# Research Papers — 2025-12 · bundle page 111 of 175 > Full-text markdown of papers #5501–5550 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/111 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/110.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/112.md) ### Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning Authors: Xinyu Liu, Hangjie Yuan, Yujie Wei, Jiazheng Xing, Yujin Han, Jiahao Pan, Yanbiao Ma, Chi-Min Chan, Kang Zhao, Shiwei Zhang, Wenhan Luo, Yike Guo Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09924v3 Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two factors: (1) existing datasets are inadequate for training and evaluating reasoning-aware video editing, and (2) an inherent disconnect between the models' reasoning and editing capabilities, which prevents understanding from guiding the editing process. To address this, we introduce the Reason-Informed Video Editing (RVE) task, which requires reasoning about physical plausibility and causal dynamics during editing. To support systematic evaluation, we construct RVE-Bench, a comprehensive benchmark with two complementary subsets: Reasoning-Aware Video Editing (RAVE) and In-Context Video-to-Video Generation (ICVG), spanning diverse reasoning dimensions across both editing and generation scenarios. Building upon this foundation, we propose ReViSE, a self-reflective learning framework that harnesses the model's internal VLM to evaluate and refine its own generation during training. Unlike prior reward-based approaches that rely on external critics, ReViSE leverages the model's internal VLM as a self-reflective evaluator, providing differentiable feedback that directly refines the generator's reasoning behavior during training. Extensive experiments on RVE-Bench demonstrate that ReViSE enhances editing accuracy and visual fidelity, outperforming the finetuned counterpart by 10% in Overall score on the RAVE subset, demonstrating the effectiveness of self-reflective differentiable reward. --- ### ReViSE: Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning Authors: Xinyu Liu, Hangjie Yuan, Yujie Wei, Jiazheng Xing, Yujin Han, Jiahao Pan, Yanbiao Ma, Chi-Min Chan, Kang Zhao, Shiwei Zhang, Wenhan Luo, Yike Guo Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09924v1 Video unified models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two factors: 1) existing datasets are inadequate for training and evaluating reasoning-aware video editing, and 2) an inherent disconnect between the models' reasoning and editing capabilities, which prevents the rich understanding from effectively instructing the editing process. Bridging this gap requires an integrated framework that connects reasoning with visual transformation. To address this gap, we introduce the Reason-Informed Video Editing (RVE) task, which requires reasoning about physical plausibility and causal dynamics during editing. To support systematic evaluation, we construct RVE-Bench, a comprehensive benchmark with two complementary subsets: Reasoning-Informed Video Editing and In-Context Video Generation. These subsets cover diverse reasoning dimensions and real-world editing scenarios. Building upon this foundation, we propose the ReViSE, a Self-Reflective Reasoning (SRF) framework that unifies generation and evaluation within a single architecture. The model's internal VLM provides intrinsic feedback by assessing whether the edited video logically satisfies the given instruction. The differential feedback that refines the generator's reasoning behavior during training. Extensive experiments on RVE-Bench demonstrate that ReViSE significantly enhances editing accuracy and visual fidelity, achieving a 32% improvement of the Overall score in the reasoning-informed video editing subset over state-of-the-art methods. --- ### Splatent: Splatting Diffusion Latents for Novel View Synthesis Authors: Or Hirschorn, Omer Sela, Inbar Huberman-Spiegelglas, Netalee Efrat, Eli Alshan, Ianir Ideses, Frederic Devernay, Yochai Zvik, Lior Fritz Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09923v2 Radiance field representations have recently been explored in the latent space of VAEs that are commonly used by diffusion models. This direction offers efficient rendering and seamless integration with diffusion-based pipelines. However, these methods face a fundamental limitation: The VAE latent space lacks multi-view consistency, leading to blurred textures and missing details during 3D reconstruction. Existing approaches attempt to address this by fine-tuning the VAE, at the cost of reconstruction quality, or by relying on pre-trained diffusion models to recover fine-grained details, at the risk of some hallucinations. We present Splatent, a diffusion-based enhancement framework designed to operate on top of 3D Gaussian Splatting (3DGS) in the latent space of VAEs. Our key insight departs from the conventional 3D-centric view: rather than reconstructing fine-grained details in 3D space, we recover them in 2D from input views through multi-view attention mechanisms. This approach preserves the reconstruction quality of pretrained VAEs while achieving faithful detail recovery. Evaluated across multiple benchmarks, Splatent establishes a new state-of-the-art for VAE latent radiance field reconstruction. We further demonstrate that integrating our method with existing feed-forward frameworks, consistently improves detail preservation, opening new possibilities for high-quality sparse-view 3D reconstruction. Code is available on our project page: https://orhir.github.io/Splatent/ --- ### Splatent: Splatting Diffusion Latents for Novel View Synthesis Authors: Or Hirschorn, Omer Sela, Inbar Huberman-Spiegelglas, Netalee Efrat, Eli Alshan, Ianir Ideses, Frederic Devernay, Yochai Zvik, Lior Fritz Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09923v1 Radiance field representations have recently been explored in the latent space of VAEs that are commonly used by diffusion models. This direction offers efficient rendering and seamless integration with diffusion-based pipelines. However, these methods face a fundamental limitation: The VAE latent space lacks multi-view consistency, leading to blurred textures and missing details during 3D reconstruction. Existing approaches attempt to address this by fine-tuning the VAE, at the cost of reconstruction quality, or by relying on pre-trained diffusion models to recover fine-grained details, at the risk of some hallucinations. We present Splatent, a diffusion-based enhancement framework designed to operate on top of 3D Gaussian Splatting (3DGS) in the latent space of VAEs. Our key insight departs from the conventional 3D-centric view: rather than reconstructing fine-grained details in 3D space, we recover them in 2D from input views through multi-view attention mechanisms. This approach preserves the reconstruction quality of pretrained VAEs while achieving faithful detail recovery. Evaluated across multiple benchmarks, Splatent establishes a new state-of-the-art for VAE latent radiance field reconstruction. We further demonstrate that integrating our method with existing feed-forward frameworks, consistently improves detail preservation, opening new possibilities for high-quality sparse-view 3D reconstruction. --- ### LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating Authors: Junting Chen, Yunchuan Li, Panfeng Jiang, Jiacheng Du, Zixuan Chen, Chenrui Tie, Jiajun Deng, Lin Shao Published: 2025-12-10 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.09920v1 Towards human-robot coexistence, socially aware navigation is significant for mobile robots. Yet existing studies on this area focus mainly on path efficiency and pedestrian collision avoidance, which are essential but represent only a fraction of social navigation. Beyond these basics, robots must also comply with user instructions, aligning their actions to task goals and social norms expressed by humans. In this work, we present LISN-Bench, the first simulation-based benchmark for language-instructed social navigation. Built on Rosnav-Arena 3.0, it is the first standardized social navigation benchmark to incorporate instruction following and scene understanding across diverse contexts. To address this task, we further propose Social-Nav-Modulator, a fast-slow hierarchical system where a VLM agent modulates costmaps and controller parameters. Decoupling low-level action generation from the slower VLM loop reduces reliance on high-frequency VLM inference while improving dynamic avoidance and perception adaptability. Our method achieves an average success rate of 91.3%, which is greater than 63% than the most competitive baseline, with most of the improvements observed in challenging tasks such as following a person in a crowd and navigating while strictly avoiding instruction-forbidden regions. The project website is at: https://social-nav.github.io/LISN-project/ --- ### FALCON: Few-step Accurate Likelihoods for Continuous Flows Authors: Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alexander Tong Published: 2025-12-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.09914v1 Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann Generators tackle this problem by pairing a generative model, capable of exact likelihood computation, with importance sampling to obtain consistent samples under the target distribution. Current Boltzmann Generators primarily use continuous normalizing flows (CNFs) trained with flow matching for efficient training of powerful models. However, likelihood calculation for these models is extremely costly, requiring thousands of function evaluations per sample, severely limiting their adoption. In this work, we propose Few-step Accurate Likelihoods for Continuous Flows (FALCON), a method which allows for few-step sampling with a likelihood accurate enough for importance sampling applications by introducing