI research. This work represents the first such large-scale, real-world dataset and pipeline from India on autism-focused emotion analysis using social robotics, contributing an essential foundation for future personalized assistive technologies. --- ### Not All Transparency Is Equal: Source Presentation Effects on Attention, Interaction, and Persuasion in Conversational Search Authors: Jiangen He, Jiqun Liu Published: 2025-12-13 Categories: cs.HC, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2512.12207v1 Conversational search systems increasingly provide source citations, yet how citation or source presentation formats influence user engagement remains unclear. We conducted a crowdsourcing user experiment with 394 participants comparing four source presentation designs that varied citation visibility and accessibility: collapsible lists, hover cards, footer lists, and aligned sidebars.High-visibility interfaces generated substantially more hovering on sources, though clicking remained infrequent across all conditions. While interface design showed limited effects on user experience and perception measures, it significantly influenced knowledge, interest, and agreement changes. High-visibility interfaces initially reduced knowledge gain and interest, but these positive effects emerged with increasing source usage. The sidebar condition uniquely increased agreement change. Our findings demonstrate that source presentation alone may not enhance engagement and can even reduce it when insufficient sources are provided. --- ### ALERT Open Dataset and Input-Size-Agnostic Vision Transformer for Driver Activity Recognition using IR-UWB Authors: Jeongjun Park, Sunwook Hwang, Hyeonho Noh, Jin Mo Yang, Hyun Jong Yang, Saewoong Bahk Published: 2025-12-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.12206v2 Distracted driving contributes to fatal crashes worldwide. To address this, researchers are using driver activity recognition (DAR) with impulse radio ultra-wideband (IR-UWB) radar, which offers advantages such as interference resistance, low power consumption, and privacy preservation. However, two challenges limit its adoption: the lack of large-scale real-world UWB datasets covering diverse distracted driving behaviors, and the difficulty of adapting fixed-input Vision Transformers (ViTs) to UWB radar data with non-standard dimensions. This work addresses both challenges. We present the ALERT dataset, which contains 10,220 radar samples of seven distracted driving activities collected in real driving conditions. We also propose the input-size-agnostic Vision Transformer (ISA-ViT), a framework designed for radar-based DAR. The proposed method resizes UWB data to meet ViT input requirements while preserving radar-specific information such as Doppler shifts and phase characteristics. By adjusting patch configurations and leveraging pre-trained positional embedding vectors (PEVs), ISA-ViT overcomes the limitations of naive resizing approaches. In addition, a domain fusion strategy combines range- and frequency-domain features to further improve classification performance. Comprehensive experiments demonstrate that ISA-ViT achieves a 22.68% accuracy improvement over an existing ViT-based approach for UWB-based DAR. By publicly releasing the ALERT dataset and detailing our input-size-agnostic strategy, this work facilitates the development of more robust and scalable distracted driving detection systems for real-world deployment. --- ### A Multi-Year Urban Streetlight Imagery Dataset for Visual Monitoring and Spatio-Temporal Drift Detection Authors: Peizheng Li, Ioannis Mavromatis, Ajith Sahadevan, Tim Farnham, Adnan Aijaz, Aftab Khan Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12205v1 We present a large-scale, longitudinal visual dataset of urban streetlights captured by 22 fixed-angle cameras deployed across Bristol, U.K., from 2021 to 2025. The dataset contains over 526,000 images, collected hourly under diverse lighting, weather, and seasonal conditions. Each image is accompanied by rich metadata, including timestamps, GPS coordinates, and device identifiers. This unique real-world dataset enables detailed investigation of visual drift, anomaly detection, and MLOps strategies in smart city deployments. To promtoe seconardary analysis, we additionally provide a self-supervised framework based on convolutional variational autoencoders (CNN-VAEs). Models are trained separately for each camera node and for day/night image sets. We define two per-sample drift metrics: relative centroid drift, capturing latent space deviation from a baseline quarter, and relative reconstruction error, measuring normalized image-domain degradation. This dataset provides a realistic, fine-grained benchmark for evaluating long-term model stability, drift-aware learning, and deployment-ready vision systems. The images and structured metadata are publicly released in JPEG and CSV