# Research Papers — 2025-12 · bundle page 59 of 175 > Full-text markdown of papers #2901–2950 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/59 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/58.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/60.md) ### DeepBridge: A Unified and Production-Ready Framework for Multi-Dimensional Machine Learning Validation Authors: Gustavo Coelho Haase, Paulo Henrique Dourado da Silva Published: 2025-12-18 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2512.19744v1 We present DeepBridge, an 80K-line Python library that unifies multi-dimensional validation, automatic compliance verification, knowledge distillation, and synthetic data generation. DeepBridge offers: (i) 5 validation suites (fairness with 15 metrics, robustness with weakness detection, uncertainty via conformal prediction, resilience with 5 drift types, hyperparameter sensitivity), (ii) automatic EEOC/ECOA/GDPR verification, (iii) multi-format reporting system (interactive/static HTML, PDF, JSON), (iv) HPM-KD framework for knowledge distillation with meta-learning, and (v) scalable synthetic data generation via Dask. Through 6 case studies (credit scoring, hiring, healthcare, mortgage, insurance, fraud) we demonstrate that DeepBridge: reduces validation time by 89% (17 min vs. 150 min with fragmented tools), automatically detects fairness violations with complete coverage (10/10 features vs. 2/10 from existing tools), generates audit-ready reports in minutes. HPM-KD demonstrates consistent superiority across compression ratios 2.3--7x (CIFAR100): +1.00--2.04pp vs. Direct Training (p<0.05), confirming that Knowledge Distillation is effective at larger teacher-student gaps. Usability study with 20 participants shows SUS score 87.5 (top 10%, ``excellent''), 95% success rate, and low cognitive load (NASA-TLX 28/100). DeepBridge is open-source under MIT license at https://github.com/deepbridge/deepbridge, with complete documentation at https://deepbridge.readthedocs.io --- ### Real-Time Human-Robot Interaction Intent Detection Using RGB-based Pose and Emotion Cues with Cross-Camera Model Generalization Authors: Farida Mohsen, Ali Safa Published: 2025-12-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.17958v1 Service robots in public spaces require real-time understanding of human behavioral intentions for natural interaction. We present a practical multimodal framework for frame-accurate human-robot interaction intent detection that fuses camera-invariant 2D skeletal pose and facial emotion features extracted from monocular RGB video. Unlike prior methods requiring RGB-D sensors or GPU acceleration, our approach resource-constrained embedded hardware (Raspberry Pi 5, CPU-only). To address the severe class imbalance in natural human-robot interaction datasets, we introduce a novel approach to synthesize temporally coherent pose-emotion-label sequences for data re-balancing called MINT-RVAE (Multimodal Recurrent Variational Autoencoder for Intent Sequence Generation). Comprehensive offline evaluations under cross-subject and cross-scene protocols demonstrate strong generalization performance, achieving frame- and sequence-level AUROC of 0.95. Crucially, we validate real-world generalization through cross-camera evaluation on the MIRA robot head, which employs a different onboard RGB sensor and operates in uncontrolled environments not represented in the training data. Despite this domain shift, the deployed system achieves 91% accuracy and 100% recall across 32 live interaction trials. The close correspondence between offline and deployed performance confirms the cross-sensor and cross-environment robustness of the proposed multimodal approach, highlighting its suitability for ubiquitous multimedia-enabled social robots. --- ### Victor Calibration (VC): Multi-Pass Confidence Calibration and CP4.3 Governance Stress Test under Round-Table Orchestration Authors: Victor Stasiuc Published: 2025-12-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.17956v2 Safety alignment can make frontier LMs overly conservative, degrading collaboration via hedging or false refusals. We present a lightweight toolkit with three parts: (1) Victor Calibration (VC), a multi-pass protocol that elicits a scalar confidence proxy T (T0<T1<T2) through iterative evidence re-evaluation; (2) FD-Lite, a behavior-only phenomenology audit with a fixed anchor phrase and a meta-prefix trap to avoid anthropomorphic claims; and (3) CP4.3, a governance stress test for rank invariance and allocation monotonicity (M6). Across Claude 4.5 models (Haiku, Sonnet no-thinking, Sonnet thinking) and Opus, we observe monotonic VC trajectories without violating safety invariants, and stable CP4.3 behavior. ("Opus" here refers to a single Claude Opus 4.1 session accessed via a standard UI account, as reported in Table 1.) This work was conducted by a single operator (n=1) and is intended as hypothesis-generating; we explicitly invite replication, critique, and extension by the research community. We include prompt templates and an artifact plan to facilitate independent verification. --- ### CustomX: Unified Character, Action, and Scene Customization in Video World Models Authors: Yitong Wang, Fangyun Wei, Hongyang Zhang, Bo Dai, Yan Lu Published: 2025-12-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.17796v2 Recent advances in world models have greatly enhanced interactive environment simulation. Existing methods mainly fall into two categories: (1) static world generation models, which construct 3D environments without active agents, and (2) controllable-entity models, which allow a single entity to perform limited actions in an otherwise uncontrollable environment. In this work, we introduce CustomX, leveraging the realism and structural grounding of static world generation while extending controllable-entity models to support user-specified characters capable of performing open-ended actions. Users can provide a 3DGS scene and a character, then use natural language to direct the character to perform diverse behaviors, ranging from basic locomotion to object-centric interactions, while freely exploring the environment. CustomX synthesizes temporally coherent video clips that preserve visual fidelity with the provided scene and character, formulated as a conditional autoregressive video generation problem. Built upon a pre-trained video generator, our training strategy significantly enhances motion dynamics while maintaining generalization across actions and characters. Our evaluation covers a broad range of aspects, including visual quality, character consistency, action controllability, and long-horizon coherence. --- ### Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs Authors: Aaron Defazio, Konstantin Mishchenko, Parameswaran Raman, Hao-Jun Michael Shi, Lin Xiao Published: 2025-12-18 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.17131v3 We propose Generalized Primal Averaging (GPA), an extension of Nesterov's method that unifies and generalizes recent averaging-based optimizers like single-worker DiLoCo and Schedule-Free, within a non-distributed setting. While DiLoCo relies on a memory-intensive two-loop structure to periodically aggregate pseudo-gradients using Nesterov momentum, GPA eliminates this complexity by decoupling Nesterov's interpolation constants to enable smooth iterate averaging at every step. Structurally, GPA resembles Schedule-Free but replaces uniform averaging with exponential moving averaging. Empirically, GPA consistently outperforms single-worker DiLoCo and AdamW with reduced memory overhead. GPA achieves speedups of 8.71%, 10.13%, and 9.58% over the AdamW baseline in terms of steps to reach target validation loss for Llama-160M, 1B, and 8B models, respectively. Similarly, on the ImageNet ViT workload, GPA achieves speedups of 7% and 25.5% in the small and large batch settings respectively. Furthermore, we prove that for any base optimizer with $O(\sqrt{T})$ regret, where $T$ is the number of iterations, GPA matches or exceeds the original convergence guarantees depending on the interpolation constants. --- ### DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations Authors: Seong Ho Pahng, Guoye Guan, Benjamin Fefferman, Sahand Hormoz Published: 2025-12-18 Categories: cs.LG, cs.MA, cs.RO, q-bio.QM arXiv: https://arxiv.org/abs/2512.17129v2 Biological systems can form complex three-dimensional structures through the collective behavior of agents that share a common update rule and operate without central control. How such distributed control gives rise to precise global patterns remains a central question not only in developmental biology but also in distributed robotics, programmable matter, and multi-agent learning. Here, we introduce DiffeoMorph, an end-to-end differentiable framework for learning a morphogenesis protocol that guides a population of agents to morph into a target 3D shape. Each agent updates its position and internal state using an SE(3)-equivariant graph neural network, based on its own internal state and signals received from other agents. To train this system, we introduce a new shape-matching loss based on 3D Zernike polynomials, which compares the predicted and target shapes as continuous spatial distributions, not as discrete point clouds, and is invariant to agent ordering, number of agents, and global orientation. To achieve rotation invariance while preserving reflection sensitivity, we include an alignment step that optimally rotates the predicted Zernike spectrum to match the target before computing the loss. We perform benchmarking to establish