a hybrid training objective that encourages invertibility. We show FALCON outperforms state-of-the-art normalizing flow models for molecular Boltzmann sampling and is two orders of magnitude faster than the equivalently performing CNF model. --- ### NordFKB: a fine-grained benchmark dataset for geospatial AI in Norway Authors: Sander Riisøen Jyhne, Aditya Gupta, Ben Worsley, Marianne Andersen, Ivar Oveland, Alexander Salveson Nossum Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09913v1 We present NordFKB, a fine-grained benchmark dataset for geospatial AI in Norway, derived from the authoritative, highly accurate, national Felles KartdataBase (FKB). The dataset contains high-resolution orthophotos paired with detailed annotations for 36 semantic classes, including both per-class binary segmentation masks in GeoTIFF format and COCO-style bounding box annotations. Data is collected from seven geographically diverse areas, ensuring variation in climate, topography, and urbanization. Only tiles containing at least one annotated object are included, and training/validation splits are created through random sampling across areas to ensure representative class and context distributions. Human expert review and quality control ensures high annotation accuracy. Alongside the dataset, we release a benchmarking repository with standardized evaluation protocols and tools for semantic segmentation and object detection, enabling reproducible and comparable research. NordFKB provides a robust foundation for advancing AI methods in mapping, land administration, and spatial planning, and paves the way for future expansions in coverage, temporal scope, and data modalities. --- ### Supervised learning pays attention Authors: Erin Craig, Robert Tibshirani Published: 2025-12-10 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.09912v1 In-context learning with attention enables large neural networks to make context-specific predictions by selectively focusing on relevant examples. Here, we adapt this idea to supervised learning procedures such as lasso regression and gradient boosting, for tabular data. Our goals are to (1) flexibly fit personalized models for each prediction point and (2) retain model simplicity and interpretability. Our method fits a local model for each test observation by weighting the training data according to attention, a supervised similarity measure that emphasizes features and interactions that are predictive of the outcome. Attention weighting allows the method to adapt to heterogeneous data in a data-driven way, without requiring cluster or similarity pre-specification. Further, our approach is uniquely interpretable: for each test observation, we identify which features are most predictive and which training observations are most relevant. We then show how to use attention weighting for time series and spatial data, and we present a method for adapting pretrained tree-based models to distributional shift using attention-weighted residual corrections. Across real and simulated datasets, attention weighting improves predictive performance while preserving interpretability, and theory shows that attention-weighting linear models attain lower mean squared error than the standard linear model under mixture-of-models data-generating processes with known subgroup structure. --- ### Efficient Continual Learning in Neural Machine Translation: A Low-Rank Adaptation Approach Authors: Salvador Carrión, Francisco Casacuberta Published: 2025-12-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.09910v1 Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining. This study establishes Low-Rank Adaptation (LoRA) as a parameter-efficient framework to address these challenges in dedicated NMT architectures. We first demonstrate that LoRA-based fine-tuning adapts NMT models to new languages and domains with performance on par with full-parameter techniques, while utilizing only a fraction of the parameter space. Second, we propose an interactive adaptation method using a calibrated linear combination of LoRA modules. This approach functions as a gate-free mixture of experts, enabling real-time, user-controllable adjustments to domain and style without retraining. Finally, to mitigate catastrophic forgetting, we introduce a novel gradient-based regularization strategy specifically designed for low-rank decomposition matrices. Unlike methods that regularize the full parameter set, our approach weights the penalty on the low-rank updates using historical gradient information. Experimental results indicate that this strategy efficiently preserves prior domain knowledge while facilitating the acquisition of new tasks, offering a scalable paradigm for interactive and continual NMT. --- ### STACHE: Local Black-Box Explanations for Reinforcement Learning Policies Authors: Andrew Elashkin, Orna Grumberg Published: 2025-12-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.09909v1 Reinforcement learning agents often behave unexpectedly in sparse-reward or safety-critical environments, creating a strong need for reliable debugging and verification tools. In this paper, we propose STACHE, a comprehensive framework for generating local, black-box explanations for an agent's specific action within discrete Markov games. Our method produces a Composite Explanation consisting of two complementary components: (1) a Robustness Region, the connected neighborhood of states where the agent's action remains invariant, and (2) Minimal Counterfactuals, the smallest state perturbations required to alter that decision. By exploiting the structure of factored state spaces, we introduce an exact, search-based algorithm that circumvents the fidelity gaps of surrogate models. Empirical validation on Gymnasium environments demonstrates that our framework not only explains policy actions, but also effectively captures the evolution of policy logic during training - from erratic, unstable behavior to optimized, robust strategies - providing actionable insights into agent sensitivity and decision boundaries. --- ### Bayesian Networks, Markov Networks, Moralisation, Triangulation: a Categorical Perspective Authors: Antonio Lorenzin, Fabio Zanasi Published: 2025-12-10 Categories: cs.AI, cs.LO, math.CT arXiv: https://arxiv.org/abs/2512.09908v1 Moralisation and Triangulation are transformations allowing to switch between different ways of factoring a probability distribution into a graphical model. Moralisation allows to view a Bayesian network (a directed model) as a Markov network (an undirected model), whereas triangulation addresses the opposite direction. We present a categorical framework where these transformations are modelled as functors between a category of Bayesian networks and one of Markov networks. The two kinds of network (the objects of these categories) are themselves represented as functors from a `syntax' domain to a `semantics' codomain. Notably, moralisation and triangulation can be defined inductively on such syntax via functor pre-composition. Moreover, while moralisation is fully syntactic, triangulation relies on semantics. This leads to a discussion of the variable elimination algorithm, reinterpreted here as a functor in its own right, that splits the triangulation procedure in two: one purely syntactic, the other purely semantic. This approach introduces a functorial perspective into the theory of probabilistic graphical models, which highlights the distinctions between syntactic and semantic modifications. --- ### VisualActBench: Can VLMs See and Act like a Human? Authors: Daoan Zhang, Pai Liu, Xiaofei Zhou, Yuan Ge, Guangchen Lan, Jing Bi, Christopher Brinton, Ehsan Hoque, Jiebo Luo Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09907v2 Vision-Language Models (VLMs) have achieved impressive progress in perceiving and describing visual environments. However, their ability to proactively reason and act based solely on visual inputs, without explicit textual prompts, remains underexplored. We introduce a new task, Visual Action Reasoning, and propose VisualActBench, a large-scale benchmark comprising 1,074 videos and 3,733 human-annotated actions across four real-world scenarios. Each action is labeled with an Action Prioritization Level (APL) and a proactive-reactive type to assess models' human-aligned reasoning and value sensitivity. We evaluate 29 VLMs on VisualActBench and find that while frontier models like GPT4o demonstrate relatively strong performance, a significant gap remains compared to human-level reasoning, particularly in generating proactive, high-priority actions. Our results highlight limitations in current VLMs' ability to interpret complex context, anticipate outcomes, and align with human decision-making frameworks. VisualActBench establishes a comprehensive foundation for assessing and improving the real-world readiness of proactive, vision-centric AI agents. --- ### VisualActBench: Can VLMs See and Act like a Human? Authors: Daoan Zhang, Pai Liu, Xiaofei Zhou, Yuan Ge, Guangchen Lan, Jing Bi, Christopher Brinton, Ehsan Hoque, Jiebo Luo Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09907v1 Vision-Language Models (VLMs) have achieved impressive progress in perceiving and describing visual environments. However, their ability to proactively reason and act based solely on visual inputs, without explicit textual prompts, remains underexplored. We introduce a new task, Visual Action Reasoning, and propose VisualActBench, a large-scale benchmark comprising 1,074 videos and 3,733 human-annotated actions across four real-world scenarios. Each action is labeled with an Action Prioritization Level (APL) and a proactive-reactive type to assess models' human-aligned reasoning and value sensitivity. We evaluate 29 VLMs on VisualActBench and find that while frontier models like GPT4o demonstrate relatively strong performance, a significant gap remains