formats, supporting reproducibility and downstream applications such as streetlight monitoring, weather inference, and urban scene understanding. The dataset can be found at https://doi.org/10.5281/zenodo.17781192 and https://doi.org/10.5281/zenodo.17859120. --- ### Navigation Around Unknown Space Objects Using Visible-Thermal Image Fusion Authors: Eric J. Elias, Michael Esswein, Jonathan P. How, David W. Miller Published: 2025-12-13 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.12203v2 As the popularity of on-orbit operations grows, so does the need for precise navigation around unknown resident space objects (RSOs) such as other spacecraft, orbital debris, and asteroids. The use of Simultaneous Localization and Mapping (SLAM) algorithms is often studied as a method to map out the surface of an RSO and find the inspector's relative pose using a lidar or conventional camera. However, conventional cameras struggle during eclipse or shadowed periods, and lidar, though robust to lighting conditions, tends to be heavier, bulkier, and more power-intensive. Thermal-infrared cameras can track the target RSO throughout difficult illumination conditions without these limitations. While useful, thermal-infrared imagery lacks the resolution and feature-richness of visible cameras. In this work, images of a target satellite in low Earth orbit are photo-realistically simulated in both visible and thermal-infrared bands. Pixel-level fusion methods are used to create visible/thermal-infrared composites that leverage the best aspects of each camera. Navigation errors from a monocular SLAM algorithm are compared between visible, thermal-infrared, and fused imagery in various lighting and trajectories. Fused imagery yields substantially improved navigation performance over visible-only and thermal-only methods. --- ### Epistemoverse: Toward an AI-Driven Knowledge Metaverse for Intellectual Heritage Preservation Authors: Predrag K. Nikolić, Robert Prentner Published: 2025-12-13 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.12201v1 Large language models (LLMs) have often been characterized as "stochastic parrots" that merely reproduce fragments of their training data. This study challenges that assumption by demonstrating that, when placed in an appropriate dialogical context, LLMs can develop emergent conceptual structures and exhibit interaction-driven (re-)structuring of cognitive interfaces and reflective question-asking. Drawing on the biological principle of cloning and Socrates' maieutic method, we analyze authentic philosophical debates generated among AI-reincarnated philosophers within the interactive art installations of the Syntropic Counterpoints project. By engaging digital counterparts of Aristotle, Nietzsche, Machiavelli, and Sun Tzu in iterative discourse, the study reveals how machine dialogue can give rise to inferential coherence, reflective questioning, and creative synthesis. Based on these findings, we propose the concept of the Epistemoverse--a metaverse of knowledge where human and machine cognition intersect to preserve, reinterpret, and extend intellectual heritage through AI-driven interaction. This framework positions virtual and immersive environments as new spaces for epistemic exchange, digital heritage, and collaborative creativity. --- ### Thermal RGB Fusion for Micro-UAV Wildfire Perimeter Tracking with Minimal Comms Authors: Ercan Erkalkan, Vedat Topuz, Ayça Ak Published: 2025-12-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.12199v1 This study introduces a lightweight perimeter tracking method designed for micro UAV teams operating over wildfire environments under limited bandwidth conditions. Thermal image frames generate coarse hot region masks through adaptive thresholding and morphological refinement, while RGB frames contribute edge cues and suppress texture related false detections using gradient based filtering. A rule level merging strategy selects boundary candidates and simplifies them via the Ramer Douglas Peucker algorithm. The system incorporates periodic beacons and an inertial feedback loop that maintains trajectory stability in the presence of GPS degradation. The guidance loop targets sub 50 ms latency on embedded System on Chip (SoC) platforms by constraining per frame pixel operations and precomputing gradient tables. Small scale simulations demonstrate reductions in average path length and boundary jitter compared to a pure edge tracking baseline, while maintaining environmental coverage measured through intersection merge analysis. Battery consumption and computational utilization confirm the feasibility of achieving 10, 15 m/s forward motion on standard micro platforms. This approach enables rapid deployment in the field, requiring robust sensing and minimal communications for emergency reconnaissance applications. --- ### MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching Authors: Jirui Jin, Cheng Zeng, Pawan