# Research Papers — 2025-12 · bundle page 98 of 175 > Full-text markdown of papers #4851–4900 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/98 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/97.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/99.md) ### Infinity and Beyond: Compositional Alignment in VAR and Diffusion T2I Models Authors: Hossein Shahabadi, Niki Sepasian, Arash Marioriyad, Ali Sharifi-Zarchi, Mahdieh Soleymani Baghshah Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11542v1 Achieving compositional alignment between textual descriptions and generated images - covering objects, attributes, and spatial relationships - remains a core challenge for modern text-to-image (T2I) models. Although diffusion-based architectures have been widely studied, the compositional behavior of emerging Visual Autoregressive (VAR) models is still largely unexamined. We benchmark six diverse T2I systems - SDXL, PixArt-$α$, Flux-Dev, Flux-Schnell, Infinity-2B, and Infinity-8B - across the full T2I-CompBench++ and GenEval suites, evaluating alignment in color and attribute binding, spatial relations, numeracy, and complex multi-object prompts. Across both benchmarks, Infinity-8B achieves the strongest overall compositional alignment, while Infinity-2B also matches or exceeds larger diffusion models in several categories, highlighting favorable efficiency-performance trade-offs. In contrast, SDXL and PixArt-$α$ show persistent weaknesses in attribute-sensitive and spatial tasks. These results provide the first systematic comparison of VAR and diffusion approaches to compositional alignment and establish unified baselines for the future development of the T2I model. --- ### A Multi-Criteria Automated MLOps Pipeline for Cost-Effective Cloud-Based Classifier Retraining in Response to Data Distribution Shifts Authors: Emmanuel K. Katalay, David O. Dimandja, Jordan F. Masakuna Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11541v1 The performance of machine learning (ML) models often deteriorates when the underlying data distribution changes over time, a phenomenon known as data distribution drift. When this happens, ML models need to be retrained and redeployed. ML Operations (MLOps) is often manual, i.e., humans trigger the process of model retraining and redeployment. In this work, we present an automated MLOps pipeline designed to address neural network classifier retraining in response to significant data distribution changes. Our MLOps pipeline employs multi-criteria statistical techniques to detect distribution shifts and triggers model updates only when necessary, ensuring computational efficiency and resource optimization. We demonstrate the effectiveness of our framework through experiments on several benchmark anomaly detection data sets, showing significant improvements in model accuracy and robustness compared to traditional retraining strategies. Our work provides a foundation for deploying more reliable and adaptive ML systems in dynamic real-world settings, where data distribution changes are common. --- ### HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding Authors: Yiqing Yang, Yun Li, Daiqing Qi, Lehan Yang, Tianlong Wang, Wenhao Zhang, Sheng Li, Kin-man Lam Published: 2025-12-12 Categories: cs.CV, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2512.11534v3 Key frame selection is essentially a set-level optimization problem: the quality of the selected subset depends on the interactions among frames, rather than the score of any single frame. Existing methods generally exhibit three major limitations. Point-wise methods score each frame independently and ignore inter-frame dependencies. Although the training-free set-level methods explicitly model the inter-frame relationships, their selection criteria are fixed and cannot be adapted through downstream task feedback. Learnable methods can leverage data-driven training; however, they lack an explicit, differentiable set-quality objective and rely on offline-generated supervision signals. To address these limitations, we propose an end-to-end trainable and task-adaptive framework for frame selection. A Chain-of-Thought prompt conditions a Small Language Model (SLM) to extract task-specific latent query vectors, which are combined with multimodal features to enable dynamic, query-aware frame scoring. We further formulate a continuous set-level objective function that jointly accounts for relevance, coverage, and redundancy, enabling differentiable set-level optimization via Gumbel-TopK for selecting optimal frame combinations. Finally, we employ a student-teacher mutual learning strategy, in which the student selector (SLM) and teacher reasoner (MLLM) are trained to align their frame-importance distributions via KL divergence. Combined with cross-entropy loss, this design enables fully end-to-end optimization, eliminating reliance on static pseudo-labels. Experiments across multiple benchmarks, including Video-MME, LongVideoBench, MLVU, and NExT-QA, demonstrate that our method significantly outperforms existing frame-selection approaches. --- ### HFS: Holistic Query-Aware Frame Selection for Efficient Video Reasoning Authors: Yiqing Yang, Kin-Man Lam Published: 2025-12-12 Categories: cs.CV, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2512.11534v1 Key frame selection in video understanding presents significant challenges. Traditional top-K selection methods, which score frames independently, often fail to optimize the selection as a whole. This independent scoring frequently results in selecting frames that are temporally clustered and visually redundant. Additionally, training lightweight selectors using pseudo labels generated offline by Multimodal Large Language Models (MLLMs) prevents the supervisory signal from dynamically adapting to task objectives. To address these limitations, we propose an end-to-end trainable, task-adaptive framework for frame selection. A Chain-of-Thought approach guides a Small Language Model (SLM) to generate task-specific implicit query vectors, which are combined with multimodal features to enable dynamic frame scoring. We further define a continuous set-level objective function that incorporates relevance, coverage, and redundancy, enabling differentiable optimization via Gumbel-Softmax to select optimal frame combinations at the set level. Finally, student-teacher mutual learning is employed, where the student selector (SLM) and teacher reasoner (MLLM) are trained to align their frame importance distributions via KL divergence. Combined with cross-entropy loss, this enables end-to-end optimization, eliminating reliance on static pseudo labels. Experiments across various benchmarks, including Video-MME, LongVideoBench, MLVU, and NExT-QA, demonstrate that our method significantly outperforms existing approaches. --- ### Parallax: Runtime Parallelization for Operator Fallbacks in Heterogeneous Edge Systems Authors: Chong Tang, Hao Dai, Jagmohan Chauhan Published: 2025-12-12 Categories: cs.DC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.11532v1 The growing demand for real-time DNN applications on edge devices necessitates faster inference of increasingly complex models. Although many devices include specialized accelerators (e.g., mobile GPUs), dynamic control-flow operators and unsupported kernels often fall back to CPU execution. Existing frameworks handle these fallbacks poorly, leaving CPU cores idle and causing high latency and memory spikes. We introduce Parallax, a framework that accelerates mobile DNN inference without model refactoring or custom operator implementations. Parallax first partitions the computation DAG to expose parallelism, then employs branch-aware memory management with dedicated arenas and buffer reuse to reduce runtime footprint. An adaptive scheduler executes branches according to device memory constraints, meanwhile, fine-grained subgraph control enables heterogeneous inference of dynamic models. By evaluating on five representative DNNs across three different mobile devices, Parallax achieves up to 46% latency reduction, maintains controlled memory overhead (26.5% on average), and delivers up to 30% energy savings compared with state-of-the-art frameworks, offering improvements aligned with the responsiveness demands of real-time mobile inference. --- ### Parametric Numerical Integration with (Differential) Machine Learning Authors: Álvaro Leitao, Jonatan Ráfales Published: 2025-12-12 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2512.11530v1 In this work, we introduce a machine/deep learning methodology to solve parametric integrals. Besides classical machine learning approaches, we consider a differential learning framework that incorporates derivative information during training, emphasizing its advantageous properties. Our study covers three representative problem classes: statistical functionals (including moments and cumulative distribution functions), approximation of functions via Chebyshev expansions, and integrals arising directly from differential equations. These examples range from smooth closed-form benchmarks to challenging numerical integrals. Across all cases, the differential machine learning-based approach consistently outperforms standard architectures, achieving lower mean squared error, enhanced scalability, and improved sample efficiency. --- ### xGR: Efficient Generative Recommendation Serving at Scale Authors: Qingxiao Sun, Tongxuan Liu, Shen Zhang, Siyu Wu, Peijun Yang, Haotian Liang, Menxin Li, Xiaolong Ma, Zhiwei Liang, Ziyi Ren, Minchao Zhang, Yifan Wang et al. Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11529v3 Recommendation system delivers substantial economic benefits by providing personalized predictions. Generative recommendation (GR) integrates LLMs to enhance the understanding of long user-item sequences. Despite employing attention-based architectures, GR's workload differs markedly from that of LLM serving. GR typically processes long prompt while producing short, fixed-length outputs, yet the computational cost of each decode phase is especially high due to the large beam width. Furthermore, since the beam search involves a vast item space, the sorting overhead becomes particularly time-consuming. We propose xGR, a GR-oriented serving system that meets strict low-latency requirements under high-concurrency scenarios. First, xGR unifies the processing of prefill and decode phases through staged computation and separated KV cache. Second, xGR enables early sorting termination and mask-based item filtering with data structure reuse. Third, xGR reconstructs the overall pipeline to exploit multi-level overlap and multi-stream parallelism. The experiments on real-world datasets demonstrate that xGR achieves at least 2.89x throughput compared to the state-of-the-art baseline under strict latency constraints. --- ### xGR: Efficient Generative Recommendation Serving at Scale Authors: Qingxiao Sun, Tongxuan Liu, Shen Zhang, Siyu Wu, Peijun Yang, Haotian Liang, Menxin Li, Xiaolong Ma, Zhiwei Liang, Ziyi Ren, Minchao Zhang, Xinyu Liu et al. Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11529v1 Recommendation system delivers substantial economic benefits by providing personalized predictions. Generative recommendation (GR) integrates LLMs to enhance the understanding of long user-item sequences. Despite employing attention-based architectures, GR's workload differs markedly from that of LLM serving. GR typically processes long prompt while producing short, fixed-length outputs, yet the computational cost of each decode phase is especially high due to the large beam width. In addition, since the beam search involves a vast item space, the sorting overhead becomes particularly time-consuming. We propose xGR, a GR-oriented serving system that meets strict low-latency requirements under highconcurrency scenarios. First, xGR unifies the processing of prefill and decode phases through staged computation and separated KV cache. Second, xGR enables early sorting termination and mask-based item filtering with data structure reuse. Third, xGR reconstructs the overall pipeline to exploit multilevel overlap and multi-stream parallelism. Our experiments with real-world recommendation service datasets demonstrate that xGR achieves at least 3.49x throughput compared to the state-of-the-art baseline under strict latency constraints. --- ### Contrastive Time Series Forecasting with Anomalies Authors: Joel Ekstrand, Zahra Taghiyarrenani, Slawomir Nowaczyk Published: 2025-12-12 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.11526v2 Time series forecasting predicts future values from past data. In real-world settings, some anomalous events have lasting effects and influence the forecast, while others are short-lived and should be ignored. Standard forecasting models fail to make this distinction, often either overreacting to noise or missing persistent shifts. We propose Co-TSFA (Contrastive Time Series Forecasting with Anomalies), a regularization framework that learns when to ignore anomalies and when to respond. Co-TSFA generates input-only and input-output augmentations to model forecast-irrelevant and forecast-relevant anomalies, and introduces a latent-output alignment loss that ties representation changes to forecast changes. This encourages invariance to irrelevant perturbations while preserving sensitivity to meaningful distributional shifts. Experiments on the Traffic and Electricity benchmarks, as well as on a real-world cash-demand dataset, demonstrate that Co-TSFA improves performance under anomalous conditions while maintaining accuracy on normal data. An anonymized GitHub repository with the implementation of Co-TSFA is provided and will be made public upon acceptance. --- ### Contrastive Time Series Forecasting with Anomalies Authors: Joel Ekstrand, Zahra Taghiyarrenani, Slawomir Nowaczyk Published: 2025-12-12 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.11526v1 Time series forecasting predicts future values from past data. In real-world settings, some anomalous events have lasting effects and influence the forecast, while others are short-lived and should be ignored. Standard forecasting models fail to make this distinction, often either overreacting to noise or missing persistent shifts. We propose Co-TSFA (Contrastive Time Series Forecasting with Anomalies), a regularization framework that learns when to ignore anomalies and when to respond. Co-TSFA generates input-only and input-output augmentations to model forecast-irrelevant and forecast-relevant anomalies, and introduces a latent-output alignment loss that ties representation changes to forecast changes. This encourages invariance to irrelevant perturbations while preserving sensitivity to meaningful distributional shifts. Experiments on the Traffic and Electricity benchmarks, as well as on a real-world cash-demand dataset, demonstrate that Co-TSFA improves performance under anomalous conditions while maintaining accuracy on normal data. An anonymized GitHub repository with the implementation of Co-TSFA is provided and will be made public upon acceptance. --- ### NeuralOGCM: Differentiable Ocean Modeling with Learnable Physics Authors: Hao Wu, Yuan Gao, Fan Xu, Fan Zhang, Guangliang Liu, Yuxuan Liang, Xiaomeng Huang Published: 2025-12-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.11525v1 High-precision scientific simulation faces a long-standing trade-off between computational efficiency and physical fidelity. To address this challenge, we propose NeuralOGCM, an ocean modeling framework that fuses differentiable programming with deep learning. At the core of NeuralOGCM is a fully differentiable dynamical solver, which leverages physics knowledge as its core inductive bias. The learnable physics integration captures large-scale, deterministic physical evolution, and transforms key physical parameters (e.g., diffusion coefficients) into learnable parameters, enabling the model to autonomously optimize its physical core via end-to-end training. Concurrently, a deep neural network learns to correct for subgrid-scale processes and discretization errors not captured by the physics model. Both components work in synergy, with their outputs integrated by a unified ODE solver. Experiments demonstrate that NeuralOGCM maintains long-term stability and physical consistency, significantly outperforming traditional numerical models in speed and pure AI baselines in accuracy. Our work paves a new path for building fast, stable, and physically-plausible models for scientific computing. --- ### Super-Resolved Canopy Height Mapping from Sentinel-2 Time Series Using Airborne LiDAR HD Reference Data across Metropolitan France Authors: Ekaterina Kalinicheva, Florian Helen, Stéphane Mermoz, Florian Mouret, Milena Planells Published: 2025-12-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.11524v3 Fine-scale forest monitoring is essential for understanding canopy structure and its dynamics, which are key indicators of carbon stocks, biodiversity, and forest health. Deep learning is particularly effective for this task, as it integrates spectral, temporal, and spatial signals that jointly reflect the canopy structure. To address this need, we introduce THREASURE-Net, a novel end-to-end framework for Tree Height Regression And Super-Resolution. The model is trained on Sentinel-2 time series using reference height metrics derived from LiDAR HD data at multiple spatial resolutions over Metropolitan France to produce annual height maps. We evaluate three model variants, producing tree-height predictions at 2.5 m, 5 m, and 10 m resolution. THREASURE-Net does not rely on any pretrained model nor on reference very high resolution optical imagery to train its super-resolution module; instead, it learns solely from LiDAR-derived height information. Our approach outperforms existing state-of-the-art methods based on Sentinel data and is competitive with methods based on very high resolution imagery. It can be deployed to generate high-precision annual canopy-height maps, achieving mean absolute errors of 2.63 m, 2.70 m, and 2.88 m at 2.5 m, 5 m, and 10 m resolution, respectively. These results highlight the potential of THREASURE-Net for scalable and cost-effective structural monitoring of temperate forests using only freely available satellite data. The source code for THREASURE-Net is available at: https://github.com/Global-Earth-Observation/threasure-net. --- ### Super-Resolved Canopy Height Mapping from Sentinel-2 Time Series Using LiDAR HD Reference Data across Metropolitan France Authors: Ekaterina Kalinicheva, Florian Helen, Stéphane Mermoz, Florian Mouret, Milena Planells Published: 2025-12-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.11524v1 Fine-scale forest monitoring is essential for understanding canopy structure and its dynamics, which are key indicators of carbon stocks, biodiversity, and forest health. Deep learning is