compared to human-level reasoning, particularly in generating proactive, high-priority actions. Our results highlight limitations in current VLMs' ability to interpret complex context, anticipate outcomes, and align with human decision-making frameworks. VisualActBench establishes a comprehensive foundation for assessing and improving the real-world readiness of proactive, vision-centric AI agents. --- ### YOPO-Nav: Visual Navigation using 3DGS Graphs from One-Pass Videos Authors: Ryan Meegan, Adam D'Souza, Bryan Bo Cao, Shubham Jain, Kristin Dana Published: 2025-12-10 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.09903v1 Visual navigation has emerged as a practical alternative to traditional robotic navigation pipelines that rely on detailed mapping and path planning. However, constructing and maintaining 3D maps is often computationally expensive and memory-intensive. We address the problem of visual navigation when exploration videos of a large environment are available. The videos serve as a visual reference, allowing a robot to retrace the explored trajectories without relying on metric maps. Our proposed method, YOPO-Nav (You Only Pass Once), encodes an environment into a compact spatial representation composed of interconnected local 3D Gaussian Splatting (3DGS) models. During navigation, the framework aligns the robot's current visual observation with this representation and predicts actions that guide it back toward the demonstrated trajectory. YOPO-Nav employs a hierarchical design: a visual place recognition (VPR) module provides coarse localization, while the local 3DGS models refine the goal and intermediate poses to generate control actions. To evaluate our approach, we introduce the YOPO-Campus dataset, comprising 4 hours of egocentric video and robot controller inputs from over 6 km of human-teleoperated robot trajectories. We benchmark recent visual navigation methods on trajectories from YOPO-Campus using a Clearpath Jackal robot. Experimental results show YOPO-Nav provides excellent performance in image-goal navigation for real-world scenes on a physical robot. The dataset and code will be made publicly available for visual navigation and scene representation research. --- ### Visual Heading Prediction for Autonomous Aerial Vehicles Authors: Reza Ahmari, Ahmad Mohammadi, Vahid Hemmati, Mohammed Mynuddin, Parham Kebria, Mahmoud Nabil Mahmoud, Xiaohong Yuan, Abdollah Homaifar Published: 2025-12-10 Categories: cs.RO, cs.AI, cs.CV, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2512.09898v1 The integration of Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) is increasingly central to the development of intelligent autonomous systems for applications such as search and rescue, environmental monitoring, and logistics. However, precise coordination between these platforms in real-time scenarios presents major challenges, particularly when external localization infrastructure such as GPS or GNSS is unavailable or degraded (1). This paper proposes a vision-based, data-driven framework for real-time UAV-UGV integration, with a focus on robust UGV detection and heading angle prediction for navigation and coordination. The system employs a fine-tuned YOLOv5 model to detect UGVs and extract bounding box features, which are then used by a lightweight artificial neural network (ANN) to estimate the UAV's required heading angle. A VICON motion capture system was used to generate ground-truth data during training, resulting in a dataset of over 13,000 annotated images collected in a controlled lab environment. The trained ANN achieves a mean absolute error of 0.1506° and a root mean squared error of 0.1957°, offering accurate heading angle predictions using only monocular camera inputs. Experimental evaluations achieve 95% accuracy in UGV detection. This work contributes a vision-based, infrastructure- independent solution that demonstrates strong potential for deployment in GPS/GNSS-denied environments, supporting reliable multi-agent coordination under realistic dynamic conditions. A demonstration video showcasing the system's real-time performance, including UGV detection, heading angle prediction, and UAV alignment under dynamic conditions, is available at: https://github.com/Kooroshraf/UAV-UGV-Integration --- ### SCOPE: Language Models as One-Time Teacher for Hierarchical Planning in Text Environments Authors: Haoye Lu, Pavan Seshadri, Kaheer Suleman Published: 2025-12-10 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.09897v1 Long-term planning in complex, text-based environments presents significant challenges due to open-ended action spaces, ambiguous observations, and sparse feedback. Recent research suggests that large language models (LLMs) encode rich semantic knowledge about the world, which can be valuable for guiding agents in high-level reasoning and planning across both embodied and purely textual settings. However, existing approaches often depend heavily on querying LLMs during training and inference, making them computationally expensive and difficult to deploy efficiently. In addition, these methods typically employ a pretrained, unaltered LLM whose parameters remain fixed throughout training, providing no opportunity for adaptation to the target task. To address these limitations, we introduce SCOPE (Subgoal-COnditioned Pretraining for Efficient planning), a one-shot hierarchical planner that leverages LLM-generated subgoals only at initialization to pretrain a lightweight student model. Unlike prior approaches that distill LLM knowledge by repeatedly prompting the model to adaptively generate subgoals during training, our method derives subgoals directly from example trajectories. This design removes the need for repeated LLM queries, significantly improving efficiency, though at the cost of reduced explainability and potentially suboptimal subgoals. Despite their suboptimality, our results on the TextCraft environment show that LLM-generated subgoals can still serve as a strong starting point for hierarchical goal decomposition in text-based planning tasks. Compared to the LLM-based hierarchical agent ADaPT (Prasad et al., 2024), which achieves a 0.52 success rate, our method reaches 0.56 and reduces inference time from 164.4 seconds to just 3.0 seconds. --- ### Human-in-the-Loop and AI: Crowdsourcing Metadata Vocabulary for Materials Science Authors: Jane Greenberg, Scott McClellan, Addy Ireland, Robert Sammarco, Colton Gerber, Christopher B. Rauch, Mat Kelly, John Kunze, Yuan An, Eric Toberer Published: 2025-12-10 Categories: cs.AI, cs.DL arXiv: https://arxiv.org/abs/2512.09895v1 Metadata vocabularies are essential for advancing FAIR and FARR data principles, but their development constrained by limited human resources and inconsistent standardization practices. This paper introduces MatSci-YAMZ, a platform that integrates artificial intelligence (AI) and human-in-the-loop (HILT), including crowdsourcing, to support metadata vocabulary development. The paper reports on a proof-of-concept use case evaluating the AI-HILT model in materials science, a highly interdisciplinary domain Six (6) participants affiliated with the NSF Institute for Data-Driven Dynamical Design (ID4) engaged with the MatSci-YAMZ plaform over several weeks, contributing term definitions and providing examples to prompt the AI-definitions refinement. Nineteen (19) AI-generated definitions were successfully created, with iterative feedback loops demonstrating the feasibility of AI-HILT refinement. Findings confirm the feasibility AI-HILT model highlighting 1) a successful proof of concept, 2) alignment with FAIR and open-science principles, 3) a research protocol to guide future studies, and 4) the potential for scalability across domains. Overall, MatSci-YAMZ's underlying model has the capacity to enhance semantic transparency and reduce time required for consensus building and metadata vocabulary development. --- ### Exploring Protein Language Model Architecture-Induced Biases for Antibody Comprehension Authors: Mengren, Liu, Yixiang Zhang, Yiming, Zhang Published: 2025-12-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.09894v1 Recent advances in protein language models (PLMs) have demonstrated remarkable capabilities in understanding protein sequences. However, the extent to which different model architectures capture antibody-specific biological properties remains unexplored. In this work, we systematically investigate how architectural choices in PLMs influence their ability to comprehend antibody sequence characteristics and functions. We evaluate three state-of-the-art PLMs-AntiBERTa, BioBERT, and ESM2--against a general-purpose language model (GPT-2) baseline on antibody target specificity prediction tasks. Our results demonstrate that while all PLMs achieve high classification accuracy, they exhibit distinct biases in capturing biological features such as V gene usage, somatic hypermutation patterns, and isotype information. Through attention attribution analysis, we show that antibody-specific models like AntiBERTa naturally learn to focus on complementarity-determining regions (CDRs), while general protein models benefit significantly from explicit CDR-focused training strategies. These findings provide insights into the relationship between model architecture and biological feature extraction, offering valuable guidance for future PLM development in computational antibody design. --- ### Provably Learning from Modern Language Models via Low Logit Rank Authors: Noah Golowich, Allen Liu, Abhishek Shetty Published: 2025-12-10 Categories: cs.LG, cs.AI, cs.DS, stat.ML arXiv: https://arxiv.org/abs/2512.09892v1 While modern language models and their inner workings are incredibly complex, recent work (Golowich, Liu & Shetty; 2025) has proposed a simple and potentially tractable abstraction for them through the observation that empirically, these language models all seem to have approximately low logit rank. Roughly, this means that a matrix formed by the model's log probabilities of various tokens conditioned on certain sequences of tokens is well approximated by a low rank matrix. In this paper, our focus is on understanding how this structure can be exploited algorithmically for obtaining provable learning guarantees. Since low logit rank models can encode hard-to-learn distributions such as noisy parities, we study a query learning model with logit queries that reflects the access model for common APIs. Our main result is an efficient algorithm for learning any approximately low logit rank model from queries. We emphasize that our structural assumption closely reflects the behavior that is empirically observed in modern language models. Thus, our result gives what we believe is the first end-to-end learning guarantee for a generative model that plausibly captures modern language models. --- ### Analysis of Dirichlet Energies as Over-smoothing Measures Authors: Anna Bison, Alessandro Sperduti Published: 2025-12-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.09890v1 We analyze the distinctions between two functionals often used as over-smoothing measures: the Dirichlet energies induced by the unnormalized graph Laplacian and the normalized graph Laplacian. We demonstrate that the latter fails to satisfy the axiomatic definition of a node-similarity measure proposed by Rusch \textit{et al.