Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing

AAAI Conference on Artificial Intelligence (AAAI), 2025

24 February 2025

Papers citing "Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing"

40 / 40 papers shown

Title
Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration Jingbo Wang Sendong Zhao Haochun Wang Yuzheng Fan L. Zhang Yan Liu Ting Liu 88 0 0 04 Nov 2025
ICL-Router: In-Context Learned Model Representations for LLM Routing Chenxu Wang Hao Li Yiqun Zhang L. Chen Jianhao Chen Ping Jian Peng Ye Qiaosheng Zhang Shuyue Hu 113 0 0 10 Oct 2025
Learning Compact Representations of LLM Abilities via Item Response Theory Jianhao Chen Chenxu Wang G. Zhang Peng Ye Lei Bai Wei Hu Yuzhong Qu Shuyue Hu 64 0 0 01 Oct 2025
RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers Yifan Lu Rixin Liu Jiayi Yuan Xingqi Cui Shenrun Zhang Hongyi Liu Jiarong Xing ELM 251 0 0 30 Sep 2025
Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say Jacob Fein-Ashley Dhruv Parikh Rajgopal Kannan Viktor Prasanna MoE MoMe LRM 108 1 0 25 Sep 2025
One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo Hao-Nan Shi Ting Huang Lu Han De-Chuan Zhan Han-Jia Ye AI4TS 142 0 0 04 Sep 2025
The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants Yiqun Zhang Hao Li Chenxu Wang L. Chen Qiaosheng Zhang ... Xinrun Wang Jia Xu Mengwei He Xuming He Shuyue Hu 319 13 0 26 May 2025
INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling Haochen Shi Tianshi Zheng Weiqi Wang Baixuan Xu Chunyang Li Chunkit Chan Tao Fan Yangqiu Song Qiang Yang 226 5 0 22 May 2025
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs Zhongzhan Huang Guoming Ling Vincent S. Liang Yupei Lin Yandong Chen Shanshan Zhong Hefeng Wu LRM 590 18 0 08 Mar 2025
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text RetrievalConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 Xin Zhang Yanzhao Zhang Dingkun Long Wen Xie Ziqi Dai ... Pengjun Xie Fei Huang Meishan Zhang Wenjie Li Min Zhang 266 214 0 29 Jul 2024
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools Team GLM : Aohan Zeng Bin Xu Bowen Wang ... Zhaoyu Wang Zhen Yang Zhengxiao Du Zhenyu Hou Zihan Wang ALM 286 1,109 0 18 Jun 2024
Wings: Learning Multimodal LLMs without Text-only Forgetting Yi-Kai Zhang Shiyin Lu Yang Li Yanqing Ma Qing-Guo Chen Zhao Xu Weihua Luo Kaifu Zhang De-Chuan Zhan Han-Jia Ye VLM 224 17 0 05 Jun 2024
Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing KV Aditya Srivatsa Kaushal Kumar Maurya Ekaterina Kochmar 190 30 0 01 May 2024
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing Dujian Ding Ankur Mallick Chi Wang Robert Sim Subhabrata Mukherjee Victor Rühle L. Lakshmanan Ahmed Hassan Awadallah 303 172 0 22 Apr 2024
RouterBench: A Benchmark for Multi-LLM Routing System Qitian Jason Hu Jacob Bieker Xiuyu Li Nan Jiang Benjamin Keigwin Gaurav Ranganath Kurt Keutzer Shriyash Kaustubh Upadhyay 219 95 0 18 Mar 2024
Yi: Open Foundation Models by 01.AI 01. AI Alex Young 01.AI Alex Young Bei Chen Chao Li ... Yue Wang Yuxuan Cai Zhenyu Gu Zhiyuan Liu Zonghong Dai OSLM LRM 681 751 0 07 Mar 2024
Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM Xiaoding Lu Zongyi Liu Adian Liusie Vyas Raina Vineet Mudupalli Yuwen Zhang W. Beauchamp 211 27 0 04 Jan 2024
ShareGPT4V: Improving Large Multi-Modal Models with Better CaptionsEuropean Conference on Computer Vision (ECCV), 2023 Lin Chen Jinsong Li Xiao-wen Dong Pan Zhang Conghui He Yuan Liu Feng Zhao Dahua Lin MLLM VLM 295 907 0 21 Nov 2023
Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small ScorerNeural Information Processing Systems (NeurIPS), 2023 Bowen Tan Yun Zhu Lijuan Liu Eric P. Xing Zhiting Hu Jindong Chen ALM LRM 175 9 0 12 Nov 2023
Large Language Model Routing with Benchmark Datasets Tal Shnitzer Anthony Ou Mírian Silva Kate Soule Yuekai Sun Justin Solomon Neil Thompson Mikhail Yurochkin RALM 245 105 0 27 Sep 2023
Llama 2: Open Foundation and Fine-Tuned Chat Models Hugo Touvron Louis Martin Kevin R. Stone Peter Albert Amjad Almahairi ... Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov Thomas Scialom AI4MH ALM 5.1K 14,855 0 18 Jul 2023
