Margin-based optimization is fundamental to improving generalization and robustness in classification tasks. In the context of reward model learning from preferences within Reinforcement Learning from Human Feedback (RLHF), existing methods typically rely on no margins, fixed margins, or margins that are simplistic functions of preference ratings. However, such formulations often fail to account for the varying strengths of different preferences, for example some preferences are associated with larger margins between responses, or they rely on noisy margin information derived from ratings. We argue that modeling the strength of preferences can lead to better generalization and more faithful alignment. Furthermore, many existing methods that use adaptive margins assume access to accurate preference scores, which can be difficult for humans to provide reliably. We propose an approach that leverages preferences over preferences, that is annotations indicating which of two preferences reflects a stronger distinction. We use this ordinal signal to infer adaptive margins on a per-datapoint basis. We introduce an extension to Direct Preference Optimization (DPO), DPO-PoP, that incorporates adaptive margins from preference-over-preference supervision, enabling improved discriminative and generative performance. Empirically, our method outperforms vanilla DPO, DPO with fixed margins, and DPO with ground-truth margins on the UltraFeedback dataset. Additionally, we show that there is a tradeoff between discriminative and generative performance: improving test classification accuracy, particularly by correctly labeling weaker preferences at the expense of stronger ones, can lead to a decline in generative quality. To navigate this tradeoff, we propose two sampling strategies to gather preference-over-preference labels: one favoring discriminative performance and one favoring generative performance.

Automating the translation of natural language to first-order logic (FOL) is crucial for knowledge representation and formal methods, yet remains challenging. We present a systematic evaluation of fine-tuned LLMs for this task, comparing architectures (encoder-decoder vs. decoder-only) and training strategies. Using the MALLS and Willow datasets, we explore techniques like vocabulary extension, predicate conditioning, and multilingual training, introducing metrics for exact match, logical equivalence, and predicate alignment. Our fine-tuned Flan-T5-XXL achieves 70% accuracy with predicate lists, outperforming GPT-4o and even the DeepSeek-R1-0528 model with CoT reasoning ability as well as symbolic systems like ccg2lambda. Key findings show: (1) predicate availability boosts performance by 15-20%, (2) T5 models surpass larger decoder-only LLMs, and (3) models generalize to unseen logical arguments (FOLIO dataset) without specific training. While structural logic translation proves robust, predicate extraction emerges as the main bottleneck.

Prior-data fitted networks (PFNs) are a promising alternative to time-consuming Gaussian process (GP) inference for creating fast surrogates of physical systems. PFN reduces the computational burden of GP-training by replacing Bayesian inference in GP with a single forward pass of a learned prediction model. We introduce Decoupled-V alue Attention (DV A)- motivated by the GP property that the function space is fully characterized by the kernel over inputs and the predictive mean is a weighted sum of training targets. DV A computes similarities from inputs only and propagates labels solely through values. Thus, the proposed DV A mirrors the GP update while remaining kernel-free. We demonstrate that PFNs are backbone architecture invariant and the crucial factor for scaling PFNs is the attention rule rather than the architecture itself. Specifically, our results demonstrate that (a) localized attention consistently reduces out-of-sample validation loss in PFNs across different dimensional settings, with validation loss reduced by more than 50% in five-and ten-dimensional cases, and (b) the role of attention is more decisive than the choice of backbone architecture, showing that CNN, RNN and LSTM-based PFNs can perform at par with their Transformer-based counterparts. Bayesian inference provides a powerful framework for reasoning under uncertainty, with methods like Gaussian processes (GPs) offering well-calibrated predictions and principled uncertainty estimates (Williams & Rasmussen, 2006). However, the practical application of these methods is often hindered by the heavy computational burden of learning kernel hyperparameters. For example, exact GP inference scales cubically with the number of data points, making its deployment infeasible for large datasets or problems requiring repeated training. Consider a physical system where a surrogate GP is chosen due to its uncertainty estimates and differentiable closed-form expressions. However, the underlying input dataset and configuration changes frequently, and the surrogate is supposed to work for these new, previously unseen variations. In such conditions, GP needs to be trained repeatedly, incurring significant computing cost, each time the dataset changes.

