3 citations · 7 across the 13 of their papers we have counts for
9 papers · 1 filter
Universality and Convergence of Generative Flows
Leo Brunswic
Generative flows sample from an unnormalized target by training a flow to be balanced, and the training loss is the signal a practitioner watches. We ask what that signal is worth:…
JPmHC Dynamical Isometry via Orthogonal Hyper-Connections
Biswa Sengupta, Jinhua Wang, Leo Brunswic
Recent advances in deep learning, exemplified by Hyper-Connections (HC), have expanded the residual connection paradigm by introducing wider residual streams and diverse connectivi…
A Theory of Multi-Agent Generative Flow Networks
Leo Maxime Brunswic, Haozhi Wang, Shuang Luo +3
Generative flow networks utilize a flow-matching loss to learn a stochastic policy for generating objects from a sequence of actions, such that the probability of generating a patt…
Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling
Derek Li, Jiaming Zhou, Leo Maxime Brunswic +8
The pursuit of general-purpose artificial intelligence depends on large language models (LLMs) that can handle both structured reasoning and open-ended generation. We present Omni-…
Ergodic Generative Flows
Leo Maxime Brunswic, Mateo Clemente, Rui Heng Yang +3
Generative Flow Networks (GFNs) were initially introduced on directed acyclic graphs to sample from an unnormalized distribution density. Recent works have extended the theoretical…
NoT: Federated Unlearning via Weight Negation
Yasser H. Khalil, Leo Brunswic, Soufiane Lamghari +3
Federated unlearning (FU) aims to remove a participant's data contributions from a trained federated learning (FL) model, ensuring privacy and regulatory compliance. Traditional FU…
Generative Models in Decision Making: A Survey
Xinyu Shao, Jianping Zhang, Haozhi Wang +9
Generative models have fundamentally reshaped the landscape of decision-making, reframing the problem from pure scalar reward maximization to high-fidelity trajectory generation an…
Parametric Feature Transfer: One-shot Federated Learning with Foundation Models
Mahdi Beitollahi, Alex Bie, Sobhan Hemati +4
In one-shot federated learning (FL), clients collaboratively train a global model in a single round of communication. Existing approaches for one-shot FL enhance communication effi…
A Theory of Non-Acyclic Generative Flow Networks
Leo Maxime Brunswic, Yinchuan Li, Yushun Xu +2
GFlowNets is a novel flow-based method for learning a stochastic policy to generate objects via a sequence of actions and with probability proportional to a given positive reward.…