MMBench: Is Your Multi-modal Model an All-around Player?European Conference on Computer Vision (ECCV), 2023 Yuanzhan Liu Haodong Duan Yuanhan Zhang Yue Liu Songyang Zhang ... Yuan Liu Conghui He Ziwei Liu Kai-xiang Chen Dahua Lin 464 1,578 0 12 Jul 2023
An Information-Theoretic Approach to Transferability in Task Transfer LearningInternational Conference on Information Photonics (ICIP), 2019 Yajie Bao Yongni Li Shao-Lun Huang Lin Zhang Lizhong Zheng Amir Zamir Leonidas Guibas 231 143 0 20 Dec 2022
PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification TasksEuropean Conference on Computer Vision (ECCV), 2022 Nan Ding Xi Chen Tomer Levinboim Soravit Changpinyo Radu Soricut 177 34 0 10 Mar 2022
Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model HubsJournal of machine learning research (JMLR), 2021 Kaichao You Yong Liu Ziyang Zhang Jianmin Wang Sai Li Mingsheng Long 310 38 0 20 Oct 2021
Finetuned Language Models Are Zero-Shot Learners Jason W. Wei Maarten Bosma Vincent Zhao Kelvin Guu Adams Wei Yu Brian Lester Nan Du Andrew M. Dai Quoc V. Le ALM UQCV 1.0K 4,506 0 03 Sep 2021
OTCE: A Transferability Metric for Cross-Domain Cross-Task RepresentationsComputer Vision and Pattern Recognition (CVPR), 2021 Yang Tan Yang Li Shao-Lun Huang OT OOD OODD 172 82 0 25 Mar 2021
GLM: General Language Model Pretraining with Autoregressive Blank InfillingAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Zhengxiao Du Yujie Qian Xiao Liu Ming Ding J. Qiu Zhilin Yang Jie Tang BDL AI4CE 276 1,757 0 18 Mar 2021
LogME: Practical Assessment of Pre-trained Models for Transfer LearningInternational Conference on Machine Learning (ICML), 2021 Kaichao You Yong Liu Jianmin Wang Mingsheng Long 248 225 0 22 Feb 2021
Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge Sumithra Bhakthavatsalam Daniel Khashabi Tushar Khot Bhavana Dalvi Kyle Richardson Ashish Sabharwal Carissa Schoenick Oyvind Tafjord Peter Clark RALM AI4CE 153 79 0 05 Feb 2021
A linearized framework and a new benchmark for model selection for fine-tuning Aditya Deshpande Alessandro Achille Avinash Ravichandran Hao Li Luca Zancato Charless C. Fowlkes Rahul Bhotika Stefano Soatto Pietro Perona ALM 304 56 0 29 Jan 2021
Ranking Neural CheckpointsComputer Vision and Pattern Recognition (CVPR), 2020 Yandong Li Xuhui Jia Ruoxin Sang Yukun Zhu Bradley Green Liqiang Wang Boqing Gong FedML ELM UQCV 355 59 0 23 Nov 2020
Measuring Massive Multitask Language UnderstandingInternational Conference on Learning Representations (ICLR), 2020 Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Basel Alomair Jacob Steinhardt ELM RALM 1.2K 6,264 0 07 Sep 2020
Dense Passage Retrieval for Open-Domain Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 Vladimir Karpukhin Barlas Oğuz Sewon Min Patrick Lewis Ledell Yu Wu Sergey Edunov Danqi Chen Anuj Kumar RALM 530 4,648 0 10 Apr 2020
LEEP: A New Measure to Evaluate Transferability of Learned RepresentationsInternational Conference on Machine Learning (ICML), 2020 Cuong V Nguyen Tal Hassner Matthias Seeger Cédric Archambeau 250 252 0 27 Feb 2020
Transferability and Hardness of Supervised Classification TasksIEEE International Conference on Computer Vision (ICCV), 2019 Anh Tran Cuong V Nguyen Tal Hassner 298 191 0 21 Aug 2019
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No QuestionsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2019 Christopher Clark Kenton Lee Ming-Wei Chang Tom Kwiatkowski Michael Collins Kristina Toutanova 603 1,975 0 24 May 2019
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding Alex Jinpeng Wang Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 1.6K 7,907 0 20 Apr 2018
A Diagram Is Worth A Dozen Images Aniruddha Kembhavi M. Salvato Eric Kolve Minjoon Seo Hannaneh Hajishirzi Ali Farhadi 3DV 204 729 0 24 Mar 2016
Microsoft COCO Captions: Data Collection and Evaluation Server Xinlei Chen Hao Fang Nayeon Lee Ramakrishna Vedantam Saurabh Gupta Piotr Dollar C. L. Zitnick 642 2,715 0 01 Apr 2015