the advantages of our shape-matching loss over other standard distance metrics for shape comparison tasks. We then demonstrate that DiffeoMorph can form a range of complex shapes from minimally patterned initial conditions. DiffeoMorph provides a general framework for learning distributed control strategies for morphogenesis, swarm robotics, and programmable self-assembly. --- ### Disentangled representations via score-based variational autoencoders Authors: Benjamin S. H. Lyo, Eero P. Simoncelli, Cristina Savin Published: 2025-12-18 Categories: stat.ML, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.17127v1 We present the Score-based Autoencoder for Multiscale Inference (SAMI), a method for unsupervised representation learning that combines the theoretical frameworks of diffusion models and VAEs. By unifying their respective evidence lower bounds, SAMI formulates a principled objective that learns representations through score-based guidance of the underlying diffusion process. The resulting representations automatically capture meaningful structure in the data: it recovers ground truth generative factors in our synthetic dataset, learns factorized, semantic latent dimensions from complex natural images, and encodes video sequences into latent trajectories that are straighter than those of alternative encoders, despite training exclusively on static images. Furthermore, SAMI can extract useful representations from pre-trained diffusion models with minimal additional training. Finally, the explicitly probabilistic formulation provides new ways to identify semantically meaningful axes in the absence of supervised labels, and its mathematical exactness allows us to make formal statements about the nature of the learned representation. Overall, these results indicate that implicit structural information in diffusion models can be made explicit and interpretable through synergistic combination with a variational autoencoder. --- ### The Effect of Negation on CLIP in Medical Imaging: Limitations of Contrastive Language-Image Pretraining Authors: Jasmine Vu, Shivanand Sheshappanavar Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17121v1 Large vision-language models like CLIP are increasingly used in medical imaging tasks due to their ability to align images and text without the need for extensive labeled data. This makes them particularly useful for applications like image retrieval, report generation, and classification in clinical settings. A potential issue to this approach is that CLIP-based models often under perform when interpreting negated phrases, which is especially problematic in the context of medical diagnosing. In this study, we evaluate the Stanford AIMI CheXagent model on its ability to correctly retrieve chest X-ray images using prompts with and without negation. The goal of this project is to understand where this model fails and then use it as a base model to improve its retrieval accuracy by fine tuning methods outlined in previous work. Results from this study show improvement in handling of negation in the CLIP model with a slight decrease in accuracy of positive prompt evaluation. Alongside retrieval accuracy, we examined internal model behavior through token attribution, t-SNE projection, and attention-head ablation to better characterize how each fine tuning approach reshaped the text encoders representation of negated clinical language. Through this work, we hope to better understand the internal behavior of CLIP and improve its handling of negation using clinically relevant language for improving its reliability in medical AI devices. --- ### Digitizing Nepal's Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts Authors: Anjali Sarawgi, Esteban Garces Arias, Christof Zotter Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17111v2 This paper presents the first end-to-end pipeline for Handwritten Text Recognition (HTR) for Old Nepali, a historically significant but low-resource language. We adopt a line-level transcription approach and systematically explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy. Our best model achieves a Character Error Rate (CER) of 4.9\%. In addition, we implement and evaluate decoding strategies and analyze token-level confusions to better understand model behavior and error patterns. Although the evaluation dataset is confidential, we release our training code, model configurations, and evaluation scripts to support further research on HTR for low-resource historical scripts. --- ### Bridging Training and Merging Through Momentum-Aware Optimization Authors: Alireza Moayedikia, Alicia Troncoso Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17109v3 Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature information during training, discard it, then recompute similar information for merging--wasting computation and discarding valuable trajectory data. We introduce a unified framework that maintains factorized momentum and curvature statistics during training, then reuses this information for geometry-aware model composition. The proposed method incurs modest memory overhead (approximately 30% over AdamW) to accumulate task saliency scores that enable curvature-aware merging. These scores, computed as a byproduct of optimization, provide importance estimates comparable to post-hoc Fisher computation while producing merge-ready models directly from training. We establish convergence guarantees for non-convex objectives with approximation error bounded by gradient singular value decay. On natural language understanding benchmarks, curvature-aware parameter selection outperforms magnitude-only baselines across all sparsity levels, with multi-task merging improving 1.6% over strong baselines. The proposed framework exhibits rank-invariant convergence and superior hyperparameter robustness compared to existing low-rank optimizers. By treating the optimization trajectory as a reusable asset rather than discarding it, our approach demonstrates that training-time curvature information suffices for effective model composition, enabling a unified training-merging pipeline. --- ### Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse Authors: Kunjal Panchal, Saayan Mitra, Somdeb Sarkhel, Haoliang Wang, Ishita Dasgupta, Gang Wu, Hui Guan Published: 2025-12-18 Categories: cs.LG, cs.MM arXiv: https://arxiv.org/abs/2512.17108v1 Recent advances in video-language models have enabled powerful applications like video retrieval, captioning, and assembly. However, executing such multi-stage pipelines efficiently on mobile devices remains challenging due to redundant model loads and fragmented execution. We introduce Atom, an on-device system that restructures video-language pipelines for fast and efficient execution. Atom decomposes a billion-parameter model into reusable modules, such as the visual encoder and language decoder, and reuses them across subtasks like captioning, reasoning, and indexing. This reuse-centric design eliminates repeated model loading and enables parallel execution, reducing end-to-end latency without sacrificing performance. On commodity smartphones, Atom achieves 27--33% faster execution compared to non-reuse baselines, with only marginal performance drop ($\leq$ 2.3 Recall@1 in retrieval, $\leq$ 1.5 CIDEr in captioning). These results position Atom as a practical, scalable approach for efficient video-language understanding on edge devices. --- ### Fault Diagnosis and Quantification for Photovoltaic Arrays based on Differentiable Physical Models Authors: Zenan Yang, Yuanliang Li, Jingwei Zhang, Yongjie Liu, Kun Ding Published: 2025-12-18 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2512.17107v1 Accurate fault diagnosis and quantification are essential for the reliable operation and intelligent maintenance of photovoltaic (PV) arrays. However, existing fault quantification methods often suffer from limited efficiency and interpretability. To address these challenges, this paper proposes a novel fault quantification approach for PV strings based on a differentiable fast fault simulation model (DFFSM). The proposed DFFSM accurately models I-V characteristics under multiple faults and provides analytical gradients with respect to fault parameters. Leveraging this property, a gradient-based fault parameters identification (GFPI) method using the Adahessian optimizer is developed to efficiently quantify partial shading, short-circuit, and series-resistance degradation. Experimental results on both simulated and measured I-V curves demonstrate that the proposed GFPI achieves high quantification accuracy across different faults, with the I-V reconstruction error below 3%, confirming the feasibility and effectiveness of the application of differentiable physical simulators for PV system fault diagnosis. --- ### Reinforcement Learning for Self-Improving Agent with Skill Library Authors: Jiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, Lin Lee Cheong Published: 2025-12-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.17102v2 Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt when deployed in new environments. One promising approach is implementing skill libraries that allow agents to learn, validate, and apply new skills. However, current skill library approaches rely primarily on LLM prompting, making consistent skill library implementation challenging. To overcome these challenges, we propose a Reinforcement Learning (RL)-based approach to enhance agents' self-improvement capabilities with a skill library. Specifically, we introduce Skill Augmented GRPO for self-Evolution (SAGE), a novel RL