} By formalizing fundamental spectral properties of these two definitions, we highlight critical distinctions necessary to select the metric that is spectrally compatible with the GNN architecture, thereby resolving ambiguities in monitoring the dynamics. --- ### HPM-KD: Hierarchical Progressive Multi-Teacher Framework for Knowledge Distillation and Efficient Model Compression Authors: Gustavo Coelho Haase, Paulo Henrique Dourado da Silva Published: 2025-12-10 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2512.09886v1 Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requiring extensive manual tuning, (2) capacity gap when distilling from very large teachers to small students, (3) suboptimal coordination in multi-teacher scenarios, and (4) inefficient use of computational resources. We present \textbf{HPM-KD}, a framework that integrates six synergistic components: (i) Adaptive Configuration Manager via meta-learning that eliminates manual hyperparameter tuning, (ii) Progressive Distillation Chain with automatically determined intermediate models, (iii) Attention-Weighted Multi-Teacher Ensemble that learns dynamic per-sample weights, (iv) Meta-Learned Temperature Scheduler that adapts temperature throughout training, (v) Parallel Processing Pipeline with intelligent load balancing, and (vi) Shared Optimization Memory for cross-experiment reuse. Experiments on CIFAR-10, CIFAR-100, and tabular datasets demonstrate that HPM-KD: achieves 10x-15x compression while maintaining 85% accuracy retention, eliminates the need for manual tuning, and reduces training time by 30-40% via parallelization. Ablation studies confirm independent contribution of each component (0.10-0.98 pp). HPM-KD is available as part of the open-source DeepBridge library. --- ### Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing Authors: Justin W. Lin, Eliot Krzysztof Jones, Donovan Julian Jasper, Ethan Jun-shen Ho, Anna Wu, Arnold Tianyi Yang, Neil Perry, Andy Zou, Matt Fredrikson, J. Zico Kolter, Percy Liang, Dan Boneh et al. Published: 2025-12-10 Categories: cs.AI, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2512.09882v2 We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arbitrary sub-agents, and automatic vulnerability triaging. In our comparative study, ARTEMIS placed second overall, discovering 9 valid vulnerabilities with an 82% valid submission rate and outperforming 9 of 10 human participants. While existing scaffolds such as Codex and CyAgent underperformed relative to most human participants, ARTEMIS demonstrated technical sophistication and submission quality comparable to the strongest participants. We observe that AI agents offer advantages in systematic enumeration, parallel exploitation, and cost -- certain ARTEMIS variants cost $18/hour versus $60/hour for professional penetration testers. We also identify key capability gaps: AI agents exhibit higher false-positive rates and struggle with GUI-based tasks. --- ### Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing Authors: Justin W. Lin, Eliot Krzysztof Jones, Donovan Julian Jasper, Ethan Jun-shen Ho, Anna Wu, Arnold Tianyi Yang, Neil Perry, Andy Zou, Matt Fredrikson, J. Zico Kolter, Percy Liang, Dan Boneh et al. Published: 2025-12-10 Categories: cs.AI, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2512.09882v1 We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arbitrary sub-agents, and automatic vulnerability triaging. In our comparative study, ARTEMIS placed second overall, discovering 9 valid vulnerabilities with an 82% valid submission rate and outperforming 9 of 10 human participants. While existing scaffolds such as Codex and CyAgent underperformed relative to most human participants, ARTEMIS demonstrated technical sophistication and submission quality comparable to the strongest participants. We observe that AI agents offer advantages in systematic enumeration, parallel exploitation, and cost -- certain ARTEMIS variants cost $18/hour versus $60/hour for professional penetration testers. We also identify key capability gaps: AI agents exhibit higher false-positive rates and struggle with GUI-based tasks. --- ### Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs Authors: Pius Horn, Janis Keuper Published: 2025-12-10 Categories: cs.CV, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2512.09874v3 Correctly parsing mathematical formulas from PDFs is critical for training large language models and building scientific knowledge bases from academic literature, yet existing benchmarks either exclude formulas entirely or lack semantically-aware evaluation metrics. We introduce a benchmarking framework centered on synthetically generated PDFs with precise LaTeX ground truth, enabling systematic control over layout, formulas, and content characteristics. For evaluation, we apply LLM-as-a-judge to assess semantic equivalence of parsed formulas, capturing mathematical meaning beyond surface-level notation differences. We validate this approach through a human study (250 formula pairs, 750 ratings from 30 evaluators), showing a Pearson correlation of r=0.78 with human judgment, compared to r=0.34 for character-level matching (CDM) and r~0 for text similarity. Our robust two-stage matching pipeline combining LLM-based extraction with fuzzy validation reliably aligns parsed formulas with ground truth despite format inconsistencies across parsers. Evaluating 20+ contemporary PDF parsers across 100 synthetic documents with 2,000+ formulas reveals significant performance disparities, providing actionable guidance for practitioners selecting parsers for downstream applications. Code and benchmark data: https://github.com/phorn1/pdf-parse-bench and https://github.com/phorn1/formula-metric-study --- ### Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs Authors: Pius Horn, Janis Keuper Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09874v1 Correctly parsing mathematical formulas from PDFs is critical for training large language models and building scientific knowledge bases from academic literature, yet existing benchmarks either exclude formulas entirely or lack semantically-aware evaluation metrics. We introduce a novel benchmarking framework centered on synthetically generated PDFs with precise LaTeX ground truth, enabling systematic control over layout, formulas, and content characteristics. A key methodological contribution is pioneering LLM-as-a-judge for semantic formula assessment, combined with a robust two-stage matching pipeline that handles parser output inconsistencies. Through human validation on 250 formula pairs (750 ratings from 30 evaluators), we demonstrate that LLM-based evaluation achieves substantially higher correlation with human judgment (Pearson r=0.78) compared to CDM (r=0.34) and text similarity (r~0). Evaluating 20+ contemporary PDF parsers (including specialized OCR models, vision-language models, and rule-based approaches) across 100 synthetic documents with 2,000+ formulas reveals significant performance disparities. Our findings provide crucial insights for practitioners selecting parsers for downstream applications and establish a robust, scalable methodology that enables reproducible evaluation of PDF formula extraction quality. Code and benchmark data: https://github.com/phorn1/pdf-parse-bench --- ### FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning Authors: Khurram Khalil, Khaza Anuarul Hoque Published: 2025-12-10 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.09872v1 Generative Artificial Intelligence models, such as Large Language Models (LLMs) and Large Vision Models (VLMs), exhibit state-of-the-art performance but remain vulnerable to hardware-based threats, specifically bit-flip attacks (BFAs). Existing BFA discovery methods lack generalizability and struggle to scale, often failing to analyze the vast parameter space and complex interdependencies of modern foundation models in a reasonable time. This paper proposes FlipLLM, a reinforcement learning (RL) architecture-agnostic framework that formulates BFA discovery as a sequential decision-making problem. FlipLLM combines sensitivity-guided layer pruning with Q-learning to efficiently identify minimal, high-impact bit sets that can induce catastrophic failure. We demonstrate the effectiveness and generalizability of FlipLLM by applying it to a diverse set of models, including prominent text-only LLMs (GPT-2 Large, LLaMA 3.1 8B, and DeepSeek-V2 