# Research Papers — 2026-01 · bundle page 156 of 189 > Full-text markdown of papers #7751–7800 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/156 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/155.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/157.md) ### Pilot Study on Student Public Opinion Regarding GAI Authors: William Franz Lamberti, Sunbin Kim, Samantha Rose Lawrence Published: 2026-01-07 Categories: cs.AI, cs.HC, stat.AP arXiv: https://arxiv.org/abs/2601.04336v1 The emergence of generative AI (GAI) has sparked diverse opinions regarding its appropriate use across various domains, including education. This pilot study investigates university students' perceptions of GAI in higher education classrooms, aiming to lay the groundwork for understanding these attitudes. With a participation rate of approximately 4.4%, the study highlights the challenges of engaging students in GAI-related research and underscores the need for larger sample sizes in future studies. By gaining insights into student perspectives, instructors can better prepare to integrate discussions of GAI into their classrooms, fostering informed and critical engagement with this transformative technology. --- ### ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation Authors: Erel Kaplan, Tomer Bitan, Lian Ghrayeb, Le Chen, Tom Yotam, Niranjan Hasabnis, Gal Oren Published: 2026-01-07 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2601.04327v1 Parallel programming is central to HPC and AI, but producing code that is correct and fast remains challenging, especially for OpenMP GPU offload, where data movement and tuning dominate. Autonomous coding agents can compile, test, and profile on target hardware, but outputs are brittle without domain scaffolding. We present ParaCodex, an HPC-engineer workflow that turns a Codex-based agent into an autonomous OpenMP GPU offload system using staged hotspot analysis, explicit data planning, correctness gating, and profiling-guided refinement. We evaluate translation from serial CPU kernels to OpenMP GPU offload kernels on HeCBench, Rodinia, and NAS. After excluding five kernels, ParaCodex succeeded on all 31 valid kernels. The generated kernels improved GPU time over reference OpenMP implementations in 25/31 cases, achieving geometric-mean speedups of 3x on HeCBench and 5x on Rodinia, and outperforming a zero-shot Codex baseline on all suites. We also evaluate CUDA to OpenMP offload translation on ParEval, where ParaCodex maintains high compilation and validation rates in code-only and end-to-end settings. --- ### Embedding Textual Information in Images Using Quinary Pixel Combinations Authors: A V Uday Kiran Kandala Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.04302v1 This paper presents a novel technique for embedding textual data into images using quinary combinations of pixel intensities in RGB space. Existing methods predominantly rely on least and most significant bit (LSB & MSB) manipulation, Pixel Value Differencing (PVD), spatial perturbations in RGB channels, transform domain based methods, Quantization methods, Edge and Region based methods and more recently through deep learning methods and generative AI techniques for hiding textual information in spatial domain of images. Most of them are dependent on pixel intensity flipping over multiple pixels, such as LSB and combination of LSB based methodologies, and on transform coefficients, often resulting in the form of noise. Encoding and Decoding are deterministic in most of the existing approaches and are computationally heavy in case of higher models such as deep learning and gen AI approaches. The proposed method works on quinary pixel intensity combinations in RGB space, where five controlled different pixel intensity variations in each of the R, G, and B channels formulate up to one hundred and twenty five distinct pixel intensity combinations. These combinations are mapped to textual symbols, enabling the representation of uppercase and lowercase alphabetic characters, numeric digits, whitespace, and commonly used special characters. Different metrics such as MSE, MAE, SNR, PSNR, SSIM, Histogram Comparison and Heatmap analysis, were evaluated for both original and encoded images resulting in no significant distortion in the images. Furthermore, the method achieves improved embedding efficiency by encoding a complete textual symbol within a single RGB pixel, in contrast to LSB and MSB based approaches that typically require multiple pixels or multi-step processes, as well as transform and learning based methods that incur higher computational overhead. --- ### Quantifying the Effect of Test Set Contamination on Generative Evaluations Authors: Rylan Schaeffer, Joshua Kazdan, Baber Abbasi, Ken Ziyu Liu, Brando Miranda, Ahmed Ahmed, Fazl Berez, Abhay Puri, Stella Biderman, Niloofar Mireshghallah, Sanmi Koyejo Published: 2026-01-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.04301v3 As frontier AI systems are pretrained on web-scale data, test set contamination has become a critical concern for accurately assessing their capabilities. While research has thoroughly investigated the impact of test set contamination on discriminative evaluations like multiple-choice question-answering, comparatively little research has studied the impact of test set contamination on generative evaluations. In this work, we quantitatively assess the effect of test set contamination on generative evaluations through the language model lifecycle. We pretrain language models on mixtures of web data and the MATH benchmark, sweeping model sizes and number of test set replicas contaminating the pretraining corpus; performance improves with contamination and model size. Using scaling laws, we make a surprising discovery: including even a single test set replica enables models to achieve lower loss than the irreducible error of training on the uncontaminated corpus. We then study further training: overtraining with fresh data reduces the effects of contamination, whereas supervised finetuning on the training set can either increase or decrease performance on test data, depending on the amount of pretraining contamination. Finally, at inference, we identify factors that modulate memorization: high sampling temperatures mitigate contamination effects, and longer solutions are exponentially more difficult to memorize than shorter ones, presenting a contrast with discriminative evaluations, where solutions are only a few tokens in length. By characterizing how generation and memorization interact, we highlight a new layer of complexity for trustworthy evaluation of AI systems. --- ### Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes Authors: Chenye Meng, Zejian Li, Zhongni Liu, Yize Li, Changle Xie, Kaixin Jia, Ling Yang, Huanghuang Deng, Shiying Ding, Shengyuan Zhang, Jiayi Li, Lingyun Sun Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.04300v1 Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is hierarchical and fine-grained. To address this, we first construct a hierarchical, fine-grained evaluation criteria with domain experts, which decomposes image quality into multiple positive and negative attributes organized in a tree structure. Building on this, we propose a two-stage alignment framework. First, we inject domain knowledge to an auxiliary diffusion model via Supervised Fine-Tuning. Second, we introduce Complex Preference Optimization (CPO) that extends DPO to align the target diffusion to our non-binary, hierarchical criteria. Specifically, we reformulate the alignment problem to simultaneously maximize the probability of positive attributes while minimizing the probability of negative attributes with the auxiliary diffusion. We instantiate our approach in the domain of painting generation and conduct CPO training with an annotated dataset of painting with fine-grained attributes based on our criteria. Extensive experiments demonstrate that CPO significantly enhances generation quality and alignment with expertise, opening new avenues for fine-grained criteria alignment. --- ### Transformer-Based Multi-Modal Temporal Embeddings for Explainable Metabolic Phenotyping in Type 1 Diabetes Authors: Pir Bakhsh Khokhar, Carmine Gravino, Fabio Palomba, Sule Yildrim Yayilgan, Sarang Shaikh Published: 2026-01-07 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2601.04299v1 Type 1 diabetes (T1D) is a highly metabolically heterogeneous disease that cannot be adequately characterized by conventional biomarkers such as glycated hemoglobin (HbA1c). This study proposes an explainable deep learning framework that integrates continuous glucose monitoring (CGM) data with laboratory profiles to learn multimodal temporal embeddings of individual metabolic status. Temporal dependencies across modalities are modeled using a transformer encoder, while latent metabolic phenotypes are identified via Gaussian mixture modeling. Model interpretability is achieved through transformer attention visualization and SHAP-based feature attribution. Five latent metabolic phenotypes, ranging from metabolic stability to elevated cardiometabolic risk, were identified among 577 individuals with T1D. These phenotypes exhibit distinct biochemical profiles, including differences in glycemic control, lipid metabolism, renal markers, and thyrotropin (TSH) levels. Attention analysis highlights glucose variability as a dominant temporal factor, while SHAP analysis identifies HbA1c, triglycerides, cholesterol, creatinine, and TSH as key contributors to phenotype differentiation. Phenotype membership shows statistically significant, albeit modest, associations with hypertension, myocardial infarction, and heart failure. Overall, this explainable multimodal