# Research Papers — 2025-12 · bundle page 64 of 175

> Full-text markdown of papers #3151–3200 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/64
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/63.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/65.md)

### YOLO11-4K: An Efficient Architecture for Real-Time Small Object Detection in 4K Panoramic Images

Authors: Huma Hafeez, Matthew Garratt, Jo Plested, Sankaran Iyer, Arcot Sowmya
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16493v1

The processing of omnidirectional 360-degree images poses significant challenges for object detection due to inherent spatial distortions, wide fields of view, and ultra-high-resolution inputs. Conventional detectors such as YOLO are optimised for standard image sizes (for example, 640x640 pixels) and often struggle with the computational demands of 4K or higher-resolution imagery typical of 360-degree vision. To address these limitations, we introduce YOLO11-4K, an efficient real-time detection framework tailored for 4K panoramic images. The architecture incorporates a novel multi-scale detection head with a P2 layer to improve sensitivity to small objects often missed at coarser scales, and a GhostConv-based backbone to reduce computational complexity without sacrificing representational power. To enable evaluation, we manually annotated the CVIP360 dataset, generating 6,876 frame-level bounding boxes and producing a publicly available, detection-ready benchmark for 4K panoramic scenes. YOLO11-4K achieves 0.95 mAP at 0.50 IoU with 28.3 milliseconds inference per frame, representing a 75 percent latency reduction compared to YOLO11 (112.3 milliseconds), while also improving accuracy (mAP at 0.50 of 0.95 versus 0.908). This balance of efficiency and precision enables robust object detection in expansive 360-degree environments, making the framework suitable for real-world high-resolution panoramic applications. While this work focuses on 4K omnidirectional images, the approach is broadly applicable to high-resolution detection tasks in autonomous navigation, surveillance, and augmented reality.

---

### Best Practices For Empirical Meta-Algorithmic Research: Guidelines from the COSEAL Research Network

Authors: Theresa Eimer, Lennart Schäpermeier, André Biedenkapp, Alexander Tornede, Lars Kotthoff, Pieter Leyman, Matthias Feurer, Katharina Eggensperger, Kaitlin Maile, Tanja Tornede, Anna Kozak, Ke Xue et al.
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16491v2

Empirical research on meta-algorithmics, such as algorithm selection, configuration, and scheduling, often relies on extensive and thus computationally expensive experiments. With the large degree of freedom we have over our experimental setup and design comes a plethora of possible error sources that threaten the scalability and validity of our scientific insights. Best practices for meta-algorithmic research exist, but they are scattered between different publications and fields, and continue to evolve separately from each other. In this report, we collect good practices for empirical meta-algorithmic research across the subfields of the COSEAL community, encompassing the entire experimental cycle: from formulating research questions and selecting an experimental design, to executing experiments, and ultimately, analyzing and presenting results impartially. It establishes the current state-of-the-art practices within meta-algorithmic research and serves as a guideline to both new researchers and practitioners in meta-algorithmic fields.

---

### Best Practices For Empirical Meta-Algorithmic Research Guidelines from the COSEAL Research Network

Authors: Theresa Eimer, Lennart Schäpermeier, André Biedenkapp, Alexander Tornede, Lars Kotthoff, Pieter Leyman, Matthias Feurer, Katharina Eggensperger, Kaitlin Maile, Tanja Tornede, Anna Kozak, Ke Xue et al.
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16491v1

Empirical research on meta-algorithmics, such as algorithm selection, configuration, and scheduling, often relies on extensive and thus computationally expensive experiments. With the large degree of freedom we have over our experimental setup and design comes a plethora of possible error sources that threaten the scalability and validity of our scientific insights. Best practices for meta-algorithmic research exist, but they are scattered between different publications and fields, and continue to evolve separately from each other. In this report, we collect good practices for empirical meta-algorithmic research across the subfields of the COSEAL community, encompassing the entire experimental cycle: from formulating research questions and selecting an experimental design, to executing ex- periments, and ultimately, analyzing and presenting results impartially. It establishes the current state-of-the-art practices within meta-algorithmic research and serves as a guideline to both new researchers and practitioners in meta-algorithmic fields.

---

### Advantages and limitations in the use of transfer learning for individual treatment effects in causal machine learning

Authors: Seyda Betul Aydin, Holger Brandt
Published: 2025-12-18
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.16489v1

Generalizing causal knowledge across diverse environments is challenging, especially when estimates from large-scale datasets must be applied to smaller or systematically different contexts, where external validity is critical. Model-based estimators of individual treatment effects (ITE) from machine learning require large sample sizes, limiting their applicability in domains such as behavioral sciences with smaller datasets. We demonstrate how estimation of ITEs with Treatment Agnostic Representation Networks (TARNet; Shalit et al., 2017) can be improved by leveraging knowledge from source datasets and adapting it to new settings via transfer learning (TL-TARNet; Aloui et al., 2023). In simulations that vary source and sample sizes and consider both randomized and non-randomized intervention target settings, the transfer-learning extension TL-TARNet improves upon standard TARNet, reducing ITE error and attenuating bias when a large unbiased source is available and target samples are small. In an empirical application using the India Human Development Survey (IHDS-II), we estimate the effect of mothers' firewood collection time on children's weekly study time; transfer learning pulls the target mean ITEs toward the source ITE estimate, reducing bias in the estimates obtained without transfer. These results suggest that transfer learning for causal models can improve the estimation of ITE in small samples.

---

### Smile on the Face, Sadness in the Eyes: Bridging the Emotion Gap with a Multimodal Dataset of Eye and Facial Behaviors

Authors: Kejun Liu, Yuanyuan Liu, Lin Wei, Chang Tang, Yibing Zhan, Zijing Chen, Zhe Chen
Published: 2025-12-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.16485v1

Emotion Recognition (ER) is the process of analyzing and identifying human emotions from sensing data. Currently, the field heavily relies on facial expression recognition (FER) because visual channel conveys rich emotional cues. However, facial expressions are often used as social tools rather than manifestations of genuine inner emotions. To understand and bridge this gap between FER and ER, we introduce eye behaviors as an important emotional cue and construct an Eye-behavior-aided Multimodal Emotion Recognition (EMER) dataset. To collect data with genuine emotions, spontaneous emotion induction paradigm is exploited with stimulus material, during which non-invasive eye behavior data, like eye movement sequences and eye fixation maps, is captured together with facial expression videos. To better illustrate the gap between ER and FER, multi-view emotion labels for mutimodal ER and FER are separately annotated. Furthermore, based on the new dataset, we design a simple yet effective Eye-behavior-aided MER Transformer (EMERT) that enhances ER by bridging the emotion gap. EMERT leverages modality-adversarial feature decoupling and a multitask Transformer to model eye behaviors as a strong complement to facial expressions. In the experiment, we introduce seven multimodal benchmark protocols for a variety of comprehensive evaluations of the EMER dataset. The results show that the EMERT outperforms other state-of-the-art multimodal methods by a great margin, revealing the importance of modeling eye behaviors for robust ER. To sum up, we provide a comprehensive analysis of the importance of eye behaviors in ER, advancing the study on addressing the gap between FER and ER for more robust ER performance. Our EMER dataset and the trained EMERT models will be publicly available at https://github.com/kejun1/EMER.

---

### Guiding Perception-Reasoning Closer to Human in Blind Image Quality Assessment

Authors: Yuan Li, Yahan Yu, Youyuan Lin, Yong-Hao Yang, Chenhui Chu, Shin'ya Nishida
Published: 2025-12-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.16484v1

Humans assess image quality through a perception-reasoning cascade, integrating sensory cues with implicit reasoning to form self-consistent judgments. In this work, we investigate how a model can acquire both human-like and self-consistent reasoning capability for blind image quality assessment (BIQA). We first collect human evaluation data that capture several aspects of human perception-reasoning pipeline. Then, we adopt reinforcement learning, using human annotations as reward signals to guide the model toward human-like perception and reasoning. To enable the model to internalize self-consistent reasoning capability, we design a reward that drives the model to infer the image quality purely from self-generated descriptions. Empirically, our approach achieves score prediction performance comparable to state-of-the-art BIQA systems under general metrics, including Pearson and Spearman correlation coefficients. In addition to the rating score, we assess human-model alignment using ROUGE-1 to measure the similarity between model-generated and human perception-reasoning chains. On over 1,000 human-annotated samples, our model reaches a ROUGE-1 score of 0.512 (cf. 0.443 for baseline), indicating substantial coverage of human explanations and marking a step toward human-like interpretable reasoning in BIQA.

