Generative Flow Networks
PulseAugur coverage of Generative Flow Networks — every cluster mentioning Generative Flow Networks across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
GFlowNet training methods explored via policy gradients and information geometry · 2 sources tracked
Two new research papers explore advanced training methods for Generative Flow Networks (GFlowNets). The first paper introduces a policy-gradient-based framework that bridges GFlowNet's flow balance with reinforcement le…
-
New paper unifies evolutionary computation for autonomous trading signal discovery
A new paper proposes a unified evolutionary computation (EC) perspective on automated formulaic alpha discovery, a process for generating trading signals from symbolic factor spaces. The research introduces a six-compon…
-
New regression losses enhance Generative Flow Network training
Researchers have developed new regression loss functions for Generative Flow Networks (GFlowNets) to improve their training process. By theoretically linking regression losses to specific divergence measures, the team d…
-
New MCMC method uses neural nets to adaptively stop sampling
Researchers have developed a new framework that uses neural classifiers to adaptively determine when to stop sampling in Markov chain Monte Carlo (MCMC) methods. This approach, framed within Generative Flow Networks (GF…
-
GFlowNets shown to learn optimal transport plans
Researchers have established a theoretical link between Generative Flow Networks (GFlowNets) and optimal transport (OT). Their work demonstrates that non-acyclic GFlowNets, when optimized, can effectively encode an opti…
-
GFlowGR framework uses Generative Flow Networks for recommendation fine-tuning
Researchers have introduced GFlowGR, a novel fine-tuning framework for generative recommendation systems that utilizes Generative Flow Networks (GFlowNets). This approach aims to address the exposure bias problem inhere…
-
New GFlowNet Framework Composes Pre-trained Models for Multi-Objective Generation
Researchers have developed a new framework for Generative Flow Networks (GFlowNets) that allows for the composition of pre-trained models at inference time. This approach enables rapid adaptation to new multi-objective …
-
New GFlowNet training method improves LLM prefix balance and diversity
Researchers have introduced a new training method for Generative Flow Networks (GFlowNets) called Rooted absorbed prefix Trajectory Balance (RapTB), designed to address issues like prefix collapse and length bias in lar…
-
New GFlowNet training method improves offline learning
Researchers have developed a new proxy-free training framework for Generative Flow Networks (GFlowNets) called Trajectory-Distilled GFlowNet (TD-GFN). This method uses inverse reinforcement learning to extract detailed …
-
AI framework accelerates radio propagation modeling with generative networks
Researchers have developed a new machine-learning framework using Generative Flow Networks to significantly speed up radio propagation modeling. This approach tackles the computational complexity of traditional ray trac…
-
Stable-GFN enhances LLM red-teaming with stable, diverse attack generation
Researchers have introduced Stable-GFlowNet (S-GFN), a novel method designed to enhance the diversity and robustness of Large Language Model (LLM) red-teaming. This approach addresses the training instability and mode c…