temporal embedding framework reveals physiologically coherent metabolic subgroups in T1D and supports risk stratification beyond single biomarkers. --- ### ArtCognition: A Multimodal AI Framework for Affective State Sensing from Visual and Kinematic Drawing Cues Authors: Behrad Binaei-Haghighi, Nafiseh Sadat Sajadi, Mehrad Liviyan, Reyhane Akhavan Kharazi, Fatemeh Amirkhani, Behnam Bahrak Published: 2026-01-07 Categories: cs.LG, cs.CV, cs.HC, cs.IR arXiv: https://arxiv.org/abs/2601.04297v1 The objective assessment of human affective and psychological states presents a significant challenge, particularly through non-verbal channels. This paper introduces digital drawing as a rich and underexplored modality for affective sensing. We present a novel multimodal framework, named ArtCognition, for the automated analysis of the House-Tree-Person (HTP) test, a widely used psychological instrument. ArtCognition uniquely fuses two distinct data streams: static visual features from the final artwork, captured by computer vision models, and dynamic behavioral kinematic cues derived from the drawing process itself, such as stroke speed, pauses, and smoothness. To bridge the gap between low-level features and high-level psychological interpretation, we employ a Retrieval-Augmented Generation (RAG) architecture. This grounds the analysis in established psychological knowledge, enhancing explainability and reducing the potential for model hallucination. Our results demonstrate that the fusion of visual and behavioral kinematic cues provides a more nuanced assessment than either modality alone. We show significant correlations between the extracted multimodal features and standardized psychological metrics, validating the framework's potential as a scalable tool to support clinicians. This work contributes a new methodology for non-intrusive affective state assessment and opens new avenues for technology-assisted mental healthcare. --- ### Correct and Weight: A Simple Yet Effective Loss for Implicit Feedback Recommendation Authors: Minglei Yin, Chuanbo Hu, Bin Liu, Neil Zhenqiang Gong, Yanfang, Ye, Xin Li Published: 2026-01-07 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2601.04291v1 Learning from implicit feedback has become the standard paradigm for modern recommender systems. However, this setting is fraught with the persistent challenge of false negatives, where unobserved user-item interactions are not necessarily indicative of negative preference. To address this issue, this paper introduces a novel and principled loss function, named Corrected and Weighted (CW) loss, that systematically corrects for the impact of false negatives within the training objective. Our approach integrates two key techniques. First, inspired by Positive-Unlabeled learning, we debias the negative sampling process by re-calibrating the assumed negative distribution. By theoretically approximating the true negative distribution (p-) using the observable general data distribution (p) and the positive interaction distribution (p^+), our method provides a more accurate estimate of the likelihood that a sampled unlabeled item is truly negative. Second, we introduce a dynamic re-weighting mechanism that modulates the importance of each negative instance based on the model's current prediction. This scheme encourages the model to enforce a larger ranking margin between positive items and confidently predicted (i.e., easy) negative items, while simultaneously down-weighting the penalty on uncertain negatives that have a higher probability of being false negatives. A key advantage of our approach is its elegance and efficiency; it requires no complex modifications to the data sampling process or significant computational overhead, making it readily applicable to a wide array of existing recommendation models. Extensive experiments conducted on four large-scale, sparse benchmark datasets demonstrate the superiority of our proposed loss. The results show that our method consistently and significantly outperforms a suite of state-of-the-art loss functions across multiple ranking-oriented metrics. --- ### Human-in-the-Loop Testing of AI Agents for Air Traffic Control with a Regulated Assessment Framework Authors: Ben Carvell, Marc Thomas, Andrew Pace, Christopher Dorney, George De Ath, Richard Everson, Nick Pepper, Adam Keane, Samuel Tomlinson, Richard Cannon Published: 2026-01-07 Categories: cs.HC, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2601.04288v1 We present a rigorous, human-in-the-loop evaluation framework for assessing the performance of AI agents on the task of Air Traffic Control, grounded in a regulator-certified simulator-based curriculum used for training and testing real-world trainee controllers. By leveraging legally regulated assessments and involving expert human instructors in the evaluation process, our framework enables a more authentic and domain-accurate measurement of AI performance. This work addresses a critical gap in the existing literature: the frequent misalignment between academic representations of Air Traffic Control and the complexities of the actual operational environment. It also lays the foundations for effective future human-machine teaming paradigms by aligning machine performance with human assessment targets. --- ### Online Action-Stacking Improves Reinforcement Learning Performance for Air Traffic Control Authors: Ben Carvell, George De Ath, Eseoghene Benjamin, Richard Everson Published: 2026-01-07 Categories: cs.LG, cs.AI, cs.MA, cs.RO arXiv: https://arxiv.org/abs/2601.04287v1 We introduce online action-stacking, an inference-time wrapper for reinforcement learning policies that produces realistic air traffic control commands while allowing training on a much smaller discrete action space. Policies are trained with simple incremental heading or level adjustments, together with an action-damping penalty that reduces instruction frequency and leads agents to issue commands in short bursts. At inference, online action-stacking compiles these bursts of primitive actions into domain-appropriate compound clearances. Using Proximal Policy Optimisation and the BluebirdDT digital twin platform, we train agents to navigate aircraft along lateral routes, manage climb and descent to target flight levels, and perform two-aircraft collision avoidance under a minimum separation constraint. In our lateral navigation experiments, action stacking greatly reduces the number of issued instructions relative to a damped baseline and achieves comparable performance to a policy trained with a 37-dimensional action space, despite operating with only five actions. These results indicate that online action-stacking helps bridge a key gap between standard reinforcement learning formulations and operational ATC requirements, and provides a simple mechanism for scaling to more complex control scenarios. --- ### Enhancing Robustness of Asynchronous EEG-Based Movement Prediction using Classifier Ensembles Authors: Niklas Kueper, Kartik Chari, Elsa Andrea Kirchner Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.04286v1 Objective: Stroke is one of the leading causes of disabilities. One promising approach is to extend the rehabilitation with self-initiated robot-assisted movement therapy. To enable this, it is required to detect the patient's intention to move to trigger the assistance of a robotic device. This intention to move can be detected from human surface electroencephalography (EEG) signals; however, it is particularly challenging to decode when classifications are performed online and asynchronously. In this work, the effectiveness of classifier ensembles and a sliding-window postprocessing technique was investigated to enhance the robustness of such asynchronous classification. Approach: To investigate the effectiveness of classifier ensembles and a sliding-window postprocessing, two EEG datasets with 14 healthy subjects who performed self-initiated arm movements were analyzed. Offline and pseudo-online evaluations were conducted to compare ensemble combinations of the support vector machine (SVM), multilayer perceptron (MLP), and EEGNet classification models. Results: The results of the pseudo-online evaluation show that the two model ensembles significantly outperformed the best single model for the optimal number of postprocessing windows. In particular, for single models, an increased number of postprocessing windows significantly improved classification performances. Interestingly, we found no significant improvements between performances of the best single model and classifier ensembles in the offline evaluation. Significance: We demonstrated that classifier ensembles and appropriate postprocessing methods effectively enhance the asynchronous detection of movement intentions from EEG signals. In particular, the classifier ensemble approach yields greater improvements in online classification than in offline classification, and reduces false detections, i.e., early false positives. --- ### A Future Capabilities Agent for Tactical Air Traffic Control Authors: Paul Kent, George De Ath, Martin Layton, Allen Hart, Richard Everson, Ben Carvell Published: 2026-01-07 Categories: cs.AI, cs.HC, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2601.04285v1 Escalating air traffic demand is driving the adoption of automation to support air traffic controllers, but existing approaches face a trade-off between safety assurance and interpretability. Optimisation-based methods such as reinforcement learning offer strong performance but are difficult to verify and explain, while rules-based systems are transparent yet rarely check safety under uncertainty. This paper outlines Agent Mallard, a forward-planning, rules-based