Portrait de Mohsin Hasan

Mohsin Hasan

Doctorat - UdeM
Superviseur⋅e principal⋅e
Sujets de recherche
Modèles génératifs
Modèles probabilistes
Systèmes dynamiques

Publications

Discrete Feynman-Kac Correctors
Marta Skreta
Alan Aspuru-Guzik
The performance of Large Language Models (LLMs) directly depends on the size of the context that the model was trained on. Despite significa… (voir plus)nt progress in increasing the context size of the current models, some applications remain bottlenecked by the number of processed tokens at inference time. A particular mathematical problem LLMs can be used for is inferring parameters in a statistical model, given data-points as input. Here we make a case demonstrating that discrete diffusion models offer a promising avenue for scaling such parameter prediction tasks, by combining the outputs of the same model evaluated on different parts of the training data. We propose Discrete Fenyman-Kac Correctors --- a framework that allows for controlling the generated distribution of discrete masked diffusion models at inference time. We derive Sequential Monte Carlo (SMC) algorithms that, given a trained discrete diffusion model, sample from its annealed distribution or the product of distributions with different conditions. Notably, our framework does not require any training, finetuning and external reward functions. Finally, we apply our framework to amortized linear regression using LLaDA and demonstrate that it drastically outperforms the standard inference procedure in terms of accuracy and adherence to prompt format.
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
Any well-behaved generative model over a variable …
Solving Bayesian inverse problems with diffusion priors and off-policy RL
This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (R… (voir plus)L) objective that can asymptotically solve Bayesian inverse problems optimally. We extend the original work by using RTB to train conditional diffusion model posteriors from pretrained unconditional priors for challenging linear and non-linear inverse problems in vision, and science. We use the objective alongside techniques such as off-policy backtracking exploration to improve training. Importantly, our results show that existing training-free diffusion posterior methods struggle to perform effective posterior inference in latent space due to inherent biases.
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
Any well-behaved generative model over a variable …
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
Zhangzhi Peng
Zachary Quinn
Cheng-Hao Liu
Nouha Dziri
Michael M. Bronstein
Pranam Chatterjee
Alexander Tong
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
Zhangzhi Peng
Zachary Quinn
Cheng-Hao Liu
Nouha Dziri
Michael M. Bronstein
Pranam Chatterjee
Alexander Tong
Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very buil… (voir plus)ding blocks of life in protein sequences. However, application domains need to exert control over the generated data by steering the generative process - typically via RLHF - to satisfy a specified property, reward, or affinity metric. In this paper, we study the problem of steering Masked Diffusion Models (MDMs), a recent class of discrete diffusion models that offer a compelling alternative to traditional autoregressive models. We introduce Discrete Denoising Posterior Prediction (DDPP), a novel framework that casts the task of steering pre-trained MDMs as a problem of probabilistic inference by learning to sample from a target Bayesian posterior. Our DDPP framework leads to a family of three novel objectives that are all simulation-free, and thus scalable while applying to general non-differentiable reward functions. Empirically, we instantiate DDPP by steering MDMs to perform class-conditional pixel-level image modeling, RLHF-based alignment of MDMs using text-based rewards, and finetuning protein language models to generate more diverse secondary structures and shorter proteins. We substantiate our designs via wet-lab validation, where we observe transient expression of reward-optimized protein sequences.
Amortizing intractable inference in diffusion models for vision, language, and control
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors … (voir plus)in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data,
Amortizing intractable inference in diffusion models for vision, language, and control
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors … (voir plus)in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data,
Amortizing intractable inference in diffusion models for vision, language, and control
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors … (voir plus)in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data,
Amortizing intractable inference in diffusion models for vision, language, and control
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors … (voir plus)in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data,
Estimating Expectations without Sampling: Neural Stein Estimation
Cheikh Ahmed
Awa Khouna
We propose a method for estimating the expected value of a given function …