7B), VLMs such as LLaVA 1.6, and datasets, such as MMLU, MMLU-Pro, VQAv2, and TextVQA. Our results show that FlipLLM can identify critical bits that are vulnerable to BFAs up to 2.5x faster than SOTA methods. We demonstrate that flipping the FlipLLM-identified bits plummets the accuracy of LLaMA 3.1 8B from 69.9% to ~0.2%, and for LLaVA's VQA score from 78% to almost 0%, by flipping as few as 5 and 7 bits, respectively. Further analysis reveals that applying standard hardware protection mechanisms, such as ECC SECDED, to the FlipLLM-identified bit locations completely mitigates the BFA impact, demonstrating the practical value of our framework in guiding hardware-level defenses. FlipLLM offers the first scalable and adaptive methodology for exploring the BFA vulnerability of both language and multimodal foundation models, paving the way for comprehensive hardware-security evaluation. --- ### Diffusion Posterior Sampler for Hyperspectral Unmixing with Spectral Variability Modeling Authors: Yimin Zhu, Lincoln Linlin Xu Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09871v1 Linear spectral mixture models (LMM) provide a concise form to disentangle the constituent materials (endmembers) and their corresponding proportions (abundance) in a single pixel. The critical challenges are how to model the spectral prior distribution and spectral variability. Prior knowledge and spectral variability can be rigorously modeled under the Bayesian framework, where posterior estimation of Abundance is derived by combining observed data with endmember prior distribution. Considering the key challenges and the advantages of the Bayesian framework, a novel method using a diffusion posterior sampler for semiblind unmixing, denoted as DPS4Un, is proposed to deal with these challenges with the following features: (1) we view the pretrained conditional spectrum diffusion model as a posterior sampler, which can combine the learned endmember prior with observation to get the refined abundance distribution. (2) Instead of using the existing spectral library as prior, which may raise bias, we establish the image-based endmember bundles within superpixels, which are used to train the endmember prior learner with diffusion model. Superpixels make sure the sub-scene is more homogeneous. (3) Instead of using the image-level data consistency constraint, the superpixel-based data fidelity term is proposed. (4) The endmember is initialized as Gaussian noise for each superpixel region, DPS4Un iteratively updates the abundance and endmember, contributing to spectral variability modeling. The experimental results on three real-world benchmark datasets demonstrate that DPS4Un outperforms the state-of-the-art hyperspectral unmixing methods. --- ### Hierarchy-Aware Multimodal Unlearning for Medical AI Authors: Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, Mohit Bansal Published: 2025-12-10 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.09867v3 Pretrained Multimodal Large Language Models (MLLMs) are increasingly used in sensitive domains such as medical AI, where privacy regulations like HIPAA and GDPR require specific removal of individuals' or institutions' data. This motivates machine unlearning, which aims to remove the influence of target data from a trained model. However, existing unlearning benchmarks fail to reflect the hierarchical and multimodal structure of real-world medical data, limiting their ability to properly evaluate unlearning in practice. Therefore, we introduce MedForget, a hierarchy-aware multimodal unlearning benchmark that models hospital data as a nested structure, enabling fine-grained evaluation of multimodal unlearning across retain and forget splits. Experiments with current unlearning methods show that existing approaches struggle to achieve effective hierarchy-aware forgetting without degrading downstream medical utility. To address this limitation, we propose Cross-modal Hierarchy-Informed Projection for unlearning (CHIP), a training-free, hierarchy-aware multimodal unlearning method that deletes information by selectively removing target-specific weight subspaces while preserving sibling-shared information. Experiments show that CHIP achieves the highest forget-retain performance gap across all hierarchy levels while maintaining competitive downstream utility compared to existing methods. Overall, MedForget provides a practical, HIPAA-aligned benchmark for evaluating structured multimodal unlearning for medical data, and CHIP offers an effective and general solution for hierarchy-aware forgetting that balances deletion with utility. --- ### MedForget: Hierarchy-Aware Multimodal Unlearning Testbed for Medical AI Authors: Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, Mohit Bansal Published: 2025-12-10 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.09867v1 Pretrained Multimodal Large Language Models (MLLMs) are increasingly deployed in medical AI systems for clinical reasoning, diagnosis support, and report generation. However, their training on sensitive patient data raises critical privacy and compliance challenges under regulations such as HIPAA and GDPR, which enforce the "right to be forgotten". Unlearning, the process of tuning models to selectively remove the influence of specific training data points, offers a potential solution, yet its effectiveness in complex medical settings remains underexplored. To systematically study this, we introduce MedForget, a Hierarchy-Aware Multimodal Unlearning Testbed with explicit retain and forget splits and evaluation sets containing rephrased variants. MedForget models hospital data as a nested hierarchy (Institution -> Patient -> Study -> Section), enabling fine-grained assessment across eight organizational levels. The benchmark contains 3840 multimodal (image, question, answer) instances, each hierarchy level having a dedicated unlearning target, reflecting distinct unlearning challenges. Experiments with four SOTA unlearning methods on three tasks (generation, classification, cloze) show that existing methods struggle to achieve complete, hierarchy-aware forgetting without reducing diagnostic performance. To test whether unlearning truly deletes hierarchical pathways, we introduce a reconstruction attack that progressively adds hierarchical level context to prompts. Models unlearned at a coarse granularity show strong resistance, while fine-grained unlearning leaves models vulnerable to such reconstruction. MedForget provides a practical, HIPAA-aligned testbed for building compliant medical AI systems. --- ### UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving Authors: Hao Lu, Ziyang Liu, Guangfeng Jiang, Yuanfei Luo, Sheng Chen, Yangang Zhang, Ying-Cong Chen Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09864v1 Autonomous driving (AD) systems struggle in long-tail scenarios due to limited world knowledge and weak visual dynamic modeling. Existing vision-language-action (VLA)-based methods cannot leverage unlabeled videos for visual causal learning, while world model-based methods lack reasoning capabilities from large language models. In this paper, we construct multiple specialized datasets providing reasoning and planning annotations for complex scenarios. Then, a unified Understanding-Generation-Planning framework, named UniUGP, is proposed to synergize scene reasoning, future video generation, and trajectory planning through a hybrid expert architecture. By integrating pre-trained VLMs and video generation models, UniUGP leverages visual dynamics and semantic reasoning to enhance planning performance. Taking multi-frame observations and language instructions as input, it produces interpretable chain-of-thought reasoning, physically consistent trajectories, and coherent future videos. We introduce a four-stage training strategy that progressively builds these capabilities across multiple existing AD datasets, along with the proposed specialized datasets. Experiments demonstrate state-of-the-art performance in perception, reasoning, and decision-making, with superior generalization to challenging long-tail situations. --- ### Mitigating Social Bias in English and Urdu Language Models Using PRM-Guided Candidate Selection and Sequential Refinement Authors: Muneeb Ur Raheem Khan Published: 2025-12-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.09854v1 Large language models (LLMs) increasingly mediate human communication, decision support, content creation, and information retrieval. Despite impressive fluency, these systems frequently produce biased or stereotypical content, especially when prompted with socially sensitive language. A growing body of research has demonstrated that such biases disproportionately affect low-resource languages, where training data is limited and culturally unrepresentative. This paper presents a comprehensive study of inference-time bias mitigation, a strategy that avoids retraining or fine-tuning and instead operates directly on model outputs. Building on preference-ranking models (PRMs), we introduce a unified evaluation framework comparing three methods: (1) baseline single-word generation, (2) PRM-Select best-of-N sampling, and (3) PRM-Sequential refinement guided by PRM critiques. We evaluate these techniques across 200 English prompts and their Urdu counterparts, designed to reflect socio-cultural contexts relevant to gender, ethnicity, religion, nationality, disability, profession, age, and socioeconomic categories. Using GPT-3.5 as a candidate generator and GPT-4o-mini as a PRM-based bias and utility scorer, we provide an extensive quantitative analysis of bias reduction, utility preservation, and cross-lingual disparities. Our findings show: (a) substantial gains over the baseline for both languages; (b) consistently lower fairness scores for Urdu across all methods, highlighting structural inequities in multilingual LLM training; and (c) distinct improvement trajectories between PRM-Select and PRM-Sequential. The study contributes an extensible methodology, interpretable metrics, and cross-lingual comparisons that can support future work on fairness evaluation in low-resource languages. --- ### New Approximation Results and Optimal Estimation for Fully Connected Deep Neural Networks Authors: Zhaoji Tang Published: 2025-12-10 Categories: econ.EM, stat.ML arXiv: https://arxiv.org/abs/2512.09853v1 \citet{farrell2021deep} establish non-asymptotic high-probability bounds for general deep feedforward neural network (with rectified linear unit activation function) estimators, with \citet(Theorem 1){farrell2021deep} achieving a suboptimal convergence rate for fully connected feedforward networks. The authors suggest that improved approximation of fully connected networks could yield sharper versions of \citet(Theorem 1){farrell2021deep} without altering the theoretical framework. By deriving approximation bounds specifically for a narrower fully connected deep neural network, this note demonstrates that \citet(Theorem 1){farrell2021deep} can be improved to achieve an optimal rate (up to a logarithmic factor). Furthermore, this note briefly shows that deep neural network estimators can mitigate the curse of dimensionality for functions with compositional structure and functions defined on manifolds. --- ### Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation Authors: Yuyang Li, Yinghan Chen, Zihang Zhao, Puhao Li, Tengyu Liu, Siyuan Huang, Yixin Zhu Published: 2025-12-10 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.09851v2 Robotic manipulation requires both rich multimodal perception and effective learning frameworks to handle complex real-world tasks. See-through-skin (STS) sensors, which combine tactile and visual perception, offer promising sensing capabilities, while modern imitation learning provides powerful tools for policy acquisition. However, existing STS designs lack simultaneous multimodal perception and suffer from unreliable tactile tracking. Furthermore, integrating these rich multimodal signals into learning-based manipulation pipelines remains an open challenge. We introduce TacThru, an STS sensor enabling simultaneous visual perception and robust tactile signal extraction, and TacThru-UMI, an imitation learning framework that leverages these multimodal signals for manipulation. Our sensor features a fully transparent elastomer, persistent illumination, novel keyline markers, and efficient tracking, while our learning system integrates these signals through a Transformer-based Diffusion Policy. Experiments on five challenging real-world tasks show that TacThru-UMI achieves an average success rate of 85.5%, significantly outperforming the baselines of tactile policy(66.3%) and vision-only policy (55.4%). The system excels in critical scenarios, including contact detection with thin and soft objects and precision manipulation requiring multimodal coordination. This work demonstrates that combining simultaneous multimodal perception with modern learning frameworks enables more precise, adaptable robotic manipulation. --- ### Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation Authors: Yuyang Li, Yinghan Chen, Zihang Zhao, Puhao Li, Tengyu Liu, Siyuan Huang, Yixin Zhu Published: 2025-12-10 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.09851v1 Robotic manipulation requires both rich multimodal perception and effective learning frameworks to handle complex real-world tasks. See-through-skin (STS) sensors, which combine tactile and visual perception, offer promising sensing capabilities, while modern imitation learning provides powerful tools for policy acquisition. However, existing STS designs lack simultaneous multimodal perception and suffer from unreliable tactile tracking. Furthermore, integrating these rich multimodal signals into learning-based manipulation pipelines remains an open challenge. We introduce TacThru, an STS sensor enabling simultaneous visual perception and robust tactile signal extraction, and TacThru-UMI, an imitation learning framework that leverages these multimodal signals for manipulation. Our sensor features a fully transparent elastomer, persistent illumination, novel keyline markers, and efficient tracking, while our learning system integrates these signals through a Transformer-based Diffusion Policy. Experiments on five challenging real-world tasks show that TacThru-UMI achieves an average success rate of 85.5%, significantly outperforming the baselines of alternating tactile-visual (66.3%) and vision-only (55.4%). The system excels in critical scenarios, including contact detection with thin and soft objects and precision manipulation requiring multimodal coordination. This work demonstrates that combining simultaneous multimodal perception with modern learning frameworks enables more precise, adaptable robotic manipulation. --- ### Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability Authors: Simone Cuonzo, Nina Deliu Published: 2025-12-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.09850v2 We introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making under uncertainty. Traditional regret-minimisation bandit strategies like Thompson Sampling and Upper Confidence Bound (UCB) typically rely on distributional assumptions or asymptotic guarantees; further, they remain largely focused on regret, neglecting their statistical properties. We address this gap. Through the adoption of CP, we bridge the regret-minimising potential of a decision-making bandit policy with statistical guarantees in the form of finite-sample prediction coverage. We demonstrate the potential of Conformal Bandits through simulation studies and an application to portfolio allocation, a typical scenario where differences in arm rewards are far too small (weak arm separability) for classical policies to be optimal in finite sample. We showcase our framework's practical advantage in terms of regret in this setting, as well as its added value in achieving nominal coverage guarantees where classical UCB policies may fail. Focusing on our application of interest, we further illustrate how integrating hidden Markov models to capture the regime-switching behaviour of financial markets, enhances the exploration-exploitation trade-off, and translates into higher risk-adjusted returns, while preserving coverage guarantees. --- ### Conformal Bandits: Bringing statistical validity and reward efficiency to the small-gap regime Authors: Simone Cuonzo, Nina Deliu Published: 2025-12-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.09850v1 We introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making under uncertainty. Traditional regret-minimisation bandit strategies like Thompson Sampling and Upper Confidence Bound (UCB) typically rely on distributional assumptions or asymptotic guarantees; further, they remain largely focused on regret, neglecting their statistical properties. We address this gap. Through the adoption of CP, we bridge the regret-minimising potential of a decision-making bandit policy with statistical guarantees in the form of finite-time prediction coverage. We demonstrate the potential of it Conformal Bandits through simulation studies and an application to portfolio allocation, a typical small-gap regime, where differences in arm rewards are far too small for classical policies to achieve optimal regret bounds in finite sample. Motivated by this, we showcase our framework's practical advantage in terms of regret in small-gap settings, as well as its added value in achieving nominal coverage guarantees where classical UCB policies fail. Focusing on our application of interest, we further illustrate how integrating hidden Markov models to capture the regime-switching behaviour of financial markets, enhances the exploration-exploitation trade-off, and translates into higher risk-adjusted regret efficiency returns, while preserving coverage guarantees. --- ### From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities Authors: Shijia Feng, Michael Wray, Walterio Mayol-Cuevas Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09847v1 Understanding human skill performance is essential for intelligent assistive systems, with struggle recognition offering a natural cue for identifying user difficulties. While prior work focuses on offline struggle classification and localization, real-time applications require models capable of detecting and anticipating struggle online. We reformulate struggle localization as an online detection task and further extend it to anticipation, predicting struggle moments before they occur. We adapt two off-the-shelf models as baselines for online struggle detection and anticipation. Online struggle detection achieves 70-80% per-frame mAP, while struggle anticipation up to 2 seconds ahead yields comparable performance with slight drops. We further examine generalization across tasks and activities and analyse the impact of skill evolution. Despite larger domain gaps in activity-level generalization, models still outperform random baselines by 4-20%. Our feature-based models run at up to 143 FPS, and the whole pipeline, including feature extraction, operates at around 20 FPS, sufficient for real-time assistive applications. --- ### ChronusOmni: Improving Time Awareness of Omni Large Language Models Authors: Yijing Chen, Yihan Wu, Kaisi Guan, Yuchen Ren, Yuyue Wang, Ruihua Song, Liyun Ru Published: 2025-12-10 Categories: cs.CL, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2512.09841v1 Time awareness is a fundamental ability of omni large language models, especially for understanding long videos and answering complex questions. Previous approaches mainly target vision-language scenarios and focus on the explicit temporal grounding questions, such as identifying when a visual event occurs or determining what event