---

### FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models

Authors: Senmao Li, Kai Wang, Salman Khan, Fahad Shahbaz Khan, Jian Yang, Yaxing Wang
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16483v2

Visual Autoregressive (VAR) modeling departs from the next-token prediction paradigm of traditional Autoregressive (AR) models through next-scale prediction, enabling high-quality image generation. However, the VAR paradigm suffers from sharply increased computational complexity and running time at large-scale steps. Although existing acceleration methods reduce runtime for large-scale steps, but rely on manual step selection and overlook the varying importance of different stages in the generation process. To address this challenge, we present FasterVAR, a systematic study and plug-and-play acceleration framework for VAR models. Our analysis shows that early steps are critical for preserving semantic and structural consistency and should remain intact,while later steps mainly refine details and can be pruned or approximated for acceleration. Building on these insights, FasterVAR introduces a plug-and-play acceleration strategy that exploits semantic irrelevance and low-rank properties in late-stage computations, without requiring additional training. Our proposed FasterVAR achieves up to 3.4x speedup with almost no performance loss. consistently outperforming existing acceleration baselines.These results highlight stage-aware design as a powerful principle for efficient visual autoregressive image generation.

---

### StageVAR: Stage-Aware Acceleration for Visual Autoregressive Models

Authors: Senmao Li, Kai Wang, Salman Khan, Fahad Shahbaz Khan, Jian Yang, Yaxing Wang
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16483v1

Visual Autoregressive (VAR) modeling departs from the next-token prediction paradigm of traditional Autoregressive (AR) models through next-scale prediction, enabling high-quality image generation. However, the VAR paradigm suffers from sharply increased computational complexity and running time at large-scale steps. Although existing acceleration methods reduce runtime for large-scale steps, but rely on manual step selection and overlook the varying importance of different stages in the generation process. To address this challenge, we present StageVAR, a systematic study and stage-aware acceleration framework for VAR models. Our analysis shows that early steps are critical for preserving semantic and structural consistency and should remain intact, while later steps mainly refine details and can be pruned or approximated for acceleration. Building on these insights, StageVAR introduces a plug-and-play acceleration strategy that exploits semantic irrelevance and low-rank properties in late-stage computations, without requiring additional training. Our proposed StageVAR achieves up to 3.4x speedup with only a 0.01 drop on GenEval and a 0.26 decrease on DPG, consistently outperforming existing acceleration baselines. These results highlight stage-aware design as a powerful principle for efficient visual autoregressive image generation.

---

### Efficient and scalable clustering of survival curves

Authors: Nora M. Villanueva, Marta Sestelo, Luis Meira-Machado
Published: 2025-12-18
Categories: stat.ME, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2512.16481v2

Survival analysis encompasses a broad range of methods for analyzing time-to-event data, with one key objective being the comparison of survival curves across groups. Traditional approaches for identifying clusters of survival curves often rely on computationally intensive bootstrap techniques to approximate the null hypothesis distribution. While effective, these methods impose significant computational burdens. In this work, we propose a novel approach that leverages the k-means and log-rank test to efficiently identify and cluster survival curves. Our method eliminates the need for computationally expensive resampling, significantly reducing processing time while maintaining statistical reliability. By systematically evaluating survival curves and determining optimal clusters, the proposed method ensures a practical and scalable alternative for large-scale survival data analysis. Through simulation studies, we demonstrate that our approach achieves results comparable to existing bootstrap-based clustering methods while dramatically improving computational efficiency. These findings suggest that the log-rank-based clustering procedure offers a viable and time-efficient solution for researchers working with multiple survival curves in medical and epidemiological studies.

---

### Efficient and scalable clustering of survival curves

Authors: Nora M. Villanueva, Marta Sestelo, Luis Meira-Machado
Published: 2025-12-18
Categories: stat.ME, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2512.16481v1

Survival analysis encompasses a broad range of methods for analyzing time-to-event data, with one key objective being the comparison of survival curves across groups. Traditional approaches for identifying clusters of survival curves often rely on computationally intensive bootstrap techniques to approximate the null hypothesis distribution. While effective, these methods impose significant computational burdens. In this work, we propose a novel approach that leverages the k-means and log-rank test to efficiently identify and cluster survival curves. Our method eliminates the need for computationally expensive resampling, significantly reducing processing time while maintaining statistical reliability. By systematically evaluating survival curves and determining optimal clusters, the proposed method ensures a practical and scalable alternative for large-scale survival data analysis. Through simulation studies, we demonstrate that our approach achieves results comparable to existing bootstrap-based clustering methods while dramatically improving computational efficiency. These findings suggest that the log-rank-based clustering procedure offers a viable and time-efficient solution for researchers working with multiple survival curves in medical and epidemiological studies.

---

### Batch Normalization-Free Fully Integer Quantized Neural Networks via Progressive Tandem Learning

Authors: Pengfei Sun, Wenyu Jiang, Piew Yoong Chee, Paul Devos, Dick Botteldooren
Published: 2025-12-18
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2512.16476v1

Quantised neural networks (QNNs) shrink models and reduce inference energy through low-bit arithmetic, yet most still depend on a running statistics batch normalisation (BN) layer, preventing true integer-only deployment. Prior attempts remove BN by parameter folding or tailored initialisation; while helpful, they rarely recover BN's stability and accuracy and often impose bespoke constraints. We present a BN-free, fully integer QNN trained via a progressive, layer-wise distillation scheme that slots into existing low-bit pipelines. Starting from a pretrained BN-enabled teacher, we use layer-wise targets and progressive compensation to train a student that performs inference exclusively with integer arithmetic and contains no BN operations. On ImageNet with AlexNet, the BN-free model attains competitive Top-1 accuracy under aggressive quantisation. The procedure integrates directly with standard quantisation workflows, enabling end-to-end integer-only inference for resource-constrained settings such as edge and embedded devices.

---

### Quantifying Fidelity: A Decisive Feature Approach to Comparing Synthetic and Real Imagery

Authors: Danial Safaei, Siddartha Khastgir, Mohsen Alirezaei, Jeroen Ploeg, Son Tong, Chih-Hong Cheng, Xingyu Zhao
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16468v3

Virtual testing using synthetic data has become a cornerstone of autonomous vehicle (AV) safety assurance. Despite progress in improving visual realism through advanced simulators and generative AI, recent studies reveal that pixel-level fidelity alone does not ensure reliable transfer from simulation to the real world. What truly matters is whether the system-under-test (SUT) bases its decisions on consistent decision evidence in both real and simulated environments, not just whether images "look real" to humans. To this end this paper proposes a behavior-grounded fidelity measure by introducing Decisive Feature Fidelity (DFF), a new SUT-specific metric that extends the existing fidelity spectrum to capture mechanism parity, that is, agreement in the model-specific decisive evidence that drives the SUT's decisions across domains. DFF leverages explainable-AI methods to identify and compare the decisive features driving the SUT's outputs for matched real-synthetic pairs. We further propose estimators based on counterfactual explanations, along with a DFF-guided calibration scheme to enhance simulator fidelity. Experiments on 2126 matched KITTI-VirtualKITTI2 pairs demonstrate that DFF reveals discrepancies overlooked by conventional output-value fidelity. Furthermore, results show that DFF-guided calibration improves decisive-feature and input-level fidelity without sacrificing output value fidelity across diverse SUTs.