framework that systematically incorporates skills into learning. The framework's key component, Sequential Rollout, iteratively deploys agents across a chain of similar tasks for each rollout. As agents navigate through the task chain, skills generated from previous tasks accumulate in the library and become available for subsequent tasks. Additionally, the framework enhances skill generation and utilization through a Skill-integrated Reward that complements the original outcome-based rewards. Experimental results on AppWorld demonstrate that SAGE, when applied to supervised-finetuned model with expert experience, achieves 8.9% higher Scenario Goal Completion while requiring 26% fewer interaction steps and generating 59% fewer tokens, substantially outperforming existing approaches in both accuracy and efficiency. --- ### UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Data Authors: Justin Li, Efe Sencan, Jasper Zheng Duan, Vitus J. Leung, Stephen Tsaur, Ayse K. Coskun Published: 2025-12-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.17100v2 Machine learning models, particularly deep neural networks, have demonstrated strong performance in classifying complex time series data. However, their black-box nature limits trust and adoption, especially in high-stakes domains such as healthcare. To address this challenge, we introduce UniCoMTE, a model-agnostic framework for generating counterfactual explanations for multivariate time series classifiers. The framework identifies temporal features that most heavily influence a model's prediction by modifying the input sample and assessing its impact on the model's prediction. UniCoMTE is compatible with a wide range of model architectures and operates directly on raw time series inputs. In this study, we evaluate UniCoMTE's explanations on a time series ECG classifier. We quantify explanation quality by comparing our explanations' comprehensibility to comprehensibility of established techniques (LIME and SHAP) and assessing their generalizability to similar samples. Furthermore, clinical utility is assessed through a questionnaire completed by medical experts who review counterfactual explanations presented alongside original ECG samples. Results show that our approach produces concise, stable, and human-aligned explanations that outperform existing methods in both clarity and applicability. By linking model predictions to meaningful signal patterns, the framework advances the interpretability of deep learning models for real-world time series applications. --- ### Predictive Modeling of Maritime Radar Data Using Transformer Architecture Authors: Bjorna Qesaraku, Jan Steckel Published: 2025-12-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17098v2 Maritime autonomous systems require robust predictive capabilities to anticipate vessel motion and environmental dynamics. While transformer architectures have revolutionized AIS-based trajectory prediction and demonstrated feasibility for sonar frame forecasting, their application to maritime radar frame prediction remains unexplored, creating a critical gap given radar's all-weather reliability for navigation. This survey systematically reviews predictive modeling approaches relevant to maritime radar, with emphasis on transformer architectures for spatiotemporal sequence forecasting, where existing representative methods are analyzed according to data type, architecture, and prediction horizon. Our review shows that, while the literature has demonstrated transformer-based frame prediction for sonar sensing, no prior work addresses transformer-based maritime radar frame prediction, thereby defining a clear research gap and motivating a concrete research direction for future work in this area. --- ### DGH: Dynamic Gaussian Hair Authors: Junying Wang, Yuanlu Xu, Edith Tretschk, Ziyan Wang, Anastasia Ianina, Aljaz Bozic, Ulrich Neumann, Tony Tung Published: 2025-12-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17094v1 The creation of photorealistic dynamic hair remains a major challenge in digital human modeling because of the complex motions, occlusions, and light scattering. Existing methods often resort to static capture and physics-based models that do not scale as they require manual parameter fine-tuning to handle the diversity of hairstyles and motions, and heavy computation to obtain high-quality appearance. In this paper, we present Dynamic Gaussian Hair (DGH), a novel framework that efficiently learns hair dynamics and appearance. We propose: (1) a coarse-to-fine model that learns temporally coherent hair motion dynamics across diverse hairstyles; (2) a strand-guided optimization module that learns a dynamic 3D Gaussian representation for hair appearance with support for differentiable rendering, enabling gradient-based learning of view-consistent appearance under motion. Unlike prior simulation-based pipelines, our approach is fully data-driven, scales with training data, and generalizes across various hairstyles and head motion sequences. Additionally, DGH can be seamlessly integrated into a 3D Gaussian avatar framework, enabling realistic, animatable hair for high-fidelity avatar representation. DGH achieves promising geometry and appearance results, providing a scalable, data-driven alternative to physics-based simulation and rendering. --- ### A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving Authors: Timo Pierre Schrader, Lukas Lange, Tobias Kaminski, Simon Razniewski, Annemarie Friedrich Published: 2025-12-18 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.17093v1 The rise of large language models (LLMs) has sparked interest in coding assistants. While general-purpose programming languages are well supported, generating code for domain-specific languages remains a challenging problem for LLMs. In this paper, we focus on the LLM-based generation of code for Answer Set Programming (ASP), a particularly effective approach for finding solutions to combinatorial search problems. The effectiveness of LLMs in ASP code generation is currently hindered by the limited number of examples seen during their initial pre-training phase. In this paper, we introduce a novel ASP-solver-in-the-loop approach for solver-guided instruction-tuning of LLMs to addressing the highly complex semantic parsing task inherent in ASP code generation. Our method only requires problem specifications in natural language and their solutions. Specifically, we sample ASP statements for program continuations from LLMs for unriddling logic puzzles. Leveraging the special property of declarative ASP programming that partial encodings increasingly narrow down the solution space, we categorize them into chosen and rejected instances based on solver feedback. We then apply supervised fine-tuning to train LLMs on the curated data and further improve robustness using a solver-guided search that includes best-of-N sampling. Our experiments demonstrate consistent improvements in two distinct prompting settings on two datasets. --- ### Data Augmentation Supporting a Conversational Agent Designed for Smoking Cessation Support Groups Authors: Salar Hashemitaheri, Ian Harris Published: 2025-12-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.17092v1 Online support groups for smoking cessation are economical and accessible, yet they often face challenges with low user engagement and stigma. The use of an automatic conversational agent would improve engagement by ensuring that all user comments receive a timely response.). We address the challenge of insufficient high-quality data by employing a two-level data augmentation strategy: synthetic data augmentation and real data augmentation. First, we fine-tuned an open source LLM to classify posts from our existing smoking cessation support groups and identify intents with low F1 (precision+recall) scores. Then, for these intents, we generate additional synthetic data using prompt engineering with the GPT model, with an average of 87\% of the generated synthetic posts deemed high quality by human annotators. Overall, the synthetic augmentation process resulted in 43\% of the original posts being selected for augmentation, followed by 140\% synthetic expansion of these posts. Additionally, we scraped more than 10,000 real posts from a related online support context, of which 73\% were validated as good quality by human annotators. Each synthetic or scraped post underwent rigorous validation involving human reviewers to ensure quality and relevance. The validated new data, combined with the original support group posts, formed an augmented dataset used to retrain the intent classifier. Performance evaluation of the retrained model demonstrated a 32\% improvement in F1, confirming the effectiveness of our data augmentation approach. Synthetic and real post augmentation led to similar performance improvements. This study provides a replicable framework for enhancing conversational agent performance in domains where data scarcity is a critical issue. --- ### Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making Authors: Toshiaki Hori, Jonathan DeCastro, Deepak Gopinath, Avinash Balachandran, Guy Rosman Published: 2025-12-18 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2512.17091v2 We propose a new approach for solving planning problems with a hierarchical structure, fusing reinforcement learning and MPC planning. Our formulation tightly and elegantly couples the two planning paradigms. It leverages reinforcement learning actions to inform the MPPI sampler, and adaptively aggregates MPPI samples to inform the value estimation. The resulting adaptive