Výsledky vyhledávání - "Hasan, Mohsin"

Report

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Autor: Rector-Brooks, Jarrid, Hasan, Mohsin, Peng, Zhangzhi, Quinn, Zachary, Liu, Chenghao, Mittal, Sarthak, Dziri, Nouha, Bronstein, Michael, Bengio, Yoshua, Chatterjee, Pranam, Tong, Alexander, Bose, Avishek Joey

Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very building blocks of life in protein sequences. However, application domains need to exert control over the generate

Externí odkaz: http://arxiv.org/abs/2410.08134

Zobrazit plný text záznamu

Report

Amortizing intractable inference in diffusion models for vision, language, and control

Autor: Venkatraman, Siddarth, Jain, Moksh, Scimeca, Luca, Kim, Minsu, Sendera, Marcin, Hasan, Mohsin, Rowe, Luke, Mittal, Sarthak, Lemos, Pablo, Bengio, Emmanuel, Adam, Alexandre, Rector-Brooks, Jarrid, Bengio, Yoshua, Berseth, Glen, Malkin, Nikolay

Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of

Externí odkaz: http://arxiv.org/abs/2405.20971

Zobrazit plný text záznamu

Report

Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space

Autor: Hasan, Mohsin, Zhang, Guojun, Guo, Kaiyang, Chen, Xi, Poupart, Pascal

Federated Learning (FL) involves training a model over a dataset distributed among clients, with the constraint that each client's dataset is localized and possibly heterogeneous. In FL, small and noisy datasets are common, highlighting the need for

Externí odkaz: http://arxiv.org/abs/2312.09817

Zobrazit plný text záznamu

Report

Robust One Round Federated Learning with Predictive Space Bayesian Inference

Autor: Hasan, Mohsin, Zhang, Zehao, Guo, Kaiyang, Karami, Mahdi, Zhang, Guojun, Chen, Xi, Poupart, Pascal

Making predictions robust is an important challenge. A separate challenge in federated learning (FL) is to reduce the number of communication rounds, particularly since doing so reduces performance in heterogeneous data settings. To tackle both issue

Externí odkaz: http://arxiv.org/abs/2206.09526

Zobrazit plný text záznamu