---

### Quantifying and Bridging the Fidelity Gap: A Decisive-Feature Approach to Comparing Synthetic and Real Imagery

Authors: Danial Safaei, Siddartha Khastgir, Mohsen Alirezaei, Jeroen Ploeg, Son Tong, Xingyu Zhao
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16468v1

Virtual testing using synthetic data has become a cornerstone of autonomous vehicle (AV) safety assurance. Despite progress in improving visual realism through advanced simulators and generative AI, recent studies reveal that pixel-level fidelity alone does not ensure reliable transfer from simulation to the real world. What truly matters is whether the system-under-test (SUT) bases its decisions on the same causal evidence in both real and simulated environments - not just whether images "look real" to humans. This paper addresses the lack of such a behavior-grounded fidelity measure by introducing Decisive Feature Fidelity (DFF), a new SUT-specific metric that extends the existing fidelity spectrum to capture mechanism parity - the agreement in causal evidence underlying the SUT's decisions across domains. DFF leverages explainable-AI (XAI) methods to identify and compare the decisive features driving the SUT's outputs for matched real-synthetic pairs. We further propose practical estimators based on counterfactual explanations, along with a DFF-guided calibration scheme to enhance simulator fidelity. Experiments on 2126 matched KITTI-VirtualKITTI2 pairs demonstrate that DFF reveals discrepancies overlooked by conventional output-value fidelity. Furthermore, results show that DFF-guided calibration improves decisive-feature and input-level fidelity without sacrificing output value fidelity across diverse SUTs.

---

### cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

Authors: Jinwu Chen, Qidie Wu, Bin Li, Lin Ma, Xin Si, Yang Hu, Shouyi Yin, Jun Yang
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16465v2

Optimizing CUDA kernels is a challenging and labor-intensive task, given the need for hardware-software co-design expertise and the proprietary nature of high-performance kernel libraries. While recent large language models (LLMs) combined with evolutionary algorithms show promise in automatic kernel optimization, existing approaches often fall short in performance due to their suboptimal agent designs and mismatched evolution representations. This work identifies these mismatches and proposes cuPilot, a strategy-coordinated multi-agent framework that introduces strategy as an intermediate semantic representation for kernel evolution. Key contributions include a strategy-coordinated evolution algorithm, roofline-guided prompting, and strategy-level population initialization. Experimental results show that the generated kernels by cuPilot achieve an average speed up of 3.09$\times$ over PyTorch on a benchmark of 100 kernels. On the GEMM tasks, cuPilot showcases sophisticated optimizations and achieves high utilization of critical hardware units. The generated kernels are open-sourced at https://github.com/champloo2878/cuPilot-Kernels.git.

---

### cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

Authors: Jinwu Chen, Qidie Wu, Bin Li, Lin Ma, Xin Si, Yang Hu, Shouyi Yin, Jun Yang
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16465v1

Optimizing CUDA kernels is a challenging and labor-intensive task, given the need for hardware-software co-design expertise and the proprietary nature of high-performance kernel libraries. While recent large language models (LLMs) combined with evolutionary algorithms show promise in automatic kernel optimization, existing approaches often fall short in performance due to their suboptimal agent designs and mismatched evolution representations. This work identifies these mismatches and proposes cuPilot, a strategy-coordinated multi-agent framework that introduces strategy as an intermediate semantic representation for kernel evolution. Key contributions include a strategy-coordinated evolution algorithm, roofline-guided prompting, and strategy-level population initialization. Experimental results show that the generated kernels by cuPilot achieve an average speed up of 3.09$\times$ over PyTorch on a benchmark of 100 kernels. On the GEMM tasks, cuPilot showcases sophisticated optimizations and achieves high utilization of critical hardware units. The generated kernels are open-sourced at https://github.com/champloo2878/cuPilot-Kernels.git.

---

### SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning

Authors: Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso, Eric Sax
Published: 2025-12-18
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.16461v1

Autonomous robotic systems require spatio-temporal understanding of dynamic environments to ensure reliable navigation and interaction. While Vision-Language Models (VLMs) provide open-world semantic priors, they lack grounding in 3D geometry and temporal dynamics. Conversely, geometric perception captures structure and motion but remains semantically sparse. We propose SNOW (Scene Understanding with Open-World Knowledge), a training-free and backbone-agnostic framework for unified 4D scene understanding that integrates VLM-derived semantics with point cloud geometry and temporal consistency. SNOW processes synchronized RGB images and 3D point clouds, using HDBSCAN clustering to generate object-level proposals that guide SAM2-based segmentation. Each segmented region is encoded through our proposed Spatio-Temporal Tokenized Patch Encoding (STEP), producing multimodal tokens that capture localized semantic, geometric, and temporal attributes. These tokens are incrementally integrated into a 4D Scene Graph (4DSG), which serves as 4D prior for downstream reasoning. A lightweight SLAM backend anchors all STEP tokens spatially in the environment, providing the global reference alignment, and ensuring unambiguous spatial grounding across time. The resulting 4DSG forms a queryable, unified world model through which VLMs can directly interpret spatial scene structure and temporal dynamics. Experiments on a diverse set of benchmarks demonstrate that SNOW enables precise 4D scene understanding and spatially grounded inference, thereby setting new state-of-the-art performance in several settings, highlighting the importance of structured 4D priors for embodied reasoning and autonomous robotics.

---

### Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach

Authors: Masashi Hatano, Saptarshi Sinha, Jacob Chalk, Wei-Hong Li, Hideo Saito, Dima Damen
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16456v2

Human motion generation is a challenging task that aims to create realistic motion imitating natural human behaviour. We focus on the well-studied behaviour of priming an object/location for pick up or put down - that is, the spotting of an object/location from a distance, known as gaze priming, followed by the motion of approaching and reaching the target location. To that end, we curate, for the first time, 23.7K gaze-primed human motion sequences for reaching target object locations from five publicly available datasets, i.e., HD-EPIC, MoGaze, HOT3D, ADT, and GIMO. We pre-train a text-conditioned diffusion-based motion generation model, then fine-tune it conditioned on goal pose or location, on our curated sequences. Importantly, we evaluate the ability of the generated motion to imitate natural human movement through several metrics, including the 'Reach Success' and a newly introduced 'Prime Success' metric. Tested on 5 datasets, our model generates diverse full-body motion, exhibiting both priming and reaching behaviour, and outperforming baselines and recent methods.

---

### Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach

Authors: Masashi Hatano, Saptarshi Sinha, Jacob Chalk, Wei-Hong Li, Hideo Saito, Dima Damen
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16456v1

Human motion generation is a challenging task that aims to create realistic motion imitating natural human behaviour. We focus on the well-studied behaviour of priming an object/location for pick up or put down -- that is, the spotting of an object/location from a distance, known as gaze priming, followed by the motion of approaching and reaching the target location. To that end, we curate, for the first time, 23.7K gaze-primed human motion sequences for reaching target object locations from five publicly available datasets, i.e., HD-EPIC, MoGaze, HOT3D, ADT, and GIMO. We pre-train a text-conditioned diffusion-based motion generation model, then fine-tune it conditioned on goal pose or location, on our curated sequences. Importantly, we evaluate the ability of the generated motion to imitate natural human movement through several metrics, including the 'Reach Success' and a newly introduced 'Prime Success' metric. On the largest dataset, HD-EPIC, our model achieves 60% prime success and 89% reach success when conditioned on the goal object location.