process leverages further MPPI exploration where value estimates are uncertain, and improves training robustness and the overall resulting policies. This results in a robust planning approach that can handle complex planning problems and easily adapts to different applications, as demonstrated over several domains, including race driving, modified Acrobot, and Lunar Lander with added obstacles. Our results in these domains show better data efficiency and overall performance in terms of both rewards and task success, with up to a 72% increase in success rate compared to existing approaches, as well as accelerated convergence (x2.1) compared to non-adaptive sampling. --- ### How to Square Tensor Networks and Circuits Without Squaring Them Authors: Lorenzo Loconte, Adrián Javaloy, Antonio Vergari Published: 2025-12-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.17090v2 Squared tensor networks (TNs) and their extension as computational graphs--squared circuits--have been used as expressive distribution estimators, yet supporting closed-form marginalization. However, the squaring operation introduces additional complexity when computing the partition function or marginalizing variables, which hinders their applicability in ML. To solve this issue, canonical forms of TNs are parameterized via unitary matrices to simplify the computation of marginals. However, these canonical forms do not apply to circuits, as they can represent factorizations that do not directly map to a known TN. Inspired by the ideas of orthogonality in canonical forms and determinism in circuits enabling tractable maximization, we show how to parameterize squared circuits to overcome their marginalization overhead. Our parameterizations unlock efficient marginalization even in factorizations different from TNs, but encoded as circuits, whose structure would otherwise make marginalization computationally hard. Finally, our experiments on distribution estimation show how our proposed conditions in squared circuits come with no expressiveness loss, while enabling more efficient learning. --- ### Value Under Ignorance in Universal Artificial Intelligence Authors: Cole Wyeth, Marcus Hutter Published: 2025-12-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.17086v2 We generalize the AIXI reinforcement learning agent to admit a wider class of utility functions. Assigning a utility to each possible interaction history forces us to confront the ambiguity that some hypotheses in the agent's belief distribution only predict a finite prefix of the history, which is sometimes interpreted as implying a chance of death equal to a quantity called the semimeasure loss. This death interpretation suggests one way to assign utilities to such history prefixes. We argue that it is as natural to view the belief distributions as imprecise probability distributions, with the semimeasure loss as total ignorance. This motivates us to consider the consequences of computing expected utilities with Choquet integrals from imprecise probability theory, including an investigation of their computability level. We recover the standard recursive value function as a special case. However, our most general expected utilities under the death interpretation cannot be characterized as such Choquet integrals. --- ### When F1 Fails: Granularity-Aware Evaluation for Dialogue Topic Segmentation Authors: Michael H. Coen Published: 2025-12-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.17083v3 Dialogue topic segmentation supports summarization, retrieval, memory management, and conversational continuity. Despite decades of work, evaluation practice remains dominated by strict boundary matching and F1-based metrics. Modern large language model (LLM) based conversational systems increasingly rely on segmentation to manage conversation history beyond fixed context windows. In such systems, unstructured context accumulation degrades efficiency and coherence. This paper introduces an evaluation framework that reports boundary density and segment alignment diagnostics (purity and coverage) alongside window-tolerant F1 (W-F1). By separating boundary scoring from boundary selection, we evaluate segmentation quality across density regimes rather than at a single operating point. Cross-dataset evaluation shows that reported performance differences often reflect annotation granularity mismatch rather than boundary placement quality alone. We evaluate structurally distinct segmentation strategies across eight dialogue datasets spanning task-oriented, open-domain, meeting-style, and synthetic interactions. Boundary-based metrics are strongly coupled to boundary density: threshold sweeps produce larger W-F1 changes than switching between methods. These findings support viewing topic segmentation as a granularity selection problem rather than prediction of a single correct boundary set. This motivates separating boundary scoring from boundary selection for analyzing and tuning segmentation under varying annotation granularities. --- ### Interpretable Similarity of Synthetic Image Utility Authors: Panagiota Gatoula, George Dimas, Dimitris K. Iakovidis Published: 2025-12-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17080v2 Synthetic medical image data can unlock the potential of deep learning (DL)-based clinical decision support (CDS) systems through the creation of large scale, privacy-preserving, training sets. Despite the significant progress in this field, there is still a largely unanswered research question: "How can we quantitatively assess the similarity of a synthetically generated set of images with a set of real images in a given application domain?". Today, answers to this question are mainly provided via user evaluation studies, inception-based measures, and the classification performance achieved on synthetic images. This paper proposes a novel measure to assess the similarity between synthetically generated and real sets of images, in terms of their utility for the development of DL-based CDS systems. Inspired by generalized neural additive models, and unlike inception-based measures, the proposed measure is interpretable (Interpretable Utility Similarity, IUS), explaining why a synthetic dataset could be more useful than another one in the context of a CDS system based on clinically relevant image features. The experimental results on publicly available benchmark datasets from various color medical imaging modalities including endoscopic, dermoscopic and fundus imaging, indicate that selecting synthetic images of high utility similarity using IUS can result in relative improvements of up to 54.6% in terms of classification performance. The generality of IUS for synthetic data assessment is demonstrated also for grayscale X-ray and ultrasound imaging modalities. IUS implementation is available at https://github.com/innoisys/ius. --- ### Can Large Reasoning Models Improve Accuracy on Mathematical Tasks Using Flawed Thinking? Authors: Saraswathy Amjith, Mihika Dusad, Neha Muramalla, Shweta Shah Published: 2025-12-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.17079v1 Chain-of-thought (CoT) prompting has become central to mathematical reasoning in large language models, yet models remain brittle to early errors: a single arithmetic slip or unjustified inference typically propagates uncorrected to an incorrect final answer. We investigate whether training on intentionally flawed reasoning traces can teach models to detect and recover from such errors without degrading standard problem-solving ability. Using competition-level problems from MATH-lighteval, we generate CoT prefixes containing exactly one controlled error, either a calculation error (sign flips, dropped terms) or a reasoning error (misapplied rules, unjustified logical steps), and fine-tune Qwen3-4B with GRPO using a binary final-answer reward. Our Mixed-CoT-RL model matches standard RL on clean problems (41% vs 41%) while substantially outperforming it on problems prefilled with flawed reasoning (24% vs 19%). Notably, clean-only RL fine-tuning degrades robustness below the untuned baseline 19% vs. 20%), indicating that conventional training increases susceptibility to misleading prefills. Among error types, training on reasoning errors yields greater robustness gains than calculation errors alone, with mixed training performing best. These findings demonstrate that exposure to flawed traces during training can improve error-recovery behavior without sacrificing accuracy, suggesting a path toward more robust mathematical reasoning in LLMs. --- ### Perturb Your Data: Paraphrase-Guided Training Data Watermarking Authors: Pranav Shetty, Mirazul Haque, Petr Babkin, Zhiqiang Ma, Xiaomo Liu, Manuela Veloso Published: 2025-12-18 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.17075v1 Training data detection is critical for enforcing copyright and data licensing, as Large Language Models (LLM) are trained on massive text corpora scraped from the internet. We present SPECTRA, a watermarking approach that makes training data reliably detectable even when it comprises less than 0.001% of the training corpus. SPECTRA works by paraphrasing text using an LLM and assigning a score based on how likely each paraphrase is, according to a separate scoring model. A paraphrase is chosen so that its score closely matches that of the original text, to avoid introducing any distribution shifts. To test whether a suspect model has been trained on the watermarked data, we compare its token probabilities against those of the scoring model. We demonstrate that SPECTRA achieves a consistent p-value gap of over