# Research Papers — 2025-12 · bundle page 132 of 175 > Full-text markdown of papers #6551–6600 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/132 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/131.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/133.md) ### SparseCoop: Cooperative Perception with Kinematic-Grounded Queries Authors: Jiahao Wang, Zhongwei Jiang, Wenchao Sun, Jiaru Zhong, Haibao Yu, Yuner Zhang, Chenyang Lu, Chuang Zhang, Lei He, Shaobing Xu, Jianqiang Wang Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06838v1 Cooperative perception is critical for autonomous driving, overcoming the inherent limitations of a single vehicle, such as occlusions and constrained fields-of-view. However, current approaches sharing dense Bird's-Eye-View (BEV) features are constrained by quadratically-scaling communication costs and the lack of flexibility and interpretability for precise alignment across asynchronous or disparate viewpoints. While emerging sparse query-based methods offer an alternative, they often suffer from inadequate geometric representations, suboptimal fusion strategies, and training instability. In this paper, we propose SparseCoop, a fully sparse cooperative perception framework for 3D detection and tracking that completely discards intermediate BEV representations. Our framework features a trio of innovations: a kinematic-grounded instance query that uses an explicit state vector with 3D geometry and velocity for precise spatio-temporal alignment; a coarse-to-fine aggregation module for robust fusion; and a cooperative instance denoising task to accelerate and stabilize training. Experiments on V2X-Seq and Griffin datasets show SparseCoop achieves state-of-the-art performance. Notably, it delivers this with superior computational efficiency, low transmission cost, and strong robustness to communication latency. Code is available at https://github.com/wang-jh18-SVM/SparseCoop. --- ### Neural Factorization-based Bearing Fault Diagnosis Authors: Zhenhao Li, Xu Cheng, Yi Zhou Published: 2025-12-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06837v1 This paper studies the key problems of bearing fault diagnosis of high-speed train. As the core component of the train operation system, the health of bearings is directly related to the safety of train operation. The traditional diagnostic methods are facing the challenge of insufficient diagnostic accuracy under complex conditions. To solve these problems, we propose a novel Neural Factorization-based Classification (NFC) framework for bearing fault diagnosis. It is built on two core idea: 1) Embedding vibration time series into multiple mode-wise latent feature vectors to capture diverse fault-related patterns; 2) Leveraging neural factorization principles to fuse these vectors into a unified vibration representation. This design enables effective mining of complex latent fault characteristics from raw time-series data. We further instantiate the framework with two models CP-NFC and Tucker-NFC based on CP and Tucker fusion schemes, respectively. Experimental results show that both models achieve superior diagnostic performance compared with traditional machine learning methods. The comparative analysis provides valuable empirical evidence and practical guidance for selecting effective diagnostic strategies in high-speed train bearing monitoring. --- ### Leveraging LLMs to support co-evolution between definitions and instances of textual DSLs Authors: Weixing Zhang, Regina Hebig, Daniel Strüber Published: 2025-12-07 Categories: cs.SE, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2512.06836v1 Software languages evolve over time for various reasons, such as the addition of new features. When the language's grammar definition evolves, textual instances that originally conformed to the grammar become outdated. For DSLs in a model-driven engineering context, there exists a plethora of techniques to co-evolve models with the evolving metamodel. However, these techniques are not geared to support DSLs with a textual syntax -- applying them to textual language definitions and instances may lead to the loss of information from the original instances, such as comments and layout information, which are valuable for software comprehension and maintenance. This study explores the potential of Large Language Model (LLM)-based solutions in achieving grammar and instance co-evolution, with attention to their ability to preserve auxiliary information when directly processing textual instances. By applying two advanced language models, Claude-3.5 and GPT-4o, and conducting experiments across seven case languages, we evaluated the feasibility and limitations of this approach. Our results indicate a good ability of the considered LLMs for migrating textual instances in small-scale cases with limited instance size, which are representative of a subset of cases encountered in practice. In addition, we observe significant challenges with the scalability of LLM-based solutions to larger instances, leading to insights that are useful for informing future research. --- ### Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning Authors: Tingyu Li, Zheng Sun, Jingxuan Wei, Siyuan Li, Conghui He, Lijun Wu, Cheng Tan Published: 2025-12-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.06835v1 Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience. However, RL for VLMs requires abundant high-quality multimodal data, especially challenging in specialized domains like chemistry, earth sciences, and multimodal mathematics. Existing strategies such as synthetic data and self-rewarding mechanisms suffer from limited distributions and alignment difficulties, ultimately causing reward hacking: models exploit high-reward patterns, collapsing policy entropy and destabilizing training. We propose DoGe (Decouple to Generalize), a dual-decoupling framework that guides models to first learn from context rather than problem solving by refocusing on the problem context scenarios overlooked by synthetic data methods. By decoupling learning process into dual components (Thinker and Solver), we reasonably quantify the reward signals of this process and propose a two-stage RL post-training approach from freely exploring context to practically solving tasks. Second, to increase the diversity of training data, DoGe constructs an evolving curriculum learning pipeline: an expanded native domain knowledge corpus and an iteratively evolving seed problems pool. Experiments show that our method consistently outperforms the baseline across various benchmarks, providing a scalable pathway for realizing self-evolving LVLMs. --- ### MeshSplatting: Differentiable Rendering with Opaque Meshes Authors: Jan Held, Sanghyun Son, Renaud Vandeghen, Daniel Rebain, Matheus Gadelha, Yi Zhou, Anthony Cioppa, Ming C. Lin, Marc Van Droogenbroeck, Andrea Tagliasacchi Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06818v1 Primitive-based splatting methods like 3D Gaussian Splatting have revolutionized novel view synthesis with real-time rendering. However, their point-based representations remain incompatible with mesh-based pipelines that power AR/VR and game engines. We present MeshSplatting, a mesh-based reconstruction approach that jointly optimizes geometry and appearance through differentiable rendering. By enforcing connectivity via restricted Delaunay triangulation and refining surface consistency, MeshSplatting creates end-to-end smooth, visually high-quality meshes that render efficiently in real-time 3D engines. On Mip-NeRF360, it boosts PSNR by +0.69 dB over the current state-of-the-art MiLo for mesh-based novel view synthesis, while training 2x faster and using 2x less memory, bridging neural rendering and interactive 3D graphics for seamless real-time scene interaction. The project page is available at https://meshsplatting.github.io/. --- ### CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation Authors: Dibyanayan Bandyopadhyay, Soham Bhattacharjee, Mohammed Hasanuzzaman, Asif Ekbal Published: 2025-12-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.06814v1 Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natural language explanations (NLEs). To build trust, such explanations must faithfully capture the classifier's internal decision making behavior, a property known as faithfulness. In this paper, we propose CAuSE (Causal Abstraction under Simulated Explanations), a novel framework to generate faithful NLEs for any pretrained multimodal classifier. We demonstrate that CAuSE generalizes across datasets and models through extensive empirical evaluations. Theoretically, we show that CAuSE, trained via interchange intervention, forms a causal abstraction of the underlying classifier. We further validate this through a redesigned metric for measuring causal faithfulness in multimodal settings. CAuSE surpasses other methods on this metric, with qualitative analysis reinforcing its advantages. We perform detailed error analysis to pinpoint the failure cases of CAuSE. For replicability, we make the codes available at https://github.com/newcodevelop/CAuSE --- ### Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation Authors: Agung Nugraha, Heungjun Im, Jihwan Lee Published: 2025-12-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06813v3 High-performance concrete (HPC) requires complex mix design decisions involving interdependent variables and practical constraints. While data-driven methods have improved predictive modeling for forward design in concrete engineering, inverse design remains limited, especially when some variables are fixed and only the remaining ones must be inferred. This study proposes a cooperative neural network framework for the partial inverse design of HPC. The framework integrates an imputation model with a surrogate strength predictor and learns through cooperative training. Once trained, it generates valid and performance-consistent mix designs in a single forward pass without retraining for different constraint scenarios. Compared with baseline models, including