2 citations · 3 across the 4 of their papers we have counts for
4 papers
Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques
Asankhaya Sharma
Large language models have transformed natural language processing, yet supervised fine-tuning (SFT) remains computationally intensive. This paper formally proves that capabilities…
Patched MOA: optimizing inference for diverse software development tasks
Asankhaya Sharma
This paper introduces Patched MOA (Mixture of Agents), an inference optimization technique that significantly enhances the performance of large language models (LLMs) across divers…
Patched RTC: evaluating LLMs for diverse software development tasks
Asankhaya Sharma
This paper introduces Patched Round-Trip Correctness (Patched RTC), a novel evaluation technique for Large Language Models (LLMs) applied to diverse software development tasks, par…
Evaluating Pre-trained Language Models for Repairing API Misuses
Ting Zhang, Ivana Clairine Irsan, Ferdian Thung +3
API misuses often lead to software bugs, crashes, and vulnerabilities. While several API misuse detectors have been proposed, there are no automatic repair tools specifically desig…