happens at aspecific time. However, they often make insufficient use of the audio modality, and overlook implicit temporal grounding across modalities--for example, identifying what is visually present when a character speaks, or determining what is said when a visual event occurs--despite such cross-modal temporal relations being prevalent in real-world scenarios. In this paper, we propose ChronusOmni, an omni large language model designed to enhance temporal awareness for both explicit and implicit audiovisual temporal grounding. First, we interleave text-based timestamp tokens with visual and audio representations at each time unit, enabling unified temporal modeling across modalities. Second, to enforce correct temporal ordering and strengthen fine-grained temporal reasoning, we incorporate reinforcement learning with specially designed reward functions. Moreover, we construct ChronusAV, a temporally-accurate, modality-complete, and cross-modal-aligned dataset to support the training and evaluation on audiovisual temporal grounding task. Experimental results demonstrate that ChronusOmni achieves state-of-the-art performance on ChronusAV with more than 30% improvement and top results on most metrics upon other temporal grounding benchmarks. This highlights the strong temporal awareness of our model across modalities, while preserving general video and audio understanding capabilities. --- ### Fast Factorized Learning: Powered by In-Memory Database Systems Authors: Bernhard Stöckl, Maximilian E. Schüle Published: 2025-12-10 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2512.09836v1 Learning models over factorized joins avoids redundant computations by identifying and pre-computing shared cofactors. Previous work has investigated the performance gain when computing cofactors on traditional disk-based database systems. Due to the absence of published code, the experiments could not be reproduced on in-memory database systems. This work describes the implementation when using cofactors for in-database factorized learning. We benchmark our open-source implementation for learning linear regression on factorized joins with PostgreSQL -- as a disk-based database system -- and HyPer -- as an in-memory engine. The evaluation shows a performance gain of factorized learning on in-memory database systems by 70\% to non-factorized learning and by a factor of 100 compared to disk-based database systems. Thus, modern database engines can contribute to the machine learning pipeline by pre-computing aggregates prior to data extraction to accelerate training. --- ### Predicting the Containment Time of California Wildfires Using Machine Learning Authors: Shashank Bhardwaj Published: 2025-12-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.09835v1 California's wildfire season keeps getting worse over the years, overwhelming the emergency response teams. These fires cause massive destruction to both property and human life. Because of these reasons, there's a growing need for accurate and practical predictions that can help assist with resources allocation for the Wildfire managers or the response teams. In this research, we built machine learning models to predict the number of days it will require to fully contain a wildfire in California. Here, we addressed an important gap in the current literature. Most prior research has concentrated on wildfire risk or how fires spread, and the few that examine the duration typically predict it in broader categories rather than a continuous measure. This research treats the wildfire duration prediction as a regression task, which allows for more detailed and precise forecasts rather than just the broader categorical predictions used in prior work. We built the models by combining three publicly available datasets from California Department of Forestry and Fire Protection's Fire and Resource Assessment Program (FRAP). This study compared the performance of baseline ensemble regressor, Random Forest and XGBoost, with a Long Short-Term Memory (LSTM) neural network. The results show that the XGBoost model slightly outperforms the Random Forest model, likely due to its superior handling of static features in the dataset. The LSTM model, on the other hand, performed worse than the ensemble models because the dataset lacked temporal features. Overall, this study shows that, depending on the feature availability, Wildfire managers or Fire management authorities can select the most appropriate model to accurately predict wildfire containment duration and allocate resources effectively. --- ### Interpretation as Linear Transformation: A Cognitive-Geometric Model of Concepts and Meaning Authors: Chainarong Amornbunchornvej Published: 2025-12-10 Categories: cs.AI, cs.LG, cs.MA, cs.SI arXiv: https://arxiv.org/abs/2512.09831v2 This paper develops a geometric framework for modeling concepts, motivation, and influence across cognitively heterogeneous agents. Each agent is represented by a personalized value space, a vector space encoding the internal dimensions through which the agent interprets and evaluates meaning. Evaluative concepts are formalized as structured vectors, abstract beings, whose transmission is mediated by linear interpretation maps. An abstract being survives communication only if it avoids the null spaces of these maps, yielding a structural criterion for intelligibility, miscommunication, and concept death. Within this framework, I show how conceptual distortion, motivational drift, and the limits of mutual understanding arise from purely algebraic constraints. A central result, the No-Null-Space Leadership Condition, characterizes leadership as a property of representational reachability rather than persuasion or authority. More broadly, the model explains how abstract beings can propagate, mutate, or disappear as they traverse diverse cognitive geometries. The account unifies insights from conceptual spaces, social epistemology, and AI value alignment by grounding meaning preservation in structural compatibility rather than shared information or rationality. I argue that this cognitive-geometric perspective clarifies the epistemic boundaries of influence in both human and artificial systems, and offers a general foundation for analyzing conceptual dynamics across heterogeneous agents. --- ### Interpretation as Linear Transformation: A Cognitive-Geometric Model of Belief and Meaning Authors: Chainarong Amornbunchornvej Published: 2025-12-10 Categories: cs.AI, cs.LG, cs.MA, cs.SI arXiv: https://arxiv.org/abs/2512.09831v1 This paper develops a geometric framework for modeling belief, motivation, and influence across cognitively heterogeneous agents. Each agent is represented by a personalized value space, a vector space encoding the internal dimensions through which the agent interprets and evaluates meaning. Beliefs are formalized as structured vectors-abstract beings-whose transmission is mediated by linear interpretation maps. A belief survives communication only if it avoids the null spaces of these maps, yielding a structural criterion for intelligibility, miscommunication, and belief death. Within this framework, I show how belief distortion, motivational drift, counterfactual evaluation, and the limits of mutual understanding arise from purely algebraic constraints. A central result-"the No-Null-Space Leadership Condition"-characterizes leadership as a property of representational reachability rather than persuasion or authority. More broadly, the model explains how abstract beings can propagate, mutate, or disappear as they traverse diverse cognitive geometries. The account unifies insights from conceptual spaces, social epistemology, and AI value alignment by grounding meaning preservation in structural compatibility rather than shared information or rationality. I argue that this cognitive-geometric perspective clarifies the epistemic boundaries of influence in both human and artificial systems, and offers a general foundation for analyzing belief dynamics across heterogeneous agents. --- ### LLMs in Interpreting Legal Documents Authors: Simone Corbo Published: 2025-12-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.09830v2 This chapter explores the application of Large Language Models in the legal domain, showcasing their potential to optimise and augment traditional legal tasks by analysing possible use cases, such as assisting in interpreting statutes, contracts, and case law, enhancing clarity in legal summarisation, contract negotiation, and information retrieval. There are several challenges that can arise from the application of such technologies, such as algorithmic monoculture, hallucinations, and compliance with existing regulations, including the EU's AI Act and recent U.S. initiatives, alongside the emerging approaches in China. Furthermore, two different benchmarks are presented. --- ### LLMs in Interpreting Legal Documents Authors: Simone Corbo Published: 2025-12-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.09830v1 This chapter explores the application of Large Language Models in the legal domain, showcasing their potential to optimise and augment traditional legal tasks by analysing possible use cases, such as assisting in interpreting statutes, contracts, and case law, enhancing clarity in legal summarisation, contract negotiation, and information retrieval. There are several challenges that can arise from the application of such technologies, such as algorithmic monoculture, hallucinations, and compliance with existing regulations, including the EU's AI Act and recent U.S. initiatives, alongside the emerging approaches in China. Furthermore, two different benchmarks are presented. --- ### RIFT: A Scalable Methodology for LLM Accelerator Fault Assessment using Reinforcement Learning Authors: Khurram Khalil, Muhammad Mahad Khaliq, Khaza Anuarul Hoque Published: 2025-12-10 