autoencoder models and Bayesian inference with Gaussian process surrogates, the proposed method achieves strength consistency between the surrogate-predicted strength of the generated mixes and the target strength with R-squared values of 0.84 to 0.89 and substantially reduces the mean squared error of this strength consistency by approximately 42% and 60%, respectively. The results demonstrate a novel, accurate, and computationally efficient application of artificial intelligence in concrete science by applying a cooperative neural network for constraint-aware partial inverse design of HPC mix generation. --- ### Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation Authors: Agung Nugraha, Heungjun Im, Jihwan Lee Published: 2025-12-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06813v1 High-performance concrete offers exceptional strength and durability but requires complex mix designs involving many interdependent variables and practical constraints. While data-driven methods have advanced predictive modeling for forward design, inverse design, which focuses on determining mix compositions that achieve target performance, remains limited, particularly in design situations where some mix variables are fixed by constraints and only the remaining variables must be determined. This study proposes a cooperative neural network framework for the partial inverse design of high-performance concrete. The framework combines two coupled neural network models, an imputation model that infers the undetermined variables and a surrogate model that predicts compressive strength. Through cooperative learning, the model generates valid and performance-consistent mix designs in a single forward pass while accommodating different constraint combinations without retraining. Its performance is compared with both probabilistic and generative approaches, including Bayesian inference based on a Gaussian process surrogate and autoencoder-based models. Evaluated on a benchmark dataset, the proposed model achieves stable and higher R-squared values of 0.87-0.92 and reduces mean squared error by an average of 50 percent compared with autoencoder baselines and by an average of 70 percent compared with Bayesian inference. The results demonstrate that the cooperative neural network provides an accurate, robust, and computationally efficient foundation for constraint-aware, data-driven mix proportioning in concrete engineering. --- ### Large Language Model-Based Generation of Discharge Summaries Authors: Tiago Rodrigues, Carla Teixeira Lopes Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06812v1 Discharge Summaries are documents written by medical professionals that detail a patient's visit to a care facility. They contain a wealth of information crucial for patient care, and automating their generation could significantly reduce the effort required from healthcare professionals, minimize errors, and ensure that critical patient information is easily accessible and actionable. In this work, we explore the use of five Large Language Models on this task, from open-source models (Mistral, Llama 2) to proprietary systems (GPT-3, GPT-4, Gemini 1.5 Pro), leveraging MIMIC-III summaries and notes. We evaluate them using exact-match, soft-overlap, and reference-free metrics. Our results show that proprietary models, particularly Gemini with one-shot prompting, outperformed others, producing summaries with the highest similarity to the gold-standard ones. Open-source models, while promising, especially Mistral after fine-tuning, lagged in performance, often struggling with hallucinations and repeated information. Human evaluation by a clinical expert confirmed the practical utility of the summaries generated by proprietary models. Despite the challenges, such as hallucinations and missing information, the findings suggest that LLMs, especially proprietary models, are promising candidates for automatic discharge summary generation as long as data privacy is ensured. --- ### RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models Authors: Xiang Lin, Weixin Li, Shu Guo, Lihong Wang, Di Huang Published: 2025-12-07 Categories: cs.CV, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2512.06811v1 Pre-trained Vision-Language Models (VLMs), \textit{e.g.} CLIP, have become essential tools in multimodal transfer learning. However, fine-tuning VLMs in few-shot scenarios poses significant challenges in balancing task-specific adaptation and generalization in the obtained model. Meanwhile, current researches have predominantly focused on prompt-based adaptation methods, leaving adapter-based approaches underexplored and revealing notable performance gaps. To address these challenges, we introduce a novel Reconstruction-based Multimodal Adapter (RMAdapter), which leverages a dual-branch architecture. Unlike conventional single-branch adapters, RMAdapter consists of: (1) an adaptation branch that injects task-specific knowledge through parameter-efficient fine-tuning, and (2) a reconstruction branch that preserves general knowledge by reconstructing latent space features back into the original feature space. This design facilitates a dynamic balance between general and task-specific knowledge. Importantly, although RMAdapter introduces an additional reconstruction branch, it is carefully optimized to remain lightweight. By computing reconstruction loss locally at each layer and sharing projection modules, the overall computational overhead is kept minimal. A consistency constraint is also incorporated to better regulate the trade-off between discriminability and generalization. We comprehensively evaluate the effectiveness of RMAdapter on three representative tasks: generalization to new categories, generalization to new target datasets, and domain generalization. Without relying on data augmentation or duplicate prompt designs, our RMAdapter consistently outperforms state-of-the-art approaches across all evaluation metrics. --- ### MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning Authors: Yueqian Wang, Songxiang Liu, Disong Wang, Nuo Xu, Guanglu Wan, Huishuai Zhang, Dongyan Zhao Published: 2025-12-07 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2512.06810v1 Recent advances in video multimodal large language models (Video MLLMs) have significantly enhanced video understanding and multi-modal interaction capabilities. While most existing systems operate in a turn-based manner where the model can only reply after user turns, proactively deciding when to reply during video playback presents a promising yet challenging direction for real-time applications. In this work, we propose a novel text-to-text approach to proactive interaction, where the model autonomously determines whether to respond or remain silent at each turn based on dialogue history and visual context up to current frame of an streaming video. To overcome difficulties in previous methods such as manually tuning response decision thresholds and annotating precise reply times, we introduce a multi-turn RL based training method that encourages timely and accurate responses without requiring precise response time annotations. We train our model MMDuet2 on a dataset of 52k videos with two types of dialogues via SFT and RL. Experimental results demonstrate that MMDuet2 outperforms existing proactive Video MLLM baselines in response timing and quality, achieving state-of-the-art performance on the ProactiveVideoQA benchmark. --- ### A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems Authors: Jiong Yang Published: 2025-12-07 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2512.06809v1 Battery safety is paramount for electric vehicles. Early fault diagnosis remains a challenge due to the subtle nature of anomalies and the interference of dynamic operating noise. Existing data-driven methods often suffer from "physical blindness" leading to missed detections or false alarms. To address this, we propose a Physics-Aware Attention LSTM Autoencoder (PA-ALSTM-AE). This novel framework explicitly integrates battery aging laws (mileage) into the deep learning pipeline through a multi-stage fusion mechanism. Specifically, an adaptive physical feature construction module selects mileage-sensitive features, and a physics-guided latent fusion module dynamically calibrates the memory cells of the LSTM based on the aging state. Extensive experiments on the large-scale Vloong real-world dataset demonstrate that the proposed method significantly outperforms state-of-the-art baselines. Notably, it improves the recall rate of early faults by over 3 times while maintaining high precision, offering a robust solution for industrial battery management systems. --- ### VDOT: Efficient Unified Video Creation via Optimal Transport Distillation Authors: Yutong Wang, Haiyu Zhang, Tianfan Xue, Yu Qiao, Yaohui Wang, Chang Xu, Xinyuan Chen Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06802v3 The rapid development of generative models has significantly advanced image and video applications. Among these, video creation, aimed at generating videos under various conditions, has gained substantial attention. However, existing video creation models either focus solely on a few specific conditions or suffer from excessively long generation times due to complex model inference, making them impractical for real-world applications. To mitigate these issues, we propose an efficient unified video creation model, named VDOT. Concretely, we model the training process with the distribution matching distillation (DMD) paradigm. Instead of using the Kullback-Leibler (KL) minimization, we additionally employ a novel computational optimal transport (OT) technique to optimize the discrepancy between the real and fake score distributions. The OT distance inherently imposes geometric constraints, mitigating potential zero-forcing or gradient collapse issues that may arise during KL-based distillation within the few-step generation scenario, and thus, enhances the efficiency and stability of the distillation process. Further, we integrate