\n \n \n
\n\n\n
\n
\n\n \n \n \n \n \n \n LogSay: An Efficient Comprehension System for Log Numerical Reasoning.\n \n \n \n \n\n\n \n Qi, J.; Luan, Z.; Huang, S.; Fung, C. J.; and Yang, H.\n\n\n \n\n\n\n
IEEE Trans. Computers, 73(7): 1809–1821. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/tc/QiLHFY24,\n author = {Jiaxing Qi and\n Zhongzhi Luan and\n Shaohan Huang and\n Carol J. Fung and\n Hailong Yang},\n title = {LogSay: An Efficient Comprehension System for Log Numerical Reasoning},\n journal = {{IEEE} Trans. Computers},\n volume = {73},\n number = {7},\n pages = {1809--1821},\n year = {2024},\n url = {https://doi.org/10.1109/TC.2024.3386068},\n doi = {10.1109/TC.2024.3386068},\n timestamp = {Thu, 04 Jul 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/tc/QiLHFY24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n SpikeLog: Log-Based Anomaly Detection via Potential-Assisted Spiking Neuron Network.\n \n \n \n \n\n\n \n Qi, J.; Luan, Z.; Huang, S.; Fung, C. J.; Yang, H.; and Qian, D.\n\n\n \n\n\n\n
IEEE Trans. Knowl. Data Eng., 36(12): 9322–9335. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/tkde/QiLHFYQ24,\n author = {Jiaxing Qi and\n Zhongzhi Luan and\n Shaohan Huang and\n Carol J. Fung and\n Hailong Yang and\n Depei Qian},\n title = {SpikeLog: Log-Based Anomaly Detection via Potential-Assisted Spiking\n Neuron Network},\n journal = {{IEEE} Trans. Knowl. Data Eng.},\n volume = {36},\n number = {12},\n pages = {9322--9335},\n year = {2024},\n url = {https://doi.org/10.1109/TKDE.2023.3347695},\n doi = {10.1109/TKDE.2023.3347695},\n timestamp = {Sun, 22 Dec 2024 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/tkde/QiLHFYQ24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Text Diffusion with Reinforced Conditioning.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n In Wooldridge, M. J.; Dy, J. G.; and Natarajan, S., editor(s),
Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pages 14069–14077, 2024. AAAI Press\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/aaai/LiuYHZHWDSZ24,\n author = {Yuxuan Liu and\n Tianchi Yang and\n Shaohan Huang and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang},\n editor = {Michael J. Wooldridge and\n Jennifer G. Dy and\n Sriraam Natarajan},\n title = {Text Diffusion with Reinforced Conditioning},\n booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}\n 2024, Thirty-Sixth Conference on Innovative Applications of Artificial\n Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances\n in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,\n Canada},\n pages = {14069--14077},\n publisher = {{AAAI} Press},\n year = {2024},\n url = {https://doi.org/10.1609/aaai.v38i12.29316},\n doi = {10.1609/AAAI.V38I12.29316},\n timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/aaai/LiuYHZHWDSZ24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Se\\(^2\\): Sequential Example Selection for In-Context Learning.\n \n \n \n \n\n\n \n Liu, H.; Liu, J.; Huang, S.; Zhan, Y.; Sun, H.; Deng, W.; Wei, F.; and Zhang, Q.\n\n\n \n\n\n\n In Ku, L.; Martins, A.; and Srikumar, V., editor(s),
Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024, pages 5262–5284, 2024. Association for Computational Linguistics\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/LiuLHZSDW024,\n author = {Haoyu Liu and\n Jianfeng Liu and\n Shaohan Huang and\n Yuefeng Zhan and\n Hao Sun and\n Weiwei Deng and\n Furu Wei and\n Qi Zhang},\n editor = {Lun{-}Wei Ku and\n Andre Martins and\n Vivek Srikumar},\n title = {Se{\\({^2}\\)}: Sequential Example Selection for In-Context Learning},\n booktitle = {Findings of the Association for Computational Linguistics, {ACL} 2024,\n Bangkok, Thailand and virtual meeting, August 11-16, 2024},\n pages = {5262--5284},\n publisher = {Association for Computational Linguistics},\n year = {2024},\n url = {https://doi.org/10.18653/v1/2024.findings-acl.312},\n doi = {10.18653/V1/2024.FINDINGS-ACL.312},\n timestamp = {Tue, 24 Sep 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/acl/LiuLHZSDW024.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n In Ku, L.; Martins, A.; and Srikumar, V., editor(s),
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024, pages 7641–7660, 2024. Association for Computational Linguistics\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/LiuYHZHWD0024,\n author = {Yuxuan Liu and\n Tianchi Yang and\n Shaohan Huang and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang},\n editor = {Lun{-}Wei Ku and\n Andre Martins and\n Vivek Srikumar},\n title = {HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical\n Criteria Decomposition},\n booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational\n Linguistics (Volume 1: Long Papers), {ACL} 2024, Bangkok, Thailand,\n August 11-16, 2024},\n pages = {7641--7660},\n publisher = {Association for Computational Linguistics},\n year = {2024},\n url = {https://doi.org/10.18653/v1/2024.acl-long.413},\n doi = {10.18653/V1/2024.ACL-LONG.413},\n timestamp = {Sun, 19 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/conf/acl/LiuYHZHWD0024.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n ResLoRA: Identity Residual Mapping in Low-Rank Adaption.\n \n \n \n \n\n\n \n Shi, S.; Huang, S.; Song, M.; Li, Z.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n In Ku, L.; Martins, A.; and Srikumar, V., editor(s),
Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024, pages 8870–8884, 2024. Association for Computational Linguistics\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/acl/ShiHSLZHWD0Z24,\n author = {Shuhua Shi and\n Shaohan Huang and\n Minghui Song and\n Zhoujun Li and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang},\n editor = {Lun{-}Wei Ku and\n Andre Martins and\n Vivek Srikumar},\n title = {ResLoRA: Identity Residual Mapping in Low-Rank Adaption},\n booktitle = {Findings of the Association for Computational Linguistics, {ACL} 2024,\n Bangkok, Thailand and virtual meeting, August 11-16, 2024},\n pages = {8870--8884},\n publisher = {Association for Computational Linguistics},\n year = {2024},\n url = {https://doi.org/10.18653/v1/2024.findings-acl.525},\n doi = {10.18653/V1/2024.FINDINGS-ACL.525},\n timestamp = {Tue, 24 Sep 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/acl/ShiHSLZHWD0Z24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Calibrating LLM-Based Evaluator.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n In Calzolari, N.; Kan, M.; Hoste, V.; Lenci, A.; Sakti, S.; and Xue, N., editor(s),
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC/COLING 2024, 20-25 May, 2024, Torino, Italy, pages 2638–2656, 2024. ELRA and ICCL\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/coling/LiuYHZHWDSZ24,\n author = {Yuxuan Liu and\n Tianchi Yang and\n Shaohan Huang and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang},\n editor = {Nicoletta Calzolari and\n Min{-}Yen Kan and\n V{\\'{e}}ronique Hoste and\n Alessandro Lenci and\n Sakriani Sakti and\n Nianwen Xue},\n title = {Calibrating LLM-Based Evaluator},\n booktitle = {Proceedings of the 2024 Joint International Conference on Computational\n Linguistics, Language Resources and Evaluation, {LREC/COLING} 2024,\n 20-25 May, 2024, Torino, Italy},\n pages = {2638--2656},\n publisher = {{ELRA} and {ICCL}},\n year = {2024},\n url = {https://aclanthology.org/2024.lrec-main.237},\n timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/coling/LiuYHZHWDSZ24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Instruction Pre-Training: Language Models are Supervised Multitask Learners.\n \n \n \n \n\n\n \n Cheng, D.; Gu, Y.; Huang, S.; Bi, J.; Huang, M.; and Wei, F.\n\n\n \n\n\n\n In Al-Onaizan, Y.; Bansal, M.; and Chen, Y., editor(s),
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, November 12-16, 2024, pages 2529–2550, 2024. Association for Computational Linguistics\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/ChengGHBHW24,\n author = {Daixuan Cheng and\n Yuxian Gu and\n Shaohan Huang and\n Junyu Bi and\n Minlie Huang and\n Furu Wei},\n editor = {Yaser Al{-}Onaizan and\n Mohit Bansal and\n Yun{-}Nung Chen},\n title = {Instruction Pre-Training: Language Models are Supervised Multitask\n Learners},\n booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural\n Language Processing, {EMNLP} 2024, Miami, FL, USA, November 12-16,\n 2024},\n pages = {2529--2550},\n publisher = {Association for Computational Linguistics},\n year = {2024},\n url = {https://aclanthology.org/2024.emnlp-main.148},\n timestamp = {Thu, 14 Nov 2024 17:20:54 +0100},\n biburl = {https://dblp.org/rec/conf/emnlp/ChengGHBHW24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Scaling Sentence Embeddings with Large Language Models.\n \n \n \n \n\n\n \n Jiang, T.; Huang, S.; Luan, Z.; Wang, D.; and Zhuang, F.\n\n\n \n\n\n\n In Al-Onaizan, Y.; Bansal, M.; and Chen, Y., editor(s),
Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, pages 3182–3196, 2024. Association for Computational Linguistics\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/emnlp/JiangHLWZ24,\n author = {Ting Jiang and\n Shaohan Huang and\n Zhongzhi Luan and\n Deqing Wang and\n Fuzhen Zhuang},\n editor = {Yaser Al{-}Onaizan and\n Mohit Bansal and\n Yun{-}Nung Chen},\n title = {Scaling Sentence Embeddings with Large Language Models},\n booktitle = {Findings of the Association for Computational Linguistics: {EMNLP}\n 2024, Miami, Florida, USA, November 12-16, 2024},\n pages = {3182--3196},\n publisher = {Association for Computational Linguistics},\n year = {2024},\n url = {https://aclanthology.org/2024.findings-emnlp.181},\n timestamp = {Mon, 18 Nov 2024 09:05:59 +0100},\n biburl = {https://dblp.org/rec/conf/emnlp/JiangHLWZ24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Semantic-Aware Log Understanding and Analysis.\n \n \n \n \n\n\n \n Huang, S.; and Luan, Z.\n\n\n \n\n\n\n In Dazzi, P.; Mencagli, G.; Lowenthal, D. K.; and Badia, R. M., editor(s),
Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing, HPDC 2024, Pisa, Italy, June 3-7, 2024, pages 413–416, 2024. ACM\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/hpdc/HuangL24,\n author = {Shaohan Huang and\n Zhongzhi Luan},\n editor = {Patrizio Dazzi and\n Gabriele Mencagli and\n David K. Lowenthal and\n Rosa M. Badia},\n title = {Semantic-Aware Log Understanding and Analysis},\n booktitle = {Proceedings of the 33rd International Symposium on High-Performance\n Parallel and Distributed Computing, {HPDC} 2024, Pisa, Italy, June\n 3-7, 2024},\n pages = {413--416},\n publisher = {{ACM}},\n year = {2024},\n url = {https://doi.org/10.1145/3625549.3658830},\n doi = {10.1145/3625549.3658830},\n timestamp = {Sun, 19 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/conf/hpdc/HuangL24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Adapting Large Language Models via Reading Comprehension.\n \n \n \n \n\n\n \n Cheng, D.; Huang, S.; and Wei, F.\n\n\n \n\n\n\n In
The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024, 2024. OpenReview.net\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/iclr/ChengHW24,\n author = {Daixuan Cheng and\n Shaohan Huang and\n Furu Wei},\n title = {Adapting Large Language Models via Reading Comprehension},\n booktitle = {The Twelfth International Conference on Learning Representations,\n {ICLR} 2024, Vienna, Austria, May 7-11, 2024},\n publisher = {OpenReview.net},\n year = {2024},\n url = {https://openreview.net/forum?id=y886UXPEZ0},\n timestamp = {Wed, 07 Aug 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/iclr/ChengHW24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Kosmos-G: Generating Images in Context with Multimodal Large Language Models.\n \n \n \n \n\n\n \n Pan, X.; Dong, L.; Huang, S.; Peng, Z.; Chen, W.; and Wei, F.\n\n\n \n\n\n\n In
The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024, 2024. OpenReview.net\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/iclr/Pan0HPCW24,\n author = {Xichen Pan and\n Li Dong and\n Shaohan Huang and\n Zhiliang Peng and\n Wenhu Chen and\n Furu Wei},\n title = {Kosmos-G: Generating Images in Context with Multimodal Large Language\n Models},\n booktitle = {The Twelfth International Conference on Learning Representations,\n {ICLR} 2024, Vienna, Austria, May 7-11, 2024},\n publisher = {OpenReview.net},\n year = {2024},\n url = {https://openreview.net/forum?id=he6mX9LTyE},\n timestamp = {Wed, 07 Aug 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/iclr/Pan0HPCW24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Grounding Multimodal Large Language Models to the World.\n \n \n \n \n\n\n \n Peng, Z.; Wang, W.; Dong, L.; Hao, Y.; Huang, S.; Ma, S.; Ye, Q.; and Wei, F.\n\n\n \n\n\n\n In
The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024, 2024. OpenReview.net\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/iclr/Peng00HHMYW24,\n author = {Zhiliang Peng and\n Wenhui Wang and\n Li Dong and\n Yaru Hao and\n Shaohan Huang and\n Shuming Ma and\n Qixiang Ye and\n Furu Wei},\n title = {Grounding Multimodal Large Language Models to the World},\n booktitle = {The Twelfth International Conference on Learning Representations,\n {ICLR} 2024, Vienna, Austria, May 7-11, 2024},\n publisher = {OpenReview.net},\n year = {2024},\n url = {https://openreview.net/forum?id=lLmqxkfSIw},\n timestamp = {Wed, 07 Aug 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/iclr/Peng00HHMYW24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Mixture of LoRA Experts.\n \n \n \n \n\n\n \n Wu, X.; Huang, S.; and Wei, F.\n\n\n \n\n\n\n In
The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024, 2024. OpenReview.net\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/iclr/WuHW24,\n author = {Xun Wu and\n Shaohan Huang and\n Furu Wei},\n title = {Mixture of LoRA Experts},\n booktitle = {The Twelfth International Conference on Learning Representations,\n {ICLR} 2024, Vienna, Austria, May 7-11, 2024},\n publisher = {OpenReview.net},\n year = {2024},\n url = {https://openreview.net/forum?id=uWvKBCYh4S},\n timestamp = {Wed, 07 Aug 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/iclr/WuHW24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n KOSMOS-E : Learning to Follow Instruction for Robotic Grasping.\n \n \n \n \n\n\n \n Wang, Z.; Wu, X.; Huang, S.; Dong, L.; Wang, W.; Ma, S.; and Wei, F.\n\n\n \n\n\n\n In