The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these deficiencies, we propose a principled engineering framework comprising Runtime Goal Refinement (RGR), Observable Cognitive Architecture (OCA), and Evolutionary Memory Architecture (EMA). In this framework, RGR ensures robustness and intent alignment via knowledge-constrained refinement and human-in-the-loop clarification; OCA builds an observable and maintainable white-box architecture using component decoupling, logic layering, and state-control separation; and EMA employs an execution-evolution dual-loop for evolvability. We implemented and empirically validated Fairy, a mobile GUI agent based on this framework. On RealMobile-Eval, our novel benchmark for ambiguous and complex tasks, Fairy outperformed the best SoTA baseline in user requirement completion by 33.7%. Subsequent controlled experiments, human-subject studies, and ablation studies further confirmed that the RGR enhances refinement accuracy and prevents intent deviation; the OCA improves maintainability; and the EMA is crucial for long-term performance. This research provides empirically validated specifications and a practical blueprint for building reliable, observable, and evolvable Agentic AI systems.

World models have shown potential in artificial intelligence by predicting and reasoning about world states beyond direct observations. However, existing approaches are predominantly evaluated in synthetic environments or constrained scene settings, limiting their validation in real-world contexts with broad spatial coverage and complex semantics. Meanwhile, remote sensing applications urgently require spatial reasoning capabilities for disaster response and urban planning. This paper bridges these gaps by introducing the first framework for world modeling in remote sensing. We formulate remote sensing world modeling as direction-conditioned spatial extrapolation, where models generate semantically consistent adjacent image tiles given a central observation and directional instruction. To enable rigorous evaluation, we develop RSWISE (Remote Sensing World-Image Spatial Evaluation), a benchmark containing 1,600 evaluation tasks across four scenarios: general, flood, urban, and rural. RSWISE combines visual fidelity assessment with instruction compliance evaluation using GPT-4o as a semantic judge, ensuring models genuinely perform spatial reasoning rather than simple replication. Afterwards, we present RemoteBAGEL, a unified multimodal model fine-tuned on remote sensing data for spatial extrapolation tasks. Extensive experiments demonstrate that RemoteBAGEL consistently outperforms state-of-the-art baselines on RSWISE.

Lane-change maneuvers are a leading cause of highway accidents, underscoring the need for accurate intention prediction to improve the safety and decision-making of autonomous driving systems. While prior studies using machine learning and deep learning methods (e.g., SVM, CNN, LSTM, Transformers) have shown promise, most approaches remain limited by binary classification, lack of scenario diversity, and degraded performance under longer prediction horizons. In this study, we propose a physics-informed AI framework that explicitly integrates vehicle kinematics, interaction feasibility, and traffic-safety metrics (e.g., distance headway, time headway, time-to-collision, closing gap time) into the learning process. lane-change prediction is formulated as a three-class problem that distinguishes left change, right change, and no change, and is evaluated across both straight highway segments (highD) and complex ramp scenarios (exiD). By integrating vehicle kinematics with interaction features, our machine learning models, particularly LightGBM, achieve state-of-the-art accuracy and strong generalization. Results show up to 99.8% accuracy and 93.6% macro F1 on highD, and 96.1% accuracy and 88.7% macro F1 on exiD at a 1-second horizon, outperforming a two-layer stacked LSTM baseline. These findings demonstrate the practical advantages of a physics-informed and feature-rich machine learning framework for real-time lane-change intention prediction in autonomous driving systems.