a discriminator to enable the model to perceive real video data, thereby enhancing the quality of generated videos. To support training unified video creation models, we propose a fully automated pipeline for video data annotation and filtering that accommodates multiple video creation tasks. Meanwhile, we curate a unified testing benchmark, UVCBench, to standardize evaluation. Experiments demonstrate that our 4-step VDOT outperforms or matches other baselines with 100 denoising steps. --- ### VDOT: Efficient Unified Video Creation via Optimal Transport Distillation Authors: Yutong Wang, Haiyu Zhang, Tianfan Xue, Yu Qiao, Yaohui Wang, Chang Xu, Xinyuan Chen Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06802v1 The rapid development of generative models has significantly advanced image and video applications. Among these, video creation, aimed at generating videos under various conditions, has gained substantial attention. However, existing video creation models either focus solely on a few specific conditions or suffer from excessively long generation times due to complex model inference, making them impractical for real-world applications. To mitigate these issues, we propose an efficient unified video creation model, named VDOT. Concretely, we model the training process with the distribution matching distillation (DMD) paradigm. Instead of using the Kullback-Leibler (KL) minimization, we additionally employ a novel computational optimal transport (OT) technique to optimize the discrepancy between the real and fake score distributions. The OT distance inherently imposes geometric constraints, mitigating potential zero-forcing or gradient collapse issues that may arise during KL-based distillation within the few-step generation scenario, and thus, enhances the efficiency and stability of the distillation process. Further, we integrate a discriminator to enable the model to perceive real video data, thereby enhancing the quality of generated videos. To support training unified video creation models, we propose a fully automated pipeline for video data annotation and filtering that accommodates multiple video creation tasks. Meanwhile, we curate a unified testing benchmark, UVCBench, to standardize evaluation. Experiments demonstrate that our 4-step VDOT outperforms or matches other baselines with 100 denoising steps. --- ### Optimal and Diffusion Transports in Machine Learning Authors: Gabriel Peyré Published: 2025-12-07 Categories: math.OC, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.06797v2 Several problems in machine learning are naturally expressed as the design and analysis of time-evolving probability distributions. This includes sampling via diffusion methods, optimizing the weights of neural networks, and analyzing the evolution of token distributions across layers of large language models. While the targeted applications differ (samples, weights, tokens), their mathematical descriptions share a common structure. A key idea is to switch from the Eulerian representation of densities to their Lagrangian counterpart through vector fields that advect particles. This dual view introduces challenges, notably the non-uniqueness of Lagrangian vector fields, but also opportunities to craft density evolutions and flows with favorable properties in terms of regularity, stability, and computational tractability. This survey presents an overview of these methods, with emphasis on two complementary approaches: diffusion methods, which rely on stochastic interpolation processes and underpin modern generative AI, and optimal transport, which defines interpolation by minimizing displacement cost. We illustrate how both approaches appear in applications ranging from sampling, neural network optimization, to modeling the dynamics of transformers for large language models. --- ### Optimal and Diffusion Transports in Machine Learning Authors: Gabriel Peyré Published: 2025-12-07 Categories: math.OC, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.06797v1 Several problems in machine learning are naturally expressed as the design and analysis of time-evolving probability distributions. This includes sampling via diffusion methods, optimizing the weights of neural networks, and analyzing the evolution of token distributions across layers of large language models. While the targeted applications differ (samples, weights, tokens), their mathematical descriptions share a common structure. A key idea is to switch from the Eulerian representation of densities to their Lagrangian counterpart through vector fields that advect particles. This dual view introduces challenges, notably the non-uniqueness of Lagrangian vector fields, but also opportunities to craft density evolutions and flows with favorable properties in terms of regularity, stability, and computational tractability. This survey presents an overview of these methods, with emphasis on two complementary approaches: diffusion methods, which rely on stochastic interpolation processes and underpin modern generative AI, and optimal transport, which defines interpolation by minimizing displacement cost. We illustrate how both approaches appear in applications ranging from sampling, neural network optimization, to modeling the dynamics of transformers for large language models. --- ### ADAM Optimization with Adaptive Batch Selection Authors: Gyu Yeol Kim, Min-hwan Oh Published: 2025-12-07 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.06795v1 Adam is a widely used optimizer in neural network training due to its adaptive learning rate. However, because different data samples influence model updates to varying degrees, treating them equally can lead to inefficient convergence. To address this, a prior work proposed adapting the sampling distribution using a bandit framework to select samples adaptively. While promising, the bandit-based variant of Adam suffers from limited theoretical guarantees. In this paper, we introduce Adam with Combinatorial Bandit Sampling (AdamCB), which integrates combinatorial bandit techniques into Adam to resolve these issues. AdamCB is able to fully utilize feedback from multiple samples at once, enhancing both theoretical guarantees and practical performance. Our regret analysis shows that AdamCB achieves faster convergence than Adam-based methods including the previous bandit-based variant. Numerical experiments demonstrate that AdamCB consistently outperforms existing methods. --- ### Generalized Geometry Encoding Volume for Real-time Stereo Matching Authors: Jiaxin Liu, Gangwei Xu, Xianqi Wang, Chengliang Zhang, Xin Yang Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06793v1 Real-time stereo matching methods primarily focus on enhancing in-domain performance but often overlook the critical importance of generalization in real-world applications. In contrast, recent stereo foundation models leverage monocular foundation models (MFMs) to improve generalization, but typically suffer from substantial inference latency. To address this trade-off, we propose Generalized Geometry Encoding Volume (GGEV), a novel real-time stereo matching network that achieves strong generalization. We first extract depth-aware features that encode domain-invariant structural priors as guidance for cost aggregation. Subsequently, we introduce a Depth-aware Dynamic Cost Aggregation (DDCA) module that adaptively incorporates these priors into each disparity hypothesis, effectively enhancing fragile matching relationships in unseen scenes. Both steps are lightweight and complementary, leading to the construction of a generalized geometry encoding volume with strong generalization capability. Experimental results demonstrate that our GGEV surpasses all existing real-time methods in zero-shot generalization capability, and achieves state-of-the-art performance on the KITTI 2012, KITTI 2015, and ETH3D benchmarks. --- ### Small-Gain Nash: Certified Contraction to Nash Equilibria in Differentiable Games Authors: Vedansh Sharma Published: 2025-12-07 Categories: cs.LG, cs.GT, math.OC arXiv: https://arxiv.org/abs/2512.06791v2 Classical convergence guarantees for gradient-based learning in games require the pseudo-gradient to be (strongly) monotone in Euclidean geometry as shown by rosen(1965), a condition that often fails even in simple games with strong cross-player couplings. We introduce Small-Gain Nash (SGN), a block small-gain condition in a custom block-weighted geometry. SGN converts local curvature and cross-player Lipschitz coupling bounds into a tractable certificate of contraction. It constructs a weighted block metric in which the pseudo-gradient becomes strongly monotone on any region where these bounds hold, even when it is non-monotone in the Euclidean sense. The continuous flow is exponentially contracting in this designed geometry, and projected Euler and RK4 discretizations converge under explicit step-size bounds derived from the SGN margin and a local Lipschitz constant. Our analysis reveals a certified "timescale band", a non-asymptotic, metric-based certificate that plays a TTUR-like role: rather than forcing asymptotic timescale separation via vanishing, unequal step sizes, SGN identifies a finite band of relative metric weights for which a single-step-size dynamics is provably contractive. We validate the framework on quadratic games where Euclidean monotonicity analysis fails to predict convergence, but SGN successfully certifies it, and extend the construction to mirror/Fisher geometries for entropy-regularized policy gradient in Markov games. The result is an offline certification pipeline that estimates curvature, coupling, and Lipschitz parameters on compact regions, optimizes block weights to enlarge the SGN margin, and returns a structural, computable convergence certificate consisting of a metric, contraction rate, and safe step-sizes for non-monotone games. --- ### Small-Gain Nash: Certified Contraction to Nash Equilibria in Differentiable Games Authors: Vedansh Sharma Published: 2025-12-07 Categories: cs.LG, cs.GT, math.OC arXiv: https://arxiv.org/abs/2512.06791v1 