activity
20242026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads

Şuayp Talha Kocabay, Şuayp Talha Kocabay, Talha Rüzgar Akkuş +2

Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the final language-modeling head (L…

cs.CL2025

Efficient Machine Translation Corpus Generation: Integrating Human-in-the-Loop Post-Editing with Large Language Models

Kamer Ali Yuksel, Ahmet Gunduz, Abdul Baseet Anees +1

This paper introduces an advanced methodology for machine translation (MT) corpus generation, integrating semi-automated, human-in-the-loop post-editing with large language models…

cs.CL2025

MediaMind: Revolutionizing Media Monitoring using Agentification

Ahmet Gunduz, Kamer Ali Yuksel, Hassan Sawaf

In an era of rapid technological advancements, agentification of software tools has emerged as a critical innovation, enabling systems to function autonomously and adaptively. This…

cs.CL2025

ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters

Kamer Ali Yuksel, Hassan Sawaf

Recent advances in large language models (LLMs) have shown remarkable performance across diverse tasks. However, these models are typically deployed with fixed weights, which limit…

cs.CL2024

A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops

Kamer Ali Yuksel, Hassan Sawaf

Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-inten…

cs.CL2024

AutoMode-ASR: Learning to Select ASR Systems for Better Quality and Cost

Ahmet Gündüz, Yunsu Kim, Kamer Ali Yuksel +3

We present AutoMode-ASR, a novel framework that effectively integrates multiple ASR systems to enhance the overall transcription quality while optimizing cost. The idea is to train…