nine orders of magnitude when detecting data used for training versus data not used for training, which is greater than all baselines tested. SPECTRA equips data owners with a scalable, deploy-before-release watermark that survives even large-scale LLM training. --- ### Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation Authors: Zhenyu Liu, Yunzhen Liu, Zehao Fan, Garrett Gagnon, Yayue Hou, Nan Wu, Yangwook Kang, Liu Liu Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17073v1 Mixture-of-Experts (MoE) models scale capacity via sparse activation but stress memory and bandwidth. Offloading alleviates GPU memory by fetching experts on demand, yet token-level routing causes irregular transfers that make inference I/O-bound. Static uniform quantization reduces traffic but degrades accuracy under aggressive compression by ignoring expert heterogeneity. We present Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation, which performs router-guided precision restoration using precomputed low-rank compensators. At inference time, our method transfers compact low-rank factors with Top-n (n<k) experts per token and applies compensation to them, keeping others low-bit. Integrated with offloading on GPU and GPU-NDP systems, our method delivers a superior bandwidth-accuracy trade-off and improved throughput. --- ### Bots Don't Sit Still: A Longitudinal Study of Bot Behaviour Change, Temporal Drift, and Feature-Structure Evolution Authors: Ohoud Alzahrani, Russell Beale, Bob Hendley Published: 2025-12-18 Categories: cs.HC, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2512.17067v1 Social bots are now deeply embedded in online platforms for promotion, persuasion, and manipulation. Most bot-detection systems still treat behavioural features as static, implicitly assuming bots behave stationarily over time. We test that assumption for promotional Twitter bots, analysing change in both individual behavioural signals and the relationships between them. Using 2,615 promotional bot accounts and 2.8M tweets, we build yearly time series for ten content-based meta-features. Augmented Dickey-Fuller and KPSS tests plus linear trends show all ten are non-stationary: nine increase over time, while language diversity declines slightly. Stratifying by activation generation and account age reveals systematic differences: second-generation bots are most active and link-heavy; short-lived bots show intense, repetitive activity with heavy hashtag/URL use; long-lived bots are less active but more linguistically diverse and use emojis more variably. We then analyse co-occurrence across generations using 18 interpretable binary features spanning actions, topic similarity, URLs, hashtags, sentiment, emojis, and media (153 pairs). Chi-square tests indicate almost all pairs are dependent. Spearman correlations shift in strength and sometimes polarity: many links (e.g. multiple hashtags with media; sentiment with URLs) strengthen, while others flip from weakly positive to weakly or moderately negative. Later generations show more structured combinations of cues. Taken together, these studies provide evidence that promotional social bots adapt over time at both the level of individual meta-features and the level of feature interdependencies, with direct implications for the design and evaluation of bot-detection systems trained on historical behavioural features. --- ### Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations Authors: Suhaib Abdurahman, Farzan Karimi-Malekabadi, Chenxiao Yu, Nour S. Kteily, Morteza Dehghani Published: 2025-12-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.17066v1 Human conflict is often attributed to threats against material conditions and symbolic values, yet it remains unclear how they interact and which dominates. Progress is limited by weak causal control, ethical constraints, and scarce temporal data. We address these barriers using simulations of large language model (LLM)-driven agents in virtual societies, independently varying realistic and symbolic threat while tracking actions, language, and attitudes. Representational analyses show that the underlying LLM encodes realistic threat, symbolic threat, and hostility as distinct internal states, that our manipulations map onto them, and that steering these states causally shifts behavior. Our simulations provide a causal account of threat-driven conflict over time: realistic threat directly increases hostility, whereas symbolic threat effects are weaker, fully mediated by ingroup bias, and increase hostility only when realistic threat is absent. Non-hostile intergroup contact buffers escalation, and structural asymmetries concentrate hostility among majority groups. --- ### XLM: A Python package for non-autoregressive language models Authors: Dhruvesh Patel, Durga Prasad Maram, Sai Sreenivas Chintha, Benjamin Rozonoyer, Andrew McCallum Published: 2025-12-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.17065v1 In recent years, there has been a resurgence of interest in non-autoregressive text generation in the context of general language modeling. Unlike the well-established autoregressive language modeling paradigm, which has a plethora of standard training and inference libraries, implementations of non-autoregressive language modeling have largely been bespoke making it difficult to perform systematic comparisons of different methods. Moreover, each non-autoregressive language model typically requires it own data collation, loss, and prediction logic, making it challenging to reuse common components. In this work, we present the XLM python package, which is designed to make implementing small non-autoregressive language models faster with a secondary goal of providing a suite of small pre-trained models (through a companion xlm-models package) that can be used by the research community. The code is available at https://github.com/dhruvdcoder/xlm-core. --- ### On the Role of Contextual Information and Ego States in LLM Agent Behavior for Transactional Analysis Dialogues Authors: Monika Zamojska, Jarosław A. Chudziak Published: 2025-12-18 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2512.17060v1 LLM-powered agents are now used in many areas, from customer support to education, and there is increasing interest in their ability to act more like humans. This includes fields such as social, political, and psychological research, where the goal is to model group dynamics and social behavior. However, current LLM agents often lack the psychological depth and consistency needed to capture the real patterns of human thinking. They usually provide direct or statistically likely answers, but they miss the deeper goals, emotional conflicts, and motivations that drive real human interactions. This paper proposes a Multi-Agent System (MAS) inspired by Transactional Analysis (TA) theory. In the proposed system, each agent is divided into three ego states - Parent, Adult, and Child. The ego states are treated as separate knowledge structures with their own perspectives and reasoning styles. To enrich their response process, they have access to an information retrieval mechanism that allows them to retrieve relevant contextual information from their vector stores. This architecture is evaluated through ablation tests in a simulated dialogue scenario, comparing agents with and without information retrieval. The results are promising and open up new directions for exploring how psychologically grounded structures can enrich agent behavior. The contribution is an agent architecture that integrates Transactional Analysis theory with contextual information retrieval to enhance the realism of LLM-based multi-agent simulations. --- ### Universal consistency of the $k$-NN rule in metric spaces and Nagata dimension. III Authors: Vladimir G. Pestov Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17058v3 We establish the last missing link allowing to describe those complete separable metric spaces $X$ in which the $k$ nearest neighbour classifier is universally consistent, both in combinatorial terms of dimension theory and via a fundamental property of real analysis. The following are equivalent: (1) The $k$-nearest neighbour classifier is universally consistent in $X$, (2) The strong Lebesgue--Besicovitch differentiation property holds in $X$ for every locally finite Borel measure, (3) $X$ is sigma-finite dimensional in the sense of Jun-Iti Nagata. The equivalence (2)$\iff$(3) was announced by Preiss (1983), while a detailed proof of the implication (3)$\Rightarrow$(2) has only appeared in Assouad and Quentin de Gromard (2006). The implication (2)$\Rightarrow$(1) was established by Cérou and Guyader (2006). We prove the implication (1)$\Rightarrow$(3). We further show that the weak (instead of strong) Lebesgue--Besicovitch property is insufficient for the consistency of the $k$-NN rule, as witnessed, for example, by the Heisenberg group (here we correct a wrong claim made in the previous article (Kumari and Pestov 2024)). A bit counter-intuitively, there is a metric on the real line uniformly equivalent to the usual distance but under which the $k$-NN classifier fails. Finally, another equivalent condition that can be added to the above is the Cover--Hart property: (4) the error of the $1$-nearest neighbour classifier is asymptotically at most twice as bad as the Bayes error. --- ### Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQL Authors: Khushboo Thaker, Yony Bresler Published: 2025-12-18 Categories: cs.CL, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2512.17053v3 Deploying accurate Text-to-SQL systems at the