1 code implementation • 3 May 2024 • Piotr Padlewski, Max Bain, Matthew Henderson, Zhongkai Zhu, Nishant Relan, Hai Pham, Donovan Ong, Kaloyan Aleksiev, Aitor Ormazabal, Samuel Phua, Ethan Yeo, Eugenie Lamprecht, Qi Liu, Yuqi Wang, Eric Chen, Deyu Fu, Lei LI, Che Zheng, Cyprien de Masson d'Autume, Dani Yogatama, Mikel Artetxe, Yi Tay
We introduce Vibe-Eval: a new open benchmark and framework for evaluating multimodal chat models.
no code implementations • 18 Apr 2024 • Aitor Ormazabal, Che Zheng, Cyprien de Masson d'Autume, Dani Yogatama, Deyu Fu, Donovan Ong, Eric Chen, Eugenie Lamprecht, Hai Pham, Isaac Ong, Kaloyan Aleksiev, Lei LI, Matthew Henderson, Max Bain, Mikel Artetxe, Nishant Relan, Piotr Padlewski, Qi Liu, Ren Chen, Samuel Phua, Yazheng Yang, Yi Tay, Yuqi Wang, Zhongkai Zhu, Zhihui Xie
On text benchmarks, Core not only performs competitively to other frontier models on a set of well-established benchmarks (e. g. MMLU, GSM8K) but also outperforms GPT4-0613 on human evaluation.
no code implementations • 30 Aug 2023 • Hai Pham, Young Jin Kim, Subhabrata Mukherjee, David P. Woodruff, Barnabas Poczos, Hany Hassan Awadalla
Mixture-of-experts (MoE) architecture has been proven a powerful method for diverse tasks in training deep models in many applications.
1 code implementation • 24 May 2023 • Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabás Póczos
Our method outperforms the very LLM that was used to generate the annotated dataset -- with Few-Shot Prompting on GPT3. 5 achieving 58%, 61%, and 64% on the respective datasets, a consistently lower correction accuracy, despite using nearly 800 times as many parameters as our model.
no code implementations • 8 Nov 2022 • Han Nguyen, Hai Pham, Sashank J. Reddi, Barnabás Póczos
Despite their popularity in deep learning and machine learning in general, the theoretical properties of adaptive optimizers such as Adagrad, RMSProp, Adam or AdamW are not yet fully understood.
1 code implementation • 10 Oct 2022 • Nikita Dvornik, Isma Hadji, Hai Pham, Dhaivat Bhatt, Brais Martinez, Afsaneh Fazly, Allan D. Jepson
In this setup, we seek the optimal step ordering consistent with the procedure flow graph and a given video.
no code implementations • 17 Aug 2022 • Hai Pham, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang
Despite several successes in document understanding, the practical task for long document understanding is largely under-explored due to several challenges in computation and how to efficiently absorb long multimodal input.
2 code implementations • NAACL 2021 • Yiwei Lyu, Paul Pu Liang, Hai Pham, Eduard Hovy, Barnabás Póczos, Ruslan Salakhutdinov, Louis-Philippe Morency
Many of the existing style transfer benchmarks primarily focus on individual high-level semantic changes (e. g. positive to negative), which enable controllability at a high level but do not offer fine-grained control involving sentence structure, emphasis, and content of the sentence.
1 code implementation • NeurIPS 2020 • Quang Minh Hoang, Trong Nghia Hoang, Hai Pham, David P. Woodruff
We introduce a new scalable approximation for Gaussian processes with provable guarantees which hold simultaneously over its entire parameter space.
no code implementations • 18 Aug 2020 • Hai Pham, Amrith Setlur, Saket Dingliwal, Tzu-Hsiang Lin, Barnabas Poczos, Kang Huang, Zhuo Li, Jae Lim, Collin McCormack, Tam Vu
Despite the advent of deep learning in computer vision, the general handwriting recognition problem is far from solved.
no code implementations • 20 Feb 2020 • Ilqar Ramazanli, Han Nguyen, Hai Pham, Sashank J. Reddi, Barnabas Poczos
It often leads to the dependence of convergence rate on maximum Lipschitz constant of gradients across the devices.
no code implementations • 25 Sep 2019 • Tung-Long Vuong, Han Nguyen, Hai Pham, Kenneth Tran
Under this framework, the objective function can represented end-to-end as a single computational graph, which allows seamless policy gradient computation via backpropagation through the models.
2 code implementations • 19 Dec 2018 • Hai Pham, Paul Pu Liang, Thomas Manzini, Louis-Philippe Morency, Barnabas Poczos
Our method is based on the key insight that translation from a source to a target modality provides a method of learning joint representations using only the source modality as input.
no code implementations • WS 2018 • Hai Pham, Thomas Manzini, Paul Pu Liang, Barnabas Poczos
Multimodal machine learning is a core research area spanning the language, visual and acoustic modalities.