agent for tactical control in systemised airspace that embeds a stochastic digital twin directly into its conflict-resolution loop. Mallard operates on predefined GPS-guided routes, reducing continuous 4D vectoring to discrete choices over lanes and levels, and constructs hierarchical plans from an expert-informed library of deconfliction strategies. A depth-limited backtracking search uses causal attribution, topological plan splicing, and monotonic axis constraints to seek a complete safe plan for all aircraft, validating each candidate manoeuvre against uncertain execution scenarios (e.g., wind variation, pilot response, communication loss) before commitment. Preliminary walkthroughs with UK controllers and initial tests in the BluebirdDT airspace digital twin indicate that Mallard's behaviour aligns with expert reasoning and resolves conflicts in simplified scenarios. The architecture is intended to combine model-based safety assessment, interpretable decision logic, and tractable computational performance in future structured en-route environments. --- ### Mitigating Position-Shift Failures in Text-Based Modular Arithmetic via Position Curriculum and Template Diversity Authors: Nikolay Yudin Published: 2026-01-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.04283v1 Building on insights from the grokking literature, we study character-level Transformers trained to compute modular addition from text, and focus on robustness under input-format variation rather than only in-distribution accuracy. We identify a previously under-emphasized failure mode: models that achieve high in-distribution accuracy can fail catastrophically when the same expression is shifted to different absolute character positions ("position shift") or presented under out-of-distribution natural-language templates. Using a disjoint-pair split over all ordered pairs for p=97, we show that a baseline model reaches strong in-distribution performance yet collapses under position shift and template OOD. We then introduce a simple training recipe that combines (i) explicit expression boundary markers, (ii) position curriculum that broadens the range of absolute positions seen during training, (iii) diverse template mixtures, and (iv) consistency training across multiple variants per example. Across three seeds, this intervention substantially improves robustness to position shift and template OOD while maintaining high in-distribution accuracy, whereas an ALiBi-style ablation fails to learn the task under our setup. Our results suggest that steering procedural generalization under noisy supervision benefits from explicitly training invariances that are otherwise absent from the data distribution, and we provide a reproducible evaluation protocol and artifacts. --- ### LEGATO: Good Identity Unlearning Is Continuous Authors: Qiang Chen, Chun-Wun Cheng, Xiu Su, Hongyan Xu, Xi Lin, Shan You, Angelica I. Aviles-Rivero, Yi Chen Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.04282v1 Machine unlearning has become a crucial role in enabling generative models trained on large datasets to remove sensitive, private, or copyright-protected data. However, existing machine unlearning methods face three challenges in learning to forget identity of generative models: 1) inefficient, where identity erasure requires fine-tuning all the model's parameters; 2) limited controllability, where forgetting intensity cannot be controlled and explainability is lacking; 3) catastrophic collapse, where the model's retention capability undergoes drastic degradation as forgetting progresses. Forgetting has typically been handled through discrete and unstable updates, often requiring full-model fine-tuning and leading to catastrophic collapse. In this work, we argue that identity forgetting should be modeled as a continuous trajectory, and introduce LEGATO - Learn to ForgEt Identity in GenerAtive Models via Trajectory-consistent Neural Ordinary Differential Equations. LEGATO augments pre-trained generators with fine-tunable lightweight Neural ODE adapters, enabling smooth, controllable forgetting while keeping the original model weights frozen. This formulation allows forgetting intensity to be precisely modulated via ODE step size, offering interpretability and robustness. To further ensure stability, we introduce trajectory consistency constraints that explicitly prevent catastrophic collapse during unlearning. Extensive experiments across in-domain and out-of-domain identity unlearning benchmarks show that LEGATO achieves state-of-the-art forgetting performance, avoids catastrophic collapse and reduces fine-tuned parameters. --- ### Generation of synthetic delay time series for air transport applications Authors: Pau Esteve, Massimiliano Zanin Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.04279v1 The generation of synthetic data is receiving increasing attention from the scientific community, thanks to its ability to solve problems like data scarcity and privacy, and is starting to find applications in air transport. We here tackle the problem of generating synthetic, yet realistic, time series of delays at airports, starting from large collections of operations in Europe and the US. We specifically compare three models, two of them based on state of the art Deep Learning algorithms, and one simplified Genetic Algorithm approach. We show how the latter can generate time series that are almost indistinguishable from real ones, while maintaining a high variability. We further validate the resulting time series in a problem of detecting delay propagations between airports. We finally make the synthetic data available to the scientific community. --- ### From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning Authors: Xiaoyu Xu, Minxin Du, Zitong Li, Zi Liang, Zhibiao Guo, Shiyu Zhang, Peizhao Hu, Qingqing Ye, Haibo Hu Published: 2026-01-07 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.04278v2 Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully represent the true ``forgetting scope'' learned by the model. We formalize two distinct unlearning granularities, domain-level and instance-level, and propose \BiForget, an automated framework for synthesizing high-quality forget sets. Unlike prior work relying on \emph{external} generators, \BiForget exploits the target model per se to elicit data that matches its internal knowledge distribution through seed-guided and adversarial prompting. Our experiments across diverse benchmarks show that it achieves a superior balance of relevance, diversity, and efficiency. Quantitatively, in the Harry Potter domain, it improves relevance by ${\sim}20$ and diversity by ${\sim}$0.05 while \emph{halving} the total data size compared to SOTAs. Ultimately, it facilitates more robust forgetting and better utility preservation, providing a more rigorous foundation for evaluating LLM unlearning. --- ### Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs Authors: Beier Luo, Cheng Wang, Hongxin Wei, Sharon Li, Xuefeng Du Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.04277v1 Post-training improves large language models (LLMs) but often worsens confidence calibration, leading to systematic overconfidence. Recent unsupervised post-hoc methods for post-trained LMs (PoLMs) mitigate this by aligning PoLM confidence to that of well-calibrated pre-trained counterparts. However, framing calibration as static output-distribution matching overlooks the inference-time dynamics introduced by post-training. In particular, we show that calibration errors arise from two regimes: (i) confidence drift, where final confidence inflates despite largely consistent intermediate decision processes, and (ii) process drift, where intermediate inference pathways diverge. Guided by this diagnosis, we propose Dual-Align, an unsupervised post-hoc framework for dual alignment in confidence calibration. Dual-Align performs confidence alignment to correct confidence drift via final-distribution matching, and introduces process alignment to address process drift by locating the layer where trajectories diverge and realigning the stability of subsequent inference. This dual strategy learns a single temperature parameter that corrects both drift types without sacrificing post-training performance gains. Experiments show consistent improvements over baselines, reducing calibration errors and approaching a supervised oracle. --- ### Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs Authors: Dinesh Srivasthav P, Ashok Urlana, Rahul Mishra, Bala Mallikarjunarao Garlapati, Ponnurangam Kumaraguru Published: 2026-01-07 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.04275v2 Machine unlearning aims to selectively remove the influence of specific training samples to satisfy privacy regulations such as the GDPR's 'Right to be Forgotten'. However, many existing methods require access to the data being removed, exposing it to membership inference attacks and potential misuse of Personally Identifiable Information (PII). We address this critical challenge by proposing Shadow Unlearning, a novel paradigm of approximate unlearning, that performs machine unlearning on anonymized forget data without exposing PII. We further propose a novel privacy-preserving framework, Neuro-Semantic Projector Unlearning (NSPU) to achieve Shadow unlearning. To evaluate our method, we compile Multi-domain Fictitious Unlearning (MuFU) forget set across five diverse domains and introduce an evaluation stack to quantify the trade-off between knowledge retention and unlearning effectiveness. Experimental results on various LLMs show that NSPU achieves superior unlearning performance, preserves model utility, and enhances user privacy. Additionally, the proposed