particularly effective for this task, as it integrates spectral, temporal, and spatial signals that jointly reflect the canopy structure. To address this need, we introduce THREASURE-Net, a novel end-to-end framework for Tree Height Regression And Super-Resolution. The model is trained on Sentinel-2 time series using reference height metrics derived from LiDAR HD data at multiple spatial resolutions over Metropolitan France to produce annual height maps. We evaluate three model variants, producing tree-height predictions at 2.5 m, 5 m, and 10 m resolution. THREASURE-Net does not rely on any pretrained model nor on reference very high resolution optical imagery to train its super-resolution module; instead, it learns solely from LiDAR-derived height information. Our approach outperforms existing state-of-the-art methods based on Sentinel data and is competitive with methods based on very high resolution imagery. It can be deployed to generate high-precision annual canopy-height maps, achieving mean absolute errors of 2.62 m, 2.72 m, and 2.88 m at 2.5 m, 5 m, and 10 m resolution, respectively. These results highlight the potential of THREASURE-Net for scalable and cost-effective structural monitoring of temperate forests using only freely available satellite data. The source code for THREASURE-Net is available at: https://github.com/Global-Earth-Observation/threasure-net. --- ### Reconstruction as a Bridge for Event-Based Visual Question Answering Authors: Hanyue Lou, Jiayi Zhou, Yang Zhang, Boyu Li, Yi Wang, Guangnan Ye, Boxin Shi Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11510v1 Integrating event cameras with Multimodal Large Language Models (MLLMs) promises general scene understanding in challenging visual conditions, yet requires navigating a trade-off between preserving the unique advantages of event data and ensuring compatibility with frame-based models. We address this challenge by using reconstruction as a bridge, proposing a straightforward Frame-based Reconstruction and Tokenization (FRT) method and designing an efficient Adaptive Reconstruction and Tokenization (ART) method that leverages event sparsity. For robust evaluation, we introduce EvQA, the first objective, real-world benchmark for event-based MLLMs, comprising 1,000 event-Q&A pairs from 22 public datasets. Our experiments demonstrate that our methods achieve state-of-the-art performance on EvQA, highlighting the significant potential of MLLMs in event-based vision. --- ### Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs Authors: Mohor Banerjee, Nadya Yuki Wangsajaya, Syed Ali Redha Alsagoff, Min Sen Tan, Zachary Choy Kit Chun, Alvin Chan Guo Wei Published: 2025-12-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.11509v2 Large Language Models (LLMs) exhibit remarkable capabilities in natural language understanding and reasoning, but suffer from hallucination: the generation of factually incorrect content. While numerous methods have been developed to reduce hallucinations, their impact on creative generations remains unexplored. This gap is particularly critical for AI-assisted scientific discovery, which requires both factual accuracy and creative hypothesis generation. We investigate how three hallucination-reduction techniques: Chain of Verification (CoVe), Decoding by Contrasting Layers (DoLa), and Retrieval-Augmented Generation (RAG), affect creativity in LLMs. Evaluating multiple model families (LLaMA, Qwen, Mistral) at varying scales (1B - 70B parameters) on two creativity benchmarks (NeoCoder and CS4), we find that these methods have opposing effects on divergent creativity. CoVe enhances divergent thinking, DoLa suppresses it, and RAG shows minimal impact. Our findings provide guidance for selecting appropriate hallucination-reduction methods in scientific applications, where the balance between factual accuracy and creative exploration is crucial. --- ### Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs Authors: Mohor Banerjee, Nadya Yuki Wangsajaya, Syed Ali Redha Alsagoff, Min Sen Tan, Zachary Choy Kit Chun, Alvin Chan Guo Wei Published: 2025-12-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.11509v1 Large Language Models (LLMs) exhibit remarkable capabilities in natural language understanding and reasoning, but suffer from hallucination: the generation of factually incorrect content. While numerous methods have been developed to reduce hallucinations, their impact on creative generations remains unexplored. This gap is particularly critical for AI-assisted scientific discovery, which requires both factual accuracy and creative hypothesis generation. We investigate how three hallucination-reduction techniques: Chain of Verification (CoVe), Decoding by Contrasting Layers (DoLa), and Retrieval-Augmented Generation (RAG), affect creativity in LLMs. Evaluating multiple model families (LLaMA, Qwen, Mistral) at varying scales (1B - 70B parameters) on two creativity benchmarks (NeoCoder and CS4), we find that these methods have opposing effects on divergent creativity. CoVe enhances divergent thinking, DoLa suppresses it, and RAG shows minimal impact. Our findings provide guidance for selecting appropriate hallucination-reduction methods in scientific applications, where the balance between factual accuracy and creative exploration is crucial. --- ### On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models Authors: Jelena Bratulić, Sudhanshu Mittal, Thomas Brox, Christian Rupprecht Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11508v2 Feed-forward 3D reconstruction models such as DUSt3R, VGGT, and Depth Anything 3 (DA3) are transformer-based foundation models that infer camera geometry and dense scene structure in a single forward pass. Trained at scale in a supervised fashion, they raise a central question: do these models build upon geometric principles akin to traditional multi-view pipelines, or do they primarily rely on learned priors arising from the large-scale training setup? We find that epipolar geometry emerges within the intermediate layers of all three models and is causally linked to correspondence patterns in attention heads. To study this, we perform a systematic analysis of their internal representations across three real-world datasets and a controlled synthetic dataset. We quantify geometric understanding by probing intermediate features, analyzing attention patterns to identify correspondence matching patterns, and performing targeted interventions at the attention level. Further, we assess the role of learned priors by applying challenging input-level perturbations, such as occlusions, scene ambiguities, and varying camera configurations, and compare them against classical multi-stage reconstruction pipelines. --- ### On Geometric Understanding and Learned Data Priors in VGGT Authors: Jelena Bratulić, Sudhanshu Mittal, Thomas Brox, Christian Rupprecht Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11508v1 The Visual Geometry Grounded Transformer (VGGT) is a 3D foundation model that infers camera geometry and scene structure in a single feed-forward pass. Trained in a supervised, single-step fashion on large datasets, VGGT raises a key question: does it build upon geometric concepts like traditional multi-view methods, or does it rely primarily on learned appearance-based data-driven priors? In this work, we conduct a systematic analysis of VGGT's internal mechanisms to uncover whether geometric understanding emerges within its representations. By probing intermediate features, analyzing attention patterns, and performing interventions, we examine how the model implements its functionality. Our findings reveal that VGGT implicitly performs correspondence matching within its global attention layers and encodes epipolar geometry, despite being trained without explicit geometric constraints. We further investigate VGGT's dependence on its learned data priors. Using spatial input masking and perturbation experiments, we assess its robustness to occlusions, appearance variations, and camera configurations, comparing it with classical multi-stage pipelines. Together, these insights highlight how VGGT internalizes geometric structure while using learned data-driven priors. --- ### SSA3D: Text-Conditioned Assisted Self-Supervised Framework for Automatic Dental Abutment Design Authors: Mianjie Zheng, Xinquan Yang, Along He, Xuguang Li, Feilie Zhong, Xuefen Liu, Kun Tang, Zhicheng Zhang, Linlin Shen Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11507v1 Abutment design is a critical step in dental implant restoration. However, manual design involves tedious measurement and fitting, and research on automating this process with AI is limited, due to the unavailability of large annotated datasets. Although self-supervised learning (SSL) can alleviate data scarcity, its need for pre-training and fine-tuning results in high computational costs and long training times. In this paper, we propose a Self-supervised assisted automatic abutment design framework (SS$A^3$D), which employs a dual-branch architecture with a reconstruction branch and a regression branch. The reconstruction branch learns to restore masked intraoral scan data and transfers the learned structural information to the regression branch. The regression branch then predicts the abutment parameters under supervised learning, which eliminates the separate pre-training and fine-tuning process. We also design a Text-Conditioned Prompt (TCP) module to incorporate