enterprise level faces a difficult trilemma involving cost, security and performance. Current solutions force enterprises to choose between expensive, proprietary Large Language Models (LLMs) and low-performing Small Language Models (SLMs). Efforts to improve SLMs often rely on distilling reasoning from large LLMs using unstructured Chain-of-Thought (CoT) traces, a process that remains inherently ambiguous. Instead, we hypothesize that a formal, structured reasoning representation provides a clearer, more reliable teaching signal, as the Text-to-SQL task requires explicit and precise logical steps. To evaluate this hypothesis, we propose Struct-SQL, a novel Knowledge Distillation (KD) framework that trains an SLM to emulate a powerful large LLM. Consequently, we adopt a query execution plan as a formal blueprint to derive this structured reasoning. Our SLM, distilled with structured CoT, achieves an absolute improvement of 8.1% over an unstructured CoT distillation baseline. A detailed error analysis reveals that a key factor in this gain is a marked reduction in syntactic errors. This demonstrates that teaching a model to reason using a structured logical blueprint is beneficial for reliable SQL generation in SLMs. --- ### Dynamic Tool Dependency Retrieval for Lightweight Function Calling Authors: Bhrij Patel, Davide Belli, Amir Jalalirad, Maximilian Arnold, Aleksandr Ermolov, Bence Major Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17052v4 Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a retrieval module to select relevant tools, improving performance and reducing context length. However, existing retrieval methods rely on static and limited inputs, failing to capture multi-step tool dependencies and evolving task context. This limitation often introduces irrelevant tools that mislead the agent, degrading efficiency and accuracy. We propose Dynamic Tool Dependency Retrieval (DTDR), a lightweight retrieval method that conditions on both the initial query and the evolving tool calling plan. DTDR models tool dependencies from function calling demonstrations, enabling adaptive retrieval as plans unfold. We benchmark DTDR against state-of-the-art retrieval methods across multiple datasets and LLM backbones, evaluating retrieval precision, downstream task accuracy, and computational efficiency. Additionally, we explore strategies to integrate retrieved tools into prompts. Our results show that DTDR improves function calling success rates between $23\%$ and $104\%$ compared to state-of-the-art static retrievers. --- ### SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples Authors: Haoye Lu, Yaoliang Yu, Darren Lo Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17051v2 In many real-world scenarios, obtaining fully observed samples is prohibitively expensive or even infeasible, while partial and noisy observations are comparatively easy to collect. In this work, we study distribution restoration with abundant noisy samples, assuming the corruption process is available as a black-box generator. We show that this task can be framed as a one-sided entropic optimal transport problem and solved via an EM-like algorithm. We further provide a test criterion to determine whether the true underlying distribution is recoverable under per-sample information loss, and show that in otherwise unrecoverable cases, a small number of clean samples can render the distribution largely recoverable. Building on these insights, we introduce SFBD-OMNI, a bridge model-based framework that maps corrupted sample distributions to the ground-truth distribution. Our method generalizes Stochastic Forward-Backward Deconvolution (SFBD; Lu et al., 2025) to handle arbitrary measurement models beyond Gaussian corruption. Experiments across benchmark datasets and diverse measurement settings demonstrate significant improvements in both qualitative and quantitative performance. --- ### Another Fit Bites the Dust: Conformal Prediction as a Calibration Standard for Machine Learning in High-Energy Physics Authors: Jack Y. Araz, Michael Spannowsky Published: 2025-12-18 Categories: hep-ph, cs.AI, hep-ex arXiv: https://arxiv.org/abs/2512.17048v1 Machine-learning techniques are essential in modern collider research, yet their probabilistic outputs often lack calibrated uncertainty estimates and finite-sample guarantees, limiting their direct use in statistical inference and decision-making. Conformal prediction (CP) provides a simple, distribution-free framework for calibrating arbitrary predictive models without retraining, yielding rigorous uncertainty quantification with finite-sample coverage guarantees under minimal exchangeability assumptions, without reliance on asymptotics, limit theorems, or Gaussian approximations. In this work, we investigate CP as a unifying calibration layer for machine-learning applications in high-energy physics. Using publicly available collider datasets and a diverse set of models, we show that a single conformal formalism can be applied across regression, binary and multi-class classification, anomaly detection, and generative modelling, converting raw model outputs into statistically valid prediction sets, typicality regions, and p-values with controlled false-positive rates. While conformal prediction does not improve raw model performance, it enforces honest uncertainty quantification and transparent error control. We argue that conformal calibration should be adopted as a standard component of machine-learning pipelines in collider physics, enabling reliable interpretation, robust comparisons, and principled statistical decisions in experimental and phenomenological analyses. --- ### UniRel: Relation-Centric Knowledge Graph Question Answering with RL-Tuned LLM Reasoning Authors: Yinxu Tang, Chengsong Huang, Jiaxin Huang, William Yeoh Published: 2025-12-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.17043v2 Knowledge Graph Question Answering (KGQA) has largely focused on entity-centric queries that return a single answer entity. However, many real-world questions are inherently relational, aiming to understand how entities are associated rather than which entity satisfies a query. In this work, we introduce relation-centric KGQA, a complementary setting in which the answer is a subgraph that represents the semantic relations among entities. The main challenge lies in the abundance of candidate subgraphs, where trivial or overly common connections often obscure the identification of unique and informative answers. To tackle this, we propose UniRel, a unified modular framework that combines a subgraph retriever with an LLM fine-tuned using reinforcement learning. The framework uses a reward function to prefer compact and specific subgraphs with informative relations and low-degree intermediate entities. Experiments show that UniRel improves connectivity and reward over Prompting baselines and generalizes well to unseen entities and relations. Moreover, UniRel can be applied to conventional entity-centric KGQA, achieving competitive or improved performance in several settings. --- ### Security Risks of Agentic Vehicles: A Systematic Analysis of Cognitive and Cross-Layer Threats Authors: Ali Eslami, Jiangbo Yu Published: 2025-12-18 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2512.17041v1 Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles (AgVs), with capabilities such as memory-based personalization, goal interpretation, strategic reasoning, and tool-mediated assistance. While frameworks such as the OWASP Agentic AI Security Risks highlight vulnerabilities in reasoning-driven AI systems, they are not designed for safety-critical cyber-physical platforms such as vehicles, nor do they account for interactions with other layers such as perception, communication, and control layers. This paper investigates security threats in AgVs, including OWASP-style risks and cyber-attacks from other layers affecting the agentic layer. By introducing a role-based architecture for agentic vehicles, consisting of a Personal Agent and a Driving Strategy Agent, we will investigate vulnerabilities in both agentic AI layer and cross-layer risks, including risks originating from upstream layers (e.g., perception layer, control layer, etc.). A severity matrix and attack-chain analysis illustrate how small distortions can escalate into misaligned or unsafe behavior in both human-driven and autonomous vehicles. The resulting framework provides the first structured foundation for analyzing security risks of agentic AI in both current and emerging vehicle platforms. --- ### Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation Authors: Min-Jung Kim, Jeongho Kim, Hoiyeong Jin, Junha Hyung, Jaegul Choo Published: 2025-12-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17040v1 Recent progress in video diffusion models has spurred growing interest in camera-controlled novel-view video generation for dynamic scenes, aiming to provide creators with cinematic camera control capabilities in post-production. A key challenge in camera-controlled video generation is ensuring fidelity to the specified camera pose, while maintaining view consistency and reasoning about occluded geometry from limited observations. To address this, existing methods either train trajectory-conditioned video generation model on trajectory-video pair dataset, or estimate depth from the input video to reproject it along a target trajectory and generate the unprojected regions. Nevertheless, existing methods struggle to generate camera-pose-faithful, high-quality videos for two main reasons: (1) reprojection-based approaches