approach is at least 10x more computationally efficient than standard unlearning approaches. Our findings foster a new direction for privacy-aware machine unlearning that balances data protection and model fidelity. --- ### An ASP-based Solution to the Medical Appointment Scheduling Problem Authors: Alina Vozna, Andrea Monaldini, Stefania Costantini, Valentina Pitoni, Dawid Pado Published: 2026-01-07 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2601.04274v1 This paper presents an Answer Set Programming (ASP)-based framework for medical appointment scheduling, aimed at improving efficiency, reducing administrative overhead, and enhancing patient-centered care. The framework personalizes scheduling for vulnerable populations by integrating Blueprint Personas. It ensures real-time availability updates, conflict-free assignments, and seamless interoperability with existing healthcare platforms by centralizing planning operations within an ASP logic model. --- ### Hybrid MKNF for Aeronautics Applications: Usage and Heuristics Authors: Arun Raveendran Nair Sheela, Florence De Grancey, Christophe Rey, Victor Charpenay Published: 2026-01-07 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2601.04273v1 The deployment of knowledge representation and reasoning technologies in aeronautics applications presents two main challenges: achieving sufficient expressivity to capture complex domain knowledge, and executing reasoning tasks efficiently while minimizing memory usage and computational overhead. An effective strategy for attaining necessary expressivity involves integrating two fundamental KR concepts: rules and ontologies. This study adopts the well-established KR language Hybrid MKNF owing to its seamless integration of rules and ontologies through its semantics and query answering capabilities. We evaluated Hybrid MKNF to assess its suitability in the aeronautics domain through a concrete case study. We identified additional expressivity features that are crucial for developing aeronautics applications and proposed a set of heuristics to support their integration into Hybrid MKNF framework. --- ### Propositional Abduction via Only-Knowing: A Non-Monotonic Approach Authors: Sanderson Molick, Vaishak Belle Published: 2026-01-07 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2601.04272v1 The paper introduces a basic logic of knowledge and abduction by extending Levesque logic of only-knowing with an abduction modal operator defined via the combination of basic epistemic concepts. The upshot is an alternative approach to abduction that employs a modal vocabulary and explores the relation between abductive reasoning and epistemic states of only knowing. Furthermore, by incorporating a preferential relation into modal frames, we provide a non-monotonic extension of our basic framework capable of expressing different selection methods for abductive explanations. Core metatheoretic properties of non-monotonic consequence relations are explored within this setting and shown to provide a well-behaved foundation for abductive reasoning. --- ### Correcting Autonomous Driving Object Detection Misclassifications with Automated Commonsense Reasoning Authors: Keegan Kimbrell, Wang Tianhao, Feng Chen, Gopal Gupta Published: 2026-01-07 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2601.04271v1 Autonomous Vehicle (AV) technology has been heavily researched and sought after, yet there are no SAE Level 5 AVs available today in the marketplace. We contend that over-reliance on machine learning technology is the main reason. Use of automated commonsense reasoning technology, we believe, can help achieve SAE Level 5 autonomy. In this paper, we show how automated common-sense reasoning technology can be deployed in situations where there are not enough data samples available to train a deep learning-based AV model that can handle certain abnormal road scenarios. Specifically, we consider two situations where (i) a traffic signal is malfunctioning at an intersection and (ii) all the cars ahead are slowing down and steering away due to an unexpected obstruction (e.g., animals on the road). We show that in such situations, our commonsense reasoning-based solution accurately detects traffic light colors and obstacles not correctly captured by the AV's perception model. We also provide a pathway for efficiently invoking commonsense reasoning by measuring uncertainty in the computer vision model and using commonsense reasoning to handle uncertain scenarios. We describe our experiments conducted using the CARLA simulator and the results obtained. The main contribution of our research is to show that automated commonsense reasoning effectively corrects AV-based object detection misclassifications and that hybrid models provide an effective pathway to improving AV perception. --- ### Predictable Gradient Manifolds in Deep Learning: Temporal Path-Length and Intrinsic Rank as a Complexity Regime Authors: Anherutowa Calvo Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.04270v1 Deep learning optimization exhibits structure that is not captured by worst-case gradient bounds. Empirically, gradients along training trajectories are often temporally predictable and evolve within a low-dimensional subspace. In this work we formalize this observation through a measurable framework for predictable gradient manifolds. We introduce two computable quantities: a prediction-based path length that measures how well gradients can be forecast from past information, and a predictable rank that quantifies the intrinsic temporal dimension of gradient increments. We show how classical online and nonconvex optimization guarantees can be restated so that convergence and regret depend explicitly on these quantities, rather than on worst-case variation. Across convolutional networks, vision transformers, language models, and synthetic control tasks, we find that gradient trajectories are locally predictable and exhibit strong low-rank structure over time. These properties are stable across architectures and optimizers, and can be diagnosed directly from logged gradients using lightweight random projections. Our results provide a unifying lens for understanding optimization dynamics in modern deep learning, reframing standard training as operating in a low-complexity temporal regime. This perspective suggests new directions for adaptive optimizers, rank-aware tracking, and prediction-based algorithm design grounded in measurable properties of real training runs. --- ### Systems Explaining Systems: A Framework for Intelligence and Consciousness Authors: Sean Niklas Semmler Published: 2026-01-07 Categories: cs.AI, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2601.04269v1 This paper proposes a conceptual framework in which intelligence and consciousness emerge from relational structure rather than from prediction or domain-specific mechanisms. Intelligence is defined as the capacity to form and integrate causal connections between signals, actions, and internal states. Through context enrichment, systems interpret incoming information using learned relational structure that provides essential context in an efficient representation that the raw input itself does not contain, enabling efficient processing under metabolic constraints. Building on this foundation, we introduce the systems-explaining-systems principle, where consciousness emerges when recursive architectures allow higher-order systems to learn and interpret the relational patterns of lower-order systems across time. These interpretations are integrated into a dynamically stabilized meta-state and fed back through context enrichment, transforming internal models from representations of the external world into models of the system's own cognitive processes. The framework reframes predictive processing as an emergent consequence of contextual interpretation rather than explicit forecasting and suggests that recursive multi-system architectures may be necessary for more human-like artificial intelligence. --- ### Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning Authors: Pritthijit Nath, Sebastian Schemm, Henry Moss, Peter Haynes, Emily Shuckburgh, Mark J. Webb Published: 2026-01-07 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2601.04268v4 Weather and climate models rely on parametrisations to represent unresolved sub-grid processes. Traditional schemes rely on fixed coefficients that are weakly constrained and tuned offline, contributing to persistent biases that limit their ability to adapt to underlying physics. This study presents a framework that learns components of parametrisation schemes online as a function of the evolving model state using reinforcement learning (RL) and evaluates policy-driven parameter updates across idealised testbeds spanning a simple climate bias correction (SCBC), a radiative-convective equilibrium (RCE), and a zonal mean energy balance model (EBM) with single-agent and federated multi-agent settings. Across nine RL algorithms, Truncated Quantile Critics (TQC), Deep Deterministic Policy Gradient (DDPG), and Twin Delayed DDPG (TD3) achieved the highest skill and stable convergence, with performance assessed against a static baseline using area-weighted RMSE, temperature and pressure-level diagnostics. For the EBM, single-agent RL outperformed static parameter tuning with the strongest gains in tropical and mid-latitude bands, while federated RL on multi-agent setups enabled specialised control and faster convergence, with a six-agent DDPG configuration using frequent aggregation yielding the lowest area-weighted RMSE across the tropics and mid-latitudes. The learnt corrections were also physically meaningful as agents modulated EBM radiative