Classical convergence guarantees for gradient-based learning in games require the pseudo-gradient to be (strongly) monotone in Euclidean geometry as shown by rosen(1965), a condition that often fails even in simple games with strong cross-player couplings. We introduce Small-Gain Nash (SGN), a block small-gain condition in a custom block-weighted geometry. SGN converts local curvature and cross-player Lipschitz coupling bounds into a tractable certificate of contraction. It constructs a weighted block metric in which the pseudo-gradient becomes strongly monotone on any region where these bounds hold, even when it is non-monotone in the Euclidean sense. The continuous flow is exponentially contracting in this designed geometry, and projected Euler and RK4 discretizations converge under explicit step-size bounds derived from the SGN margin and a local Lipschitz constant. Our analysis reveals a certified ``timescale band'', a non-asymptotic, metric-based certificate that plays a TTUR-like role: rather than forcing asymptotic timescale separation via vanishing, unequal step sizes, SGN identifies a finite band of relative metric weights for which a single-step-size dynamics is provably contractive. We validate the framework on quadratic games where Euclidean monotonicity analysis fails to predict convergence, but SGN successfully certifies it, and extend the construction to mirror/Fisher geometries for entropy-regularized policy gradient in Markov games. The result is an offline certification pipeline that estimates curvature, coupling, and Lipschitz parameters on compact regions, optimizes block weights to enlarge the SGN margin, and returns a structural, computable convergence certificate consisting of a metric, contraction rate, and safe step-sizes for non-monotone games. --- ### LLM4SFC: Sequential Function Chart Generation via Large Language Models Authors: Ofek Glick, Vladimir Tchuiev, Marah Ghoummaid, Michal Moshkovitz, Dotan Di-Castro Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06787v1 While Large Language Models (LLMs) are increasingly used for synthesizing textual PLC programming languages like Structured Text (ST) code, other IEC 61131-3 standard graphical languages like Sequential Function Charts (SFCs) remain underexplored. Generating SFCs is challenging due to graphical nature and ST actions embedded within, which are not directly compatible with standard generation techniques, often leading to non-executable code that is incompatible with industrial tool-chains In this work, we introduce LLM4SFC, the first framework to receive natural-language descriptions of industrial workflows and provide executable SFCs. LLM4SFC is based on three components: (i) A reduced structured representation that captures essential topology and in-line ST and reduced textual verbosity; (ii) Fine-tuning and few-shot retrieval-augmented generation (RAG) for alignment with SFC programming conventions; and (iii) A structured generation approach that prunes illegal tokens in real-time to ensure compliance with the textual format of SFCs. We evaluate LLM4SFC on a dataset of real-world SFCs from automated manufacturing projects, using both open-source and proprietary LLMs. The results show that LLM4SFC reliably generates syntactically valid SFC programs effectively bridging graphical and textual PLC languages, achieving a generation generation success of 75% - 94%, paving the way for automated industrial programming. --- ### Angular Regularization for Positive-Unlabeled Learning on the Hypersphere Authors: Vasileios Sevetlidis, George Pavlidis, Antonios Gasteratos Published: 2025-12-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06785v1 Positive-Unlabeled (PU) learning addresses classification problems where only a subset of positive examples is labeled and the remaining data is unlabeled, making explicit negative supervision unavailable. Existing PU methods often rely on negative-risk estimation or pseudo-labeling, which either require strong distributional assumptions or can collapse in high-dimensional settings. We propose AngularPU, a novel PU framework that operates on the unit hypersphere using cosine similarity and angular margin. In our formulation, the positive class is represented by a learnable prototype vector, and classification reduces to thresholding the cosine similarity between an embedding and this prototype-eliminating the need for explicit negative modeling. To counteract the tendency of unlabeled embeddings to cluster near the positive prototype, we introduce an angular regularizer that encourages dispersion of the unlabeled set over the hypersphere, improving separation. We provide theoretical guarantees on the Bayes-optimality of the angular decision rule, consistency of the learned prototype, and the effect of the regularizer on the unlabeled distribution. Experiments on benchmark datasets demonstrate that AngularPU achieves competitive or superior performance compared to state-of-the-art PU methods, particularly in settings with scarce positives and high-dimensional embeddings, while offering geometric interpretability and scalability. --- ### Physics Informed Human Posture Estimation Based on 3D Landmarks from Monocular RGB-Videos Authors: Tobias Leuthold, Michele Xiloyannis, Yves Zimmermann Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06783v1 Applications providing automated coaching for physical training are increasing in popularity, for example physical therapy. These applications rely on accurate and robust pose estimation using monocular video streams. State-of-the-art models like BlazePose excel in real-time pose tracking, but their lack of anatomical constraints indicates improvement potential by including physical knowledge. We present a real-time post-processing algorithm fusing the strengths of BlazePose 3D and 2D estimations using a weighted optimization, penalizing deviations from expected bone length and biomechanical models. Bone length estimations are refined to the individual anatomy using a Kalman filter with adapting measurement trust. Evaluation using the Physio2.2M dataset shows a 10.2 percent reduction in 3D MPJPE and a 16.6 percent decrease in errors of angles between body segments compared to BlazePose 3D estimation. Our method provides a robust, anatomically consistent pose estimation based on a computationally efficient video-to-3D pose estimation, suitable for automated physiotherapy, healthcare, and sports coaching on consumer-level laptops and mobile devices. The refinement runs on the backend with anonymized data only. --- ### Measuring Over-smoothing beyond Dirichlet energy Authors: Weiqi Guan, Zihao Shi Published: 2025-12-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06782v1 While Dirichlet energy serves as a prevalent metric for quantifying over-smoothing, it is inherently restricted to capturing first-order feature derivatives. To address this limitation, we propose a generalized family of node similarity measures based on the energy of higher-order feature derivatives. Through a rigorous theoretical analysis of the relationships among these measures, we establish the decay rates of Dirichlet energy under both continuous heat diffusion and discrete aggregation operators. Furthermore, our analysis reveals an intrinsic connection between the over-smoothing decay rate and the spectral gap of the graph Laplacian. Finally, empirical results demonstrate that attention-based Graph Neural Networks (GNNs) suffer from over-smoothing when evaluated under these proposed metrics. --- ### From Description to Score: Can LLMs Quantify Vulnerabilities? Authors: Sima Jafarikhah, Daniel Thompson, Eva Deans, Hossein Siadati, Yi Liu Published: 2025-12-07 Categories: cs.CR, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2512.06781v3 Manual vulnerability scoring, such as assigning Common Vulnerability Scoring System (CVSS) scores, is a resource-intensive process that is often influenced by subjective interpretation. This study investigates the potential of general-purpose large language models (LLMs), namely ChatGPT, Llama, Grok, DeepSeek, and Gemini, to automate this process by analyzing over 31{,}000 recent Common Vulnerabilities and Exposures (CVE) entries. The results show that LLMs substantially outperform the baseline on certain metrics (e.g., \textit{Availability Impact}), while offering more modest gains on others (e.g., \textit{Attack Complexity}). Moreover, model performance varies across both LLM families and individual CVSS metrics, with ChatGPT-5 attaining the highest precision. Our analysis reveals that LLMs tend to misclassify many of the same CVEs, and ensemble-based meta-classifiers only marginally improve performance. Further examination shows that CVE descriptions often lack critical context or contain ambiguous phrasing, which contributes to systematic misclassifications. These findings underscore the importance of enhancing vulnerability descriptions and incorporating richer contextual details to support more reliable automated reasoning and alleviate the growing backlog of CVEs awaiting triage. --- ### From Description to Score: Can LLMs Quantify Vulnerabilities? Authors: Sima Jafarikhah, Daniel Thompson, Eva Deans, Hossein Siadati, Yi Liu Published: 2025-12-07 Categories: cs.CR, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2512.06781v1 Manual vulnerability scoring, such as assigning Common Vulnerability Scoring System (CVSS) scores, is a resource-intensive process that is often influenced by subjective interpretation. This study investigates the potential of general-purpose large language models (LLMs), namely ChatGPT, Llama, Grok, DeepSeek, and Gemini, to automate this process by analyzing over 31{,}000 recent Common Vulnerabilities and Exposures (CVE) entries. The results show that LLMs substantially outperform the baseline on certain metrics (e.g., \textit{Availability Impact}), while offering more modest gains on others (e.g., \textit{Attack Complexity}). Moreover, model performance varies across both LLM families and individual CVSS metrics, with ChatGPT-5 