are highly susceptible to errors caused by inaccurate depth estimation; and (2) the limited diversity of camera trajectories in existing datasets restricts learned models. To address these limitations, we present InfCam, a depth-free, camera-controlled video-to-video generation framework with high pose fidelity. The framework integrates two key components: (1) infinite homography warping, which encodes 3D camera rotations directly within the 2D latent space of a video diffusion model. Conditioning on this noise-free rotational information, the residual parallax term is predicted through end-to-end training to achieve high camera-pose fidelity; and (2) a data augmentation pipeline that transforms existing synthetic multiview datasets into sequences with diverse trajectories and focal lengths. Experimental results demonstrate that InfCam outperforms baseline methods in camera-pose accuracy and visual fidelity, generalizing well from synthetic to real-world data. Link to our project page:https://emjay73.github.io/InfCam/ --- ### GB-DQN: Gradient Boosted DQN Models for Non-stationary Reinforcement Learning Authors: Chang-Hwan Lee, Chanseung Lee Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17034v1 Non-stationary environments pose a fundamental challenge for deep reinforcement learning, as changes in dynamics or rewards invalidate learned value functions and cause catastrophic forgetting. We propose \emph{Gradient-Boosted Deep Q-Networks (GB-DQN)}, an adaptive ensemble method that addresses model drift through incremental residual learning. Instead of retraining a single Q-network, GB-DQN constructs an additive ensemble in which each new learner is trained to approximate the Bellman residual of the current ensemble after drift. We provide theoretical results showing that each boosting step reduces the empirical Bellman residual and that the ensemble converges to the post-drift optimal value function under standard assumptions. Experiments across a diverse set of control tasks with controlled dynamics changes demonstrate faster recovery, improved stability, and greater robustness compared to DQN and common non-stationary baselines. --- ### Adversarial VR: An Open-Source Testbed for Evaluating Adversarial Robustness of VR Cybersickness Detection and Mitigation Authors: Istiak Ahmed, Ripan Kumar Kundu, Khaza Anuarul Hoque Published: 2025-12-18 Categories: cs.CR, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.17029v1 Deep learning (DL)-based automated cybersickness detection methods, along with adaptive mitigation techniques, can enhance user comfort and interaction. However, recent studies show that these DL-based systems are susceptible to adversarial attacks; small perturbations to sensor inputs can degrade model performance, trigger incorrect mitigation, and disrupt the user's immersive experience (UIX). Additionally, there is a lack of dedicated open-source testbeds that evaluate the robustness of these systems under adversarial conditions, limiting the ability to assess their real-world effectiveness. To address this gap, this paper introduces Adversarial-VR, a novel real-time VR testbed for evaluating DL-based cybersickness detection and mitigation strategies under adversarial conditions. Developed in Unity, the testbed integrates two state-of-the-art (SOTA) DL models: DeepTCN and Transformer, which are trained on the open-source MazeSick dataset, for real-time cybersickness severity detection and applies a dynamic visual tunneling mechanism that adjusts the field-of-view based on model outputs. To assess robustness, we incorporate three SOTA adversarial attacks: MI-FGSM, PGD, and C&W, which successfully prevent cybersickness mitigation by fooling DL-based cybersickness models' outcomes. We implement these attacks using a testbed with a custom-built VR Maze simulation and an HTC Vive Pro Eye headset, and we open-source our implementation for widespread adoption by VR developers and researchers. Results show that these adversarial attacks are capable of successfully fooling the system. For instance, the C&W attack results in a $5.94x decrease in accuracy for the Transformer-based cybersickness model compared to the accuracy without the attack. --- ### A Women's Health Benchmark for Large Language Models Authors: Victoria-Elisabeth Gruber, Razvan Marinescu, Diego Fajardo, Amin H. Nassar, Christopher Arkfeld, Alexandria Ludlow, Shama Patel, Mehrnoosh Samaei, Valerie Klug, Anna Huber, Marcel Gühner, Albert Botta i Orfila et al. Published: 2025-12-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.17028v1 As large language models (LLMs) become primary sources of health information for millions, their accuracy in women's health remains critically unexamined. We introduce the Women's Health Benchmark (WHB), the first benchmark evaluating LLM performance specifically in women's health. Our benchmark comprises 96 rigorously validated model stumps covering five medical specialties (obstetrics and gynecology, emergency medicine, primary care, oncology, and neurology), three query types (patient query, clinician query, and evidence/policy query), and eight error types (dosage/medication errors, missing critical information, outdated guidelines/treatment recommendations, incorrect treatment advice, incorrect factual information, missing/incorrect differential diagnosis, missed urgency, and inappropriate recommendations). We evaluated 13 state-of-the-art LLMs and revealed alarming gaps: current models show approximately 60\% failure rates on the women's health benchmark, with performance varying dramatically across specialties and error types. Notably, models universally struggle with "missed urgency" indicators, while newer models like GPT-5 show significant improvements in avoiding inappropriate recommendations. Our findings underscore that AI chatbots are not yet fully able of providing reliable advice in women's health. --- ### Unexpected Knowledge: Auditing Wikipedia and Grokipedia Search Recommendations Authors: Erica Coppolillo, Simone Mungari Published: 2025-12-18 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.17027v1 Encyclopedic knowledge platforms are key gateways through which users explore information online. The recent release of Grokipedia, a fully AI-generated encyclopedia, introduces a new alternative to traditional, well-established platforms like Wikipedia. In this context, search engine mechanisms play an important role in guiding users exploratory paths, yet their behavior across different encyclopedic systems remains underexplored. In this work, we address this gap by providing the first comparative analysis of search engine in Wikipedia and Grokipedia. Using nearly 10,000 neutral English words and their substrings as queries, we collect over 70,000 search engine results and examine their semantic alignment, overlap, and topical structure. We find that both platforms frequently generate results that are weakly related to the original query and, in many cases, surface unexpected content starting from innocuous queries. Despite these shared properties, the two systems often produce substantially different recommendation sets for the same query. Through topical annotation and trajectory analysis, we further identify systematic differences in how content categories are surfaced and how search engine results evolve over multiple stages of exploration. Overall, our findings show that unexpected search engine outcomes are a common feature of both the platforms, even though they exhibit discrepancies in terms of topical distribution and query suggestions. --- ### FORMSpoT: Revealing Fine-Scale Forest Disturbances from Nation-Wide 1.5 m Forest Canopy Height Time Series Authors: Martin Schwartz, Fajwel Fogel, Nikola Besic, Damien Robert, Louis Geist, Jean-Pierre Renaud, Jean-Matthieu Monnet, Clemens Mosig, Cédric Vega, Alexandre d'Aspremont, Loic Landrieu, Philippe Ciais Published: 2025-12-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17021v2 Current large-scale satellite-based forest disturbance monitoring systems operate at 10-30~m resolution, too coarse to detect changes at the scale of individual trees and resulting in a systematic underestimation of forest disturbances. Here, we introduce FORMSpoT (Forest Mapping with SPOT Time series), a decade-long (2014-2024), country-scale mapping of forest canopy height at 1.5 m resolution over France, together with FORMSpoT-$Δ$, annual disturbance polygons derived from height differences in the FORMSpoT time series. Canopy heights were derived from annual SPOT-6/7 composites using a hierarchical transformer model (PVTv2) trained on high-resolution airborne laser scanning (ALS) data. To enable robust change detection, we developed a post-processing pipeline combining co-registration and spatio-temporal total variation denoising. We find that (1) the French disturbance regime is dominated by small events. Sub-100 m$^{2}$ disturbances alone represent 72% of all events, and disturbances below 0.1 ha account for 97% of events and 39% of the disturbed area. These events are largely missed by Sentinel-1/2 and Landsat-based products. (2) Validated against successive ALS revisits across 19 sites and 5,087 NFI plot revisits, FORMSpoT-$Δ$ provides reliable detection (F1>0.8) above 100 m$^{2}$ while retaining sensitivity to finer events that coarser products do not capture. (3) At the national scale, FORMSpoT-$Δ$ resolves contrasted disturbance regimes, from clear-cut-dominated dynamics in maritime pine plantations to diffuse, smaller disturbance events in mountain forests, and captures their temporal dynamics, including the salvage-logging