most citedScaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2025

To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples

Vignesh Kothapalli, Ata Fatahibaarzi, Hamed Firooz +1

Chain-of-thought (CoT) prompting combined with few-shot in-context learning (ICL) has unlocked significant reasoning capabilities in large language models (LLMs). However, ICL with…

cs.CL2025

Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation

Wei-Rui Chen, Vignesh Kothapalli, Ata Fatahibaarzi +5

Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data. However, knowledge disti…