attaining the highest precision. Our analysis reveals that LLMs tend to misclassify many of the same CVEs, and ensemble-based meta-classifiers only marginally improve performance. Further examination shows that CVE descriptions often lack critical context or contain ambiguous phrasing, which contributes to systematic misclassifications. These findings underscore the importance of enhancing vulnerability descriptions and incorporating richer contextual details to support more reliable automated reasoning and alleviate the growing backlog of CVEs awaiting triage. --- ### From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs Authors: Yuchuan Tian, Yuchen Liang, Shuo Zhang, Yingte Shu, Guangwen Yang, Wei He, Sibo Fang, Tianyu Guo, Kai Han, Chao Xu, Hanting Chen, Xinghao Chen et al. Published: 2025-12-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.06776v2 Diffusion Language Models (DLMs) enable fast generation, yet training large DLMs from scratch is costly. As a practical shortcut, adapting off-the-shelf Auto-Regressive (AR) model weights into a DLM could quickly equip the DLM with strong long-context generation capabilies. Prior "adaptation" attempts either modify logits or randomly grow attention masks to Full-Sequence diffusion, or simply transplant AR weights into a Block-Diffusion recipe, leaving two key questions unaddressed: where is the final destination of adaptation, and how to adapt better? For manifold benefits, we reframe the whole AR-to-DLM adaptation under the Block-Diffusion paradigm, transitioning from block size 1 to the final Block-Diffusion state. Concretely, the principled pathway of adaptation is designed as follows: we keep a context-causal path where causal attention is kept in the prefix, an efficient parallel adaptation procedure where an AR guidance is maintained, and gradual increment of the generation block size for a smoother transition. Built on these components, the adaptation is proved competitive on various models at different scales. With better adaptation, we propose NBDiff-7B that could inherit the long-context modeling and reasoning capabilities, and achieve state-of-the-art performance among the 7B-class DLMs. Codes: https://github.com/YuchuanTian/NBDiff. --- ### From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs Authors: Yuchuan Tian, Yuchen Liang, Jiacheng Sun, Shuo Zhang, Guangwen Yang, Yingte Shu, Sibo Fang, Tianyu Guo, Kai Han, Chao Xu, Hanting Chen, Xinghao Chen et al. Published: 2025-12-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.06776v1 Large language models (LLMs) excel at generation but dominant autoregressive (AR) decoding is inherently sequential, creating a throughput bottleneck. Diffusion Language Models (DLMs)--especially block-wise variants--enable parallel generation and intra-block bidirectional reasoning, yet training large DLMs from scratch is costly and wastes the knowledge in mature AR checkpoints. Prior "adaptation" attempts either modify logits or randomly grow attention masks to full-sequence diffusion, or simply transplant AR weights into a block-diffusion recipe, leaving a fundamental mismatch between AR causality and block-wise bidirectionality unaddressed. We reframe adaptation as a intra-paradigm path from AR to Block-Diffusion by viewing AR as Block-Diffusion with blocksize=1. Concretely, we design the pathway of adaptation as follows: we use a context-causal attention mask (causal in context, bidirectional only within the active block), an efficient parallel adaptation procedure, an auxiliary AR loss to maximize data utilization and retain pretrained knowledge, and gradual increment of the generation block size. The recipe integrates cleanly with masked block-diffusion and maintains train-inference consistency. Built on these components, NBDiff-7B (Base and Instruct) could inherit the long-context modeling and reasoning capabilities, and achieve state-of-the-art performance among the 7B-class DLMs, delivering strong gains on general-knowledge, math, and code benchmarks over strong baselines. These results demonstrate that principled AR-to-block-diffusion adaptation is an effective and compute-efficient alternative to training DLMs from scratch. Codes: https://github.com/YuchuanTian/NBDiff. --- ### RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing Authors: Longjie Zhao, Ziming Hong, Zhenyang Ren, Runnan Chen, Mingming Gong, Tongliang Liu Published: 2025-12-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06774v2 3D Gaussian Splatting (3DGS) has become a leading representation for high-fidelity 3D assets, yet protecting these assets via digital watermarking remains an open challenge. Existing 3DGS watermarking methods are robust only to classical distortions and fail under diffusion editing, which operates at both the 2D image level and the 3D scene level, covertly erasing embedded watermarks while preserving visual plausibility. We present RDSplat, the first 3DGS watermarking framework designed to withstand both 2D and 3D diffusion editing. Our key observation is that diffusion models act as low-pass filters that preserve low-frequency structures while regenerating high-frequency details. RDSplat exploits this by embedding 100-bit watermarks exclusively into low-frequency Gaussian primitives identified through Frequency-Aware Primitive Selection (FAPS), which combines the Mip score and directional balance score, while freezing all other primitives. Training efficiency is achieved through a surrogate strategy that replaces costly diffusion forward passes with Gaussian blur augmentation. A dedicated decoder, GeoMark, built on ViT-S/16 with spatially periodic secret embedding, jointly resists diffusion editing and the geometric transformations inherent to novel-view rendering. Extensive experiments on four benchmarks under seven 2D diffusion attacks and iterative 3D editing demonstrate strong classical robustness (bit accuracy 0.811) and competitive diffusion robustness (bit accuracy 0.701) at 100-bit capacity, while completing fine-tuning in 3 to 7 minutes on a single RTX 4090 GPU. --- ### RDSplat: Robust Watermarking Against Diffusion Editing for 3D Gaussian Splatting Authors: Longjie Zhao, Ziming Hong, Zhenyang Ren, Runnan Chen, Mingming Gong, Tongliang Liu Published: 2025-12-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06774v1 3D Gaussian Splatting (3DGS) has enabled the creation of digital assets and downstream applications, underscoring the need for robust copyright protection via digital watermarking. However, existing 3DGS watermarking methods remain highly vulnerable to diffusion-based editing, which can easily erase embedded provenance. This challenge highlights the urgent need for 3DGS watermarking techniques that are intrinsically resilient to diffusion-based editing. In this paper, we introduce RDSplat, a Robust watermarking paradigm against Diffusion editing for 3D Gaussian Splatting. RDSplat embeds watermarks into 3DGS components that diffusion-based editing inherently preserve, achieved through (i) proactively targeting low-frequency Gaussians and (ii) adversarial training with a diffusion proxy. Specifically, we introduce a multi-domain framework that operates natively in 3DGS space and embeds watermarks into diffusion-editing-preserved low-frequency Gaussians via coordinated covariance regularization and 2D filtering. In addition, we exploit the low-pass filtering behavior of diffusion-based editing by using Gaussian blur as an efficient training surrogate, enabling adversarial fine-tuning that further enhances watermark robustness against diffusion-based editing. Empirically, comprehensive quantitative and qualitative evaluations on three benchmark datasets demonstrate that RDSplat not only maintains superior robustness under diffusion-based editing, but also preserves watermark invisibility, achieving state-of-the-art performance. --- ### Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding Authors: Hang Yin, Xiaomin He, PeiWen Yuan, Yiwei Li, Jiayi Shi, Wenxiao Fan, Shaoxiong Feng, Kan Li Published: 2025-12-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06769v1 Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that this problem mainly stems from the asymmetric properties between images and text. To enrich the spatial understanding ability of vision-language models, we propose a simple, annotation-free, plug-and-play method named $\text{Stitch and Tell}$ (abbreviated as SiTe), which injects structured spatial supervision into data. It constructs stitched image-text pairs by stitching images along a spatial axis and generating spatially-aware captions or question answer pairs based on the layout of stitched image, without relying on costly advanced models or human involvement. We evaluate SiTe across three architectures including LLaVA-v1.5-7B, LLaVA-Qwen2-1.5B and HALVA-7B, two training datasets, and eight benchmarks. Experiments show that SiTe improves spatial understanding tasks such as $\text{MME}_{\text{Position}}$ (+5.50%) and Spatial-MM (+4.19%), while maintaining or improving performance on general vision-language benchmarks including COCO-QA (+1.02%) and MMBench (+4.76%). Our findings suggest that explicitly injecting spatially-aware structure into training data offers an effective way to mitigate spatial hallucinations and improve spatial understanding, while preserving general vision-language capabilities. --- ### JOCA: Task-Driven Joint Optimisation of Camera Hardware and Adaptive Camera Control Algorithms Authors: Chengyang Yan, Mitch Bryson, Donald G. Dansereau Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06763v1 The quality of captured images strongly influences the performance of downstream perception tasks. Recent works on co-designing camera systems with perception tasks have shown improved task performance. However, most prior approaches focus on optimising fixed camera parameters set at manufacturing, while many parameters, such as exposure settings, require adaptive control at runtime. This paper introduces a method that jointly optimises camera hardware and adaptive camera control