Recent studies [42,56]have visualized the mean attention distance of ViTs, offering deeper insights into weight redundancy among attention heads across different layers.

In this section, we examine three algorithms via four numerical examples. The first algorithm is the Sliding Window-UCB (SW-UCB) algorithm presented in our paper. The second algorithm is the naive UCB algorithm without any sliding windows (Agrawal and Devanur, 2014). The third algorithm is LagrangeBwK presented in (Immorlica et al., 2019), which is originally proposed for the adversarial BwK problem. Note that the LagrangeBwK requires an approximation of the static best distribution benchmark. For simplicity, we put the exact value of the benchmark into the algorithm. All the regret performances are reported based on the average over 100 simulation trials.

The best neural architecture for a given machine learning problem depends on many factors: not only the complexity and structure of the dataset, but also on resource constraints including latency, compute, energy consumption, etc. Neural architecture search (NAS) for tabular datasets is an important but under-explored problem. Previous NAS algorithms designed for image search spaces incorporate resource constraints directly into the reinforcement learning (RL) rewards. However, for NAS on tabular datasets, this protocol often discovers suboptimal architectures. This paper develops TabNAS, a new and more effective approach to handle resource constraints in tabular NAS using an RL controller motivated by the idea of rejection sampling. TabNAS immediately discards any architecture that violates the resource constraints without training or learning from that architecture. TabNAS uses a Monte-Carlo-based correction to the RL policy gradient update to account for this extra filtering step. Results on several tabular datasets demonstrate the superiority of TabNAS over previous reward-shaping methods: it finds better models that obey the constraints.

Training and deploying multiple vision transformer (ViT) models for different resource constraints is costly and inefficient. To address this, we propose transforming a pre-trained ViT into a stratified knowledge-density super-network, where knowledge is hierarchically organized across weights. This enables flexible extraction of sub-networks that retain maximal knowledge for varying model sizes. We introduce \textbf{W}eighted \textbf{P}CA for \textbf{A}ttention \textbf{C}ontraction (WPAC), which concentrates knowledge into a compact set of critical weights. WPAC applies token-wise weighted principal component analysis to intermediate features and injects the resulting transformation and inverse matrices into adjacent layers, preserving the original network function while enhancing knowledge compactness. To further promote stratified knowledge organization, we propose \textbf{P}rogressive \textbf{I}mportance-\textbf{A}ware \textbf{D}ropout (PIAD). PIAD progressively evaluates the importance of weight groups, updates an importance-aware dropout list, and trains the super-network under this dropout regime to promote knowledge stratification. Experiments demonstrate that WPAC outperforms existing pruning criteria in knowledge concentration, and the combination with PIAD offers a strong alternative to state-of-the-art model compression and model expansion methods.

Generative Artificial Intelligence (GenAI) presents transformative opportunities for organizations, yet both midsize organizations and larger enterprises face distinctive adoption challenges. Midsize organizations encounter resource constraints and limited AI expertise, while enterprises struggle with organizational complexity and coordination challenges. Existing technology adoption frameworks, including TAM (Technology Acceptance Model), TOE (Technology Organization Environment), and DOI (Diffusion of Innovations) theory, lack the specificity required for GenAI implementation across these diverse contexts, creating a critical gap in adoption literature. This paper introduces FAIGMOE (Framework for the Adoption and Integration of Generative AI in Midsize Organizations and Enterprises), a conceptual framework addressing the unique needs of both organizational types. FAIGMOE synthesizes technology adoption theory, organizational change management, and innovation diffusion perspectives into four interconnected phases: Strategic Assessment, Planning and Use Case Development, Implementation and Integration, and Operationalization and Optimization. Each phase provides scalable guidance on readiness assessment, strategic alignment, risk governance, technical architecture, and change management adaptable to organizational scale and complexity. The framework incorporates GenAI specific considerations including prompt engineering, model orchestration, and hallucination management that distinguish it from generic technology adoption frameworks. As a perspective contribution, FAIGMOE provides the first comprehensive conceptual framework explicitly addressing GenAI adoption across midsize and enterprise organizations, offering actionable implementation protocols, assessment instruments, and governance templates requiring empirical validation through future research.

We introduce Constraint-Aware Federated Learning with Lagrangian Dual Optimization (CAFL-L), a principled extension of FedAvg that explicitly incorporates device-level resource constraints including energy, communication, memory, and thermal budgets. CAFL-L employs Lagrangian dual optimization to dynamically adapt training hyperparameters -- freezing depth, local steps, batch size, and communication compression -- while preserving training stability through token-budget preservation via gradient accumulation. Experiments on a character-level language model demonstrate that CAFL-L achieves superior constraint satisfaction compared to standard FedAvg (reducing memory usage by 20% and communication by 95%) while maintaining competitive validation performance, making it practical for deployment on resource-constrained edge devices.

Neural Architecture Search (NAS) has emerged as a powerful approach for automating neural network design. However, existing NAS methods face critical limitations in real-world deployments: architectures lack adaptability across scenarios, each deployment context requires costly separate searches, and performance consistency across diverse platforms remains challenging. We propose DANCE (Dynamic Architectures with Neural Continuous Evolution), which reformulates architecture search as a continuous evolution problem through learning distributions over architectural components. DANCE introduces three key innovations: a continuous architecture distribution enabling smooth adaptation, a unified architecture space with learned selection gates for efficient sampling, and a multi-stage training strategy for effective deployment optimization. Extensive experiments across five datasets demonstrate DANCE's effectiveness. Our method consistently outperforms state-of-the-art NAS approaches in terms of accuracy while significantly reducing search costs. Under varying computational constraints, DANCE maintains robust performance while smoothly adapting architectures to different hardware requirements.

In this section, we examine three algorithms via four numerical examples. The first algorithm is the Sliding Window-UCB (SW-UCB) algorithm presented in our paper. The second algorithm is the naive UCB algorithm without any sliding windows (Agrawal and Devanur, 2014). The third algorithm is LagrangeBwK presented in (Immorlica et al., 2019), which is originally proposed for the adversarial BwK problem. Note that the LagrangeBwK requires an approximation of the static best distribution benchmark.

TinyNAS is co-designed with TinyEngine, a memory-efficient inference library to expand the search space and fit a larger model.