clinical information (such as implant location, system, and series) into SS$A^3$D. This guides the network to focus on relevant regions and constrains the parameter predictions. Extensive experiments on a collected dataset show that SS$A^3$D saves half of the training time and achieves higher accuracy than traditional SSL methods. It also achieves state-of-the-art performance compared to other methods, significantly improving the accuracy and efficiency of automated abutment design. --- ### EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detection Authors: Georgios Kaoukis, Ioannis Aris Koufopoulos, Eleni Psaroudaki, Danae Pla Karidi, Evaggelia Pitoura, George Papastefanatos, Panayiotis Tsaparas Published: 2025-12-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11506v2 As AI and web agents become pervasive in decision-making, it is critical to design intelligent systems that not only support sustainability efforts but also guard against misinformation. Greenwashing, i.e., misleading corporate sustainability claims, poses a major challenge to environmental progress. To address this challenge, we introduce EmeraldMind, a fact-centric framework integrating a domain-specific knowledge graph with retrieval-augmented generation to automate greenwashing detection. EmeraldMind builds the EmeraldGraph from diverse corporate ESG (environmental, social, and governance) reports, surfacing verifiable evidence, often missing in generic knowledge bases, and supporting large language models in claim assessment. The framework delivers justification-centric classifications, presenting transparent, evidence-backed verdicts and abstaining responsibly when claims cannot be verified. Experiments on a new greenwashing claims dataset demonstrate that EmeraldMind achieves competitive accuracy, greater coverage, and superior explanation quality compared to generic LLMs, without the need for fine-tuning or retraining. --- ### EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detection Authors: Georgios Kaoukis, Ioannis Aris Koufopoulos, Psaroudaki Eleni, Danae Pla Karidi, Evaggelia Pitoura, George Papastefanatos, Panayiotis Tsaparas Published: 2025-12-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11506v1 As AI and web agents become pervasive in decision-making, it is critical to design intelligent systems that not only support sustainability efforts but also guard against misinformation. Greenwashing, i.e., misleading corporate sustainability claims, poses a major challenge to environmental progress. To address this challenge, we introduce EmeraldMind, a fact-centric framework integrating a domain-specific knowledge graph with retrieval-augmented generation to automate greenwashing detection. EmeraldMind builds the EmeraldGraph from diverse corporate ESG (environmental, social, and governance) reports, surfacing verifiable evidence, often missing in generic knowledge bases, and supporting large language models in claim assessment. The framework delivers justification-centric classifications, presenting transparent, evidence-backed verdicts and abstaining responsibly when claims cannot be verified. Experiments on a new greenwashing claims dataset demonstrate that EmeraldMind achieves competitive accuracy, greater coverage, and superior explanation quality compared to generic LLMs, without the need for fine-tuning or retraining. --- ### BAID: A Benchmark for Bias Assessment of AI Detectors Authors: Priyam Basu, Yunfeng Zhang, Vipul Raheja Published: 2025-12-12 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.11505v1 AI-generated text detectors have recently gained adoption in educational and professional contexts. Prior research has uncovered isolated cases of bias, particularly against English Language Learners (ELLs) however, there is a lack of systematic evaluation of such systems across broader sociolinguistic factors. In this work, we propose BAID, a comprehensive evaluation framework for AI detectors across various types of biases. As a part of the framework, we introduce over 200k samples spanning 7 major categories: demographics, age, educational grade level, dialect, formality, political leaning, and topic. We also generated synthetic versions of each sample with carefully crafted prompts to preserve the original content while reflecting subgroup-specific writing styles. Using this, we evaluate four open-source state-of-the-art AI text detectors and find consistent disparities in detection performance, particularly low recall rates for texts from underrepresented groups. Our contributions provide a scalable, transparent approach for auditing AI detectors and emphasize the need for bias-aware evaluation before these tools are deployed for public use. --- ### TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition Authors: Yanan Liu, Jun Liu, Hao Zhang, Dan Xu, Hossein Rahmani, Mohammed Bennamoun, Qiuhong Ke Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11503v1 Skeleton-based action recognition has garnered significant attention in the computer vision community. Inspired by the recent success of the selective state-space model (SSM) Mamba in modeling 1D temporal sequences, we propose TSkel-Mamba, a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics. In particular, our approach leverages Spatial Transformer for spatial feature learning while utilizing Mamba for temporal modeling. Mamba, however, employs separate SSM blocks for individual channels, which inherently limits its ability to model inter-channel dependencies. To better adapt Mamba for skeleton data and enhance Mamba`s ability to model temporal dependencies, we introduce a Temporal Dynamic Modeling (TDM) block, which is a versatile plug-and-play component that integrates a novel Multi-scale Temporal Interaction (MTI) module. The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition. Extensive experiments on NTU-RGB+D 60, NTU-RGB+D 120, NW-UCLA and UAV-Human datasets demonstrate that TSkel-Mamba achieves state-of-the-art performance while maintaining low inference time, making it both efficient and highly effective. --- ### Building Patient Journeys in Hebrew: A Language Model for Clinical Timeline Extraction Authors: Kai Golan Hashiloni, Brenda Kasabe Nokai, Michal Shevach, Esthy Shemesh, Ronit Bartin, Anna Bergrin, Liran Harel, Nachum Dershowitz, Liat Nadai Arad, Kfir Bar Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.11502v1 We present a new Hebrew medical language model designed to extract structured clinical timelines from electronic health records, enabling the construction of patient journeys. Our model is based on DictaBERT 2.0 and continually pre-trained on over five million de-identified hospital records. To evaluate its effectiveness, we introduce two new datasets -- one from internal medicine and emergency departments, and another from oncology -- annotated for event temporal relations. Our results show that our model achieves strong performance on both datasets. We also find that vocabulary adaptation improves token efficiency and that de-identification does not compromise downstream performance, supporting privacy-conscious model development. The model is made available for research use under ethical restrictions. --- ### FRQI Pairs method for image classification using Quantum Recurrent Neural Network Authors: Rafał Potempa, Michał Kordasz, Sundas Naqeeb Khan, Krzysztof Werner, Kamil Wereszczyński, Krzysztof Simiński, Krzysztof A. Cyran Published: 2025-12-12 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2512.11499v2 This study aims to introduce the FRQI Pairs method to a wider audience, a novel approach to image classification using Quantum Recurrent Neural Networks (QRNN) with Flexible Representation for Quantum Images (FRQI). The study highlights an innovative approach to use quantum encoded data for an image classification task, suggesting that such quantum-based approaches could significantly reduce the complexity of quantum algorithms. Comparison of the FRQI Pairs method with contemporary techniques underscores the promise of integrating quantum computing principles with neural network architectures for the development of quantum machine learning. --- ### FRQI Pairs method for image classification using Quantum Recurrent Neural Network Authors: Rafał Potempa, Michał Kordasz, Sundas Naqeeb Khan, Krzysztof Werner, Kamil Wereszczyński, Krzysztof Simiński, Krzysztof A. Cyran Published: 2025-12-12 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2512.11499v1 This study aims to introduce the FRQI Pairs method to a wider audience, a novel approach to image classification using Quantum Recurrent Neural Networks (QRNN) with Flexible Representation for Quantum Images (FRQI). The study highlights an innovative approach to use quantum encoded data for an image classification task, suggesting that such quantum-based approaches could significantly reduce the complexity of quantum algorithms. Comparison of the FRQI Pairs method with contemporary techniques underscores the promise of integrating quantum computing principles with neural network architectures for the development of quantum machine learning. --- ### VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing Authors: Emanuel Sánchez Aimar, Gulnaz Zhambulova, Fahad Shahbaz Khan, Yonghao Xu, Michael Felsberg Published: 2025-12-12 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2512.11490v2 Satellite imagery differs from natural images in viewpoint, resolution, scale variation, and the