Ethos: Rectifying Language Models in Orthogonal Parameter Space F i n d i n g s - N A A C L

Lei Gao | Yue Niu | Tingting Tang | Salman Avestimehr | Murali Annavaram |

MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs ACL

Yavuz Faruk Bakman | Duygu Nur Yaldiz | Baturalp Buyukates | Chenyang Tao | Dimitrios Dimitriadis | Salman Avestimehr |

Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers F i n d i n g s - A C L

Tuo Zhang | Jinyue Yuan | Salman Avestimehr |

TensorOpera Router: A Multi-Model Router for Efficient LLM Inference EMNLP

Dimitris Stripelis | Zhaozhuo Xu | Zijian Hu | Alay Dilipbhai Shah | Han Jin | Yuhang Yao | Jipeng Zhang | Tong Zhang | Salman Avestimehr | Chaoyang He |

ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency EMNLP

Yuhang Yao | Han Jin | Alay Dilipbhai Shah | Shanshan Han | Zijian Hu | Dimitris Stripelis | Yide Ran | Zhaozhuo Xu | Salman Avestimehr | Chaoyang He |