---

### AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research

Authors: Ignacio Heredia, Álvaro López García, Fernando Aguilar Gómez, Diego Aguirre, Caterina Alarcón Marín, Khadijeh Alibabaei, Lisana Berberi, Miguel Caballer, Amanda Calatrava, Pedro Castro, Alessandro Costantini, Mario David et al.
Published: 2025-12-18
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2512.16455v4

The rapid growth of Artificial Intelligence and Machine Learning in scientific research has highlighted a gap between industry-standard MLOps tools and platforms, and the unique requirements of modern and Open Science, particularly regarding the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This paper presents AI4EOSC, a federated, open-source platform designed to operationalize the full AI/ML lifecycle within the European Open Science Cloud (EOSC) ecosystem. Our methodology tackles the fragmentation of distributed research infrastructures by integrating a modular and distributed architecture comprising an AI development platform, a serverless AI-as-a-Service layer, and a federated orchestration model that is able to integrate heterogeneous compute and storage resources from distributed e-Infrastructures. AI4EOSC also introduces a ``FAIR-by-design'' approach that enforces metadata standardization (via MLDCAT-AP) and W3C PROV-compliant provenance tracking through a platform-integrated CI/CD pipeline. AI4EOSC added value is demonstrated through the delivery of a diverse set of community installations, showing consistent and seamless deployment across heterogeneous cloud providers. These installations are validated by a set of scientific cases, showing how our work reduces the manual burden on researchers while ensuring high levels of reproducibility and interoperability and providing an unified environment for development, training, and production of AI/ML models in the EOSC.

---

### AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research

Authors: Ignacio Heredia, Álvaro López García, Germán Moltó, Amanda Calatrava, Valentin Kozlov, Alessandro Costantini, Viet Tran, Mario David, Daniel San Martín, Marcin Płóciennik, Marta Obregón Ruiz, Saúl Fernandez et al.
Published: 2025-12-18
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2512.16455v1

In this paper, we describe a federated compute platform dedicated to support Artificial Intelligence in scientific workloads. Putting the effort into reproducible deployments, it delivers consistent, transparent access to a federation of physically distributed e-Infrastructures. Through a comprehensive service catalogue, the platform is able to offer an integrated user experience covering the full Machine Learning lifecycle, including model development (with dedicated interactive development environments), training (with GPU resources, annotation tools, experiment tracking, and federated learning support) and deployment (covering a wide range of deployment options all along the Cloud Continuum). The platform also provides tools for traceability and reproducibility of AI models, integrates with different Artificial Intelligence model providers, datasets and storage resources, allowing users to interact with the broader Machine Learning ecosystem. Finally, it is easily customizable to lower the adoption barrier by external communities.

---

### TimeSeries2Report prompting enables adaptive large language model management of lithium-ion batteries

Authors: Jiayang Yang, Martin Guay, Zhixing Cao, Chunhui Zhao
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16453v2

Large language models (LLMs) offer promising capabilities for interpreting multivariate time-series data, yet their application to real-world battery energy storage system (BESS) operation and maintenance remains largely unexplored. Here, we present TimeSeries2Report (TS2R), a semantic translation framework that converts raw lithium-ion battery operational time-series into structured, semantically enriched reports, enabling LLMs to reason, predict, and make decisions in BESS management scenarios. TS2R encodes short-term temporal dynamics into natural language through a combination of segmentation, semantic abstraction, and rule-based interpretation, effectively bridging low-level sensor signals with high-level contextual insights. We benchmark TS2R across both lab-scale and real-world datasets, evaluating report quality and downstream task performance in anomaly detection, state-of-charge prediction, and charging/discharging management. Compared with vision-, embedding-, and text-based prompting baselines, report-based prompting via TS2R consistently improves LLM performance in terms of across accuracy, robustness, and explainability metrics. Notably, TS2R-integrated LLMs achieve expert-level decision quality and predictive consistency without retraining or architecture modification, establishing a practical path for adaptive, LLM-driven battery intelligence.

---

### TimeSeries2Report prompting enables adaptive large language model management of lithium-ion batteries

Authors: Jiayang Yang, Chunhui Zhao, Martin Guay, Zhixing Cao
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16453v1

Large language models (LLMs) offer promising capabilities for interpreting multivariate time-series data, yet their application to real-world battery energy storage system (BESS) operation and maintenance remains largely unexplored. Here, we present TimeSeries2Report (TS2R), a prompting framework that converts raw lithium-ion battery operational time-series into structured, semantically enriched reports, enabling LLMs to reason, predict, and make decisions in BESS management scenarios. TS2R encodes short-term temporal dynamics into natural language through a combination of segmentation, semantic abstraction, and rule-based interpretation, effectively bridging low-level sensor signals with high-level contextual insights. We benchmark TS2R across both lab-scale and real-world datasets, evaluating report quality and downstream task performance in anomaly detection, state-of-charge prediction, and charging/discharging management. Compared with vision-, embedding-, and text-based prompting baselines, report-based prompting via TS2R consistently improves LLM performance in terms of across accuracy, robustness, and explainability metrics. Notably, TS2R-integrated LLMs achieve expert-level decision quality and predictive consistency without retraining or architecture modification, establishing a practical path for adaptive, LLM-driven battery intelligence.

---

### IoMT-based Automated Leukemia Classification using CNN and Higher Order Singular Value

Authors: Shabnam Bagheri Marzijarani, Mohammad Zolfaghari, Hedieh Sajedi
Published: 2025-12-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.16448v1

The Internet of Things (IoT) is a concept by which objects find identity and can communicate with each other in a network. One of the applications of the IoT is in the field of medicine, which is called the Internet of Medical Things (IoMT). Acute Lymphocytic Leukemia (ALL) is a type of cancer categorized as a hematic disease. It usually begins in the bone marrow due to the overproduction of immature White Blood Cells (WBCs or leukocytes). Since it has a high rate of spread to other body organs, it is a fatal disease if not diagnosed and treated early. Therefore, for identifying cancerous (ALL) cells in medical diagnostic laboratories, blood, as well as bone marrow smears, are taken by pathologists. However, manual examinations face limitations due to human error risk and time-consuming procedures. So, to tackle the mentioned issues, methods based on Artificial Intelligence (AI), capable of identifying cancer from non-cancer tissue, seem vital. Deep Neural Networks (DNNs) are the most efficient machine learning (ML) methods. These techniques employ multiple layers to extract higher-level features from the raw input. In this paper, a Convolutional Neural Network (CNN) is applied along with a new type of classifier, Higher Order Singular Value Decomposition (HOSVD), to categorize ALL and normal (healthy) cells from microscopic blood images. We employed the model on IoMT structure to identify leukemia quickly and safely. With the help of this new leukemia classification framework, patients and clinicians can have real-time communication. The model was implemented on the Acute Lymphoblastic Leukemia Image Database (ALL-IDB2) and achieved an average accuracy of %98.88 in the test step.

---

### Towards AI-Supported Research: a Vision of the TIB AIssistant

Authors: Sören Auer, Allard Oelen, Mohamad Yaser Jaradeh, Mutahira Khalid, Farhana Keya, Sasi Kiran Gaddipati, Jennifer D'Souza, Lorenz Schlüter, Amirreza Alasti, Gollam Rabby, Azanzi Jiomekong, Oliver Karras
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16447v1

The rapid advancements in Generative AI and Large Language Models promise to transform the way research is conducted, potentially offering unprecedented opportunities to augment scholarly workflows. However, effectively integrating AI into research remains a challenge due to varying domain requirements, limited AI literacy, the complexity of coordinating tools and agents, and the unclear accuracy of Generative AI in research. We present the vision of the TIB AIssistant, a domain-agnostic human-machine collaborative platform designed to support researchers across disciplines in scientific discovery, with AI assistants supporting tasks across the research life cycle. The platform offers modular components - including prompt and tool libraries, a shared data store, and a flexible orchestration framework - that collectively facilitate ideation, literature analysis, methodology development, data analysis, and scholarly writing. We describe the conceptual framework, system architecture, and implementation of an early prototype that demonstrates the feasibility and potential impact of our approach.