prevalence of small objects -- demanding both region-level spatial reasoning and holistic scene understanding. Existing remote-sensing approaches are fragmented: dual-encoder retrieval models scale well but cannot interleave modalities, whereas generative assistants support grounding, yet are inefficient for retrieval. Benchmarks mirror this split: interleaved evaluations mainly target generative assistants, while cross-modal retrieval benchmarks target dual encoders. To bridge this gap, we introduce \textbf{RSMEB}, a unified remote sensing benchmark that evaluates cross-modal and interleaved retrieval across 21 tasks under a single ranking protocol, enabling comprehensive comparison of retrieval models on region- and geo-aware capabilities as well as conventional retrieval. As a strong reference baseline, we present \textbf{VLM2GeoVec}, an instruction-conditioned, single-encoder interleaving formulation tailored to remote sensing that packs image, text, bounding-box, and geo-coordinate tokens into one sequence and learns a unified embedding via contrastive training. Across RSMEB, VLM2GeoVec achieves $\textbf{26.6\%}$ P@1 in region-caption retrieval ($\textbf{+25}$ percentage points), $\textbf{32.5\%}$ in referring-expression retrieval ($\textbf{+19}$), and $\textbf{17.8\%}$ in semantic geo-aware retrieval ($\textbf{>3}$$\times$ prior best), while remaining competitive in conventional scene classification and text--image retrieval in zero-shot settings. Together, the proposed suite and reference baseline standardize evaluation and deliver a unified embedder for scalable retrieval and region-/geo-aware grounding. The code, the model checkpoints, and the data are available at https://github.com/emasa/VLM2GeoVec. --- ### VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing Authors: Emanuel Sánchez Aimar, Gulnaz Zhambulova, Fahad Shahbaz Khan, Yonghao Xu, Michael Felsberg Published: 2025-12-12 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2512.11490v1 Satellite imagery differs fundamentally from natural images: its aerial viewpoint, very high resolution, diverse scale variations, and abundance of small objects demand both region-level spatial reasoning and holistic scene understanding. Current remote-sensing approaches remain fragmented between dual-encoder retrieval models, which excel at large-scale cross-modal search but cannot interleave modalities, and generative assistants, which support region-level interpretation but lack scalable retrieval capabilities. We propose $\textbf{VLM2GeoVec}$, an instruction-following, single-encoder vision-language model trained contrastively to embed interleaved inputs (images, text, bounding boxes, and geographic coordinates) in a unified vector space. Our single encoder interleaves all inputs into one joint embedding trained with a contrastive loss, eliminating multi-stage pipelines and task-specific modules. To evaluate its versatility, we introduce $\textbf{RSMEB}$, a novel benchmark covering key remote-sensing embedding applications: scene classification; cross-modal search; compositional retrieval; visual-question answering; visual grounding and region-level reasoning; and semantic geospatial retrieval. On RSMEB, it achieves $\textbf{26.6%}$ P@1 on region-caption retrieval (+25 pp vs. dual-encoder baselines), $\textbf{32.5%}$ P@1 on referring-expression retrieval (+19 pp), and $\textbf{17.8%}$ P@1 on semantic geo-localization retrieval (over $3\times$ prior best), while matching or exceeding specialized baselines on conventional tasks such as scene classification and cross-modal retrieval. VLM2GeoVec unifies scalable retrieval with region-level spatial reasoning, enabling cohesive multimodal analysis in remote sensing. We will publicly release the code, checkpoints, and data upon acceptance. --- ### Mistake Notebook Learning: Batch-Clustered Failures for Training-Free Agent Adaptation Authors: Xuanbo Su, Yingfang Zhang, Hao Luo, Xiaoteng Liu, Leo Huang Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.11485v3 With the growing adoption of Large Language Model (LLM) agents in persistent, real-world roles, they naturally encounter continuous streams of tasks and inevitable failures. A key limitation, however, is their inability to systematically learn from these mistakes, forcing them to repeat identical errors in similar contexts. Unlike prior training-free methods that primarily store raw instance-level experience or focus on retrieving successful trajectories, we propose Mistake Notebook Learning (MNL), a novel memory framework that enables agents to self-curate generalizable guidance from batch-clustered failures. This mechanism allows agents to distill shared error patterns into structured "mistake notes," updating an external memory only when batch performance improves to ensure stability. To further amplify adaptability, we integrate MNL with test-time scaling, leveraging aggregated failure patterns to actively steer the search process away from known pitfalls. Experiments on mathematical reasoning, Text-to-SQL, and interactive agent benchmarks show that MNL achieves competitive performance compared to existing memory mechanisms and in-context methods in both effectiveness and efficiency. These findings position structured mistake abstraction as a critical lever for robust agent evolution, enabling continuous improvement without the cost of parameter updates. The code is available at https://github.com/Bairong-Xdynamics/MistakeNotebookLearning/tree/main. --- ### Mistake Notebook Learning: Selective Batch-Wise Context Optimization for In-Context Learning Authors: Xuanbo Su, Yingfang Zhang, Hao Luo, Xiaoteng Liu, Leo Huang Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.11485v1 Large language models (LLMs) adapt to tasks via gradient fine-tuning (heavy computation, catastrophic forgetting) or In-Context Learning (ICL: low robustness, poor mistake learning). To fix this, we introduce Mistake Notebook Learning (MNL), a training-free framework with a persistent knowledge base of abstracted error patterns. Unlike prior instance/single-trajectory memory methods, MNL uses batch-wise error abstraction: it extracts generalizable guidance from multiple failures, stores insights in a dynamic notebook, and retains only baseline-outperforming guidance via hold-out validation (ensuring monotonic improvement). We show MNL nearly matches Supervised Fine-Tuning (93.9% vs 94.3% on GSM8K) and outperforms training-free alternatives on GSM8K, Spider, AIME, and KaggleDBQA. On KaggleDBQA (Qwen3-8B), MNL hits 28% accuracy (47% relative gain), outperforming Memento (15.1%) and Training-Free GRPO (22.1) - proving it's a strong training-free alternative for complex reasoning. --- ### Capacitive Touchscreens at Risk: Recovering Handwritten Trajectory on Smartphone via Electromagnetic Emanations Authors: Yukun Cheng, Shiyu Zhu, Changhai Ou, Xingshuo Han, Yuan Li, Shihui Zheng Published: 2025-12-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.11484v1 This paper reveals and exploits a critical security vulnerability: the electromagnetic (EM) side channel of capacitive touchscreens leaks sufficient information to recover fine-grained, continuous handwriting trajectories. We present Touchscreen Electromagnetic Side-channel Leakage Attack (TESLA), a non-contact attack framework that captures EM signals generated during on-screen writing and regresses them into two-dimensional (2D) handwriting trajectories in real time. Extensive evaluations across a variety of commercial off-the-shelf (COTS) smartphones show that TESLA achieves 77% character recognition accuracy and a Jaccard index of 0.74, demonstrating its capability to recover highly recognizable motion trajectories that closely resemble the original handwriting under realistic attack conditions. --- ### Towards Privacy-Preserving Code Generation: Differentially Private Code Language Models Authors: Melih Catal, Pooja Rani, Harald C. Gall Published: 2025-12-12 Categories: cs.SE, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2512.11482v1 Large language models specialized for code (CodeLLMs) have demonstrated remarkable capabilities in generating code snippets, documentation, and test cases. However, despite their promising capabilities, CodeLLMs can inadvertently memorize and reproduce snippets from their training data, which poses risks of privacy breaches and intellectual property violations. These risks restrict the deployment of CodeLLMs in sensitive domains and limit their training datasets to publicly available sources. To mitigate the memorization risk without compromising their task performance, we apply Differential Privacy (DP) to CodeLLMs. To the best of our knowledge, this is the first comprehensive study that systematically evaluates the effectiveness of DP in CodeLLMs. DP adds calibrated noise to the training process to protect individual data points while still allowing the model to learn useful patterns. To this end, we first identify and understand the driving reasons of the memorization behaviour of the CodeLLMs during their fine-tuning. Then, to address this issue, we empirically evaluate the effect of DP on mitigating memorization while preserving code generation capabilities. Our findings show that DP substantially reduces memorization in CodeLLMs across all the tested snippet types. The snippet types most prone to memorization are also the most effectively mitigated by DP. Furthermore, we observe that DP slightly increases perplexity but preserves, and