algorithms with downstream vision tasks. We present a unified optimisation framework that integrates gradient-based and derivative-free methods, enabling support for both continuous and discrete parameters, non-differentiable image formation processes, and neural network-based adaptive control algorithms. To address non-differentiable effects such as motion blur, we propose DF-Grad, a hybrid optimisation strategy that trains adaptive control networks using signals from a derivative-free optimiser alongside unsupervised task-driven learning. Experiments show that our method outperforms baselines that optimise static and dynamic parameters separately, particularly under challenging conditions such as low light and fast motion. These results demonstrate that jointly optimising hardware parameters and adaptive control algorithms improves perception performance and provides a unified approach to task-driven camera system design. --- ### VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors Authors: Wenbo Lyu, Yingjun Du, Jinglin Zhao, Xianton Zhen, Ling Shao Published: 2025-12-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06759v1 Understanding multi-image, multi-turn scenarios is a critical yet underexplored capability for Large Vision-Language Models (LVLMs). Existing benchmarks predominantly focus on static or horizontal comparisons -- e.g., spotting visual differences or assessing appropriateness -- while relying heavily on language cues. Such settings overlook progressive, context-dependent reasoning and the challenge of visual-to-visual inference. To bridge this gap, we present VisChainBench, a large-scale benchmark designed to rigorously evaluate LVLMs' ability to perform multi-step visual reasoning across sequential, interdependent tasks with minimal language guidance. VisChainBench contains 1,457 tasks spanning over 20,000 images across three diverse domains (e.g., daily scenarios, engineering troubleshooting), structured to mimic real-world decision-making processes. Uniquely, the benchmark is constructed using a multi-agent generation pipeline, ensuring high visual diversity and controlled language bias. All the benchmark data and code for benchmark construction are available for viewing and download via following Link: https://huggingface.co/datasets/eyehole/VisChainBench --- ### Optimal Analysis for Bandit Learning in Matching Markets with Serial Dictatorship Authors: Zilong Wang, Shuai Li Published: 2025-12-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06758v1 The problem of two-sided matching markets is well-studied in computer science and economics, owing to its diverse applications across numerous domains. Since market participants are usually uncertain about their preferences in various online matching platforms, an emerging line of research is dedicated to the online setting where one-side participants (players) learn their unknown preferences through multiple rounds of interactions with the other side (arms). Sankararaman et al. provide an $Ω\left( \frac{N\log(T)}{Δ^2} + \frac{K\log(T)}Δ \right)$ regret lower bound for this problem under serial dictatorship assumption, where $N$ is the number of players, $K (\geq N)$ is the number of arms, $Δ$ is the minimum reward gap across players and arms, and $T$ is the time horizon. Serial dictatorship assumes arms have the same preferences, which is common in reality when one side participants have a unified evaluation standard. Recently, the work of Kong and Li proposes the ET-GS algorithm and achieves an $O\left( \frac{K\log(T)}{Δ^2} \right)$ regret upper bound, which is the best upper bound attained so far. Nonetheless, a gap between the lower and upper bounds, ranging from $N$ to $K$, persists. It remains unclear whether the lower bound or the upper bound needs to be improved. In this paper, we propose a multi-level successive selection algorithm that obtains an $O\left( \frac{N\log(T)}{Δ^2} + \frac{K\log(T)}Δ \right)$ regret bound when the market satisfies serial dictatorship. To the best of our knowledge, we are the first to propose an algorithm that matches the lower bound in the problem of matching markets with bandits. --- ### XM-ALIGN: Unified Cross-Modal Embedding Alignment for Face-Voice Association Authors: Zhihua Fang, Shumei Tao, Junxu Wang, Liang He Published: 2025-12-07 Categories: cs.SD, cs.CV arXiv: https://arxiv.org/abs/2512.06757v1 This paper introduces our solution, XM-ALIGN (Unified Cross-Modal Embedding Alignment Framework), proposed for the FAME challenge at ICASSP 2026. Our framework combines explicit and implicit alignment mechanisms, significantly improving cross-modal verification performance in both "heard" and "unheard" languages. By extracting feature embeddings from both face and voice encoders and jointly optimizing them using a shared classifier, we employ mean squared error (MSE) as the embedding alignment loss to ensure tight alignment between modalities. Additionally, data augmentation strategies are applied during model training to enhance generalization. Experimental results show that our approach demonstrates superior performance on the MAV-Celeb dataset. The code will be released at https://github.com/PunkMale/XM-ALIGN. --- ### Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets Authors: Chang Liu, Vivian Li, Linus Leong, Vladimir Radenkovic, Pietro Liò, Chaitanya K. Joshi Published: 2025-12-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06752v1 Geometric Graph Neural Networks (GNNs) and Transformers have become state-of-the-art for learning from 3D protein structures. However, their reliance on message passing prevents them from capturing the hierarchical interactions that govern protein function, such as global domains and long-range allosteric regulation. In this work, we argue that the network architecture itself should mirror this biological hierarchy. We introduce Geometric Graph U-Nets, a new class of models that learn multi-scale representations by recursively coarsening and refining the protein graph. We prove that this hierarchical design can theoretically more expressive than standard Geometric GNNs. Empirically, on the task of protein fold classification, Geometric U-Nets substantially outperform invariant and equivariant baselines, demonstrating their ability to learn the global structural patterns that define protein folds. Our work provides a principled foundation for designing geometric deep learning architectures that can learn the multi-scale structure of biomolecules. --- ### Becoming Experienced Judges: Selective Test-Time Learning for Evaluators Authors: Seungyeon Jwa, Daechul Ahn, Reokyoung Kim, Dongyeop Kang, Jonghyun Choi Published: 2025-12-07 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.06751v1 Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployment, these evaluators typically (i) treat each case independently, missing the opportunity to accumulate experience, and (ii) rely on a single fixed prompt for all cases, neglecting the need for sample-specific evaluation criteria. We introduce Learning While Evaluating (LWE), a framework that allows evaluators to improve sequentially at inference time without requiring training or validation sets. LWE maintains an evolving meta-prompt that (i) produces sample-specific evaluation instructions and (ii) refines itself through self-generated feedback. Furthermore, we propose Selective LWE, which updates the meta-prompt only on self-inconsistent cases, focusing computation where it matters most. This selective approach retains the benefits of sequential learning while being far more cost-effective. Across two pairwise comparison benchmarks, Selective LWE outperforms strong baselines, empirically demonstrating that evaluators can improve during sequential testing with a simple selective update, learning most from the cases they struggle with. --- ### UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement Authors: Weiqi Li, Xuanyu Zhang, Bin Chen, Jingfen Xie, Yan Wang, Kexin Zhang, Junlin Li, Li Zhang, Jian Zhang, Shijie Zhao Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06750v1 Image quality assessment (IQA) and image restoration are fundamental problems in low-level vision. Although IQA and restoration are closely connected conceptually, most existing work treats them in isolation. Recent advances in unified multimodal understanding-generation models demonstrate promising results and indicate that stronger understanding can improve generative performance. This motivates a single model that unifies IQA and restoration and explicitly studies how IQA can guide restoration, a setting that remains largely underexplored yet highly valuable. In this paper, we propose UARE, to our knowledge the first Unified vision-language model for image quality Assessment, Restoration, and Enhancement. Built on pretrained unified understanding and generation models, we introduce a two-stage training framework. First, a progressive, easy-to-hard schedule expands from single-type distortions to higher-order mixed degradations, enabling UARE to handle multiple degradations. Second, we perform unified fine-tuning of quality understanding and restoration with interleaved text-image data, aligning IQA signals with restoration objectives. Through multi-task co-training, UARE leverages IQA to boost restoration and enhancement performance. Extensive experiments across IQA, restoration, and enhancement tasks demonstrate the effectiveness of UARE. The code and models will be available at https://github.com/lwq20020127/UARE. --- ### DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems Authors: Ming Ma, Jue Zhang, Fangkai Yang, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang Published: 2025-12-07 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2512.06749v3 Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing errors to a specific agent and step. However, this paradigm has two key limitations: (i) log-only debugging lacks validation, producing untested hypotheses, and (ii) single-step or single-agent attribution is often ill-posed, as we find that