2 papers
cs.CL2025
ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
Razvan-Gabriel Dumitru, Darius Peteleaza, Vikas Yadav +1
Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, cau…
cs.CL2024
Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy
Razvan-Gabriel Dumitru, Paul-Ioan Clotan, Vikas Yadav +2
This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established b…