---

### E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotion

Authors: Enis Yalcin, Joshua O'Hara, Maria Stamatopoulou, Chengxu Zhou, Dimitrios Kanoulas
Published: 2025-12-18
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.16446v1

Vision-language models (VLMs) show promise in automating reward design in humanoid locomotion, which could eliminate the need for tedious manual engineering. However, current VLM-based methods are essentially "blind", as they lack the environmental perception required to navigate complex terrain. We present E-SDS (Environment-aware See it, Do it, Sorted), a framework that closes this perception gap. E-SDS integrates VLMs with real-time terrain sensor analysis to automatically generate reward functions that facilitate training of robust perceptive locomotion policies, grounded by example videos. Evaluated on a Unitree G1 humanoid across four distinct terrains (simple, gaps, obstacles, stairs), E-SDS uniquely enabled successful stair descent, while policies trained with manually-designed rewards or a non-perceptive automated baseline were unable to complete the task. In all terrains, E-SDS also reduced velocity tracking error by 51.9-82.6%. Our framework reduces the human effort of reward design from days to less than two hours while simultaneously producing more robust and capable locomotion policies.

---

### Topic Modelling Black Box Optimization

Authors: Roman Akramov, Artem Khamatullin, Svetlana Glazyrina, Maksim Kryzhanovskiy, Roman Ischenko
Published: 2025-12-18
Categories: cs.LG, cs.AI, cs.CL, cs.NE
arXiv: https://arxiv.org/abs/2512.16445v1

Choosing the number of topics $T$ in Latent Dirichlet Allocation (LDA) is a key design decision that strongly affects both the statistical fit and interpretability of topic models. In this work, we formulate the selection of $T$ as a discrete black-box optimization problem, where each function evaluation corresponds to training an LDA model and measuring its validation perplexity. Under a fixed evaluation budget, we compare four families of optimizers: two hand-designed evolutionary methods - Genetic Algorithm (GA) and Evolution Strategy (ES) - and two learned, amortized approaches, Preferential Amortized Black-Box Optimization (PABBO) and Sharpness-Aware Black-Box Optimization (SABBO). Our experiments show that, while GA, ES, PABBO, and SABBO eventually reach a similar band of final perplexity, the amortized optimizers are substantially more sample- and time-efficient. SABBO typically identifies a near-optimal topic number after essentially a single evaluation, and PABBO finds competitive configurations within a few evaluations, whereas GA and ES require almost the full budget to approach the same region.

---

### StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm

Authors: Yadong Li, Tong Zhang, Bo Huang, Zhen Cui
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16444v1

Deep multi-agent reinforcement learning (MARL) algorithms are booming in the field of collaborative intelligence, and StarCraft multi-agent challenge (SMAC) is widely-used as the benchmark therein. However, imaginary opponents of MARL algorithms are practically configured and controlled in a fixed built-in AI mode, which causes less diversity and versatility in algorithm evaluation. To address this issue, in this work, we establish a multi-agent algorithm-vs-algorithm environment, named StarCraft II battle arena (SC2BA), to refresh the benchmarking of MARL algorithms in an adversary paradigm. Taking StarCraft as infrastructure, the SC2BA environment is specifically created for inter-algorithm adversary with the consideration of fairness, usability and customizability, and meantime an adversarial PyMARL (APyMARL) library is developed with easy-to-use interfaces/modules. Grounding in SC2BA, we benchmark those classic MARL algorithms in two types of adversarial modes: dual-algorithm paired adversary and multi-algorithm mixed adversary, where the former conducts the adversary of pairwise algorithms while the latter focuses on the adversary to multiple behaviors from a group of algorithms. The extensive benchmark experiments exhibit some thought-provoking observations/problems in the effectivity, sensibility and scalability of these completed algorithms. The SC2BA environment as well as reproduced experiments are released in \href{https://github.com/dooliu/SC2BA}{Github}, and we believe that this work could mark a new step for the MARL field in the coming years.

---

### Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt

Authors: Shangxun Li, Youngjung Uh
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16443v3

Text-to-image diffusion models excel at generating high-quality images from natural language descriptions but often fail to preserve subject consistency across multiple outputs, limiting their use in visual storytelling. Existing approaches rely on model fine-tuning or image conditioning, which are computationally expensive and require per-subject optimization. 1Prompt1Story, a training-free approach, concatenates all scene descriptions into a single prompt and rescales token embeddings, but it suffers from semantic leakage, where embeddings across frames become entangled, causing text misalignment. In this paper, we propose a simple yet effective training-free approach that addresses semantic entanglement from a geometric perspective by refining text embeddings to suppress unwanted semantics. Extensive experiments prove that our approach significantly improves both subject consistency and text alignment over existing baselines.

---

### TIB AIssistant: a Platform for AI-Supported Research Across Research Life Cycles

Authors: Allard Oelen, Sören Auer
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16442v1

The rapidly growing popularity of adopting Artificial Intelligence (AI), and specifically Large Language Models (LLMs), is having a widespread impact throughout society, including the academic domain. AI-supported research has the potential to support researchers with tasks across the entire research life cycle. In this work, we demonstrate the TIB AIssistant, an AI-supported research platform providing support throughout the research life cycle. The AIssistant consists of a collection of assistants, each responsible for a specific research task. In addition, tools are provided to give access to external scholarly services. Generated data is stored in the assets and can be exported as an RO-Crate bundle to provide transparency and enhance reproducibility of the research project. We demonstrate the AIssistant's main functionalities by means of a sequential walk-through of assistants, interacting with each other to generate sections for a draft research paper. In the end, with the AIssistant, we lay the foundation for a larger agenda of providing a community-maintained platform for AI-supported research.

---

### From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection

Authors: Hao Li, Yubing Ren, Yanan Cao, Yingjie Li, Fang Fang, Xuebin Wang
Published: 2025-12-18
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2512.16439v1

Benefiting from the superior capabilities of large language models in natural language understanding and generation, Embeddings-as-a-Service (EaaS) has emerged as a successful commercial paradigm on the web platform. However, prior studies have revealed that EaaS is vulnerable to imitation attacks. Existing methods protect the intellectual property of EaaS through watermarking techniques, but they all ignore the most important properties of embedding: semantics, resulting in limited harmlessness and stealthiness. To this end, we propose SemMark, a novel semantic-based watermarking paradigm for EaaS copyright protection. SemMark employs locality-sensitive hashing to partition the semantic space and inject semantic-aware watermarks into specific regions, ensuring that the watermark signals remain imperceptible and diverse. In addition, we introduce the adaptive watermark weight mechanism based on the local outlier factor to preserve the original embedding distribution. Furthermore, we propose Detect-Sampling and Dimensionality-Reduction attacks and construct four scenarios to evaluate the watermarking method. Extensive experiments are conducted on four popular NLP datasets, and SemMark achieves superior verifiability, diversity, stealthiness, and harmlessness.

---

### A Novel Proposal in Wind Turbine Blade Failure Detection: An Integrated Approach to Energy Efficiency and Sustainability

Authors: Jordan Abarca-Albores, Danna Cristina Gutiérrez Cabrera, Luis Antonio Salazar-Licea, Dante Ruiz-Robles, Jesus Alejandro Franco, Alberto-Jesus Perea-Moreno, David Muñoz-Rodríguez, Quetzalcoatl Hernandez-Escobedo
Published: 2025-12-18
Categories: cs.LG, physics.app-ph
arXiv: https://arxiv.org/abs/2512.16437v1

This paper presents a novel methodology for detecting faults in wind turbine blades using com-putational learning techniques. The study evaluates two models: the first employs logistic regression, which outperformed neural networks, decision trees, and the naive Bayes method, demonstrating its effectiveness in identifying fault-related patterns. The second model leverages clustering and achieves superior performance in terms of precision and data segmentation. The results indicate that clustering may better capture the underlying data characteristics compared to supervised methods. The proposed methodology offers a new approach to early fault detection in wind turbine blades, highlighting the potential of integrating different computational learning techniques to enhance system reliability. The use of accessible tools like Orange Data Mining underscores the practical application of these advanced solutions within the wind energy sector. Future work will focus on combining these methods to improve detection accuracy further and extend the application of these techniques to other critical components in energy infrastructure.