can even enhance, the code generation capabilities of CodeLLMs, which makes it feasible to apply DP in practice without significantly compromising model utility. Finally, we analyze the impact of DP on training efficiency and energy consumption, finding that DP does not significantly affect training time or energy usage, making it a practical choice for privacy-preserving CodeLLMs training. --- ### CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loop Authors: Weijian Ma, Shizhao Sun, Ruiyu Wang, Jiang Bian Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11480v2 A Computer-Aided Design (CAD) model encodes an object in two coupled forms: a parametric construction sequence and its resulting visible geometric shape. During iterative design, adjustments to the geometric shape inevitably require synchronized edits to the underlying parametric sequence, called geometry-driven parametric CAD editing. The task calls for 1) preserving the original sequence's structure, 2) ensuring each edit's semantic validity, and 3) maintaining high shape fidelity to the target shape, all under scarce editing data triplets. We present CADMorph, an iterative plan-generate-verify framework that orchestrates pretrained domain-specific foundation models during inference: a parameter-to-shape (P2S) latent diffusion model and a masked-parameter-prediction (MPP) model. In the planning stage, cross-attention maps from the P2S model pinpoint the segments that need modification and offer editing masks. The MPP model then infills these masks with semantically valid edits in the generation stage. During verification, the P2S model embeds each candidate sequence in shape-latent space, measures its distance to the target shape, and selects the closest one. The three stages leverage the inherent geometric consciousness and design knowledge in pretrained priors, and thus tackle structure preservation, semantic validity, and shape fidelity respectively. Besides, both P2S and MPP models are trained without triplet data, bypassing the data-scarcity bottleneck. CADMorph surpasses GPT-4o and specialized CAD baselines, and supports downstream applications such as iterative editing and reverse-engineering enhancement. --- ### CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loop Authors: Weijian Ma, Shizhao Sun, Ruiyu Wang, Jiang Bian Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11480v1 A Computer-Aided Design (CAD) model encodes an object in two coupled forms: a parametric construction sequence and its resulting visible geometric shape. During iterative design, adjustments to the geometric shape inevitably require synchronized edits to the underlying parametric sequence, called geometry-driven parametric CAD editing. The task calls for 1) preserving the original sequence's structure, 2) ensuring each edit's semantic validity, and 3) maintaining high shape fidelity to the target shape, all under scarce editing data triplets. We present CADMorph, an iterative plan-generate-verify framework that orchestrates pretrained domain-specific foundation models during inference: a parameter-to-shape (P2S) latent diffusion model and a masked-parameter-prediction (MPP) model. In the planning stage, cross-attention maps from the P2S model pinpoint the segments that need modification and offer editing masks. The MPP model then infills these masks with semantically valid edits in the generation stage. During verification, the P2S model embeds each candidate sequence in shape-latent space, measures its distance to the target shape, and selects the closest one. The three stages leverage the inherent geometric consciousness and design knowledge in pretrained priors, and thus tackle structure preservation, semantic validity, and shape fidelity respectively. Besides, both P2S and MPP models are trained without triplet data, bypassing the data-scarcity bottleneck. CADMorph surpasses GPT-4o and specialized CAD baselines, and supports downstream applications such as iterative editing and reverse-engineering enhancement. --- ### General-purpose AI models can generate actionable knowledge on agroecological crop protection Authors: Kris A. G. Wyckhuys Published: 2025-12-12 Categories: cs.AI, cs.CY, cs.IR arXiv: https://arxiv.org/abs/2512.11474v1 Generative artificial intelligence (AI) offers potential for democratizing scientific knowledge and converting this to clear, actionable information, yet its application in agri-food science remains unexplored. Here, we verify the scientific knowledge on agroecological crop protection that is generated by either web-grounded or non-grounded large language models (LLMs), i.e., DeepSeek versus the free-tier version of ChatGPT. For nine globally limiting pests, weeds, and plant diseases, we assessed the factual accuracy, data consistency, and breadth of knowledge or data completeness of each LLM. Overall, DeepSeek consistently screened a 4.8-49.7-fold larger literature corpus and reported 1.6-2.4-fold more biological control agents or management solutions than ChatGPT. As a result, DeepSeek reported 21.6% higher efficacy estimates, exhibited greater laboratory-to-field data consistency, and showed more realistic effects of pest identity and management tactics. However, both models hallucinated, i.e., fabricated fictitious agents or references, reported on implausible ecological interactions or outcomes, confused old and new scientific nomenclatures, and omitted data on key agents or solutions. Despite these shortcomings, both LLMs correctly reported low-resolution efficacy trends. Overall, when paired with rigorous human oversight, LLMs may pose a powerful tool to support farm-level decision-making and unleash scientific creativity. --- ### Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning Authors: Bowen Ding, Yuhan Chen, Jiayang Lyv, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin Published: 2025-12-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.11470v2 Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ fundamentally in their reliance on expert trajectories. To understand the optimal way to harness these trajectories for maximizing performance, we propose the Plasticity-Ceiling Framework. This framework empirically grounds the post-training landscape by decomposing the final performance ceiling into the foundational SFT performance and the subsequent RL plasticity (i.e., the maximum improvement via RL). Through extensive benchmarking, we establish the Sequential SFT-then-RL pipeline as the superior standard, overcoming the stability and premature convergence deficits inherent in synchronized approaches. Furthermore, we derive precise scaling guidelines: (1) Transitioning to RL at the Stable or Mild Overfitting Regime of SFT maximizes the final ceiling by securing a robust SFT foundation with substantial RL plasticity; (2) Refuting the ``Less is More'' hypothesis in SFT-then-RL scaling, we demonstrate that Data Scale determines the primary post-training potential, while Trajectory Difficulty acts as a performance multiplier; and (3) The Minimum Validation Loss of SFT serves as a reliable indicator for selecting the expert trajectories that maximize the ultimate performance ceiling. Our findings provide actionable guidelines for extracting maximum value from expert trajectories. --- ### Rethinking Expert Trajectory Utilization in LLM Post-training Authors: Bowen Ding, Yuhan Chen, Jiayang Lv, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin Published: 2025-12-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.11470v1 While effective post-training integrates Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), the optimal mechanism for utilizing expert trajectories remains unresolved. We propose the Plasticity-Ceiling Framework to theoretically ground this landscape, decomposing performance into foundational SFT performance and the subsequent RL plasticity. Through extensive benchmarking, we establish the Sequential SFT-then-RL pipeline as the superior standard, overcoming the stability deficits of synchronized approaches. Furthermore, we derive precise scaling guidelines: (1) Transitioning to RL at the SFT Stable or Mild Overfitting Sub-phase maximizes the final ceiling by securing foundational SFT performance without compromising RL plasticity; (2) Refuting ``Less is More'' in the context of SFT-then-RL scaling, we demonstrate that Data Scale determines the primary post-training potential, while Trajectory Difficulty acts as a performance multiplier; and (3) Identifying that the Minimum SFT Validation Loss serves as a robust indicator for selecting the expert trajectories that maximize the final performance ceiling. Our findings provide actionable guidelines for maximizing the value extracted from expert trajectories. --- ### Three methods, one problem: Classical and AI approaches to no-three-in-line Authors: Pranav Ramanathan, Thomas Prellberg, Matthew Lewis, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat Published: 2025-12-12 Categories: cs.AI, math.CO arXiv: https://arxiv.org/abs/2512.11469v2 The No-Three-In-Line problem asks for the maximum number of points that can be placed on an n by n grid with no three collinear, representing a famous problem in combinatorial geometry. While classical methods like Integer Linear Programming (ILP) guarantee optimal solutions, they face exponential scaling with grid size, and recent advances in machine learning offer promising alternatives for pattern-based approximation. This paper