Darssan Eswaramoorthi

Kaushik Roy, Harshul Surana, Darssan Eswaramoorthi et al.

Large language models (LLMs) are increasingly attracting the attention of healthcare professionals for their potential to assist in diagnostic assessments, which could alleviate the strain on the healthcare system caused by a high patient load and a shortage of providers. For LLMs to be effective in supporting diagnostic assessments, it is essential that they closely replicate the standard diagnostic procedures used by clinicians. In this paper, we specifically examine the diagnostic assessment processes described in the Patient Health Questionnaire-9 (PHQ-9) for major depressive disorder (MDD) and the Generalized Anxiety Disorder-7 (GAD-7) questionnaire for generalized anxiety disorder (GAD). We investigate various prompting and fine-tuning techniques to guide both proprietary and open-source LLMs in adhering to these processes, and we evaluate the agreement between LLM-generated diagnostic outcomes and expert-validated ground truth. For fine-tuning, we utilize the Mentalllama and Llama models, while for prompting, we experiment with proprietary models like GPT-3.5 and GPT-4o, as well as open-source models such as llama-3.1-8b and mixtral-8x7b.

Chathurangi Shyalika, Renjith Prasad, Alaa Al Ghazo et al.

In the dynamic landscape of Industry 4.0, achieving efficiency, precision, and adaptability is essential to optimize manufacturing operations. Industries suffer due to supply chain disruptions caused by anomalies, which are being detected by current AI models but leaving domain experts uncertain without deeper insights into these anomalies. Additionally, operational inefficiencies persist due to inaccurate production forecasts and the limited effectiveness of traditional AI models for processing complex sensor data. Despite these advancements, existing systems lack the seamless integration of these capabilities needed to create a truly unified solution for enhancing production and decision-making. We propose SmartPilot, a neurosymbolic, multiagent CoPilot designed for advanced reasoning and contextual decision-making to address these challenges. SmartPilot processes multimodal sensor data and is compact to deploy on edge devices. It focuses on three key tasks: anomaly prediction, production forecasting, and domain-specific question answering. By bridging the gap between AI capabilities and real-world industrial needs, SmartPilot empowers industries with intelligent decision-making and drives transformative innovation in manufacturing. The demonstration video, datasets, and supplementary materials are available at https://github.com/ChathurangiShyalika/SmartPilot.

Tiffany Yu, Rye Stahle-Smith, Darssan Eswaramoorthi et al.

Graph-based accelerators have been widely adopted in symbolic data processing applications such as genomics, cybersecurity, and artificial intelligence. However, these systems often suffer from excessive memory usage and inefficiencies stemming from redundant graph structures. We present AutoSlim, a machine learning-based framework that leverages data-driven methods to prune automata graphs for hardware accelerators. Using features extracted from prior graph executions and a Random Forest classifier, AutoSlim identifies and removes low-impact nodes and edges. When applied to a Non-deterministic Finite Automata overlay architecture (NAPOLY+), AutoSlim reduces FPGA resource usage by up to 40%, with corresponding improvements in throughput and power efficiency. The framework includes a verification step to ensure functional equivalence after pruning and suggests promising directions for both hardware optimization and security.

Tiffany Yu, Rye Stahle-Smith, Darssan Eswaramoorthi et al.

Symbolic accelerators are increasingly used for symbolic data processing in domains such as genomics, NLP, and cybersecurity. However, these accelerators face scalability issues due to excessive memory use and routing complexity, especially when targeting a large set. We present AutoSlim, a machine learning-based graph simplification framework designed to reduce the complexity of symbolic accelerators built on Non-deterministic Finite Automata (NFA) deployed on FPGA-based overlays such as NAPOLY+. AutoSlim uses Random Forest classification to prune low-impact transitions based on edge scores and structural features, significantly reducing automata graph density while preserving semantic correctness. Unlike prior tools, AutoSlim targets automated score-aware simplification with weighted transitions, enabling efficient ranking-based sequence analysis. We evaluated data sets (1K to 64K nodes) in NAPOLY+ and conducted performance measurements including latency, throughput, and resource usage. AutoSlim achieves up to 40 percent reduction in FPGA LUTs and over 30 percent pruning in transitions, while scaling to graphs an order of magnitude larger than existing benchmarks. Our results also demonstrate how hardware interconnection (fanout) heavily influences hardware cost and that AutoSlim's pruning mitigates resource blowup.