---

### Emergent Bias and Fairness in Multi-Agent Decision Systems

Authors: Maeve Madigan, Parameswaran Kamalaruban, Glenn Moynihan, Tom Kempton, David Sutton, Stuart Burrell
Published: 2025-12-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.16433v1

Multi-agent systems have demonstrated the ability to improve performance on a variety of predictive tasks by leveraging collaborative decision making. However, the lack of effective evaluation methodologies has made it difficult to estimate the risk of bias, making deployment of such systems unsafe in high stakes domains such as consumer finance, where biased decisions can translate directly into regulatory breaches and financial loss. To address this challenge, we need to develop fairness evaluation methodologies for multi-agent predictive systems and measure the fairness characteristics of these systems in the financial tabular domain. Examining fairness metrics using large-scale simulations across diverse multi-agent configurations, with varying communication and collaboration mechanisms, we reveal patterns of emergent bias in financial decision-making that cannot be traced to individual agent components, indicating that multi-agent systems may exhibit genuinely collective behaviors. Our findings highlight that fairness risks in financial multi-agent systems represent a significant component of model risk, with tangible impacts on tasks such as credit scoring and income estimation. We advocate that multi-agent decision systems must be evaluated as holistic entities rather than through reductionist analyses of their constituent components.

---

### Multi-Fidelity Delayed Acceptance: hierarchical MCMC sampling for Bayesian inverse problems combining multiple solvers through deep neural networks

Authors: Filippo Zacchei, Paolo Conti, Attilio Alberto Frangi, Andrea Manzoni
Published: 2025-12-18
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2512.16430v1

Inverse uncertainty quantification (UQ) tasks such as parameter estimation are computationally demanding whenever dealing with physics-based models, and typically require repeated evaluations of complex numerical solvers. When partial differential equations are involved, full-order models such as those based on the Finite Element Method can make traditional sampling approaches like Markov Chain Monte Carlo (MCMC) computationally infeasible. Although data-driven surrogate models may help reduce evaluation costs, their utility is often limited by the expense of generating high-fidelity data. In contrast, low-fidelity data can be produced more efficiently, although relying on them alone may degrade the accuracy of the inverse UQ solution. To address these challenges, we propose a Multi-Fidelity Delayed Acceptance scheme for Bayesian inverse problems. Extending the Multi-Level Delayed Acceptance framework, the method introduces multi-fidelity neural networks that combine the predictions of solvers of varying fidelity, with high fidelity evaluations restricted to an offline training stage. During the online phase, likelihood evaluations are obtained by evaluating the coarse solvers and passing their outputs to the trained neural networks, thereby avoiding additional high-fidelity simulations. This construction allows heterogeneous coarse solvers to be incorporated consistently within the hierarchy, providing greater flexibility than standard Multi-Level Delayed Acceptance. The proposed approach improves the approximation accuracy of the low fidelity solvers, leading to longer sub-chain lengths, better mixing, and accelerated posterior inference. The effectiveness of the strategy is demonstrated on two benchmark inverse problems involving (i) steady isotropic groundwater flow, (ii) an unsteady reaction-diffusion system, for which substantial computational savings are obtained.

---

### Introducing ORKG ASK: an AI-driven Scholarly Literature Search and Exploration System Taking a Neuro-Symbolic Approach

Authors: Allard Oelen, Mohamad Yaser Jaradeh, Sören Auer
Published: 2025-12-18
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2512.16425v1

As the volume of published scholarly literature continues to grow, finding relevant literature becomes increasingly difficult. With the rise of generative Artificial Intelligence (AI), and particularly Large Language Models (LLMs), new possibilities emerge to find and explore literature. We introduce ASK (Assistant for Scientific Knowledge), an AI-driven scholarly literature search and exploration system that follows a neuro-symbolic approach. ASK aims to provide active support to researchers in finding relevant scholarly literature by leveraging vector search, LLMs, and knowledge graphs. The system allows users to input research questions in natural language and retrieve relevant articles. ASK automatically extracts key information and generates answers to research questions using a Retrieval-Augmented Generation (RAG) approach. We present an evaluation of ASK, assessing the system's usability and usefulness. Findings indicate that the system is user-friendly and users are generally satisfied while using the system.

---

### Synthelite: Chemist-aligned and feasibility-aware synthesis planning with LLMs

Authors: Nguyen Xuan-Vu, Daniel Armstrong, Milena Wehrbach, Andres M Bran, Zlatko Jončev, Philippe Schwaller
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16424v1

Computer-aided synthesis planning (CASP) has long been envisioned as a complementary tool for synthetic chemists. However, existing frameworks often lack mechanisms to allow interaction with human experts, limiting their ability to integrate chemists' insights. In this work, we introduce Synthelite, a synthesis planning framework that uses large language models (LLMs) to directly propose retrosynthetic transformations. Synthelite can generate end-to-end synthesis routes by harnessing the intrinsic chemical knowledge and reasoning capabilities of LLMs, while allowing expert intervention through natural language prompts. Our experiments demonstrate that Synthelite can flexibly adapt its planning trajectory to diverse user-specified constraints, achieving up to 95\% success rates in both strategy-constrained and starting-material-constrained synthesis tasks. Additionally, Synthelite exhibits the ability to account for chemical feasibility during route design. We envision Synthelite to be both a useful tool and a step toward a paradigm where LLMs are the central orchestrators of synthesis planning.

---

### CountZES: Counting via Zero-Shot Exemplar Selection

Authors: Muhammad Ibraheem Siddiqui, Muhammad Haris Khan
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16415v3

Object counting in complex scenes is particularly challenging in the zero-shot (ZS) setting, where instances of unseen categories are counted using only a class name. Existing ZS counting methods that infer exemplars from text often rely on off-the-shelf open-vocabulary detectors (OVDs), which in dense scenes suffer from semantic noise, appearance variability, and multi-instance proposals. Alternatively, random image-patch sampling is employed, which fails to accurately delineate object instances. Since counting is sensitive to exemplar quality, such selection strategies often yield poorly representative exemplars, leading to inaccurate count estimation. To address these issues, we propose CountZES, an inference-only approach for object counting via ZS exemplar selection. CountZES discovers diverse exemplars through three synergistic stages: Detection-Anchored Exemplar (DAE), Density-Guided Exemplar (DGE), and Feature-Consensus Exemplar (FCE). DAE refines OVD detections to isolate precise single-instance exemplars. DGE introduces a density-driven, self-supervised paradigm to identify statistically consistent and semantically compact exemplars, while FCE reinforces visual coherence through feature-space clustering. Together, these stages yield a complementary exemplar set that balances textual grounding, count consistency, and feature representativeness. Experiments on diverse datasets demonstrate CountZES superior performance among ZOC methods while generalizing effectively across domains.

---

### BrepLLM: Enabling Large Language Models to Understand Boundary Representations

Authors: Liyuan Deng, Hao Guo, Yongkang Dai, Yunpeng Bai, Yifan Zhu, Yuanyuan Gao, Huaxi Huang, Yilei Shi
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16413v2

Current token-sequence-based Large Language Models (LLMs) struggle to directly process 3D Boundary Representation (B-rep) models that contain complex geometric and topological information. To this end, we propose BrepLLM, the first multimodal framework that enables LLMs to directly parse and reason over raw B-rep data. BrepLLM adopts a two-stage training pipeline: cross-modal alignment pre-training and two-stage LLM fine-tuning. In the first stage, we design an adaptive UV sampling strategy to convert B-reps into graph representations that integrate geometric and topological information. Subsequently, we construct a hierarchical BrepEncoder to extract features from geometric elements (faces and edges) and topology, generating a global token and a sequence of node tokens. Then, via contrastive learning, we conduct an initial alignment between this global token and the text embeddings of a frozen CLIP text encoder (ViT-L/14). In the second stage, we integrate the pre-trained BrepEncoder into the LLM and employ a two-stage progressive strategy to align the sequence of node tokens: (1) training an MLP-based semantic mapping network that utilizes the prior knowledge of a 2D-VLM to align the B-rep representation to the 2D visual semantic space; (2) utilizing LoRA for parameter-efficient fine-tuning of the Q-Former and the LLM backbone network to achieve the final 3D-language generation capability. Furthermore, we construct the Brep2Text dataset, which contains 269,444 B-rep and text question-answer pairs. Experiments demonstrate that BrepLLM achieves SOTA performance on 3D object classification and captioning tasks. The project page is available at https://user-deng.github.io/BrepLLM/.