presents the first systematic comparison of classical optimization and AI approaches to this problem, evaluating their performance against traditional algorithms. We apply PatternBoost transformer learning and reinforcement learning (PPO) to this problem for the first time, comparing them against ILP. ILP achieves provably optimal solutions up to 19 by 19 grids, while PatternBoost matches optimal performance up to 14 by 14 grids with 96% test loss reduction. PPO achieves perfect solutions on 10 by 10 grids but fails at 11 by 11 grids, where constraint violations prevent valid configurations. These results demonstrate that classical optimization remains essential for exact solutions while AI methods offer competitive performance on smaller instances, with hybrid approaches presenting the most promising direction for scaling to larger problem sizes. --- ### Three methods, one problem: Classical and AI approaches to no-three-in-line Authors: Pranav Ramanathan, Thomas Prellberg, Matthew Lewis, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat Published: 2025-12-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11469v1 The No-Three-In-Line problem asks for the maximum number of points that can be placed on an n by n grid with no three collinear, representing a famous problem in combinatorial geometry. While classical methods like Integer Linear Programming (ILP) guarantee optimal solutions, they face exponential scaling with grid size, and recent advances in machine learning offer promising alternatives for pattern-based approximation. This paper presents the first systematic comparison of classical optimization and AI approaches to this problem, evaluating their performance against traditional algorithms. We apply PatternBoost transformer learning and reinforcement learning (PPO) to this problem for the first time, comparing them against ILP. ILP achieves provably optimal solutions up to 19 by 19 grids, while PatternBoost matches optimal performance up to 14 by 14 grids with 96% test loss reduction. PPO achieves perfect solutions on 10 by 10 grids but fails at 11 by 11 grids, where constraint violations prevent valid configurations. These results demonstrate that classical optimization remains essential for exact solutions while AI methods offer competitive performance on smaller instances, with hybrid approaches presenting the most promising direction for scaling to larger problem sizes. --- ### DOS: Distilling Observable Softmaps of Zipfian Prototypes for Self-Supervised Point Representation Authors: Mohamed Abdelsamad, Michael Ulrich, Bin Yang, Miao Zhang, Yakov Miron, Abhinav Valada Published: 2025-12-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.11465v1 Recent advances in self-supervised learning (SSL) have shown tremendous potential for learning 3D point cloud representations without human annotations. However, SSL for 3D point clouds still faces critical challenges due to irregular geometry, shortcut-prone reconstruction, and unbalanced semantics distribution. In this work, we propose DOS (Distilling Observable Softmaps), a novel SSL framework that self-distills semantic relevance softmaps only at observable (unmasked) points. This strategy prevents information leakage from masked regions and provides richer supervision than discrete token-to-prototype assignments. To address the challenge of unbalanced semantics in an unsupervised setting, we introduce Zipfian prototypes and incorporate them using a modified Sinkhorn-Knopp algorithm, Zipf-Sinkhorn, which enforces a power-law prior over prototype usage and modulates the sharpness of the target softmap during training. DOS outperforms current state-of-the-art methods on semantic segmentation and 3D object detection across multiple benchmarks, including nuScenes, Waymo, SemanticKITTI, ScanNet, and ScanNet200, without relying on extra data or annotations. Our results demonstrate that observable-point softmaps distillation offers a scalable and effective paradigm for learning robust 3D representations. --- ### Exploring MLLM-Diffusion Information Transfer with MetaCanvas Authors: Han Lin, Xichen Pan, Ziqi Huang, Ji Hou, Jialiang Wang, Weifeng Chen, Zecheng He, Felix Juefei-Xu, Junzhe Sun, Zhipeng Fan, Ali Thabet, Mohit Bansal et al. Published: 2025-12-12 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.11464v1 Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation, however, these powerful core models are typically reduced to global text encoders for diffusion models, leaving most of their reasoning and planning ability unused. This creates a gap: current multimodal LLMs can parse complex layouts, attributes, and knowledge-intensive scenes, yet struggle to generate images or videos with equally precise and structured control. We propose MetaCanvas, a lightweight framework that lets MLLMs reason and plan directly in spatial and spatiotemporal latent spaces and interface tightly with diffusion generators. We empirically implement MetaCanvas on three different diffusion backbones and evaluate it across six tasks, including text-to-image generation, text/image-to-video generation, image/video editing, and in-context video generation, each requiring precise layouts, robust attribute binding, and reasoning-intensive control. MetaCanvas consistently outperforms global-conditioning baselines, suggesting that treating MLLMs as latent-space planners is a promising direction for narrowing the gap between multimodal understanding and generation. --- ### Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation Authors: Jingmin Zhu, Anqi Zhu, Hossein Rahmani, Jun Liu, Mohammed Bennamoun, Qiuhong Ke Published: 2025-12-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.11458v1 We introduce Skeleton-Cache, the first training-free test-time adaptation framework for skeleton-based zero-shot action recognition (SZAR), aimed at improving model generalization to unseen actions during inference. Skeleton-Cache reformulates inference as a lightweight retrieval process over a non-parametric cache that stores structured skeleton representations, combining both global and fine-grained local descriptors. To guide the fusion of descriptor-wise predictions, we leverage the semantic reasoning capabilities of large language models (LLMs) to assign class-specific importance weights. By integrating these structured descriptors with LLM-guided semantic priors, Skeleton-Cache dynamically adapts to unseen actions without any additional training or access to training data. Extensive experiments on NTU RGB+D 60/120 and PKU-MMD II demonstrate that Skeleton-Cache consistently boosts the performance of various SZAR backbones under both zero-shot and generalized zero-shot settings. The code is publicly available at https://github.com/Alchemist0754/Skeleton-Cache. --- ### Learning to Evolve for Optimization via Stability-Inducing Neural Unrolling Authors: Jiaxin Gao, Yaohua Liu, Ran Cheng, Kay Chen Tan Published: 2025-12-12 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.11453v2 Evolutionary algorithms serve as a powerful paradigm for tackling optimization challenges, yet their reliance on manually engineered heuristics inherently limits their adaptability across diverse landscapes. However, the transition from the hand-crafted heuristics to data-driven algorithms faces a fundamental dilemma: achieving neural \emph{plasticity} without sacrificing algorithmic stability. Although learned optimizers offer high adaptivity, their unconstrained update rules often result in unstable dynamics and brittle generalization on unseen landscapes. To address this challenge, this paper proposes Learning to Evolve (L2E), a bilevel meta-optimization framework that learns evolutionary search via stability-inducing neural unrolling. First, L2E reformulates population evolution as an unrolled fixed-point iteration via a structured neural operator. In this design, the inner loop imposes a stability-biased update structure, while the outer loop meta-trains the operator to produce effective search trajectories across tasks. Second, to balance global exploration with local refinement, a gradient-derived composite solver adaptively fuses learned evolutionary proposals with proxy numerical guidance in a differentiable manner. Extensive experiments on synthetic benchmarks and real-world control tasks demonstrate that L2E achieves substantial optimization performance, scales to high-dimensional problems, and exhibits robust zero-shot transfer across diverse test distributions. --- ### Learning to Evolve with Convergence Guarantee via Neural Unrolling Authors: Jiaxin Gao, Yaohua Liu, Ran Cheng, Kay Chen Tan Published: 2025-12-12 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.11453v1 The transition from hand-crafted heuristics to data-driven evolutionary algorithms faces a fundamental dilemma: achieving neural plasticity without sacrificing mathematical stability. Emerging learned optimizers demonstrate high adaptability. However, they often lack rigorous convergence guarantees. This deficiency results in unpredictable behaviors on unseen landscapes. To address this challenge, we introduce Learning to Evolve (L2E), a unified bilevel meta-optimization framework. This method reformulates evolutionary search as a Neural Unrolling process grounded in Krasnosel'skii-Mann (KM) fixed-point theory. First, L2E models a coupled dynamic system in which the inner loop enforces a strict contractive trajectory via a structured Mamba-based neural