arXiv subjects

Naseef Mansoor

Publications and source records attributed to Naseef Mansoor.

4 recordsLinked to original sources

arXiv2026

An Agentic System for Schema Aware NL2SQL Generation

The natural language to SQL (NL2SQL) task plays a pivotal role in democratizing data access by enabling non-expert users to interact with relational databases through intuitive language. While recent frameworks have enhanced translation accuracy via task specialization, their reliance on Large Language Models (LLMs) raises significant concerns regarding computational overhead, data privacy, and real-world deployability in resource-constrained environments. To address these challenges, we propose a schema based agentic system that strategically employs Small Language Models (SLMs) as primary agents, complemented by a selective LLM fallback mechanism. The LLM is invoked only upon detection of errors in SLM-generated output, the proposed system significantly minimizes computational expenditure. Experimental results on the BIRD benchmark demonstrate that our system achieves an execution accuracy of 47.78% and a validation efficiency score of 51.05%, achieving over 90% cost reduction compared to LLM-centric baselines as approximately 67% of queries are resolved using local SLMs. The system achieves an average cost per query of 0.0085 compared to 0.094 for LLM-only systems, achieving near-zero operational costs for locally executed queries. [Github repository: https://github.com/mindslab25/CESMA.]

cs.CL↗

arXiv2024

Reviewing FID and SID Metrics on Generative Adversarial Networks

The growth of generative adversarial network (GAN) models has increased the ability of image processing and provides numerous industries with the technology to produce realistic image transformations. However, with the field being recently established there are new evaluation metrics that can further this research. Previous research has shown the Fréchet Inception Distance (FID) to be an effective metric when testing these image-to-image GANs in real-world applications. Signed Inception Distance (SID), a founded metric in 2023, expands on FID by allowing unsigned distances. This paper uses public datasets that consist of façades, cityscapes, and maps within Pix2Pix and CycleGAN models. After training these models are evaluated on both inception distance metrics which measure the generating performance of the trained models. Our findings indicate that usage of the metric SID incorporates an efficient and effective metric to complement, or even exceed the ability shown using the FID for the image-to-image GANs

cs.CV↗

arXiv2018

A Traffic-Aware Medium Access Control Mechanism for Energy-Efficient Wireless Network-on-Chip Architectures

Wireless interconnection has emerged as an energy efficient solution to the challenges of multi-hop communication over the wireline paths in conventional Networks-on-Chips (NoCs). However, to ensure the full benefits of this novel interconnect technology, design of simple, fair and efficient Medium Access Control (MAC) mechanism to grant access to the on-chip wireless communication channel is needed. Moreover, to adapt to the varying traffic demands from the applications running on a multicore environment, MAC mechanisms should dynamically adjust the transmission slots of the wireless interfaces (WIs). Such dynamic adjustment in transmission slots will result in improving the utilization of the wireless medium in a Wireless NoC (WiNoC). In this paper we present the design of two dynamic MAC mechanisms that adjust the transmission slots of the WIs based on predicted traffic demands and allow partial packet transfer. Through system level simulations, we demonstrate that the traffic aware MAC mechanisms are more energy efficient as well as capable of sustaining higher data bandwidth in WiNoCs.

cs.NI↗

arXiv2017

Energy-Efficient Wireless Interconnection Framework for Multichip Systems with In-package Memory Stacks

Multichip systems with memory stacks and various processing chips are at the heart of platform based designs such as servers and embedded systems. Full utilization of the benefits of these integrated multichip systems need a seamless, and scalable in-package interconnection framework. However, state-of-the-art inter-chip communication requires long wireline channels which increases energy consumption and latency while decreasing data bandwidth. Here, we propose the design of an energy-efficient, seamless wireless interconnection network for multichip systems. We demonstrate with cycle-accurate simulations that such a design reduces the energy consumption and latency while increasing the bandwidth in comparison to modern multichip integration systems.

cs.AR↗