Distilling long reasoning traces (10K+ tokens) from stronger teacher models into smaller student LLMs via SFT has emerged as a standard paradigm. This approach is practical and efficient: it leverages the ease of generating abundant reasoning data from stronger models and provides a direct, data-driven way to teach less capable models better reasoning. While previous work has largely focused on prompt selection with responses from a single teacher, the equally important problem of choosing the best response when multiple teacher outputs are available for a single prompt remains underexplored. This challenge becomes important in a multi-teacher setting, where different students may benefit from the outputs of different teachers. This paper fills that gap with a systematic study of response selection for reasoning distillation. We first show that the current method, which picks responses the student assigns the highest global log-probability (global naturalness), fails when responses come from multiple teachers, i.e., global naturalness no longer correlates with downstream performance, especially as the reasoning traces from strong teachers become longer. To overcome this problem, we introduce Local Naturalness, which measures the student's log-probabilities over short, sequential reasoning steps conditioned only on a small local window. Local Naturalness enables two applications: 1) Teacher Selection: Aggregating local scores across prompts reliably identifies the most helpful teacher. 2) Response Selection from a Multiple Teachers: When mixing answers from many teachers, Local Naturalness boosts a 32B student's accuracy on math benchmarks by 9.4pp over global selection, also surpassing the performance achieved by training on data from the single best teacher. These results highlight the power of localized data quality evaluation and data mixing for more effective reasoning distillation.

Continuous-depth graph neural networks, also known as Graph Neural Differential Equations (GNDEs), combine the structural inductive bias of Graph Neural Networks (GNNs) with the continuous-depth architecture of Neural ODEs, offering a scalable and principled framework for modeling dynamics on graphs. In this paper, we present a rigorous convergence analysis of GNDEs with time-varying parameters in the infinite-node limit, providing theoretical insights into their size transferability. To this end, we introduce Graphon Neural Differential Equations (Graphon-NDEs) as the infinite-node limit of GNDEs and establish their well-posedness. Leveraging tools from graphon theory and dynamical systems, we prove the trajectory-wise convergence of GNDE solutions to Graphon-NDE solutions. Moreover, we derive explicit convergence rates under two deterministic graph sampling regimes: (1) weighted graphs sampled from smooth graphons, and (2) unweighted graphs sampled from $\{0,1\}$-valued (discontinuous) graphons. We further establish size transferability bounds, providing theoretical justification for the practical strategy of transferring GNDE models trained on moderate-sized graphs to larger, structurally similar graphs without retraining. Numerical experiments using synthetic and real data support our theoretical findings.

Small language models (SLMs; 1-12B params, sometimes up to 20B) are sufficient and often superior for agentic workloads where the objective is schema- and API-constrained accuracy rather than open-ended generation. We synthesize recent evidence across open and proprietary SLMs (Phi-4-Mini, Qwen-2.5-7B, Gemma-2-9B, Llama-3.2-1B/3B, Ministral-3B/8B, Apple on-device 3B, DeepSeek-R1-Distill) and connect it to modern evaluations (BFCL v3/v4, StableToolBench) and serving stacks (vLLM, SGLang, TensorRT-LLM) paired with guided decoding libraries (XGrammar, Outlines). We formalize SLM-default, LLM-fallback systems with uncertainty-aware routing and verifier cascades, and propose engineering metrics that reflect real production goals: cost per successful task (CPS), schema validity rate, executable call rate, p50/p95 latency, and energy per request. Guided decoding, strict JSON Schema outputs, and validator-first tool execution close much of the capability gap with larger models and often let SLMs match or surpass LLMs on tool use, function calling, and RAG at 10x-100x lower token cost with materially better latency and energy. We provide design patterns for agent stacks that prioritize SLMs: schema-first prompting, type-safe function registries, confidence scoring with verifier rollups, and lightweight adaptation via LoRA/QLoRA. We also delineate limits where fallback remains valuable (open-domain reasoning and some long-horizon planning). The result is a practical blueprint for building fast, inexpensive, and reliable agents that default to SLMs while preserving headroom with targeted LLM assistance. Keywords: small language models, agents, function calling, structured outputs, JSON Schema, guided decoding, LoRA/QLoRA, routing, energy efficiency, edge inference

Humans understand the world through the integration of multiple sensory modalities, enabling them to perceive, reason about, and imagine dynamic physical processes. Inspired by this capability, multimodal foundation models (MFMs) have emerged as powerful tools for multimodal understanding and generation. However, today's MFMs fall short of serving as effective world models. They lack the essential ability such as perform counterfactual reasoning, simulate dynamics, understand the spatiotemporal information, control generated visual outcomes, and perform multifaceted reasoning. We investigates what it takes to bridge the gap between multimodal foundation models and world models. We begin by improving the reasoning capabilities of MFMs through discriminative tasks and equipping MFMs with structured reasoning skills, such as causal inference, counterfactual thinking, and spatiotemporal reasoning, enabling them to go beyond surface correlations and understand deeper relationships within visual and textual data. Next, we explore generative capabilities of multimodal foundation models across both image and video modalities, introducing new frameworks for structured and controllable generation. Our approaches incorporate scene graphs, multimodal conditioning, and multimodal alignment strategies to guide the generation process, ensuring consistency with high-level semantics and fine-grained user intent. We further extend these techniques to controllable 4D generation, enabling interactive, editable, and morphable object synthesis over time and space.