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.09829v1 The massive scale of modern AI accelerators presents critical challenges to traditional fault assessment methodologies, which face prohibitive computational costs and provide poor coverage of critical failure modes. This paper introduces RIFT (Reinforcement Learning-guided Intelligent Fault Targeting), a scalable framework that automates the discovery of minimal, high-impact fault scenarios for efficient design-time fault assessment. RIFT transforms the complex search for worst-case faults into a sequential decision-making problem, combining hybrid sensitivity analysis for search space pruning with reinforcement learning to intelligently generate minimal, high-impact test suites. Evaluated on billion-parameter Large Language Model (LLM) workloads using NVIDIA A100 GPUs, RIFT achieves a \textbf{2.2$\times$} fault assessment speedup over evolutionary methods and reduces the required test vector volume by over \textbf{99\%} compared to random fault injection, all while achieving \textbf{superior fault coverage}. The proposed framework also provides actionable data to enable intelligent hardware protection strategies, demonstrating that RIFT-guided selective error correction code provides a \textbf{12.8$\times$} improvement in \textbf{cost-effectiveness} (coverage per unit area) compared to uniform triple modular redundancy protection. RIFT automatically generates UVM-compliant verification artifacts, ensuring its findings are directly actionable and integrable into commercial RTL verification workflows. --- ### Composing Concepts from Images and Videos via Concept-prompt Binding Authors: Xianghao Kong, Zeyu Zhang, Yuwei Guo, Zhuoran Zhao, Songchun Zhang, Anyi Rao Published: 2025-12-10 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2512.09824v2 Visual concept composition, which aims to integrate different elements from images and videos into a single, coherent visual output, still falls short in accurately extracting complex concepts from visual inputs and flexibly combining concepts from both images and videos. We introduce Bind & Compose, a one-shot method that enables flexible visual concept composition by binding visual concepts with corresponding prompt tokens and composing the target prompt with bound tokens from various sources. It adopts a hierarchical binder structure for cross-attention conditioning in Diffusion Transformers to encode visual concepts into corresponding prompt tokens for accurate decomposition of complex visual concepts. To improve concept-token binding accuracy, we design a Diversify-and-Absorb Mechanism that uses an extra absorbent token to eliminate the impact of concept-irrelevant details when training with diversified prompts. To enhance the compatibility between image and video concepts, we present a Temporal Disentanglement Strategy that decouples the training process of video concepts into two stages with a dual-branch binder structure for temporal modeling. Evaluations demonstrate that our method achieves superior concept consistency, prompt fidelity, and motion quality over existing approaches, opening up new possibilities for visual creativity. --- ### Composing Concepts from Images and Videos via Concept-prompt Binding Authors: Xianghao Kong, Zeyu Zhang, Yuwei Guo, Zhuoran Zhao, Songchun Zhang, Anyi Rao Published: 2025-12-10 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2512.09824v1 Visual concept composition, which aims to integrate different elements from images and videos into a single, coherent visual output, still falls short in accurately extracting complex concepts from visual inputs and flexibly combining concepts from both images and videos. We introduce Bind & Compose, a one-shot method that enables flexible visual concept composition by binding visual concepts with corresponding prompt tokens and composing the target prompt with bound tokens from various sources. It adopts a hierarchical binder structure for cross-attention conditioning in Diffusion Transformers to encode visual concepts into corresponding prompt tokens for accurate decomposition of complex visual concepts. To improve concept-token binding accuracy, we design a Diversify-and-Absorb Mechanism that uses an extra absorbent token to eliminate the impact of concept-irrelevant details when training with diversified prompts. To enhance the compatibility between image and video concepts, we present a Temporal Disentanglement Strategy that decouples the training process of video concepts into two stages with a dual-branch binder structure for temporal modeling. Evaluations demonstrate that our method achieves superior concept consistency, prompt fidelity, and motion quality over existing approaches, opening up new possibilities for visual creativity. --- ### Geospatial Soil Quality Analysis: A Roadmap for Integrated Systems Authors: Habiba Ben Abderrahmane, Slimane Oulad-Naoui, Benameur Ziani Published: 2025-12-10 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2512.09817v2 Soil quality (SQ) plays a crucial role in sustainable agriculture, environmental conservation, and land-use planning. Traditional SQ assessment techniques rely on costly, labor-intensive sampling and laboratory analysis, limiting their spatial and temporal coverage. Advances in Geographic Information Systems (GIS), remote sensing, and machine learning (ML) enabled efficient SQ evaluation. This paper presents a comprehensive roadmap distinguishing it from previous reviews by proposing a unified and modular pipeline that integrates multi-source soil data, GIS and remote sensing tools, and machine learning techniques to support transparent and scalable soil quality assessment. It also includes practical applications. Contrary to existing studies that predominantly target isolated soil parameters or specific modeling methodologies, this approach consolidates recent advancements in Geographic Information Systems (GIS), remote sensing technologies, and machine learning algorithms within the entire soil quality assessment pipeline. It also addresses existing challenges and limitations while exploring future developments and emerging trends in the field that can deliver the next generation of soil quality systems making them more transparent, adaptive, and aligned with sustainable land management. --- ### A roadmap of geospatial soil quality analysis systems Authors: Habiba BEN ABDERRAHMANE, Slimane Oulad-Naoui, Benameur ZIANI Published: 2025-12-10 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2512.09817v1 Soil quality (SQ) plays a crucial role in sustainable agriculture, environmental conservation, and land-use planning. Traditional SQ assessment techniques rely on costly, labor-intensive sampling and laboratory analysis, limiting their spatial and temporal coverage. Advances in Geographic Information Systems (GIS), remote sensing, and machine learning (ML) enabled efficient SQ evaluation. This paper presents a comprehensive roadmap distinguishing it from previous reviews by proposing a unified and modular pipeline that integrates multi-source soil data, GIS and remote sensing tools, and machine learning techniques to support transparent and scalable soil quality assessment. It also includes practical applications. Contrary to existing studies that predominantly target isolated soil parameters or specific modeling methodologies, this approach consolidates recent advancements in Geographic Information Systems (GIS), remote sensing technologies, and machine learning algorithms within the entire soil quality assessment pipeline. It also addresses existing challenges and limitations while exploring future developments and emerging trends in the field that can deliver the next generation of soil quality systems making them more transparent, adaptive, and aligned with sustainable land management. --- ### Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation Authors: Zhizhong Wang, Tianyi Chu, Zeyi Huang, Nanyang Wang, Kehan Li Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09814v2 Personalized Text-to-Image (PT2I) generation aims to produce customized images based on reference images. A prominent interest pertains to the integration of an image prompt adapter to facilitate zero-shot PT2I without test-time fine-tuning. However, current methods grapple with three fundamental challenges: 1. the elusive equilibrium between Concept Preservation (CP) and Prompt Following (PF), 2. the difficulty in retaining fine-grained concept details in reference images, and 3. the restricted scalability to extend to multi-subject personalization. To tackle these challenges, we present Dynamic Image Prompt Adapter (DynaIP), a cutting-edge plugin to enhance the fine-grained concept fidelity, CP-PF balance, and subject scalability of state-of-the-art T2I multimodal diffusion transformers (MM-DiT) for PT2I generation. Our key finding is that MM-DiT inherently exhibit decoupling learning behavior when injecting reference image features into its dual branches via cross attentions. Based on this, we design an innovative Dynamic Decoupling Strategy that removes the interference of concept-agnostic information during inference, significantly enhancing the CP-PF balance and further bolstering the scalability of multi-subject compositions. Moreover, we identify the visual encoder as a key factor affecting fine-grained CP and reveal that the hierarchical features of commonly used CLIP can capture visual information at diverse granularity levels. Therefore, we introduce a novel Hierarchical Mixture-of-Experts Feature Fusion Module to fully leverage the hierarchical features of CLIP, remarkably elevating the fine-grained concept fidelity while also providing flexible control of visual granularity. Extensive experiments across single- and multi-subject PT2I tasks verify that our DynaIP outperforms existing approaches, while requiring only single-subject training datasets. ---