parameters to reduce meridional biases, adjusted RCE lapse rates to match vertical temperature errors, and stabilised heating increments to limit drift. Overall, results show that RL can learn skilful state-dependent parametrisation components in idealised settings, offering a scalable pathway for online learning within numerical models and a starting point for evaluation in weather and climate models. --- ### State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space Authors: Ji Guo, Wenbo Jiang, Yansong Lin, Yijing Liu, Ruichen Zhang, Guomin Lu, Aiguo Chen, Xinshuo Han, Hongwei Li Published: 2026-01-07 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.04266v2 Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new security vulnerabilities. In this paper, we investigate a backdoor threat in VLA models, where malicious inputs cause targeted misbehavior while preserving performance on clean data. Existing backdoor methods predominantly rely on inserting visible triggers into visual modality, which suffer from poor robustness and low insusceptibility in real-world settings due to environmental variability. To overcome these limitations, we introduce the State Backdoor, a novel and practical backdoor attack that leverages the robot arm's initial state as the trigger. To optimize trigger for insusceptibility and effectiveness, we design a Preference-guided Genetic Algorithm (PGA) that efficiently searches the state space for minimal yet potent triggers. Extensive experiments on five representative VLA models and five real-world tasks show that our method achieves over 90% attack success rate without affecting benign task performance, revealing an underexplored vulnerability in embodied AI systems. --- ### MemKD: Memory-Discrepancy Knowledge Distillation for Efficient Time Series Classification Authors: Nilushika Udayangani, Kishor Nandakishor, Marimuthu Palaniswami Published: 2026-01-07 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2601.04264v1 Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series data analysis. These models capture complex, sequential patterns in time series, enabling real-time assessments. However, their high computational complexity and large model sizes pose challenges for deployment in resource-constrained environments, such as wearable devices and edge computing platforms. Knowledge Distillation (KD) offers a solution by transferring knowledge from a large, complex model (teacher) to a smaller, more efficient model (student), thereby retaining high performance while reducing computational demands. Current KD methods, originally designed for computer vision tasks, neglect the unique temporal dependencies and memory retention characteristics of time series models. To this end, we propose a novel KD framework termed Memory-Discrepancy Knowledge Distillation (MemKD). MemKD leverages a specialized loss function to capture memory retention discrepancies between the teacher and student models across subsequences within time series data, ensuring that the student model effectively mimics the teacher model's behaviour. This approach facilitates the development of compact, high-performing recurrent neural networks suitable for real-time, time series analysis tasks. Our extensive experiments demonstrate that MemKD significantly outperforms state-of-the-art KD methods. It reduces parameter size and memory usage by approximately 500 times while maintaining comparable performance to the teacher model. --- ### Learning to Reason: Temporal Saliency Distillation for Interpretable Knowledge Transfer Authors: Nilushika Udayangani Hewa Dehigahawattage, Kishor Nandakishor, Marimuthu Palaniswami Published: 2026-01-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.04263v1 Knowledge distillation has proven effective for model compression by transferring knowledge from a larger network called the teacher to a smaller network called the student. Current knowledge distillation in time series is predominantly based on logit and feature aligning techniques originally developed for computer vision tasks. These methods do not explicitly account for temporal data and fall short in two key aspects. First, the mechanisms by which the transferred knowledge helps the student model learning process remain unclear due to uninterpretability of logits and features. Second, these methods transfer only limited knowledge, primarily replicating the teacher predictive accuracy. As a result, student models often produce predictive distributions that differ significantly from those of their teachers, hindering their safe substitution for teacher models. In this work, we propose transferring interpretable knowledge by extending conventional logit transfer to convey not just the right prediction but also the right reasoning of the teacher. Specifically, we induce other useful knowledge from the teacher logits termed temporal saliency which captures the importance of each input timestep to the teacher prediction. By training the student with Temporal Saliency Distillation we encourage it to make predictions based on the same input features as the teacher. Temporal Saliency Distillation requires no additional parameters or architecture specific assumptions. We demonstrate that Temporal Saliency Distillation effectively improves the performance of baseline methods while also achieving desirable properties beyond predictive accuracy. We hope our work establishes a new paradigm for interpretable knowledge distillation in time series analysis. --- ### Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis Authors: Wang Cai, Yilin Wen, Jinchang Hou, Du Su, Guoqiu Wang, Zhonghou Lv, Chenfu Bao, Yunfang Wu Published: 2026-01-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.04262v1 Safety alignment in Large Language Models (LLMs) inherently presents a multi-objective optimization conflict, often accompanied by an unintended degradation of general capabilities. Existing mitigation strategies typically rely on global gradient geometry to resolve these conflicts, yet they overlook Modular Heterogeneity within Transformers, specifically that the functional sensitivity and degree of conflict vary substantially across different attention heads. Such global approaches impose uniform update rules across all parameters, often resulting in suboptimal trade-offs by indiscriminately updating utility sensitive heads that exhibit intense gradient conflicts. To address this limitation, we propose Conflict-Aware Sparse Tuning (CAST), a framework that integrates head-level diagnosis with sparse fine-tuning. CAST first constructs a pre-alignment conflict map by synthesizing Optimization Conflict and Functional Sensitivity, which then guides the selective update of parameters. Experiments reveal that alignment conflicts in LLMs are not uniformly distributed. We find that the drop in general capabilities mainly comes from updating a small group of ``high-conflict'' heads. By simply skipping these heads during training, we significantly reduce this loss without compromising safety, offering an interpretable and parameter-efficient approach to improving the safety-utility trade-off. --- ### Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models Authors: Danchun Chen, Qiyao Yan, Chenpeng Wang, Liangming Pan Published: 2026-01-07 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.04260v2 Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying task specific circuits, they leave open the question of what computational strategies LLMs employ for propositional reasoning. We address this gap with a causal mechanistic analysis on PropLogic-MI, a controlled benchmark of 11 propositional rules across one- and two-hop tasks, applied to three model families (Qwen3, Llama-3.1, Mistral). Rather than asking which components are necessary, we ask how the reasoning process is organized, and identify four interlocking mechanisms: Staged Computation, where early, middle, and late layers take on distinct functional roles; Information Transmission, where semantic content aggregates at boundary tokens; Fact Retrospection, where fact tokens stay causally active as binding lookup in middle layers and as sustained access in late layers under hard reasoning loads; and Specialized Attention Heads that structurally implement these patterns. A prompt-order control that places the query before the facts confirms that this organization is model-internal rather than input-layout-induced. These findings show that pretrained LLMs solve propositional reasoning through a structured, layer-organized process that recurs across models, rule categories, and reasoning hops. --- ### Choreographing a World of Dynamic Objects Authors: Yanzhe Lyu, Chen Geng, Karthik Dharmarajan, Yunzhi Zhang, Hadi Alzayer, Shangzhe Wu, Jiajun Wu Published: 2026-01-07 Categories: cs.CV, cs.GR, cs.RO arXiv: https://arxiv.org/abs/2601.04194v1 Dynamic objects in our physical 4D (3D + time) world are constantly evolving, deforming, and interacting with other objects, leading to diverse 4D scene dynamics. In this paper, we present a universal generative pipeline, CHORD, for CHOReographing Dynamic objects and scenes and synthesizing this type of phenomena. Traditional rule-based graphics pipelines to create these dynamics are based on category-specific heuristics, yet are labor-intensive and not scalable. Recent learning-based methods typically demand large-scale datasets, which may not cover all object categories in interest. Our approach instead inherits the universality from the video generative models by proposing a distillation-based pipeline to extract the rich Lagrangian motion information hidden in the Eulerian representations of 2D videos. Our method is universal, versatile, and