Prakash, Ellad B. Tadmor, Adrian Roitberg, Richard G. Hennig, Stefano Martiniani, Mingjie Liu Published: 2025-12-13 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2512.12198v1 Key objectives in conditional molecular generation include ensuring chemical validity, aligning generated molecules with target properties, promoting structural diversity, and enabling efficient sampling for discovery. Recent advances in computer vision introduced a range of new guidance strategies for generative models, many of which can be adapted to support these goals. In this work, we integrate state-of-the-art guidance methods -- including classifier-free guidance, autoguidance, and model guidance -- in a leading molecule generation framework built on an SE(3)-equivariant flow matching process. We propose a hybrid guidance strategy that separately guides continuous and discrete molecular modalities -- operating on velocity fields and predicted logits, respectively -- while jointly optimizing their guidance scales via Bayesian optimization. Our implementation, benchmarked on the QM9 and QMe14S datasets, achieves new state-of-the-art performance in property alignment for de novo molecular generation. The generated molecules also exhibit high structural validity. Furthermore, we systematically compare the strengths and limitations of various guidance methods, offering insights into their broader applicability. --- ### AutoMV: An Automatic Multi-Agent System for Music Video Generation Authors: Xiaoxuan Tang, Xinping Lei, Chaoran Zhu, Shiyun Chen, Ruibin Yuan, Yizhi Li, Changjae Oh, Ge Zhang, Wenhao Huang, Emmanouil Benetos, Yang Liu, Jiaheng Liu et al. Published: 2025-12-13 Categories: cs.MM, cs.CV, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2512.12196v1 Music-to-Video (M2V) generation for full-length songs faces significant challenges. Existing methods produce short, disjointed clips, failing to align visuals with musical structure, beats, or lyrics, and lack temporal consistency. We propose AutoMV, a multi-agent system that generates full music videos (MVs) directly from a song. AutoMV first applies music processing tools to extract musical attributes, such as structure, vocal tracks, and time-aligned lyrics, and constructs these features as contextual inputs for following agents. The screenwriter Agent and director Agent then use this information to design short script, define character profiles in a shared external bank, and specify camera instructions. Subsequently, these agents call the image generator for keyframes and different video generators for "story" or "singer" scenes. A Verifier Agent evaluates their output, enabling multi-agent collaboration to produce a coherent longform MV. To evaluate M2V generation, we further propose a benchmark with four high-level categories (Music Content, Technical, Post-production, Art) and twelve ine-grained criteria. This benchmark was applied to compare commercial products, AutoMV, and human-directed MVs with expert human raters: AutoMV outperforms current baselines significantly across all four categories, narrowing the gap to professional MVs. Finally, we investigate using large multimodal models as automatic MV judges; while promising, they still lag behind human expert, highlighting room for future work. --- ### SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation Authors: Xuancheng Xu, Yaning Li, Sisi You, Bing-Kun Bao Published: 2025-12-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.12193v1 Customized video generation aims to produce videos that faithfully preserve the subject's appearance from reference images while maintaining temporally consistent motion from reference videos. Existing methods struggle to ensure both subject appearance similarity and motion pattern consistency due to the lack of object-level guidance for subject and motion. To address this, we propose SMRABooth, which leverages the self-supervised encoder and optical flow encoder to provide object-level subject and motion representations. These representations are aligned with the model during the LoRA fine-tuning process. Our approach is structured in three core stages: (1) We exploit subject representations via a self-supervised encoder to guide subject alignment, enabling the model to capture overall structure of subject and enhance high-level semantic consistency. (2) We utilize motion representations from an optical flow encoder to capture structurally coherent and object-level motion trajectories independent of appearance. (3) We propose a subject-motion association decoupling strategy that applies sparse LoRAs injection across both locations and timing, effectively reducing interference between subject and motion LoRAs. Extensive experiments show that SMRABooth excels in subject and motion customization, maintaining consistent subject appearance and motion patterns, proving its effectiveness in controllable text-to-video generation. ---