3 papers
cs.LG2025
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…
cs.SE2025
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…
cs.SE2025
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…