GFlowNets for AI-driven scientific discovery
PulseAugur coverage of GFlowNets for AI-driven scientific discovery — every cluster mentioning GFlowNets for AI-driven scientific discovery across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New GFlowNet mixture framework enhances AI scientific discovery
Researchers have developed a new theoretical framework for mixtures of GFlowNets, which are used to improve state space exploration and convergence in AI-driven scientific discovery. This framework is divided into conti…
-
GFlowNets generate diverse synthetic conversations for LLM training
Researchers have developed a novel method using Generative Flow Networks (GFlowNets) to create diverse synthetic conversational data for training Large Language Models (LLMs). This approach addresses the issue of low di…
-
Partial GFlowNet accelerates AI discovery by partitioning large state spaces
Researchers have introduced a novel approach called Partial GFlowNet to address convergence challenges in Generative Flow Networks (GFlowNets) when applied to large state spaces. This method partitions the state space i…
-
PhyloGFN uses generative flow networks for evolutionary relationship inference
Researchers have developed PhyloGFN, a novel method for phylogenetic inference that utilizes generative flow networks (GFlowNets). This approach is designed to address the computational challenges in reconstructing evol…
-
New flow networks tackle stochastic and adversarial AI challenges
Researchers have introduced Expected Flow Networks (EFlowNets), an advancement upon Generative Flow Networks (GFlowNets), designed to operate effectively in stochastic environments. These EFlowNets have demonstrated sup…
-
GFlowNets and variational inference algorithms shown to be equivalent in certain cases
This paper explores the connection between Generative Flow Networks (GFlowNets) and variational inference (VI), two families of probabilistic algorithms. The authors demonstrate that VI algorithms can be seen as special…
-
GFlowNets enhance LLM red-teaming for improved AI safety
Researchers have developed a new method using GFlowNets to improve the diversity and effectiveness of automated red-teaming for large language models (LLMs). This approach aims to discover a wider range of harmful promp…
-
GFlowNets applied to solve complex combinatorial optimization problems
Researchers have developed a novel approach using GFlowNets to tackle complex combinatorial optimization problems, which are often too difficult for traditional algorithms. The method involves designing specific Markov …
-
New 'trajectory balance' objective improves GFlowNet learning
Researchers have introduced "trajectory balance," a novel learning objective for Generative Flow Networks (GFlowNets). This new objective aims to improve credit assignment in GFlowNets, which are used for generating com…
-
FlowNeg method enhances knowledge graph embedding with diverse negative sampling
Researchers have developed FlowNeg, a novel method for generating diverse and informative negative samples in knowledge graph embedding (KGE) models. This approach utilizes a context-conditioned hierarchical generative …
-
FlowNeg method enhances knowledge graph embedding with diverse negative sampling
Researchers have developed FlowNeg, a novel method for generating diverse and informative negative samples in knowledge graph embedding (KGE) models. This approach utilizes a context-conditioned hierarchical generative …
-
GFlowNets used to generate novel LLM attacks in English and Turkish
Researchers have developed a novel method using GFlowNets to automatically generate adversarial attacks against Large Language Models (LLMs). This approach trains an attacker model to identify vulnerabilities in a victi…
-
GFlowNet interpretability study questions learned chemistry in drug discovery models
A new study published on arXiv investigates the interpretability of GFlowNets, a type of AI model used for drug discovery. Researchers developed a framework to analyze SynFlowNet, a GFlowNet trained on drug-likeness, an…
-
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 AlphaG-OPD framework enhances symbolic alpha factor discovery
Researchers have developed AlphaG-OPD, a new framework for symbolic alpha factor discovery that enhances the guidance provided by generative flow networks. This method addresses the limitation of existing models by offe…
-
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 TILDE method enables concept unlearning in text-to-image models
Researchers have developed TILDE (TILt-based Distributional Erasure), a new method for concept unlearning in text-to-image diffusion models. This technique addresses the challenge of removing specific concepts, such as …
-
New GFlowNet framework enhances active learning for molecular discovery
Researchers have developed a new active learning framework called BALD-GFlowNet, which utilizes Generative Flow Networks (GFlowNets) to improve the scalability of active learning, particularly for large datasets in area…
-
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…
-
Proximal Policy Optimization Enhances GFlowNet Training
Researchers have introduced Proximal Policy Optimization (PPO) as a novel method for training Generative Flow Networks (GFlowNets). This approach leverages connections between GFlowNets and entropy-regularized reinforce…