Abstract--In large scale e-commerce marketplaces, duplicate product listings frequently cause consumer confusion and operational inefficiencies, degrading trust on the platform and increasing costs. Traditional keyword-based search methodologies falter in accurately identifying duplicates due to their reliance on exact textual matches, neglecting semantic similarities inherent in product titles. T o address these challenges, we introduce a scalable, multimodal product deduplication designed specifically for the e-commerce domain. Our approach employs a domain-specific text model grounded in BERT architecture in conjunction with MaskedAutoEncoders for image representations. Both of these architectures are augmented with dimensionality reduction techniques to produce compact 128-dimensional embeddings without significant information loss. Complementing this, we also developed a novel decider model that leverages both text and image vectors. By integrating these feature extraction mechanisms with Milvus, an optimized vector database, our system can facilitate efficient and high-precision similarity searches across extensive product catalogs exceeding 200 million items with just 100GB of system RAM consumption. Empirical evaluations demonstrate that our matching system achieves a macro-average F1 score of 0.90, outperforming third-party solutions which attain an F1 score of 0.83. Our findings show the potential of combining domain-specific adaptations with state-of-the-art machine learning techniques to mitigate duplicate listings in large-scale e-commerce environments. In today's vast e-commerce marketplaces, particularly within the Turkish e-commerce landscape, customers frequently encounter duplicate product listings that create confusion and frustration during shopping.

In the realm of distributed artificial intelligence (AI) and privacy-focused medical applications, this paper proposes a multi-view clustering framework that links quantum field theory with federated healthcare analytics. The method uses heat kernel coefficients from spectral analysis to convert Euclidean distances into geometry-aware similarity measures that capture the structure of diverse medical data. The framework is presented through the heat kernel distance (HKD) transformation, which has convergence guarantees. Two algorithms have been developed: The first, Heat Kernel-Enhanced Multi-View Fuzzy Clustering (HK-MVFC), is used for central analysis. The second, Federated Heat Kernel Multi-View Fuzzy Clustering (FedHK-MVFC), is used for secure, privacy-preserving learning across hospitals. FedHK-MVFC uses differential privacy and secure aggregation to enable HIPAA-compliant collaboration. Tests on synthetic cardiovascular patient datasets demonstrate increased clustering accuracy, reduced communication, and retained efficiency compared to centralized methods. After being validated on 10,000 synthetic patient records across two hospitals, the methods proved useful for collaborative phenotyping involving electrocardiogram (ECG) data, cardiac imaging data, and behavioral data. The proposed methods' theoretical contributions include update rules with proven convergence, adaptive view weighting, and privacy-preserving protocols. These contributions establish a new standard for geometry-aware federated learning in healthcare, translating advanced mathematics into practical solutions for analyzing sensitive medical data while ensuring rigor and clinical relevance.

Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for teaching robots complex behaviors without reward engineering. However, its effectiveness is often limited by two critical challenges: the reliance on extensive human input and the inherent difficulties in resolving query ambiguity and credit assignment during reward learning. In this paper, we introduce PRIMT, a PbRL framework designed to overcome these challenges by leveraging foundation models (FMs) for multimodal synthetic feedback and trajectory synthesis. Unlike prior approaches that rely on single-modality FM evaluations, PRIMT employs a hierarchical neuro-symbolic fusion strategy, integrating the complementary strengths of large language models and vision-language models in evaluating robot behaviors for more reliable and comprehensive feedback. PRIMT also incorporates foresight trajectory generation, which reduces early-stage query ambiguity by warm-starting the trajectory buffer with bootstrapped samples, and hindsight trajectory augmentation, which enables counterfactual reasoning with a causal auxiliary loss to improve credit assignment. We evaluate PRIMT on 2 locomotion and 6 manipulation tasks on various benchmarks, demonstrating superior performance over FM-based and scripted baselines.

Prevailing alignment methods induce opaque parameter changes, obscuring what models truly learn. To address this, we introduce Feature Steering with Reinforcement Learning (FSRL), a framework that trains a lightweight adapter to steer model behavior by modulating interpretable sparse features. First, we theoretically demonstrate that this mechanism is expressive enough to approximate the behavioral shifts of post-training processes. We then apply FSRL to preference optimization and perform a causal analysis of the learned policy. Our analysis reveals a crucial insight: the model learns to reward stylistic presentation as a proxy for quality, disproportionately relying on features related to style and formatting over those tied to alignment concepts like honesty. By effectively optimizing the preference objective, FSRL serves as a transparent proxy for observing the alignment process. Overall, FSRL offers an interpretable control interface and a practical way to diagnose how preference optimization pressures manifest at the feature level.