multiple distinct interventions can independently repair the failed task. To address the first limitation, we introduce DoVer, an intervention-driven debugging framework, which augments hypothesis generation with active verification through targeted interventions (e.g., editing messages, altering plans). For the second limitation, rather than evaluating on attribution accuracy, we focus on measuring whether the system resolves the failure or makes quantifiable progress toward task success, reflecting a more outcome-oriented view of debugging. Within the Magnetic-One agent framework, on the datasets derived from GAIA and AssistantBench, DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses. DoVer also performs effectively on a different dataset (GSMPlus) and agent framework (AG2), where it recovers 49% of failed trials. These results highlight intervention as a practical mechanism for improving reliability in agentic systems and open opportunities for more robust, scalable debugging methods for LLM-based multi-agent systems. Project website and code will be available at https://aka.ms/DoVer. --- ### DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems Authors: Ming Ma, Jue Zhang, Fangkai Yang, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang Published: 2025-12-07 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2512.06749v1 Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing errors to a specific agent and step. However, this paradigm has two key limitations: (i) log-only debugging lacks validation, producing untested hypotheses, and (ii) single-step or single-agent attribution is often ill-posed, as we find that multiple distinct interventions can independently repair the failed task. To address the first limitation, we introduce DoVer, an intervention-driven debugging framework, which augments hypothesis generation with active verification through targeted interventions (e.g., editing messages, altering plans). For the second limitation, rather than evaluating on attribution accuracy, we focus on measuring whether the system resolves the failure or makes quantifiable progress toward task success, reflecting a more outcome-oriented view of debugging. Within the Magnetic-One agent framework, on the datasets derived from GAIA and AssistantBench, DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses. DoVer also performs effectively on a different dataset (GSMPlus) and agent framework (AG2), where it recovers 49% of failed trials. These results highlight intervention as a practical mechanism for improving reliability in agentic systems and open opportunities for more robust, scalable debugging methods for LLM-based multi-agent systems. Project website and code will be available at https://aka.ms/DoVer. --- ### PrivLLMSwarm: Privacy-Preserving LLM-Driven UAV Swarms for Secure IoT Surveillance Authors: Jifar Wakuma Ayana, Huang Qiming Published: 2025-12-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.06747v1 Large Language Models (LLMs) are emerging as powerful enablers for autonomous reasoning and natural-language coordination in unmanned aerial vehicle (UAV) swarms operating within Internet of Things (IoT) environments. However, existing LLM-driven UAV systems process sensitive operational data in plaintext, exposing them to privacy and security risks. This work introduces PrivLLMSwarm, a privacy-preserving framework that performs secure LLM inference for UAV swarm coordination through Secure Multi-Party Computation (MPC). The framework incorporates MPC-optimized transformer components with efficient approximations of nonlinear activations, enabling practical encrypted inference on resource-constrained aerial platforms. A fine-tuned GPT-based command generator, enhanced through reinforcement learning in simulation, provides reliable instructions while maintaining confidentiality. Experimental evaluation in urban-scale simulations demonstrates that PrivLLMSwarm achieves high semantic accuracy, low encrypted inference latency, and robust formation control under privacy constraints. Comparative analysis shows PrivLLMSwarm offers a superior privacy-utility balance compared to differential privacy, federated learning, and plaintext baselines. To support reproducibility, the full implementation including source code, MPC components, and a synthetic dataset is publicly available. PrivLLMSwarm establishes a practical foundation for secure, LLM-enabled UAV swarms in privacy-sensitive IoT applications including smart-city monitoring and emergency response. --- ### AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model Alignment Authors: Ruoxin Chen, Jiahui Gao, Kaiqing Lin, Keyue Zhang, Yandan Zhao, Isabel Guan, Taiping Yao, Shouhong Ding Published: 2025-12-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06746v2 Vision Language Models (VLMs) are increasingly used for detecting AI-generated images (AIGI). However, converting VLMs into reliable detectors is resource-intensive, and the resulting models often suffer from hallucination and poor generalization. To investigate the root cause, we conduct an empirical analysis and identify two consistent behaviors. First, fine-tuning VLMs with semantic supervision improves semantic discrimination and generalizes well to unseen data. Second, fine-tuning VLMs with pixel-artifact supervision leads to weak generalization. These findings reveal a fundamental task-model misalignment. VLMs are optimized for high-level semantic reasoning and lack inductive bias toward low-level pixel artifacts. In contrast, conventional vision models effectively capture pixel-level artifacts but are less sensitive to semantic inconsistencies. This indicates that different models are naturally suited to different subtasks. Based on this insight, we formulate AIGI detection as two orthogonal subtasks: semantic consistency checking and pixel-artifact detection. Neglecting either subtask leads to systematic detection failures. We further propose the Task-Model Alignment principle and instantiate it in a two-branch detector, AlignGemini. The detector combines a VLM trained with pure semantic supervision and a vision model trained with pure pixel-artifact supervision. By enforcing clear specialization, each branch captures complementary cues. Experiments on in-the-wild benchmarks show that AlignGemini improves average accuracy by 9.5 percent using simplified training data. These results demonstrate that task-model alignment is an effective principle for generalizable AIGI detection. --- ### Task-Model Alignment: A Simple Path to Generalizable AI-Generated Image Detection Authors: Ruoxin Chen, Jiahui Gao, Kaiqing Lin, Keyue Zhang, Yandan Zhao, Isabel Guan, Taiping Yao, Shouhong Ding Published: 2025-12-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06746v1 Vision Language Models (VLMs) are increasingly adopted for AI-generated images (AIGI) detection, yet converting VLMs into detectors requires substantial resource, while the resulting models still exhibit severe hallucinations. To probe the core issue, we conduct an empirical analysis and observe two characteristic behaviors: (i) fine-tuning VLMs on high-level semantic supervision strengthens semantic discrimination and well generalize to unseen data; (ii) fine-tuning VLMs on low-level pixel-artifact supervision yields poor transfer. We attribute VLMs' underperformance to task-model misalignment: semantics-oriented VLMs inherently lack sensitivity to fine-grained pixel artifacts, and semantically non-discriminative pixel artifacts thus exceeds their inductive biases. In contrast, we observe that conventional pixel-artifact detectors capture low-level pixel artifacts yet exhibit limited semantic awareness relative to VLMs, highlighting that distinct models are better matched to distinct tasks. In this paper, we formalize AIGI detection as two complementary tasks--semantic consistency checking and pixel-artifact detection--and show that neglecting either induces systematic blind spots. Guided by this view, we introduce the Task-Model Alignment principle and instantiate it as a two-branch detector, AlignGemini, comprising a VLM fine-tuned exclusively with pure semantic supervision and a pixel-artifact expert trained exclusively with pure pixel-artifact supervision. By enforcing orthogonal supervision on two simplified datasets, each branch trains to its strengths, producing complementary discrimination over semantic and pixel cues. On five in-the-wild benchmarks, AlignGemini delivers a +9.5 gain in average accuracy, supporting task-model alignment as an effective path to generalizable AIGI detection. --- ### One Word Is Not Enough: Simple Prompts Improve Word Embeddings Authors: Rajeev Ranjan Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06744v1 Text embedding models are designed for sentence-level applications like retrieval and semantic similarity, and are primarily evaluated on sentence-level benchmarks. Their behavior on isolated words is less understood. We show that simply prepending semantic prompts to words before embedding substantially improves word similarity correlations. Testing 7 text embedding models, including text-embedding-3-large (OpenAI), embed-english-v3.0 (Cohere), voyage-3(Voyage AI), all-mpnet-base-v2, and Qwen3-Embedding-8B, on 3 standard benchmarks (SimLex-999, WordSim-353, MEN-3000), we find that prompts like "meaning: {word}" or "Represent the semantic concept: {word}" improve Spearman correlations by up to +0.29 on SimLex-999. Some models fail completely on bare words (correlation = 0) but recover with prompts (+0.73 improvement). Our best results achieve correlation = 0.692 on SimLex-999 with embed-english-v3.0 (Cohere), correlation = 0.811 on WordSim-353, and correlation = 0.855 on MEN-3000 with text-embedding-3-large (OpenAI). These results outperform classic static embeddings like Word2Vec (correlation = 0.40) and even the best static method LexVec (correlation = 0.48) on SimLex-999, establishing a new state-of-the-art for pure embedding methods. This zero-shot technique requires no training and works with any text