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2024, Abu Dhabi, United Arab Emirates, October 14-18, 2024, pages 9510–9517, 2024. IEEE\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/iros/WangWH00MW24,\n author = {Zhi Wang and\n Xun Wu and\n Shaohan Huang and\n Li Dong and\n Wenhui Wang and\n Shuming Ma and\n Furu Wei},\n title = {{KOSMOS-E} : Learning to Follow Instruction for Robotic Grasping},\n booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems,\n {IROS} 2024, Abu Dhabi, United Arab Emirates, October 14-18, 2024},\n pages = {9510--9517},\n publisher = {{IEEE}},\n year = {2024},\n url = {https://doi.org/10.1109/IROS58592.2024.10802219},\n doi = {10.1109/IROS58592.2024.10802219},\n timestamp = {Thu, 02 Jan 2025 14:44:50 +0100},\n biburl = {https://dblp.org/rec/conf/iros/WangWH00MW24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n You Only Cache Once: Decoder-Decoder Architectures for Language Models.\n \n \n \n \n\n\n \n Sun, Y.; Dong, L.; Zhu, Y.; Huang, S.; Wang, W.; Ma, S.; Zhang, Q.; Wang, J.; and Wei, F.\n\n\n \n\n\n\n In Globersons, A.; Mackey, L.; Belgrave, D.; Fan, A.; Paquet, U.; Tomczak, J. M.; and Zhang, C., editor(s),
Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, 2024. \n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/nips/Sun0ZHWMZ0W24,\n author = {Yutao Sun and\n Li Dong and\n Yi Zhu and\n Shaohan Huang and\n Wenhui Wang and\n Shuming Ma and\n Quanlu Zhang and\n Jianyong Wang and\n Furu Wei},\n editor = {Amir Globersons and\n Lester Mackey and\n Danielle Belgrave and\n Angela Fan and\n Ulrich Paquet and\n Jakub M. Tomczak and\n Cheng Zhang},\n title = {You Only Cache Once: Decoder-Decoder Architectures for Language Models},\n booktitle = {Advances in Neural Information Processing Systems 38: Annual Conference\n on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,\n BC, Canada, December 10 - 15, 2024},\n year = {2024},\n url = {http://papers.nips.cc/paper\\_files/paper/2024/hash/0df38cd13520747e1e64e5b123a78ef8-Abstract-Conference.html},\n timestamp = {Thu, 13 Feb 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/conf/nips/Sun0ZHWMZ0W24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Multi-Head Mixture-of-Experts.\n \n \n \n \n\n\n \n Wu, X.; Huang, S.; Wang, W.; Ma, S.; Dong, L.; and Wei, F.\n\n\n \n\n\n\n In Globersons, A.; Mackey, L.; Belgrave, D.; Fan, A.; Paquet, U.; Tomczak, J. M.; and Zhang, C., editor(s),
Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, 2024. \n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/nips/WuH0M0W24,\n author = {Xun Wu and\n Shaohan Huang and\n Wenhui Wang and\n Shuming Ma and\n Li Dong and\n Furu Wei},\n editor = {Amir Globersons and\n Lester Mackey and\n Danielle Belgrave and\n Angela Fan and\n Ulrich Paquet and\n Jakub M. Tomczak and\n Cheng Zhang},\n title = {Multi-Head Mixture-of-Experts},\n booktitle = {Advances in Neural Information Processing Systems 38: Annual Conference\n on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,\n BC, Canada, December 10 - 15, 2024},\n year = {2024},\n url = {http://papers.nips.cc/paper\\_files/paper/2024/hash/ab05dc8bf36a9f66edbff6992ec86f56-Abstract-Conference.html},\n timestamp = {Thu, 13 Feb 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/conf/nips/WuH0M0W24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Multimodal Large Language Models Make Text-to-Image Generative Models Align Better.\n \n \n \n \n\n\n \n Wu, X.; Huang, S.; Wang, G.; Xiong, J.; and Wei, F.\n\n\n \n\n\n\n In Globersons, A.; Mackey, L.; Belgrave, D.; Fan, A.; Paquet, U.; Tomczak, J. M.; and Zhang, C., editor(s),
Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, 2024. \n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/nips/WuHWXW24,\n author = {Xun Wu and\n Shaohan Huang and\n Guolong Wang and\n Jing Xiong and\n Furu Wei},\n editor = {Amir Globersons and\n Lester Mackey and\n Danielle Belgrave and\n Angela Fan and\n Ulrich Paquet and\n Jakub M. Tomczak and\n Cheng Zhang},\n title = {Multimodal Large Language Models Make Text-to-Image Generative Models\n Align Better},\n booktitle = {Advances in Neural Information Processing Systems 38: Annual Conference\n on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,\n BC, Canada, December 10 - 15, 2024},\n year = {2024},\n url = {http://papers.nips.cc/paper\\_files/paper/2024/hash/9421261e06f1a63a352b068f1ac90609-Abstract-Conference.html},\n timestamp = {Wed, 16 Apr 2025 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/nips/WuHWXW24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Boosting Text-to-Video Generative Model with MLLMs Feedback.\n \n \n \n \n\n\n \n Wu, X.; Huang, S.; Wang, G.; Xiong, J.; and Wei, F.\n\n\n \n\n\n\n In Globersons, A.; Mackey, L.; Belgrave, D.; Fan, A.; Paquet, U.; Tomczak, J. M.; and Zhang, C., editor(s),
Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, 2024. \n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/nips/WuHWXW24a,\n author = {Xun Wu and\n Shaohan Huang and\n Guolong Wang and\n Jing Xiong and\n Furu Wei},\n editor = {Amir Globersons and\n Lester Mackey and\n Danielle Belgrave and\n Angela Fan and\n Ulrich Paquet and\n Jakub M. Tomczak and\n Cheng Zhang},\n title = {Boosting Text-to-Video Generative Model with MLLMs Feedback},\n booktitle = {Advances in Neural Information Processing Systems 38: Annual Conference\n on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,\n BC, Canada, December 10 - 15, 2024},\n year = {2024},\n url = {http://papers.nips.cc/paper\\_files/paper/2024/hash/fbe2b2f74a2ece8070d8fb073717bda6-Abstract-Conference.html},\n timestamp = {Wed, 16 Apr 2025 01:00:00 +0200},\n biburl = {https://dblp.org/rec/conf/nips/WuHWXW24a.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Gloss: Guiding Large Language Models to Answer Questions from System Logs.\n \n \n \n \n\n\n \n Huang, S.; Liu, Y.; Qi, J.; Shang, J.; Xiao, Z.; Fung, C. J.; Wu, Z.; Yang, H.; Luan, Z.; and Qian, D.\n\n\n \n\n\n\n In
