Related papers: CellE: Automated Standard Cell Library Extension v…

There are two halves to RL systems: experience collection time and policy learning time. For a large number of samples in rollouts, experience collection time is the major bottleneck. Thus, it is necessary to speed up the rollout generation…

This paper proposed a new explicit nonlinear dimensionality reduction using neural networks for image retrieval tasks. We first proposed a Quasi-curvature Locally Linear Embedding (QLLE) for training set. QLLE guarantees the linear…

Modern neural network performance typically improves as model size increases. A recent line of research on the Neural Tangent Kernel (NTK) of over-parameterized networks indicates that the improvement with size increase is a product of a…

Erasure coding (EC) affords data redundancy for large-scale systems. XOR-based EC is an easy-to-implement method for optimizing EC. This paper addresses a significant performance gap between the state-of-the-art XOR-based EC approach (with…

Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform…

Accurate question answering over real spreadsheets remains difficult due to multirow headers, merged cells, and unit annotations that disrupt naive chunking, while rigid SQL views fail on files lacking consistent schemas. We present SQuARE,…

Machine learning models are increasingly deployed in wireless networks with stringent performance requirements. However, dynamic propagation environments and fluctuating traffic densities introduce concept drift, which complicates the…

In this paper, statistical Quality of Service provisioning in next generation heterogeneous mobile cellular networks is investigated. To this aim, any active entity of the cellular network is regarded as a queuing system, whose statistical…

Edge intelligence enables AI inference at the network edge, co-located with or near the radio access network, rather than in centralized clouds or on mobile devices. It targets low-latency, resource-constrained applications with large data…

Dynamic symbolic execution (DSE) is a powerful test generation approach based on an exploration of the path space of the program under test. Well-adapted for path coverage, this approach is however less efficient for conditions, decisions,…

The problem of class incremental learning (CIL) is considered. State-of-the-art approaches use a dynamic architecture based on network expansion (NE), in which a task expert is added per task. While effective from a computational…

In this paper, we propose a distributed power control algorithm for addressing the global energy efficiency (GEE) maximization problem subject to satisfying a minimum target SINR for all user equipments (UEs) in wireless cellular networks.…

Discovering diverse visual patterns in continuous cellular automata (CA) is challenging due to the vastness and redundancy of high-dimensional behavioral spaces. Traditional exploration methods like Novelty Search (NS) expand locally by…

Quality Estimation (QE) models have the potential to change how we evaluate and maybe even train machine translation models. However, these models still lack the robustness to achieve general adoption. We show that State-of-the-art QE…

In continuous process plants controlled by model predictive control, model-plant mismatch (MPM), due to the aging of processes, causes degradation of control performance. We propose a concept called Model Life Extension (MLE) and its…

Complementary-label Learning (CLL) is a form of weakly supervised learning that trains an ordinary classifier using only complementary labels, which are the classes that certain instances do not belong to. While existing CLL studies…

Hardware architectures and machine learning (ML) libraries evolve rapidly. Traditional compilers often fail to generate high-performance code across the spectrum of new hardware offerings. To mitigate, engineers develop hand-tuned kernels…

Continual semantic segmentation requires models to adapt to new domains or modalities without sacrificing performance on previously learned tasks. Expert-based learning, in which task-specific modules specialize in different domains, has…

One of the major optimizations employed in deep learning frameworks is graph rewriting. Production frameworks rely on heuristics to decide if rewrite rules should be applied and in which order. Prior research has shown that one can discover…

Error mitigation techniques, while instrumental in extending the capabilities of near-term quantum computers, often suffer from exponential resource scaling with noise levels. To address this limitation, we introduce a novel approach,…