---

### Geometric Laplace Neural Operator

Authors: Hao Tang, Jiongyu Zhu, Zimeng Feng, Hao Li, Chao Li
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16409v1

Neural operators have emerged as powerful tools for learning mappings between function spaces, enabling efficient solutions to partial differential equations across varying inputs and domains. Despite the success, existing methods often struggle with non-periodic excitations, transient responses, and signals defined on irregular or non-Euclidean geometries. To address this, we propose a generalized operator learning framework based on a pole-residue decomposition enriched with exponential basis functions, enabling expressive modeling of aperiodic and decaying dynamics. Building on this formulation, we introduce the Geometric Laplace Neural Operator (GLNO), which embeds the Laplace spectral representation into the eigen-basis of the Laplace-Beltrami operator, extending operator learning to arbitrary Riemannian manifolds without requiring periodicity or uniform grids. We further design a grid-invariant network architecture (GLNONet) that realizes GLNO in practice. Extensive experiments on PDEs/ODEs and real-world datasets demonstrate our robust performance over other state-of-the-art models.

---

### NDRL: Cotton Irrigation and Nitrogen Application with Nested Dual-Agent Reinforcement Learning

Authors: Ruifeng Xu, Liang He
Published: 2025-12-18
Categories: cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2512.16408v1

Effective irrigation and nitrogen fertilization have a significant impact on crop yield. However, existing research faces two limitations: (1) the high complexity of optimizing water-nitrogen combinations during crop growth and poor yield optimization results; and (2) the difficulty in quantifying mild stress signals and the delayed feedback, which results in less precise dynamic regulation of water and nitrogen and lower resource utilization efficiency. To address these issues, we propose a Nested Dual-Agent Reinforcement Learning (NDRL) method. The parent agent in NDRL identifies promising macroscopic irrigation and fertilization actions based on projected cumulative yield benefits, reducing ineffective explorationwhile maintaining alignment between objectives and yield. The child agent's reward function incorporates quantified Water Stress Factor (WSF) and Nitrogen Stress Factor (NSF), and uses a mixed probability distribution to dynamically optimize daily strategies, thereby enhancing both yield and resource efficiency. We used field experiment data from 2023 and 2024 to calibrate and validate the Decision Support System for Agrotechnology Transfer (DSSAT) to simulate real-world conditions and interact with NDRL. Experimental results demonstrate that, compared to the best baseline, the simulated yield increased by 4.7% in both 2023 and 2024, the irrigation water productivity increased by 5.6% and 5.1% respectively, and the nitrogen partial factor productivity increased by 6.3% and 1.0% respectively. Our method advances the development of cotton irrigation and nitrogen fertilization, providing new ideas for addressing the complexity and precision issues in agricultural resource management and for sustainable agricultural development.

---

### Hypernetworks That Evolve Themselves

Authors: Joachim Winther Pedersen, Erwan Plantec, Eleni Nisioti, Marcello Barylli, Milton Montero, Kathrin Korte, Sebastian Risi
Published: 2025-12-18
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2512.16406v1

How can neural networks evolve themselves without relying on external optimizers? We propose Self-Referential Graph HyperNetworks, systems where the very machinery of variation and inheritance is embedded within the network. By uniting hypernetworks, stochastic parameter generation, and graph-based representations, Self-Referential GHNs mutate and evaluate themselves while adapting mutation rates as selectable traits. Through new reinforcement learning benchmarks with environmental shifts (CartPoleSwitch, LunarLander-Switch), Self-Referential GHNs show swift, reliable adaptation and emergent population dynamics. In the locomotion benchmark Ant-v5, they evolve coherent gaits, showing promising fine-tuning capabilities by autonomously decreasing variation in the population to concentrate around promising solutions. Our findings support the idea that evolvability itself can emerge from neural self-reference. Self-Referential GHNs reflect a step toward synthetic systems that more closely mirror biological evolution, offering tools for autonomous, open-ended learning agents.

---

### Navigating the Reality Gap: On-Device Continual Adaptation of ASR for Clinical Telephony

Authors: Darshil Chauhan, Adityasinh Solanki, Vansh Patel, Kanav Kapoor, Ritvik Jain, Aditya Bansal, Pratik Narang, Dhruv Kumar
Published: 2025-12-18
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.16401v6

Automatic Speech Recognition (ASR) can ease clinical documentation in resource-constrained regions, but deployment is hindered by a "Reality Gap" between laboratory performance and noisy, real-world clinical telephony, compounded by strict data residency and compute constraints. We study this gap using Gram Vaani, a telephonic Hindi corpus spanning rural healthcare and agricultural helplines, as the closest publicly available proxy for clinical telephony speech, and show that a robust multilingual model (IndicWav2Vec) degrades from 11.60% WER on clean read Hindi to 41.72% WER on this data. We evaluate a progression of adaptation regimes, from full fine-tuning and offline Low-Rank Adaptation (LoRA) upper bounds to an on-device, stream-based continual adaptation framework in which raw audio never leaves the local device, and characterize the trade-offs between data-driven and parameter-driven stabilization strategies. Our evaluation covers both lexical accuracy (WER and CER) and semantic fidelity (BERTScore) on the target domain, alongside the retention of general-domain knowledge. Multi-domain Experience Replay (ER) yields the primary gains, improving target WER by 18.2% relative and reducing catastrophic forgetting by 54% compared to naive adaptation, with BERTScore reflecting consistent gains in semantic fidelity. Combining replay with Elastic Weight Consolidation based on a stabilized importance estimate (Absolute Fisher) yields the strongest retention at a small cost in plasticity. Finally, a language model spot check empirically verifies that the core mismatch lies at the acoustic level and cannot be resolved by language models alone.

---

### Using Gaussian Splats to Create High-Fidelity Facial Geometry and Texture

Authors: Haodi He, Jihun Yu, Ronald Fedkiw
Published: 2025-12-18
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2512.16397v1

We leverage increasingly popular three-dimensional neural representations in order to construct a unified and consistent explanation of a collection of uncalibrated images of the human face. Our approach utilizes Gaussian Splatting, since it is more explicit and thus more amenable to constraints than NeRFs. We leverage segmentation annotations to align the semantic regions of the face, facilitating the reconstruction of a neutral pose from only 11 images (as opposed to requiring a long video). We soft constrain the Gaussians to an underlying triangulated surface in order to provide a more structured Gaussian Splat reconstruction, which in turn informs subsequent perturbations to increase the accuracy of the underlying triangulated surface. The resulting triangulated surface can then be used in a standard graphics pipeline. In addition, and perhaps most impactful, we show how accurate geometry enables the Gaussian Splats to be transformed into texture space where they can be treated as a view-dependent neural texture. This allows one to use high visual fidelity Gaussian Splatting on any asset in a scene without the need to modify any other asset or any other aspect (geometry, lighting, renderer, etc.) of the graphics pipeline. We utilize a relightable Gaussian model to disentangle texture from lighting in order to obtain a delit high-resolution albedo texture that is also readily usable in a standard graphics pipeline. The flexibility of our system allows for training with disparate images, even with incompatible lighting, facilitating robust regularization. Finally, we demonstrate the efficacy of our approach by illustrating its use in a text-driven asset creation pipeline.