category-agnostic. We demonstrate its effectiveness by conducting experiments to generate a diverse range of multi-body 4D dynamics, show its advantage compared to existing methods, and demonstrate its applicability in generating robotics manipulation policies. Project page: https://yanzhelyu.github.io/chord --- ### A discrete Benamou-Brenier formulation of Optimal Transport on graphs Authors: Kieran Morris, Oliver Johnson Published: 2026-01-07 Categories: cs.IT, math.PR, stat.ML arXiv: https://arxiv.org/abs/2601.04193v2 We propose a discrete transport equation on graphs which connects distributions on both vertices and edges. We then derive a discrete analogue of the Benamou-Brenier formulation for Wasserstein-$1$ distance on a graph and as a result classify all $W_1$ geodesics on graphs. --- ### Embedding Autonomous Agents in Resource-Constrained Robotic Platforms Authors: Negar Halakou, Juan F. Gutierrez, Ye Sun, Han Jiang, Xueming Wu, Yilun Song, Andres Gomez Published: 2026-01-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.04191v1 Many embedded devices operate under resource constraints and in dynamic environments, requiring local decision-making capabilities. Enabling devices to make independent decisions in such environments can improve the responsiveness of the system and reduce the dependence on constant external control. In this work, we integrate an autonomous agent, programmed using AgentSpeak, with a small two-wheeled robot that explores a maze using its own decision-making and sensor data. Experimental results show that the agent successfully solved the maze in 59 seconds using 287 reasoning cycles, with decision phases taking less than one millisecond. These results indicate that the reasoning process is efficient enough for real-time execution on resource-constrained hardware. This integration demonstrates how high-level agent-based control can be applied to resource-constrained embedded systems for autonomous operation. --- ### ImLoc: Revisiting Visual Localization with Image-based Representation Authors: Xudong Jiang, Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.04185v1 Existing visual localization methods are typically either 2D image-based, which are easy to build and maintain but limited in effective geometric reasoning, or 3D structure-based, which achieve high accuracy but require a centralized reconstruction and are difficult to update. In this work, we revisit visual localization with a 2D image-based representation and propose to augment each image with estimated depth maps to capture the geometric structure. Supported by the effective use of dense matchers, this representation is not only easy to build and maintain, but achieves highest accuracy in challenging conditions. With compact compression and a GPU-accelerated LO-RANSAC implementation, the whole pipeline is efficient in both storage and computation and allows for a flexible trade-off between accuracy and highest memory efficiency. Our method achieves a new state-of-the-art accuracy on various standard benchmarks and outperforms existing memory-efficient methods at comparable map sizes. Code will be available at https://github.com/cvg/Hierarchical-Localization. --- ### Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition Authors: Nia Touko, Matthew O A Ellis, Cristiano Capone, Alessio Burrello, Elisa Donati, Luca Manneschi Published: 2026-01-07 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2601.04181v2 Reliable long-term decoding of gestures from surface electromyography (EMG) is hindered by signal drift caused by electrode displacement, muscle fatigue, and/or posture changes. Although modern models achieve high intra-session accuracy, their performance often degrades substantially across recording sessions. Existing approaches to mitigate this problem typically rely on large training datasets or computationally intensive pipelines that are unsuitable for energy-efficient wearable devices. We propose a lightweight test-time adaptation framework for EMG decoding. The framework includes three complementary adaptation strategies: (i) causal adaptive batch normalization for online statistical alignment, (ii) Gaussian Mixture Model alignment with experience replay to mitigate forgetting, and (iii) meta-learning for rapid few-shot calibration. We evaluate these methods on the multi-session NinaPro DB6 dataset. All approaches substantially improve inter-session robustness relative to a non-adaptive baseline while maintaining low computational overhead. Replay-regularized statistical alignment provides the most stable adaptation under limited data, while meta-learning achieves the highest accuracy when sparse calibration labels are available. Overall, our self-supervised test-time adaptation methods reach up to 82% inter-session accuracy, significantly improving upon prior approaches while maintaining resource-efficient operation. These results demonstrate that lightweight test-time adaptation can enable robust, long-term EMG decoding for wearable or prosthetic applications. --- ### Robust Physics Discovery from Highly Corrupted Data: A PINN Framework Applied to the Nonlinear Schrödinger Equation Authors: Pietro de Oliveira Esteves Published: 2026-01-07 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2601.04176v1 We demonstrate a deep learning framework capable of recovering physical parameters from the Nonlinear Schrodinger Equation (NLSE) under severe noise conditions. By integrating Physics-Informed Neural Networks (PINNs) with automatic differentiation, we achieve reconstruction of the nonlinear coefficient beta with less than 0.2 percent relative error using only 500 sparse, randomly sampled data points corrupted by 20 percent additive Gaussian noise, a regime where traditional finite difference methods typically fail due to noise amplification in numerical derivatives. We validate the method's generalization capabilities across different physical regimes (beta between 0.5 and 2.0) and varying data availability (between 100 and 1000 training points), demonstrating consistent sub-1 percent accuracy. Statistical analysis over multiple independent runs confirms robustness (standard deviation less than 0.15 percent for beta equals 1.0). The complete pipeline executes in approximately 80 minutes on modest cloud GPU resources (NVIDIA Tesla T4), making the approach accessible for widespread adoption. Our results indicate that physics-based regularization acts as an effective filter against high measurement uncertainty, positioning PINNs as a viable alternative to traditional optimization methods for inverse problems in spatiotemporal dynamics where experimental data is scarce and noisy. All code is made publicly available to facilitate reproducibility. --- ### Agentic Rubrics as Contextual Verifiers for SWE Agents Authors: Mohit Raghavendra, Anisha Gunjal, Bing Liu, Yunzhong He Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.04171v1 Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE) agent settings often relies on code execution, which can be difficult to scale due to environment setup overhead. Scalable alternatives such as patch classifiers and heuristic methods exist, but they are less grounded in codebase context and harder to interpret. To this end, we explore Agentic Rubrics: an expert agent interacts with the repository to create a context-grounded rubric checklist, and candidate patches are then scored against it without requiring test execution. On SWE-Bench Verified under parallel TTS evaluation, Agentic Rubrics achieve a score of 54.2% on Qwen3-Coder-30B-A3B and 40.6% on Qwen3-32B, with at least a +3.5 percentage-point gain over the strongest baseline in our comparison set. We further analyze rubric behavior, showing that rubric scores are consistent with ground-truth tests while also flagging issues that tests do not capture. Our ablations show that agentic context gathering is essential for producing codebase-specific, unambiguous criteria. Together, these results suggest that Agentic Rubrics provide an efficient, scalable, and granular verification signal for SWE agents. --- ### Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactions Authors: Abhishek Rath Published: 2026-01-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.04170v1 Multi-agent Large Language Model (LLM) systems have emerged as powerful architectures for complex task decomposition and collaborative problem-solving. However, their long-term behavioral stability remains largely unexamined. This study introduces the concept of agent drift, defined as the progressive degradation of agent behavior, decision quality, and inter-agent coherence over extended interaction sequences. We present a comprehensive theoretical framework for understanding drift phenomena, proposing three distinct manifestations: semantic drift (progressive deviation from original intent), coordination drift (breakdown in multi-agent consensus mechanisms), and behavioral drift (emergence of unintended strategies). We introduce the Agent Stability Index (ASI), a novel composite metric framework for quantifying drift across twelve dimensions, including response consistency, tool usage patterns, reasoning pathway stability, and inter-agent agreement rates. Through simulation-based analysis and theoretical modeling, we demonstrate how unchecked agent drift can lead to substantial reductions in task completion accuracy and increased human intervention requirements. We propose three mitigation strategies: episodic memory consolidation, drift-aware routing protocols, and adaptive behavioral anchoring. Theoretical analysis suggests these approaches can significantly reduce drift-related errors while maintaining system throughput. This work establishes