embedding model. --- ### FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation Authors: M Yashwanth, Sampath Koti, Arunabh Singh, Shyam Marjit, Anirban Chakraborty Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06738v1 We address the Federated source-Free Domain Adaptation (FFreeDA) problem, with clients holding unlabeled data with significant inter-client domain gaps. The FFreeDA setup constrains the FL frameworks to employ only a pre-trained server model as the setup restricts access to the source dataset during the training rounds. Often, this source domain dataset has a distinct distribution to the clients' domains. To address the challenges posed by the FFreeDA setup, adaptation of the Source-Free Domain Adaptation (SFDA) methods to FL struggles with client-drift in real-world scenarios due to extreme data heterogeneity caused by the aforementioned domain gaps, resulting in unreliable pseudo-labels. In this paper, we introduce FedSCAl, an FL framework leveraging our proposed Server-Client Alignment (SCAl) mechanism to regularize client updates by aligning the clients' and server model's predictions. We observe an improvement in the clients' pseudo-labeling accuracy post alignment, as the SCAl mechanism helps to mitigate the client-drift. Further, we present extensive experiments on benchmark vision datasets showcasing how FedSCAl consistently outperforms state-of-the-art FL methods in the FFreeDA setup for classification tasks. --- ### Arc Gradient Descent: A Geometrically Motivated Gradient Descent-based Optimiser with Phase-Aware, User-Controlled Step Dynamics (proof-of-concept) Authors: Nikhil Verma, Joonas Linnosmaa, Leonardo Espinosa-Leal, Napat Vajragupta Published: 2025-12-07 Categories: cs.LG, cs.AI, cs.CL, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2512.06737v3 The paper presents the formulation, implementation, and evaluation of the ArcGD optimiser. The evaluation is conducted initially on a non-convex benchmark function and subsequently on a real-world ML dataset. The initial comparative study using the Adam optimiser is conducted on a stochastic variant of the highly non-convex and notoriously challenging Rosenbrock function, renowned for its narrow, curved valley, across dimensions ranging from 2D to 1000D and an extreme case of 50,000D. Two configurations were evaluated to eliminate learning-rate bias: (i) both using ArcGD's effective learning rate and (ii) both using Adam's default learning rate. ArcGD consistently outperformed Adam under the first setting and, although slower under the second, achieved superior final solutions in most cases. In the second evaluation, ArcGD is evaluated against state-of-the-art optimizers (Adam, AdamW, Lion, SGD) on the CIFAR-10 image classification dataset across 8 diverse MLP architectures ranging from 1 to 5 hidden layers. ArcGD achieved the highest average test accuracy (50.7%) at 20,000 iterations, outperforming AdamW (46.6%), Adam (46.8%), SGD (49.6%), and Lion (43.4%), winning or tying on 6 of 8 architectures. Notably, while Adam and AdamW showed strong early convergence at 5,000 iterations, but regressed with extended training, whereas ArcGD continued improving, demonstrating generalization and resistance to overfitting without requiring early stopping tuning. Strong performance on geometric stress tests and standard deep-learning benchmarks indicates broad applicability, highlighting the need for further exploration. Moreover, it is also shown that both a limiting variant of ArcGD and a momentum augmented ArcGD, recover sign-based momentum updates, revealing a clear conceptual link between ArcGD's phase structure and the core mechanism of the Lion Optimiser. --- ### Arc Gradient Descent: A Mathematically Derived Reformulation of Gradient Descent with Phase-Aware, User-Controlled Step Dynamics Authors: Nikhil Verma, Joonas Linnosmaa, Espinosa-Leal Leonardo, Napat Vajragupta Published: 2025-12-07 Categories: cs.LG, cs.AI, cs.CL, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2512.06737v1 The paper presents the formulation, implementation, and evaluation of the ArcGD optimiser. The evaluation is conducted initially on a non-convex benchmark function and subsequently on a real-world ML dataset. The initial comparative study using the Adam optimiser is conducted on a stochastic variant of the highly non-convex and notoriously challenging Rosenbrock function, renowned for its narrow, curved valley, across dimensions ranging from 2D to 1000D and an extreme case of 50,000D. Two configurations were evaluated to eliminate learning-rate bias: (i) both using ArcGD's effective learning rate and (ii) both using Adam's default learning rate. ArcGD consistently outperformed Adam under the first setting and, although slower under the second, achieved super ior final solutions in most cases. In the second evaluation, ArcGD is evaluated against state-of-the-art optimizers (Adam, AdamW, Lion, SGD) on the CIFAR-10 image classification dataset across 8 diverse MLP architectures ranging from 1 to 5 hidden layers. ArcGD achieved the highest average test accuracy (50.7%) at 20,000 iterations, outperforming AdamW (46.6%), Adam (46.8%), SGD (49.6%), and Lion (43.4%), winning or tying on 6 of 8 architectures. Notably, while Adam and AdamW showed strong early convergence at 5,000 iterations, but regressed with extended training, whereas ArcGD continued improving, demonstrating generalization and resistance to overfitting without requiring early stopping tuning. Strong performance on geometric stress tests and standard deep-learning benchmarks indicates broad applicability, highlighting the need for further exploration. Moreover, it is also shown that a variant of ArcGD can be interpreted as a special case of the Lion optimiser, highlighting connections between the inherent mechanisms of such optimisation methods. --- ### Graph Convolutional Long Short-Term Memory Attention Network for Post-Stroke Compensatory Movement Detection Based on Skeleton Data Authors: Jiaxing Fan, Jiaojiao Liu, Wenkong Wang, Yang Zhang, Xin Ma, Jichen Zhang Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06736v1 Most stroke patients experience upper limb motor dysfunction. Compensatory movements are prevalent during rehabilitation training, which is detrimental to patients' long-term recovery. Therefore, detecting compensatory movements is of great significance. In this study, a Graph Convolutional Long Short-Term Memory Attention Network (GCN-LSTM-ATT) based on skeleton data is proposed for the detection of compensatory movements after stroke. Sixteen stroke patients were selected in the research. The skeleton data of the patients performing specific rehabilitation movements were collected using the Kinect depth camera. After data processing, detection models were constructed respectively using the GCN-LSTM-ATT model, the Support Vector Machine(SVM), the K-Nearest Neighbor algorithm(KNN), and the Random Forest(RF). The results show that the detection accuracy of the GCN-LSTM-ATT model reaches 0.8580, which is significantly higher than that of traditional machine learning algorithms. Ablation experiments indicate that each component of the model contributes significantly to the performance improvement. These findings provide a more precise and powerful tool for the detection of compensatory movements after stroke, and are expected to facilitate the optimization of rehabilitation training strategies for stroke patients. --- ### A Patient-Doctor-NLP-System to contest inequality for less privileged Authors: Subrit Dikshit, Ritu Tiwari, Priyank Jain Published: 2025-12-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.06734v1 Transfer Learning (TL) has accelerated the rapid development and availability of large language models (LLMs) for mainstream natural language processing (NLP) use cases. However, training and deploying such gigantic LLMs in resource-constrained, real-world healthcare situations remains challenging. This study addresses the limited support available to visually impaired users and speakers of low-resource languages such as Hindi who require medical assistance in rural environments. We propose PDFTEMRA (Performant Distilled Frequency Transformer Ensemble Model with Random Activations), a compact transformer-based architecture that integrates model distillation, frequency-domain modulation, ensemble learning, and randomized activation patterns to reduce computational cost while preserving language understanding performance. The model is trained and evaluated on medical question-answering and consultation datasets tailored to Hindi and accessibility scenarios, and its performance is compared against standard NLP state-of-the-art model baselines. Results demonstrate that PDFTEMRA achieves comparable performance with substantially lower computational requirements, indicating its suitability for accessible, inclusive, low-resource medical NLP applications. --- ### "The Dentist is an involved parent, the bartender is not": Revealing Implicit Biases in QA with Implicit BBQ Authors: Aarushi Wagh, Saniya Srivastava Published: 2025-12-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.06732v1 Existing benchmarks evaluating biases in large language models (LLMs) primarily rely on explicit cues, declaring protected attributes like religion, race, gender by name. However, real-world interactions often contain implicit biases, inferred subtly through names, cultural cues, or traits. This critical oversight creates a significant blind spot in fairness evaluation. We introduce ImplicitBBQ, a benchmark extending the Bias Benchmark for QA (BBQ) with implicitly cued protected attributes across 6 categories. Our evaluation of GPT-4o on ImplicitBBQ illustrates troubling performance disparity from explicit BBQ prompts, with accuracy declining up to 7% in the "sexual orientation" subcategory and consistent decline located across most other categories. This indicates that current LLMs contain implicit biases undetected by explicit benchmarks. ImplicitBBQ offers a crucial tool for nuanced fairness evaluation in NLP. ---