5 articles tagged with #flow-models. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers propose QGF (Q-Guided Flow), a reinforcement learning algorithm that optimizes policies entirely at test time using value gradients to guide pre-trained flow models, avoiding the training instability issues of traditional actor-critic approaches while maintaining competitive performance on offline RL benchmarks.
Researchers introduce Safety-Guided Flow (SGF), a unified probabilistic framework that combines control barrier functions with negative guidance approaches to improve safety in AI-generated content. The framework identifies a critical time window during the denoising process where strong negative guidance is most effective for preventing harmful outputs.
Researchers have developed Value Flows, a new reinforcement learning method that uses flow-based models to estimate complete return distributions rather than single scalar values. The approach achieves 1.3x improvement in success rates across 62 benchmark tasks by better identifying states with high return uncertainty for improved decision-making.
SymTRELLIS introduces a method to enforce geometric symmetries in 3D generative models without retraining underlying systems, using learned linear operators on voxel latents and velocity symmetrization during generation. The technique substantially reduces symmetry violations across rotational, reflectional, and polyhedral symmetries compared to existing models like TRELLIS.2 and Hunyuan3D-2.1.
Researchers identify Marginal Path Collapse, a failure mode in diffusion model steering where intermediate densities become non-normalizable despite valid endpoints. They propose Adaptive Path Correction with Exponents (ACE), a framework using time-varying exponents to stabilize compositional sampling in drug design and image generation tasks.