a foundational methodology for monitoring, measuring, and mitigating agent drift in production agentic AI systems, with direct implications for enterprise deployment reliability and AI safety research. --- ### Clinical Data Goes MEDS? Let's OWL make sense of it Authors: Alberto Marfoglia, Jong Ho Jhee, Adrien Coulet Published: 2026-01-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.04164v2 The application of machine learning on healthcare data is often hindered by the lack of standardized and semantically explicit representation, leading to limited interoperability and reproducibility across datasets and experiments. The Medical Event Data Standard (MEDS) addresses these issues by introducing a minimal, event-centric data model designed for reproducible machine-learning workflows from health data. However, MEDS is defined as a data-format specification and does not natively provide integration with the Semantic Web ecosystem. In this article, we introduce MEDS-OWL, a lightweight OWL ontology that provides formal concepts and relations to represent MEDS datasets as RDF graphs. Additionally, we implemented meds2rdf, a Python conversion library that transforms MEDS events into RDF graphs, ensuring conformance with the ontology. We evaluate the proposed approach on two datasets: a synthetic clinical cohort describing care pathways for ruptured intracranial aneurysms, and a real-world subset of MIMIC-IV. To assess semantic consistency, we performed a SHACL validation against the resulting knowledge graphs. The first release of MEDS-OWL comprises 13 classes, 10 object properties, 20 data properties, and 24 OWL axioms. Combined with meds2rdf, it enables data transformation into FAIR-aligned datasets, provenance-aware publishing, and interoperability of event-based clinical data. By bridging MEDS with the Semantic Web, this work contributes a reusable semantic layer for event-based clinical data and establishes a robust foundation for subsequent graph-based analytics. --- ### Scanner-Induced Domain Shifts Undermine the Robustness of Pathology Foundation Models Authors: Erik Thiringer, Fredrik K. Gustafsson, Kajsa Ledesma Eriksson, Mattias Rantalainen Published: 2026-01-07 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.04163v1 Pathology foundation models (PFMs) have become central to computational pathology, aiming to offer general encoders for feature extraction from whole-slide images (WSIs). Despite strong benchmark performance, PFM robustness to real-world technical domain shifts, such as variability from whole-slide scanner devices, remains poorly understood. We systematically evaluated the robustness of 14 PFMs to scanner-induced variability, including state-of-the-art models, earlier self-supervised models, and a baseline trained on natural images. Using a multiscanner dataset of 384 breast cancer WSIs scanned on five devices, we isolated scanner effects independently from biological and laboratory confounders. Robustness is assessed via complementary unsupervised embedding analyses and a set of clinicopathological supervised prediction tasks. Our results demonstrate that current PFMs are not invariant to scanner-induced domain shifts. Most models encode pronounced scanner-specific variability in their embedding spaces. While AUC often remains stable, this masks a critical failure mode: scanner variability systematically alters the embedding space and impacts calibration of downstream model predictions, resulting in scanner-dependent bias that can impact reliability in clinical use cases. We further show that robustness is not a simple function of training data scale, model size, or model recency. None of the models provided reliable robustness against scanner-induced variability. While the models trained on the most diverse data, here represented by vision-language models, appear to have an advantage with respect to robustness, they underperformed on downstream supervised tasks. We conclude that development and evaluation of PFMs requires moving beyond accuracy-centric benchmarks toward explicit evaluation and optimisation of embedding stability and calibration under realistic acquisition variability. --- ### All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection Authors: Yuechen Jiang, Zhiwei Liu, Yupeng Cao, Yueru He, Ziyang Xu, Chen Xu, Zhiyang Deng, Prayag Tiwari, Xi Chen, Alejandro Lopez-Lira, Jimin Huang, Junichi Tsujii et al. Published: 2026-01-07 Categories: cs.CL, cs.CE, q-fin.CP arXiv: https://arxiv.org/abs/2601.04160v3 We introduce RFC Bench, a benchmark for evaluating large language models on financial misinformation under realistic news. RFC Bench operates at the paragraph level and captures the contextual complexity of financial news where meaning emerges from dispersed cues. The benchmark defines two complementary tasks: reference free misinformation detection and comparison based diagnosis using paired original perturbed inputs. Experiments reveal a consistent pattern: performance is substantially stronger when comparative context is available, while reference free settings expose significant weaknesses, including unstable predictions and elevated invalid outputs. These results indicate that current models struggle to maintain coherent belief states without external grounding. By highlighting this gap, RFC Bench provides a structured testbed for studying reference free reasoning and advancing more reliable financial misinformation detection in real world settings. --- ### ToTMNet: FFT-Accelerated Toeplitz Temporal Mixing Network for Lightweight Remote Photoplethysmography Authors: Vladimir Frants, Sos Agaian, Karen Panetta Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.04159v1 Remote photoplethysmography (rPPG) estimates a blood volume pulse (BVP) waveform from facial videos captured by commodity cameras. Although recent deep models improve robustness compared to classical signal-processing approaches, many methods increase computational cost and parameter count, and attention-based temporal modeling introduces quadratic scaling with respect to the temporal length. This paper proposes ToTMNet, a lightweight rPPG architecture that replaces temporal attention with an FFT-accelerated Toeplitz temporal mixing layer. The Toeplitz operator provides full-sequence temporal receptive field using a linear number of parameters in the clip length and can be applied in near-linear time using circulant embedding and FFT-based convolution. ToTMNet integrates the global Toeplitz temporal operator into a compact gated temporal mixer that combines a local depthwise temporal convolution branch with gated global Toeplitz mixing, enabling efficient long-range temporal filtering while only having 63k parameters. Experiments on two datasets, UBFC-rPPG (real videos) and SCAMPS (synthetic videos), show that ToTMNet achieves strong heart-rate estimation accuracy with a compact design. On UBFC-rPPG intra-dataset evaluation, ToTMNet reaches 1.055 bpm MAE with Pearson correlation 0.996. In a synthetic-to-real setting (SCAMPS to UBFC-rPPG), ToTMNet reaches 1.582 bpm MAE with Pearson correlation 0.994. Ablation results confirm that the gating mechanism is important for effectively using global Toeplitz mixing, especially under domain shift. The main limitation of this preprint study is the use of only two datasets; nevertheless, the results indicate that Toeplitz-structured temporal mixing is a practical and efficient alternative to attention for rPPG. --- ### FLEx: Language Modeling with Few-shot Language Explanations Authors: Adar Avsian, Christopher Richardson, Anirudh Sundar, Larry Heck Published: 2026-01-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.04157v2 Language models have become effective at a wide range of tasks, from math problem solving to open-domain question answering. However, they still make mistakes, and these mistakes are often repeated across related queries. Natural language explanations can help correct these errors, but collecting them at scale may be infeasible, particularly in domains where expert annotators are required. To address this issue, we introduce FLEx ($\textbf{F}$ew-shot $\textbf{L}$anguage $\textbf{Ex}$planations), a method for improving model behavior using a small number of explanatory examples. FLEx selects representative model errors using embedding-based clustering, verifies that the associated explanations correct those errors, and summarizes them into a prompt prefix that is prepended at inference-time. This summary guides the model to avoid similar errors on new inputs, without modifying model weights. We evaluate FLEx on CounterBench, GSM8K, and ReasonIF. We find that FLEx consistently outperforms chain-of-thought (CoT) prompting across all three datasets and reduces up to 83\% of CoT's remaining errors. --- ### Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning Authors: Yifan Wang, Yanyu Li, Gordon Guocheng Qian, Sergey Tulyakov, Yun Fu, Anil Kag Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.04153v2 Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Moreover, scalar rewards provide coarse, global supervision, offering limited prompt-generation mismatch credit assignment and making models prone to reward exploitation and unstable optimization. We propose Diffusion-DRF, a free, rich, and differentiable reward framework for video diffusion fine-tuning. Diffusion-DRF employs a frozen, off-the-shelf Vision-Language Model (VLM) as the critic, eliminating the need for reward model training. Instead of relying on a single scalar reward, it decomposes each user prompt into multi-dimensional questions with freeform dense VQA explanation queries, yielding information-rich feedback. By direct differentiable optimization over this rich