IEEE International Conference on Software Analysis, Evolution and Reengineering, SANER 2024, Rovaniemi, Finland, March 12-15, 2024, pages 91–101, 2024. IEEE\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{DBLP:conf/wcre/Huang0QSXFWYLQ24,\n author = {Shaohan Huang and\n Yi Liu and\n Jiaxing Qi and\n Jing Shang and\n Zhiwen Xiao and\n Carol J. Fung and\n Zhihui Wu and\n Hailong Yang and\n Zhongzhi Luan and\n Depei Qian},\n title = {Gloss: Guiding Large Language Models to Answer Questions from System\n Logs},\n booktitle = {{IEEE} International Conference on Software Analysis, Evolution and\n Reengineering, {SANER} 2024, Rovaniemi, Finland, March 12-15, 2024},\n pages = {91--101},\n publisher = {{IEEE}},\n year = {2024},\n url = {https://doi.org/10.1109/SANER60148.2024.00017},\n doi = {10.1109/SANER60148.2024.00017},\n timestamp = {Tue, 30 Jul 2024 11:08:59 +0200},\n biburl = {https://dblp.org/rec/conf/wcre/Huang0QSXFWYLQ24.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Improving Domain Adaptation through Extended-Text Reading Comprehension.\n \n \n \n \n\n\n \n Jiang, T.; Huang, S.; Luo, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; Zhang, Q.; Wang, D.; and Zhuang, F.\n\n\n \n\n\n\n
CoRR, abs/2401.07284. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2401-07284,\n author = {Ting Jiang and\n Shaohan Huang and\n Shengyue Luo and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang and\n Deqing Wang and\n Fuzhen Zhuang},\n title = {Improving Domain Adaptation through Extended-Text Reading Comprehension},\n journal = {CoRR},\n volume = {abs/2401.07284},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2401.07284},\n doi = {10.48550/ARXIV.2401.07284},\n eprinttype = {arXiv},\n eprint = {2401.07284},\n timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2401-07284.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models.\n \n \n \n \n\n\n \n Li, H.; Dong, Q.; Tang, Z.; Wang, C.; Zhang, X.; Huang, H.; Huang, S.; Huang, X.; Huang, Z.; Zhang, D.; Gu, Y.; Cheng, X.; Wang, X.; Chen, S.; Dong, L.; Lu, W.; Sui, Z.; Wang, B.; Lam, W.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2402.13064. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-13064,\n author = {Haoran Li and\n Qingxiu Dong and\n Zhengyang Tang and\n Chaojun Wang and\n Xingxing Zhang and\n Haoyang Huang and\n Shaohan Huang and\n Xiaolong Huang and\n Zeqiang Huang and\n Dongdong Zhang and\n Yuxian Gu and\n Xin Cheng and\n Xun Wang and\n Si{-}Qing Chen and\n Li Dong and\n Wei Lu and\n Zhifang Sui and\n Benyou Wang and\n Wai Lam and\n Furu Wei},\n title = {Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning\n for Language Models},\n journal = {CoRR},\n volume = {abs/2402.13064},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2402.13064},\n doi = {10.48550/ARXIV.2402.13064},\n eprinttype = {arXiv},\n eprint = {2402.13064},\n timestamp = {Tue, 22 Apr 2025 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2402-13064.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Se\\(^\\mbox2\\): Sequential Example Selection for In-Context Learning.\n \n \n \n \n\n\n \n Liu, H.; Liu, J.; Huang, S.; Zhan, Y.; Sun, H.; Deng, W.; Wei, F.; and Zhang, Q.\n\n\n \n\n\n\n
CoRR, abs/2402.13874. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-13874,\n author = {Haoyu Liu and\n Jianfeng Liu and\n Shaohan Huang and\n Yuefeng Zhan and\n Hao Sun and\n Weiwei Deng and\n Furu Wei and\n Qi Zhang},\n title = {Se\\({}^{\\mbox{2}}\\): Sequential Example Selection for In-Context Learning},\n journal = {CoRR},\n volume = {abs/2402.13874},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2402.13874},\n doi = {10.48550/ARXIV.2402.13874},\n eprinttype = {arXiv},\n eprint = {2402.13874},\n timestamp = {Tue, 23 Jul 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2402-13874.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Text Diffusion with Reinforced Conditioning.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n
CoRR, abs/2402.14843. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-14843,\n author = {Yuxuan Liu and\n Tianchi Yang and\n Shaohan Huang and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang},\n title = {Text Diffusion with Reinforced Conditioning},\n journal = {CoRR},\n volume = {abs/2402.14843},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2402.14843},\n doi = {10.48550/ARXIV.2402.14843},\n eprinttype = {arXiv},\n eprint = {2402.14843},\n timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2402-14843.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition.\n \n \n \n \n\n\n \n Liu, Y.; Yang, T.; Huang, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n
