Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition

Author

Moksh Jain

Mila

h-index 19 Homepage View on Semantic Scholar

We have 6 of 41 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Bayesian Symbolic Regression with Entropic Reinforcement Learning

Symbolic regression is the problem of finding an algebraic expression describing a stochastic dependence of a target variable on a set of inputs. Unlike forms of regression that fit parameters assuming a fixed model structure, symbolic regression is a search problem over the space of expressions, represented, for examp...

Oussama Boussif, Mohammed Mahfoud, Younesse Kaddar et al. · 2 citations
#machine learning May 2024

Learning diverse attacks on large language models for robust red-teaming and safety tuning

This work proposes to use GFlowNet fine-tuning followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts, and finds that the attacks generated by the method are effective against a wide range of target LLMs, both with and without safety tuning, and transfer we...

Seanie Lee, Minsu Kim, Lynn Cherif et al. · 62 citations · ⚡8
#machine learning Open access Oct 2023

PhyloGFN: Phylogenetic inference with generative flow networks

The framework of generative flow networks (GFlowNets) is adopted to tackle two core problems in phylogenetics: parsimony-based and Bayesian phylogenetic inference and it is demonstrated that the amortized posterior sampler, PhyloGFN, produces diverse and high-quality evolutionary hypotheses on real benchmark datasets.

Mingyang Zhou, Zichao Yan, Elliot Layne et al. · 37 citations · ⚡3
#machine learning Oct 2023

Amortizing intractable inference in large language models

This work interprets chain-of-thought reasoning as a latent variable modeling problem and demonstrates that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training and reward-maximizing policy optimization.

Edward J. Hu, Moksh Jain, Eric Elmoznino et al. · 110 citations · ⚡19
#machine learning May 2024

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

Amortized sampling of the posterior over data is studied, and the asymptotic correctness of a data-free learning objective, relative trajectory balance, is proved for training a diffusion model that samples from this posterior, a problem that existing methods solve only approximately or in restricted cases.

S. Venkatraman, Moksh Jain, Luca Scimeca et al. · 75 citations · ⚡5
#machine learning Jan 2022

Trajectory Balance: Improved Credit Assignment in GFlowNets

It is proved that any global minimizer of the trajectory balance objective can define a policy that samples exactly from the target distribution, and empirically demonstrate the benefits of the trajectories balance objective for GFlowNet convergence, diversity of generated samples, and robustness to long action sequenc...

Esmeralda S. Whitammer, Moksh Jain, Emmanuel Bengio et al. · 302 citations · ⚡60

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.