feedback, Diffusion-DRF achieves stable reward-based tuning without preference datasets collection. Diffusion-DRF achieves significant gains both quantitatively and qualitatively, outperforming state-of-the-art Flow-GRPO by 4.74% in overall performance on unseen VBench-2.0. --- ### Apollo: Unified Multi-Task Audio-Video Joint Generation Authors: Jun Wang, Chunyu Qiang, Yuxin Guo, Yiran Wang, Xijuan Zeng, Feng Deng Published: 2026-01-07 Categories: cs.CV, cs.AI, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2601.04151v2 Audio-video joint generation has progressed rapidly, yet substantial challenges still remain. Non-commercial approaches still suffer audio-visual asynchrony, poor lip-speech alignment, and unimodal degradation, which can be stemmed from weak audio-visual correspondence modeling, limited generalization, and scarce high-quality dense-caption data. To address these issues, we introduce Apollo and delve into three axes--model architecture, training strategy, and data curation. Architecturally, we adopt a single-tower design with unified DiT blocks and an Omni-Full Attention mechanism, achieving tight audio-visual alignment and strong scalability. Training-wise, we adopt a progressive multitask regime--random modality masking to joint optimization across tasks, and a multistage curriculum, yielding robust representations, strengthening A-V aligned world knowledge, and preventing unimodal collapse. For datasets, we present the first large-scale audio-video dataset with dense captions, and introduce a novel automated data-construction pipeline which annotates and filters millions of diverse, high-quality, strictly aligned audio-video-caption triplets. Building on this, Apollo scales to large datasets, delivering high-fidelity, semantically and temporally aligned, instruction-following generation in both joint and unimodal settings while generalizing robustly to out-of-distribution scenarios. Across tasks, it substantially outperforms prior methods by a large margin and achieves performance comparable to Veo 3, offering a unified, scalable path toward next-generation audio-video synthesis. --- ### A Theoretical and Empirical Taxonomy of Imbalance in Binary Classification Authors: Rose Yvette Bandolo Essomba, Ernest Fokoué Published: 2026-01-07 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.04149v1 Class imbalance significantly degrades classification performance, yet its effects are rarely analyzed from a unified theoretical perspective. We propose a principled framework based on three fundamental scales: the imbalance coefficient $η$, the sample--dimension ratio $κ$, and the intrinsic separability $Δ$. Starting from the Gaussian Bayes classifier, we derive closed-form Bayes errors and show how imbalance shifts the discriminant boundary, yielding a deterioration slope that predicts four regimes: Normal, Mild, Extreme, and Catastrophic. Using a balanced high-dimensional genomic dataset, we vary only $η$ while keeping $κ$ and $Δ$ fixed. Across parametric and non-parametric models, empirical degradation closely follows theoretical predictions: minority Recall collapses once $\log(η)$ exceeds $Δ\sqrtκ$, Precision increases asymmetrically, and F1-score and PR-AUC decline in line with the predicted regimes. These results show that the triplet $(η,κ,Δ)$ provides a model-agnostic, geometrically grounded explanation of imbalance-induced deterioration. --- ### Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test Authors: Chun-Kai Fan, Xiaowei Chi, Xiaozhu Ju, Hao Li, Yong Bao, Yu-Kai Wang, Lizhang Chen, Zhiyuan Jiang, Kuangzhi Ge, Ying Li, Weishi Mi, Qingpo Wuwu et al. Published: 2026-01-07 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.04137v1 As world models gain momentum in Embodied AI, an increasing number of works explore using video foundation models as predictive world models for downstream embodied tasks like 3D prediction or interactive generation. However, before exploring these downstream tasks, video foundation models still have two critical questions unanswered: (1) whether their generative generalization is sufficient to maintain perceptual fidelity in the eyes of human observers, and (2) whether they are robust enough to serve as a universal prior for real-world embodied agents. To provide a standardized framework for answering these questions, we introduce the Embodied Turing Test benchmark: WoW-World-Eval (Wow,wo,val). Building upon 609 robot manipulation data, Wow-wo-val examines five core abilities, including perception, planning, prediction, generalization, and execution. We propose a comprehensive evaluation protocol with 22 metrics to assess the models' generation ability, which achieves a high Pearson Correlation between the overall score and human preference (>0.93) and establishes a reliable foundation for the Human Turing Test. On Wow-wo-val, models achieve only 17.27 on long-horizon planning and at best 68.02 on physical consistency, indicating limited spatiotemporal consistency and physical reasoning. For the Inverse Dynamic Model Turing Test, we first use an IDM to evaluate the video foundation models' execution accuracy in the real world. However, most models collapse to $\approx$ 0% success, while WoW maintains a 40.74% success rate. These findings point to a noticeable gap between the generated videos and the real world, highlighting the urgency and necessity of benchmarking World Model in Embodied AI. --- ### LLMberjack: Guided Trimming of Debate Trees for Multi-Party Conversation Creation Authors: Leonardo Bottona, Nicolò Penzo, Bruno Lepri, Marco Guerini, Sara Tonelli Published: 2026-01-07 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2601.04135v1 We present LLMberjack, a platform for creating multi-party conversations starting from existing debates, originally structured as reply trees. The system offers an interactive interface that visualizes discussion trees and enables users to construct coherent linearized dialogue sequences while preserving participant identity and discourse relations. It integrates optional large language model (LLM) assistance to support automatic editing of the messages and speakers' descriptions. We demonstrate the platform's utility by showing how tree visualization facilitates the creation of coherent, meaningful conversation threads and how LLM support enhances output quality while reducing human effort. The tool is open-source and designed to promote transparent and reproducible workflows to create multi-party conversations, addressing a lack of resources of this type. --- ### ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models Authors: Nikhil Anand, Shwetha Somasundaram, Anirudh Phukan, Apoorv Saxena, Koyel Mukherjee Published: 2026-01-07 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.04131v2 Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability to faithfully follow externally retrieved context. When such evidence conflicts with the model's internal knowledge, LLMs often default to memorized facts, producing unfaithful outputs. In this work, we introduce ContextFocus, a lightweight activation steering approach that improves context faithfulness in such knowledge-conflict settings while preserving fluency and efficiency. Unlike prior approaches, our solution requires no model finetuning and incurs minimal inference-time overhead, making it highly efficient. We evaluate ContextFocus on the ConFiQA benchmark, comparing it against strong baselines including ContextDPO, COIECD, and prompting-based methods. Furthermore, we show that our method is complementary to prompting strategies and remains effective on larger models. Extensive experiments show that ContextFocus significantly improves contextual-faithfulness. Our results highlight the effectiveness, robustness, and efficiency of ContextFocus in improving contextual-faithfulness of LLM outputs. --- ### Pixel-Wise Multimodal Contrastive Learning for Remote Sensing Images Authors: Leandro Stival, Ricardo da Silva Torres, Helio Pedrini Published: 2026-01-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.04127v1 Satellites continuously generate massive volumes of data, particularly for Earth observation, including satellite image time series (SITS). However, most deep learning models are designed to process either entire images or complete time series sequences to extract meaningful features for downstream tasks. In this study, we propose a novel multimodal approach that leverages pixel-wise two-dimensional (2D) representations to encode visual property variations from SITS more effectively. Specifically, we generate recurrence plots from pixel-based vegetation index time series (NDVI, EVI, and SAVI) as an alternative to using raw pixel values, creating more informative representations. Additionally, we introduce PIxel-wise Multimodal Contrastive (PIMC), a new multimodal self-supervision approach that produces effective encoders based on two-dimensional pixel time series representations and remote sensing imagery (RSI). To validate our approach, we assess its performance on three downstream tasks: pixel-level forecasting and classification using the PASTIS dataset, and land cover classification on the EuroSAT dataset. Moreover, we compare our results to state-of-the-art (SOTA) methods on all downstream tasks. Our experimental results show that the use of 2D representations significantly enhances feature extraction from SITS, while contrastive learning improves the quality of representations for both pixel time series and RSI. These findings suggest that our multimodal method outperforms existing models in various Earth observation tasks, establishing it as a robust self-supervision framework for processing both SITS and RSI. Code avaliable on ---