CoRR, abs/2402.15754. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-15754,\n author = {Yuxuan Liu and\n Tianchi Yang and\n Shaohan Huang and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang},\n title = {HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical\n Criteria Decomposition},\n journal = {CoRR},\n volume = {abs/2402.15754},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2402.15754},\n doi = {10.48550/ARXIV.2402.15754},\n eprinttype = {arXiv},\n eprint = {2402.15754},\n timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2402-15754.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.\n \n \n \n \n\n\n \n Ma, S.; Wang, H.; Ma, L.; Wang, L.; Wang, W.; Huang, S.; Dong, L.; Wang, R.; Xue, J.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2402.17764. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-17764,\n author = {Shuming Ma and\n Hongyu Wang and\n Lingxiao Ma and\n Lei Wang and\n Wenhui Wang and\n Shaohan Huang and\n Li Dong and\n Ruiping Wang and\n Jilong Xue and\n Furu Wei},\n title = {The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits},\n journal = {CoRR},\n volume = {abs/2402.17764},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2402.17764},\n doi = {10.48550/ARXIV.2402.17764},\n eprinttype = {arXiv},\n eprint = {2402.17764},\n timestamp = {Fri, 19 Jul 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2402-17764.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n ResLoRA: Identity Residual Mapping in Low-Rank Adaption.\n \n \n \n \n\n\n \n Shi, S.; Huang, S.; Song, M.; Li, Z.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; and Zhang, Q.\n\n\n \n\n\n\n
CoRR, abs/2402.18039. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2402-18039,\n author = {Shuhua Shi and\n Shaohan Huang and\n Minghui Song and\n Zhoujun Li and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang},\n title = {ResLoRA: Identity Residual Mapping in Low-Rank Adaption},\n journal = {CoRR},\n volume = {abs/2402.18039},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2402.18039},\n doi = {10.48550/ARXIV.2402.18039},\n eprinttype = {arXiv},\n eprint = {2402.18039},\n timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2402-18039.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Exploring the Comprehension of ChatGPT in Traditional Chinese Medicine Knowledge.\n \n \n \n \n\n\n \n Li, Y.; Huang, S.; Qi, J.; Quan, L.; Han, D.; and Luan, Z.\n\n\n \n\n\n\n
CoRR, abs/2403.09164. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2403-09164,\n author = {Yizhen Li and\n Shaohan Huang and\n Jiaxing Qi and\n Lei Quan and\n Dongran Han and\n Zhongzhi Luan},\n title = {Exploring the Comprehension of ChatGPT in Traditional Chinese Medicine\n Knowledge},\n journal = {CoRR},\n volume = {abs/2403.09164},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2403.09164},\n doi = {10.48550/ARXIV.2403.09164},\n eprinttype = {arXiv},\n eprint = {2403.09164},\n timestamp = {Fri, 05 Apr 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2403-09164.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Mixture of LoRA Experts.\n \n \n \n \n\n\n \n Wu, X.; Huang, S.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2404.13628. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2404-13628,\n author = {Xun Wu and\n Shaohan Huang and\n Furu Wei},\n title = {Mixture of LoRA Experts},\n journal = {CoRR},\n volume = {abs/2404.13628},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2404.13628},\n doi = {10.48550/ARXIV.2404.13628},\n eprinttype = {arXiv},\n eprint = {2404.13628},\n timestamp = {Sat, 25 May 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2404-13628.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Multi-Head Mixture-of-Experts.\n \n \n \n \n\n\n \n Wu, X.; Huang, S.; Wang, W.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2404.15045. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2404-15045,\n author = {Xun Wu and\n Shaohan Huang and\n Wenhui Wang and\n Furu Wei},\n title = {Multi-Head Mixture-of-Experts},\n journal = {CoRR},\n volume = {abs/2404.15045},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2404.15045},\n doi = {10.48550/ARXIV.2404.15045},\n eprinttype = {arXiv},\n eprint = {2404.15045},\n timestamp = {Sat, 25 May 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2404-15045.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation.\n \n \n \n \n\n\n \n Wu, X.; Huang, S.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2404.15100. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2404-15100,\n author = {Xun Wu and\n Shaohan Huang and\n Furu Wei},\n title = {Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image\n Generation},\n journal = {CoRR},\n volume = {abs/2404.15100},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2404.15100},\n doi = {10.48550/ARXIV.2404.15100},\n eprinttype = {arXiv},\n eprint = {2404.15100},\n timestamp = {Sat, 25 May 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2404-15100.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n You Only Cache Once: Decoder-Decoder Architectures for Language Models.\n \n \n \n \n\n\n \n Sun, Y.; Dong, L.; Zhu, Y.; Huang, S.; Wang, W.; Ma, S.; Zhang, Q.; Wang, J.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2405.05254. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2405-05254,\n author = {Yutao Sun and\n Li Dong and\n Yi Zhu and\n Shaohan Huang and\n Wenhui Wang and\n Shuming Ma and\n Quanlu Zhang and\n Jianyong Wang and\n Furu Wei},\n title = {You Only Cache Once: Decoder-Decoder Architectures for Language Models},\n journal = {CoRR},\n volume = {abs/2405.05254},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2405.05254},\n doi = {10.48550/ARXIV.2405.05254},\n eprinttype = {arXiv},\n eprint = {2405.05254},\n timestamp = {Fri, 04 Oct 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2405-05254.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning.\n \n \n \n \n\n\n \n Jiang, T.; Huang, S.; Luo, S.; Zhang, Z.; Huang, H.; Wei, F.; Deng, W.; Sun, F.; Zhang, Q.; Wang, D.; and Zhuang, F.\n\n\n \n\n\n\n
CoRR, abs/2405.12130. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2405-12130,\n author = {Ting Jiang and\n Shaohan Huang and\n Shengyue Luo and\n Zihan Zhang and\n Haizhen Huang and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang and\n Deqing Wang and\n Fuzhen Zhuang},\n title = {MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning},\n journal = {CoRR},\n volume = {abs/2405.12130},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2405.12130},\n doi = {10.48550/ARXIV.2405.12130},\n eprinttype = {arXiv},\n eprint = {2405.12130},\n timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2405-12130.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning.\n \n \n \n \n\n\n \n Qi, J.; Luan, Z.; Huang, S.; Fung, C. J.; Yang, H.; and Qian, D.\n\n\n \n\n\n\n
CoRR, abs/2406.07925. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2406-07925,\n author = {Jiaxing Qi and\n Zhongzhi Luan and\n Shaohan Huang and\n Carol J. Fung and\n Hailong Yang and\n Depei Qian},\n title = {FDLoRA: Personalized Federated Learning of Large Language Model via\n Dual LoRA Tuning},\n journal = {CoRR},\n volume = {abs/2406.07925},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2406.07925},\n doi = {10.48550/ARXIV.2406.07925},\n eprinttype = {arXiv},\n eprint = {2406.07925},\n timestamp = {Mon, 08 Jul 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2406-07925.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Instruction Pre-Training: Language Models are Supervised Multitask Learners.\n \n \n \n \n\n\n \n Cheng, D.; Gu, Y.; Huang, S.; Bi, J.; Huang, M.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2406.14491. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2406-14491,\n author = {Daixuan Cheng and\n Yuxian Gu and\n Shaohan Huang and\n Junyu Bi and\n Minlie Huang and\n Furu Wei},\n title = {Instruction Pre-Training: Language Models are Supervised Multitask\n Learners},\n journal = {CoRR},\n volume = {abs/2406.14491},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2406.14491},\n doi = {10.48550/ARXIV.2406.14491},\n eprinttype = {arXiv},\n eprint = {2406.14491},\n timestamp = {Tue, 16 Jul 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2406-14491.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Textual Aesthetics in Large Language Models.\n \n \n \n \n\n\n \n Jiang, L.; Huang, S.; Wu, X.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2411.02930. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2411-02930,\n author = {Lingjie Jiang and\n Shaohan Huang and\n Xun Wu and\n Furu Wei},\n title = {Textual Aesthetics in Large Language Models},\n journal = {CoRR},\n volume = {abs/2411.02930},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2411.02930},\n doi = {10.48550/ARXIV.2411.02930},\n eprinttype = {arXiv},\n eprint = {2411.02930},\n timestamp = {Wed, 01 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-2411-02930.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n MH-MoE: Multi-Head Mixture-of-Experts.\n \n \n \n \n\n\n \n Huang, S.; Wu, X.; Ma, S.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2411.16205. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2411-16205,\n author = {Shaohan Huang and\n Xun Wu and\n Shuming Ma and\n Furu Wei},\n title = {MH-MoE: Multi-Head Mixture-of-Experts},\n journal = {CoRR},\n volume = {abs/2411.16205},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2411.16205},\n doi = {10.48550/ARXIV.2411.16205},\n eprinttype = {arXiv},\n eprint = {2411.16205},\n timestamp = {Wed, 01 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-2411-16205.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n On Domain-Specific Post-Training for Multimodal Large Language Models.\n \n \n \n \n\n\n \n Cheng, D.; Huang, S.; Zhu, Z.; Zhang, X.; Zhao, W. X.; Luan, Z.; Dai, B.; and Zhang, Z.\n\n\n \n\n\n\n
