Jarrid Rector-Brooks

Shuibai Zhang

Anru R. Zhang

Michael M. Bronstein

Joey Bose

Alexander Tong

Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through flexible and para… (voir plus)llel generation paths. This flexibility is enabled by new sampling strategies, or planners, that iteratively choose where to denoise along the sequence rather than sampling uniformly at random. However, by modifying reverse paths, planners introduce a mismatch between the uniformly random denoising paths used during training and the planning-based paths used at inference. In this work, we systematically investigate this mismatch and theoretically show that the standard discrete diffusion training evidence lower bound (ELBO) does not accurately describe a denoiser under non-uniform planning. To bridge this gap, we derive a new Planned Evidence Lower Bound (P-ELBO) that directly incorporates planner-based reverse dynamics into the training objective. Building on this, we propose Planner Aware Path Learning (PAPL), a simple and effective modification of the standard masked discrete diffusion loss that aligns training and inference under planned denoisers. Empirically, PAPL delivers consistent improvements across domains, including a 40% relative gain in protein sequence modeling, up to a 4x improvement in MAUVE for text generation, and a 23% relative gain in HumanEval pass@10 for code generation.

2025-09-27

ArXiv (prépublication)

Laurence Perreault-Levasseur

Solving Bayesian inverse problems with diffusion priors and off-policy RL

Moksh J. Jain

Glen Berseth

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.

2025-03-06

ICLR.cc/2025/Workshop/DeLTa (poster)

Adaptive teachers for amortized samplers

Sungsoo Ahn

Jinkyoo Park

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnorma… (voir plus)lized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the Teacher) to guide the training of the primary amortized sampler (the Student) by prioritizing high-loss regions. The Teacher, an auxiliary behavior model, is trained to sample high-error regions of the Student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage.

2025-01-22

ICLR.cc/2025/Conference (poster)

Integrating Generative and Experimental Platforms for Biomolecular Design

Cheng-Hao Liu

Soojung Yang

Sidney L Lisanza

Francesca-Zhoufan Li

Hannes Stärk

Jacob Gershon

Lauren Hong

Pranam Chatterjee

Tommi Jaakkola

Regina Barzilay

David Baker

Frances H. Arnold

Biomolecular design, through artificial engineering of proteins, ligands, and nucleic acids, holds immense promise in addressing pressing me… (voir plus)dical, industrial, and environmental challenges. While generative machine learning has shown significant potential in this area, a palpable disconnect exists with experimental biology: many ML research efforts prioritize static benchmark performance, potentially sidelining impactful biological applications. This workshop seeks to bridge this gap by bringing computationalists and experimentalists together, catalyzing a deeper interdisciplinary discourse. Together, we will explore the strengths and challenges of generative ML in biology, experimental integration of generative ML, and biological problems ready for ML. To attract high-quality and diverse research, we partnered with Nature Biotechnology for a special collection, and we created dedicated tracks for in-silico ML research and hybrid ML-experimental biology research. Our lineup features emerging leaders as speakers and renowned scientists as panelists, encapsulating a spectrum from high-throughput experimentation and computational biology to generative ML. With a diverse organizing team and backed by industry sponsors, we dedicate the workshop to pushing the boundaries of ML's role in biology.

2025-01-01

ICLR.cc/2025/Workshop_Proposals (publié)

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Zhangzhi Peng

Zachary Quinn

Cheng-Hao Liu

Michael M. Bronstein

Pranam Chatterjee

2025-01-01

ICLR (publié)

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Zhangzhi Peng

Zachary Quinn

Cheng-Hao Liu

Michael M. Bronstein

Pranam Chatterjee

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.

2024-10-10

ArXiv (prépublication)

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Zhangzhi Peng

Zachary Quinn

Cheng-Hao Liu

Michael M. Bronstein

Pranam Chatterjee

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.

2024-10-10

ArXiv (prépublication)

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Zhangzhi Peng

Zachary Quinn

Cheng-Hao Liu

Michael M. Bronstein

Pranam Chatterjee

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.

2024-10-10

ArXiv (prépublication)

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Zhangzhi Peng

Zachary Quinn

Cheng-Hao Liu

Michael M. Bronstein

Pranam Chatterjee

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.

2024-10-10

ArXiv (prépublication)

Adaptive teachers for amortized samplers

Sungsoo Ahn

Jinkyoo Park

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnorma… (voir plus)lized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the \teacher) to guide the training of the primary amortized sampler (the \student). The \teacher, an auxiliary behavior model, is trained to sample high-loss regions of the \student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage. Source code is available at https://github.com/alstn12088/adaptive-teacher.

2024-10-02

ArXiv (prépublication)

Adaptive teachers for amortized samplers

Sungsoo Ahn

Jinkyoo Park

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnorma… (voir plus)lized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the \teacher) to guide the training of the primary amortized sampler (the \student). The \teacher, an auxiliary behavior model, is trained to sample high-loss regions of the \student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage. Source code is available at https://github.com/alstn12088/adaptive-teacher.

2024-10-02

ArXiv (prépublication)

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

Moksh J. Jain

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,

2024-09-25

NeurIPS.cc/2024/Conference (poster)