Recent advances in self-supervised learning (SSL) have made it possible to learn general-purpose visual features that capture both the high level semantics and the fine-grained spatial structure of images. Most notably, the recent DINOv2 has established a new state of the art by surpassing weakly supervised methods (WSL) like OpenCLIP on most benchmarks. In this survey, we examine the core ideas behind its approach, multi-crop view augmentation and self-distillation with a mean teacher, and trace their development in previous work. W e then compare the performance of DINO and DINOv2 with other SSL and WSL methods across various downstream tasks, and highlight some remarkable emergent properties of their learned features with transformer backbones. W e conclude by briefly discussing DINOv2's limitations, its impact, and future research directions.

Remaining Useful Life (RUL) prediction for turbofan engines plays a vital role in predictive maintenance, ensuring operational safety and efficiency in aviation. Although data-driven approaches using machine learning and deep learning have shown potential, they face challenges such as limited data and distribution shifts caused by varying operating conditions. Domain Adaptation (DA) has emerged as a promising solution, enabling knowledge transfer from source domains with abundant data to target domains with scarce data while mitigating distributional shifts. Given the unique properties of turbofan engines, such as complex operating conditions, high-dimensional sensor data, and slower-changing signals, it is essential to conduct a focused review of DA techniques specifically tailored to turbofan engines. To address this need, this paper provides a comprehensive review of DA solutions for turbofan engine RUL prediction, analyzing key methodologies, challenges, and recent advancements. A novel taxonomy tailored to turbofan engines is introduced, organizing approaches into methodology-based (how DA is applied), alignment-based (where distributional shifts occur due to operational variations), and problem-based (why certain adaptations are needed to address specific challenges). This taxonomy offers a multidimensional view that goes beyond traditional classifications by accounting for the distinctive characteristics of turbofan engine data and the standard process of applying DA techniques to this area. Additionally, we evaluate selected DA techniques on turbofan engine datasets, providing practical insights for practitioners and identifying key challenges. Future research directions are identified to guide the development of more effective DA techniques, advancing the state of RUL prediction for turbofan engines.

We start with reviewing normative actions of international organizations and concerns expressed about the current technical landscape. Then we proceed with proposing a framework that comprises five key dimensions relating to the main challenges relating to AI in higher education institutions, followed by five key strategic actions that the main stakeholders need to take in order to address the current developments . W e map these actions to the main stakeholders of higher education and propose a deployment plan . This defines a framework along the dimensions: C hallenges, Actions, Stakeholders, Deployment CASD . Examples of AI specific actions at the institutional and individu al course level are also provided and discussed.

Ensuring the safety of vulnerable road users (VRUs), such as pedestrians and cyclists, remains a critical global challenge, as conventional infrastructure-based measures often prove inadequate in dynamic urban environments. Recent advances in artificial intelligence (AI), particularly in visual perception and reasoning, open new opportunities for proactive and context-aware VRU protection. However, existing surveys on AI applications for VRUs predominantly focus on detection, offering limited coverage of other vision-based tasks that are essential for comprehensive VRU understanding and protection. This paper presents a state-of-the-art review of recent progress in camera-based AI sensing systems for VRU safety, with an emphasis on developments from the past five years and emerging research trends. We systematically examine four core tasks, namely detection and classification, tracking and reidentification, trajectory prediction, and intent recognition and prediction, which together form the backbone of AI-empowered proactive solutions for VRU protection in intelligent transportation systems. To guide future research, we highlight four major open challenges from the perspectives of data, model, and deployment. By linking advances in visual AI with practical considerations for real-world implementation, this survey aims to provide a foundational reference for the development of next-generation sensing systems to enhance VRU safety.

Recommender systems have traditionally followed modular architectures comprising candidate generation, multi-stage ranking, and re-ranking, each trained separately with supervised objectives and hand-engineered features. While effective in many domains, such systems face persistent challenges including sparse and noisy interaction data, cold-start problems, limited personalization depth, and inadequate semantic understanding of user and item content. The recent emergence of Large Language Models (LLMs) offers a new paradigm for addressing these limitations through unified, language-native mechanisms that can generalize across tasks, domains, and modalities. In this paper, we present a comprehensive technical survey of how LLMs can be leveraged to tackle key challenges in modern recommender systems. We examine the use of LLMs for prompt-driven candidate retrieval, language-native ranking, retrieval-augmented generation (RAG), and conversational recommendation, illustrating how these approaches enhance personalization, semantic alignment, and interpretability without requiring extensive task-specific supervision. LLMs further enable zero- and few-shot reasoning, allowing systems to operate effectively in cold-start and long-tail scenarios by leveraging external knowledge and contextual cues. We categorize these emerging LLM-driven architectures and analyze their effectiveness in mitigating core bottlenecks of conventional pipelines. In doing so, we provide a structured framework for understanding the design space of LLM-enhanced recommenders, and outline the trade-offs between accuracy, scalability, and real-time performance. Our goal is to demonstrate that LLMs are not merely auxiliary components but foundational enablers for building more adaptive, semantically rich, and user-centric recommender systems

The emergence of reinforcement learning in post-training of large language models has sparked significant interest in reward models. Reward models assess the quality of sampled model outputs to generate training signals. This task is also performed by evaluation metrics that monitor the performance of an AI model. We find that the two research areas are mostly separate, leading to redundant terminology and repeated pitfalls. Common challenges include susceptibility to spurious correlations, impact on downstream reward hacking, methods to improve data quality, and approaches to meta-evaluation. Our position paper argues that a closer collaboration between the fields can help overcome these issues. To that end, we show how metrics outperform reward models on specific tasks and provide an extensive survey of the two areas. Grounded in this survey, we point to multiple research topics in which closer alignment can improve reward models and metrics in areas such as preference elicitation methods, avoidance of spurious correlations and reward hacking, and calibration-aware meta-evaluation.