signature of the 2017-2022 bark beetle crisis in northeastern France --- ### 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation Authors: Chiao-An Yang, Ryo Hachiuma, Sifei Liu, Subhashree Radhakrishnan, Raymond A. Yeh, Yu-Chiang Frank Wang, Min-Hung Chen Published: 2025-12-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17012v4 Despite advances in Multimodal LLMs (MLLMs), their ability to reason over 3D structures and temporal dynamics remains limited, constrained by weak 4D perception and temporal understanding. Existing 3D and 4D Video Question Answering (VQA) benchmarks also emphasize static scenes and lack region-level prompting. We tackle these issues by introducing: (a) 4D-RGPT, a specialized MLLM designed to capture 4D representations from video inputs with enhanced temporal perception; (b) Perceptual 4D Distillation (P4D), a training framework that transfers 4D representations from a frozen expert model into 4D-RGPT for comprehensive 4D perception; and (c) R4D-Bench, a benchmark for depth-aware dynamic scenes with region-level prompting, built via a hybrid automated and human-verified pipeline. Our 4D-RGPT achieves notable improvements on both existing 4D VQA benchmarks and the proposed R4D-Bench benchmark. --- ### Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs Authors: Junbo Li, Peng Zhou, Rui Meng, Meet P. Vadera, Lihong Li, Yang Li Published: 2025-12-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17008v2 Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Relative Policy Optimization (GRPO) algorithm to multi-turn tasks exposes notable limitations, particularly in scenarios requiring long-horizon reasoning. To address these challenges, we investigate more stable and effective advantage estimation strategies, especially for multi-turn settings. We first explore Proximal Policy Optimization (PPO) as an alternative and find it to be more robust than GRPO. To further enhance PPO in multi-turn scenarios, we introduce turn-PPO, a variant that operates on a turn-level MDP formulation, as opposed to the commonly used token-level MDP. Our results on the WebShop and Sokoban datasets demonstrate the effectiveness of turn-PPO, both with and without long reasoning components. --- ### A Benchmark for Omni-Modal Reasoning in Long Videos Authors: Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan, Jinxing Zhou, Sahal Shaji Mullappilly, Mohammad Almansoori, Noor Ahsan, Beknur Kalmakhanbet, Sambal Shikhar, Rishabh Lalla, Jean Lahoud, Mariette Awad, Fahad Shahbaz Khan et al. Published: 2025-12-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.16978v2 Long-form omni-modal video understanding requires integrating vision, speech, and ambient audio with coherent long-context reasoning. Existing video benchmarks often trade off temporal scale, modality coverage, open-ended interaction, and interpretable scoring. To address this gap, we introduce LongShOTBench, a long video understanding benchmark designed around three coupled goals: holistic omni-modal integration, intent-driven open-ended interaction, and rubric-level diagnosis. It builds single- and multi-turn questions from real viewing scenarios, with systematic tasks probing visual, speech, ambient-audio, temporal, and cross-modal reasoning. Each item includes a reference answer and a weighted criterion-level rubric, letting evaluation identify which perceptual facts, temporal links, modality-grounding requirements, and reasoning steps are satisfied or missed. All samples are manually verified to improve grounding, clarity, and rubric reliability. We also introduce LongShOTAgent, a training-free omni-modal evidence-seeking agent coupling full-video preprocessing with targeted retrieval, query-adaptive segment refinement, and explicit claim verification over visual, speech, and non-speech audio evidence. Its iterative search-refine-verify loop exposes intermediate evidence and lets modality-specific specialists re-analyze relevant moments before answering. We evaluate 105 video-capable models spanning open-source omni-modal models, vision-language systems, audio LLMs, agentic pipelines and closed-source APIs. Current MLLMs remain far from saturating LongShOTBench, while our LongShOTAgent is the strongest training-free system, reaching 66.64% overall. By releasing the benchmark, leaderboard, and method, we provide a shared, interpretable testbed for advancing long-form omni-modal video reasoning. Code, data, and the leaderboard are available at https://longshot.cvmbzuai.com/. --- ### Endo-SemiS: Towards Robust Semi-Supervised Image Segmentation for Endoscopic Video Authors: Hao Li, Daiwei Lu, Xing Yao, Nicholas Kavoussi, Ipek Oguz Published: 2025-12-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.16977v1 In this paper, we present Endo-SemiS, a semi-supervised segmentation framework for providing reliable segmentation of endoscopic video frames with limited annotation. EndoSemiS uses 4 strategies to improve performance by effectively utilizing all available data, particularly unlabeled data: (1) Cross-supervision between two individual networks that supervise each other; (2) Uncertainty-guided pseudo-labels from unlabeled data, which are generated by selecting high-confidence regions to improve their quality; (3) Joint pseudolabel supervision, which aggregates reliable pixels from the pseudo-labels of both networks to provide accurate supervision for unlabeled data; and (4) Mutual learning, where both networks learn from each other at the feature and image levels, reducing variance and guiding them toward a consistent solution. Additionally, a separate corrective network that utilizes spatiotemporal information from endoscopy video to improve segmentation performance. Endo-SemiS is evaluated on two clinical applications: kidney stone laser lithotomy from ureteroscopy and polyp screening from colonoscopy. Compared to state-of-the-art segmentation methods, Endo-SemiS substantially achieves superior results on both datasets with limited labeled data. The code is publicly available at https://github.com/MedICL-VU/Endo-SemiS --- ### InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression Authors: Haotian Ye, Qiyuan He, Jiaqi Han, Puheng Li, Jiaojiao Fan, Zekun Hao, Fitsum Reda, Yogesh Balaji, Huayu Chen, Sheng Liu, Angela Yao, James Zou et al. Published: 2025-12-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.16975v3 Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which rigidly compress all content at a fixed rate, leading to redundancy or information loss. Drawing inspiration from Shannon's information theory, this paper introduces InfoTok, a principled framework for adaptive video tokenization. We rigorously prove that existing data-agnostic training methods are suboptimal in representation length, and present a novel evidence lower bound (ELBO)-based algorithm that approaches theoretical optimality. Leveraging this framework, we develop a transformer-based adaptive compressor that enables adaptive tokenization. Empirical results demonstrate state-of-the-art compression performance, saving 20% tokens without influence on performance, and achieving 2.3x compression rates while still outperforming prior heuristic adaptive approaches. By allocating tokens according to informational richness, InfoTok enables a more compressed yet accurate tokenization for video representation, offering valuable insights for future research. --- ### PAACE: A Plan-Aware Automated Agent Context Engineering Framework Authors: Kamer Ali Yuksel Published: 2025-12-18 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2512.16970v1 Large Language Model (LLM) agents are increasingly deployed in complex, multi-step workflows involving planning, tool use, reflection, and interaction with external knowledge systems. These workflows generate rapidly expanding contexts that must be curated, transformed, and compressed to maintain fidelity, avoid attention dilution, and reduce inference cost. Prior work on summarization and query-aware compression largely ignores the multi-step, plan-aware nature of agentic reasoning. In this work, we introduce PAACE (Plan-Aware Automated Context Engineering), a unified framework for optimizing the evolving state of LLM agents through next-k-task relevance modeling, plan-structure analysis, instruction co-refinement, and function-preserving compression. PAACE comprises (1) PAACE-Syn, a large-scale generator of synthetic agent workflows annotated with stepwise compression supervision, and (2) PAACE-FT, a family of distilled, plan-aware compressors trained from successful teacher demonstrations. Experiments on long-horizon benchmarks (AppWorld, OfficeBench, and 8-Objective QA) demonstrate that PAACE consistently improves agent correctness while substantially reducing context load. On AppWorld, PAACE achieves higher accuracy than all baselines while lowering peak context and cumulative dependency. On OfficeBench and multi-hop QA, PAACE improves both accuracy and F1, achieving fewer steps, lower peak tokens, and reduced attention dependency. Distilled PAACE-FT retains 97 percent of the teacher's performance while reducing inference cost by over an order of magnitude, enabling practical deployment of plan-aware compression with compact models. --- ### Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows Authors: Wanghan Xu, Yuhao Zhou, Yifan Zhou, Qinglong Cao, Shuo Li, Jia Bu, Bo Liu, Yixin Chen, Xuming He, Xiangyu Zhao, Xiang Zhuang, Fengxiang Wang et al. Published: 2025-12-18 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.16969v1 Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery. ---