---

### Global universal approximation with Brownian signatures

Authors: Mihriban Ceylan, David J. Prömel
Published: 2025-12-18
Categories: math.PR, cs.LG, q-fin.MF
arXiv: https://arxiv.org/abs/2512.16396v3

We establish $L^p$-universal approximation theorems for general path-dependent and non-anticipative functionals on suitable rough path spaces, showing that linear functionals acting on signatures of time-extended rough paths are dense with respect to the $L^p$-distance. To that end, we derive global universal approximation theorems for weighted rough path spaces. We demonstrate that these $L^p$-universal approximation theorems apply to Gaussian processes, in particular, to fractional Brownian motion. As a consequence, linear functionals on the signature of the time-extended Brownian motion can approximate any $p$-integrable stochastic process adapted to the Brownian filtration, including solutions to stochastic differential equations.

---

### Adaptive Frequency Domain Alignment Network for Medical image segmentation

Authors: Zhanwei Li, Liang Li, Jiawan Zhang
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16393v2

High-quality annotated data plays a crucial role in achieving accurate segmentation. However, such data for medical image segmentation are often scarce due to the time-consuming and labor-intensive nature of manual annotation. To address this challenge, we propose the Adaptive Frequency Domain Alignment Network (AFDAN)--a novel domain adaptation framework designed to align features in the frequency domain and alleviate data scarcity. AFDAN integrates three core components to enable robust cross-domain knowledge transfer: an Adversarial Domain Learning Module that transfers features from the source to the target domain; a Source-Target Frequency Fusion Module that blends frequency representations across domains; and a Spatial-Frequency Integration Module that combines both frequency and spatial features to further enhance segmentation accuracy across domains. Extensive experiments demonstrate the effectiveness of AFDAN: it achieves an Intersection over Union (IoU) of 90.9% for vitiligo segmentation in the newly constructed VITILIGO2025 dataset and a competitive IoU of 82.6% on the retinal vessel segmentation benchmark DRIVE, surpassing existing state-of-the-art approaches.

---

### PCIA: A Path Construction Imitation Algorithm for Global Optimization

Authors: Mohammad-Javad Rezaei, Mozafar Bag-Mohammadi
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16392v1

In this paper, a new metaheuristic optimization algorithm, called Path Construction Imitation Algorithm (PCIA), is proposed. PCIA is inspired by how humans construct new paths and use them. Typically, humans prefer popular transportation routes. In the event of a path closure, a new route is built by mixing the existing paths intelligently. Also, humans select different pathways on a random basis to reach unknown destinations. PCIA generates a random population to find the best route toward the destination, similar to swarm-based algorithms. Each particle represents a path toward the destination. PCIA has been tested with 53 mathematical optimization problems and 13 constrained optimization problems. The results showed that the PCIA is highly competitive compared to both popular and the latest metaheuristic algorithms.

---

### Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference

Authors: Dhruv Deshmukh, Saurabh Goyal, Nipun Kwatra, Ramachandran Ramjee
Published: 2025-12-18
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2512.16391v2

Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascade, a training-free sparse attention method that leverages known observations such as 1) post-softmax attention is intrinsically sparse, and 2) the identity of high-weight keys is stable across nearby layers. Kascade computes exact Top-k indices in a small set of anchor layers, then reuses those indices in intermediate reuse layers. The anchor layers are selected algorithmically, via a dynamic-programming objective that maximizes cross-layer similarity over a development set, allowing easy deployment across models. The method incorporates efficient implementation constraints (e.g. tile-level operations), across both prefill and decode attention. The Top-k selection and reuse in Kascade is head-aware and we show in our experiments that this is critical for high accuracy. Kascade achieves up to 4.1x speedup in decode attention and 2.2x speedup in prefill attention over FlashAttention-3 baseline on H100 GPUs while closely matching dense attention accuracy on long-context benchmarks such as LongBench and AIME-24.

---

### Quantitative Verification of Fairness in Tree Ensembles

Authors: Zhenjiang Zhao, Takahisa Toda, Takashi Kitamura
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16386v1

This work focuses on quantitative verification of fairness in tree ensembles. Unlike traditional verification approaches that merely return a single counterexample when the fairness is violated, quantitative verification estimates the ratio of all counterexamples and characterizes the regions where they occur, which is important information for diagnosing and mitigating bias. To date, quantitative verification has been explored almost exclusively for deep neural networks (DNNs). Representative methods, such as DeepGemini and FairQuant, all build on the core idea of Counterexample-Guided Abstraction Refinement, a generic framework that could be adapted to other model classes. We extended the framework into a model-agnostic form, but discovered two limitations: (i) it can provide only lower bounds, and (ii) its performance scales poorly. Exploiting the discrete structure of tree ensembles, our work proposes an efficient quantification technique that delivers any-time upper and lower bounds. Experiments on five widely used datasets demonstrate its effectiveness and efficiency. When applied to fairness testing, our quantification method significantly outperforms state-of-the-art testing techniques.

---

### Multivariate Uncertainty Quantification with Tomographic Quantile Forests

Authors: Takuya Kanazawa
Published: 2025-12-18
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.16383v2

Quantifying predictive uncertainty is essential for safe and trustworthy real-world AI deployment. Yet, fully nonparametric estimation of conditional distributions remains challenging for multivariate targets. We propose Tomographic Quantile Forests (TQF), a nonparametric, uncertainty-aware, tree-based regression model for multivariate targets. TQF learns conditional quantiles of directional projections $\mathbf{n}^{\top}\mathbf{y}$ as functions of the input $\mathbf{x}$ and the unit direction $\mathbf{n}$. At inference, it aggregates quantiles across many directions and reconstructs the multivariate conditional distribution by minimizing the sliced Wasserstein distance via an efficient alternating scheme with convex subproblems. Unlike classical directional-quantile approaches that typically produce only convex quantile regions and require training separate models for different directions, TQF covers all directions with a single model without imposing convexity restrictions. We evaluate TQF on synthetic and real-world datasets, and release the source code on GitHub.

---

### Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs

Authors: Sara Papi, Javier Garcia Gilabert, Zachary Hopton, Vilém Zouhar, Carlos Escolano, Gerard I. Gállego, Jorge Iranzo-Sánchez, Ahrii Kim, Dominik Macháček, Patricia Schmidtova, Maike Züfle
Published: 2025-12-18
Categories: cs.CL, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2512.16378v4

As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which directly process spoken language and enable speech-to-text translation (ST) and other downstream tasks, bypassing traditional transcription-based pipelines. Whether this integration improves ST quality over established cascaded architectures, however, remains an open question. We present Hearing to Translate, the first comprehensive test suite rigorously benchmarking 6 state-of-the-art SpeechLLMs against 16 strong direct and cascade systems that couple leading speech foundation models (SFM), with multilingual LLMs. Our analysis spans 16 benchmarks, 13 language pairs, and 9 challenging conditions, including disfluent, noisy, and long-form speech. Across this extensive evaluation, we find that cascaded systems remain the most reliable solution overall, but most recent SpeechLLMs can match or even outperform cascades in various settings while SFMs lag behind both, highlighting that integrating an LLM, either within the model or in a pipeline, is essential for high-quality speech translation.

---

### Anchored Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models

Authors: Mariam Hassan, Bastien Van Delft, Wuyang Li, Alexandre Alahi
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16371v2

State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal instructions. In this paper, we argue that many errors, including apparent motion failures, originate from the model's inability to construct a semantically correct or logically consistent initial frame. We introduce Anchored Video Generation (AVG), a modular pipeline that decouples these tasks by decomposing the Text-to-Video generation into three specialized stages: (1) Reasoning, where a Large Language Model (LLM) rewrites the video prompt to describe only the initial scene, resolving temporal ambiguities; (2) Composition, where a Text-to-Image (T2I) model synthesizes a high-quality, compositionally-correct anchor frame from this new prompt; and (3) Temporal Synthesis, where a video model, finetuned to understand this anchor, focuses its entire capacity on animating the scene and following the prompt. Our approach sets a new state-of-the-art on the T2V CompBench benchmark and significantly improves all tested models on VBench2. Furthermore, we show that visual anchoring allows us to cut the number of sampling steps by 70% without any loss in performance. AVG offers a simple yet practical path toward more efficient, robust, and controllable video synthesis.

---