CoRR, abs/2411.19930. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2411-19930,\n author = {Daixuan Cheng and\n Shaohan Huang and\n Ziyu Zhu and\n Xintong Zhang and\n Wayne Xin Zhao and\n Zhongzhi Luan and\n Bo Dai and\n Zhenliang Zhang},\n title = {On Domain-Specific Post-Training for Multimodal Large Language Models},\n journal = {CoRR},\n volume = {abs/2411.19930},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2411.19930},\n doi = {10.48550/ARXIV.2411.19930},\n eprinttype = {arXiv},\n eprint = {2411.19930},\n timestamp = {Wed, 29 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-2411-19930.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n RedStone: Curating General, Code, Math, and QA Data for Large Language Models.\n \n \n \n \n\n\n \n Chang, Y.; Cui, L.; Dong, L.; Huang, S.; Huang, Y.; Huang, Y.; Li, S.; Lv, T.; Ma, S.; Sun, Q.; Wang, W.; Wei, F.; Xin, Y.; Yang, M.; Yin, Q.; and Zhang, X.\n\n\n \n\n\n\n
CoRR, abs/2412.03398. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2412-03398,\n author = {Yaoyao Chang and\n Lei Cui and\n Li Dong and\n Shaohan Huang and\n Yangyu Huang and\n Yupan Huang and\n Scarlett Li and\n Tengchao Lv and\n Shuming Ma and\n Qinzheng Sun and\n Wenhui Wang and\n Furu Wei and\n Ying Xin and\n Mao Yang and\n Qiufeng Yin and\n Xingxing Zhang},\n title = {RedStone: Curating General, Code, Math, and {QA} Data for Large Language\n Models},\n journal = {CoRR},\n volume = {abs/2412.03398},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2412.03398},\n doi = {10.48550/ARXIV.2412.03398},\n eprinttype = {arXiv},\n eprint = {2412.03398},\n timestamp = {Mon, 13 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-2412-03398.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Multimodal Latent Language Modeling with Next-Token Diffusion.\n \n \n \n \n\n\n \n Sun, Y.; Bao, H.; Wang, W.; Peng, Z.; Dong, L.; Huang, S.; Wang, J.; and Wei, F.\n\n\n \n\n\n\n
CoRR, abs/2412.08635. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2412-08635,\n author = {Yutao Sun and\n Hangbo Bao and\n Wenhui Wang and\n Zhiliang Peng and\n Li Dong and\n Shaohan Huang and\n Jianyong Wang and\n Furu Wei},\n title = {Multimodal Latent Language Modeling with Next-Token Diffusion},\n journal = {CoRR},\n volume = {abs/2412.08635},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2412.08635},\n doi = {10.48550/ARXIV.2412.08635},\n eprinttype = {arXiv},\n eprint = {2412.08635},\n timestamp = {Mon, 20 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-2412-08635.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Quantum Machine Learning in Log-based Anomaly Detection: Challenges and Opportunities.\n \n \n \n \n\n\n \n Qi, J.; Zeng, C.; Luan, Z.; Huang, S.; Yang, S.; Lu, Y.; Han, B.; Yang, H.; and Qian, D.\n\n\n \n\n\n\n
CoRR, abs/2412.13529. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2412-13529,\n author = {Jiaxing Qi and\n Chang Zeng and\n Zhongzhi Luan and\n Shaohan Huang and\n Shu Yang and\n Yao Lu and\n Bin Han and\n Hailong Yang and\n Depei Qian},\n title = {Quantum Machine Learning in Log-based Anomaly Detection: Challenges\n and Opportunities},\n journal = {CoRR},\n volume = {abs/2412.13529},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2412.13529},\n doi = {10.48550/ARXIV.2412.13529},\n eprinttype = {arXiv},\n eprint = {2412.13529},\n timestamp = {Tue, 21 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-2412-13529.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Context-DPO: Aligning Language Models for Context-Faithfulness.\n \n \n \n \n\n\n \n Bi, B.; Huang, S.; Wang, Y.; Yang, T.; Zhang, Z.; Huang, H.; Mei, L.; Fang, J.; Li, Z.; Wei, F.; Deng, W.; Sun, F.; Zhang, Q.; and Liu, S.\n\n\n \n\n\n\n
CoRR, abs/2412.15280. 2024.\n
\n\n
\n\n
\n\n
\n\n \n \n
Paper\n \n \n\n \n \n doi\n \n \n\n \n link\n \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{DBLP:journals/corr/abs-2412-15280,\n author = {Baolong Bi and\n Shaohan Huang and\n Yiwei Wang and\n Tianchi Yang and\n Zihan Zhang and\n Haizhen Huang and\n Lingrui Mei and\n Junfeng Fang and\n Zehao Li and\n Furu Wei and\n Weiwei Deng and\n Feng Sun and\n Qi Zhang and\n Shenghua Liu},\n title = {Context-DPO: Aligning Language Models for Context-Faithfulness},\n journal = {CoRR},\n volume = {abs/2412.15280},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2412.15280},\n doi = {10.48550/ARXIV.2412.15280},\n eprinttype = {arXiv},\n eprint = {2412.15280},\n timestamp = {Thu, 23 Jan 2025 00:00:00 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-2412-15280.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n