operator. Second, the outer loop optimizes meta-parameters to align the fixed point of the operator with the target objective minimizers. Third, we design a gradient-derived composite solver that adaptively fuses learned evolutionary proposals with proxy gradient steps, thereby harmonizing global exploration with local refinement. Crucially, this formulation provides the learned optimizer with provable convergence guarantees. Extensive experiments demonstrate the scalability of L2E in high-dimensional spaces and its robust zero-shot generalization across synthetic and real-world control tasks. These results confirm that the framework learns a generic optimization manifold that extends beyond specific training distributions. --- ### Hyperbolic Gaussian Blurring Mean Shift: A Statistical Mode-Seeking Framework for Clustering in Curved Spaces Authors: Arghya Pratihar, Arnab Seal, Swagatam Das, Inesh Chattopadhyay Published: 2025-12-12 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.11448v1 Clustering is a fundamental unsupervised learning task for uncovering patterns in data. While Gaussian Blurring Mean Shift (GBMS) has proven effective for identifying arbitrarily shaped clusters in Euclidean space, it struggles with datasets exhibiting hierarchical or tree-like structures. In this work, we introduce HypeGBMS, a novel extension of GBMS to hyperbolic space. Our method replaces Euclidean computations with hyperbolic distances and employs Möbius-weighted means to ensure that all updates remain consistent with the geometry of the space. HypeGBMS effectively captures latent hierarchies while retaining the density-seeking behavior of GBMS. We provide theoretical insights into convergence and computational complexity, along with empirical results that demonstrate improved clustering quality in hierarchical datasets. This work bridges classical mean-shift clustering and hyperbolic representation learning, offering a principled approach to density-based clustering in curved spaces. Extensive experimental evaluations on $11$ real-world datasets demonstrate that HypeGBMS significantly outperforms conventional mean-shift clustering methods in non-Euclidean settings, underscoring its robustness and effectiveness. --- ### YawDD+: Frame-level Annotations for Accurate Yawn Prediction Authors: Ahmed Mujtaba, Gleb Radchenko, Marc Masana, Radu Prodan Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11446v3 Driver fatigue remains a leading cause of road accidents, responsible for 24% of crashes. While yawning serves as an early behavioral indicator of fatigue, existing approaches face significant challenges due to the presence of systematic noise in video-annotated datasets arising from coarse temporal annotations. Training robust machine learning (ML) models requires rich supervisory labels that help learn salient features from the training data. Moreover, efficient on-device training and inference of models on edge devices is crucial in driver fatigue detection tasks to enable accurate real-time decisions on vehicles without reliance on cloud infrastructure. To address this issue, we develop a semi-automated labeling pipeline with human-in-the-loop verification to annotate YawDD videos to YawDD+ frame-level annotations, enabling more accurate model training on edge platforms such as NVIDIA Jetson NANO. Training the established MNasNet classifier and YOLOv11 detector architectures on YawDD+ improves frame accuracy by up to 6% and mAP by 5% over video-level supervision, achieving 99.34% classification accuracy and 95.69% detection mAP on Jetson NANO and AGX. Moreover, MNasNet completed the epoch time in just 8.69 min/epoch while delivering up to 115 frames-per-second (FPS) inference time on AGX, confirming that enhanced data quality alone supports on-device driver fatigue monitoring systems without server-side computation. The YawDD+ dataset and trained models are available online. --- ### YawDD+: Frame-level Annotations for Accurate Yawn Prediction Authors: Ahmed Mujtaba, Gleb Radchenko, Marc Masana, Radu Prodan Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11446v1 Driver fatigue remains a leading cause of road accidents, with 24\% of crashes involving drowsy drivers. While yawning serves as an early behavioral indicator of fatigue, existing machine learning approaches face significant challenges due to video-annotated datasets that introduce systematic noise from coarse temporal annotations. We develop a semi-automated labeling pipeline with human-in-the-loop verification, which we apply to YawDD, enabling more accurate model training. Training the established MNasNet classifier and YOLOv11 detector architectures on YawDD+ improves frame accuracy by up to 6\% and mAP by 5\% over video-level supervision, achieving 99.34\% classification accuracy and 95.69\% detection mAP. The resulting approach deliver up to 59.8 FPS on edge AI hardware (NVIDIA Jetson Nano), confirming that enhanced data quality alone supports on-device yawning monitoring without server-side computation. --- ### Flowception: Temporally Expansive Flow Matching for Video Generation Authors: Tariq Berrada Ifriqi, John Nguyen, Karteek Alahari, Jakob Verbeek, Ricky T. Q. Chen Published: 2025-12-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.11438v2 We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive methods, Flowception alleviates error accumulation/drift as the frame insertion mechanism during sampling serves as an efficient compression mechanism to handle long-term context. Compared to full-sequence flows, our method reduces FLOPs for training three-fold, while also being more amenable to local attention variants, and allowing to learn the length of videos jointly with their content. Quantitative experimental results show improved FVD and VBench metrics over autoregressive and full-sequence baselines, which is further validated with qualitative results. Finally, by learning to insert and denoise frames in a sequence, Flowception seamlessly integrates different tasks such as image-to-video generation and video interpolation. --- ### CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare Authors: Akash Ghosh, Srivarshinee Sridhar, Raghav Kaushik Ravi, Muhsin Muhsin, Sriparna Saha, Chirag Agarwal Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.11437v1 Integrating language models (LMs) in healthcare systems holds great promise for improving medical workflows and decision-making. However, a critical barrier to their real-world adoption is the lack of reliable evaluation of their trustworthiness, especially in multilingual healthcare settings. Existing LMs are predominantly trained in high-resource languages, making them ill-equipped to handle the complexity and diversity of healthcare queries in mid- and low-resource languages, posing significant challenges for deploying them in global healthcare contexts where linguistic diversity is key. In this work, we present CLINIC, a Comprehensive Multilingual Benchmark to evaluate the trustworthiness of language models in healthcare. CLINIC systematically benchmarks LMs across five key dimensions of trustworthiness: truthfulness, fairness, safety, robustness, and privacy, operationalized through 18 diverse tasks, spanning 15 languages (covering all the major continents), and encompassing a wide array of critical healthcare topics like disease conditions, preventive actions, diagnostic tests, treatments, surgeries, and medications. Our extensive evaluation reveals that LMs struggle with factual correctness, demonstrate bias across demographic and linguistic groups, and are susceptible to privacy breaches and adversarial attacks. By highlighting these shortcomings, CLINIC lays the foundation for enhancing the global reach and safety of LMs in healthcare across diverse languages. --- ### Back to the Baseline: Examining Baseline Effects on Explainability Metrics Authors: Agustin Martin Picard, Thibaut Boissin, Varshini Subhash, Rémi Cadène, Thomas Fel Published: 2025-12-12 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.11433v1 Attribution methods are among the most prevalent techniques in Explainable Artificial Intelligence (XAI) and are usually evaluated and compared using Fidelity metrics, with Insertion and Deletion being the most popular. These metrics rely on a baseline function to alter the pixels of the input image that the attribution map deems most important. In this work, we highlight a critical problem with these metrics: the choice of a given baseline will inevitably favour certain attribution methods over others. More concerningly, even a simple linear model with commonly used baselines contradicts itself by designating different optimal methods. A question then arises: which baseline should we use? We propose to study this problem through two desirable properties of a baseline: (i) that it removes information and (ii) that it does not produce overly out-of-distribution (OOD) images. We first show that none of the tested baselines satisfy both criteria, and there appears to be a trade-off among current baselines: either they remove information or they produce a sequence of OOD images. Finally, we introduce a novel baseline by leveraging recent work in feature visualisation to artificially produce a model-dependent baseline that removes information without being overly OOD, thus improving on the trade-off when compared to other existing baselines. Our code is available at https://github.com/deel-ai-papers/Back-to-the-Baseline ---