REVIEW 17 cited by
Guided Flows for Generative Modeling and Decision Making
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Classifier-free guidance is a key component for enhancing the performance of conditional generative models across diverse tasks. While it has previously demonstrated remarkable improvements for the sample quality, it has only been exclusively employed for diffusion models. In this paper, we integrate classifier-free guidance into Flow Matching (FM) models, an alternative simulation-free approach that trains Continuous Normalizing Flows (CNFs) based on regressing vector fields. We explore the usage of \emph{Guided Flows} for a variety of downstream applications. We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text-to-speech synthesis, boasting state-of-the-art performance. Notably, we are the first to apply flow models for plan generation in the offline reinforcement learning setting, showcasing a 10x speedup in computation compared to diffusion models while maintaining comparable performance.
Forward citations
Cited by 17 Pith papers
-
La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching
La-Proteina generates full-atom protein structures and sequences via flow matching over an explicit alpha-carbon backbone plus fixed-size per-residue latents, achieving state-of-the-art co-designability and scaling to...
-
GraspMeanFlow: SE(3)-Equivariant MeanFlow for Few-Step 6-DoF Grasp Generation
An SE(3)-equivariant average-velocity flow generates 6-DoF grasps in one or a few function evaluations, matching iterative flow baselines on ACRONYM.
-
Feynman-Kac-Flow: Inference Steering of Conditional Flow Matching to an Energy-Tilted Posterior
Feynman-Kac particle steering, previously diffusion-only, is derived for conditional flow matching and used to generate chirality-correct chemical transition states.
-
Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
Nabla-R2D3 aligns 3D-native diffusion models with human preferences by backpropagating multi-view 2D reward gradients through the denoising process, improving reward without destroying the pretrained 3D prior.
-
Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching
A flow-matching model equipped with a learned permutation-equivariant token mapping outperforms regression and generative baselines at inferring synthesizer parameters from audio.
-
Decision Flow Policy Optimization
Decision Flow frames the gradual action generation of flow-based policies as a flow MDP and updates the flow policy with flow-level value functions, reporting state-of-the-art results on several D4RL tasks.
-
FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
FlowQ uses energy-guided flow matching to learn an offline RL policy approximating π(a|s) ∝ πβ(a|s) exp(Q(s,a)) with guidance applied during training rather than at inference.
-
CellFlux: Simulating Cellular Morphology Changes via Flow Matching
A flow matching model that transforms same-batch control cell images into perturbed cell images achieves state-of-the-art FID and mode-of-action accuracy on BBBC021, RxRx1, and JUMP.
-
Designing a Conditional Prior Distribution for Flow-Based Generative Models
Condition-specific Gaussian mixture priors shorten flow-matching paths and improve FID, KID, and CLIP scores at low sampling steps on ImageNet-64 and MS-COCO.
-
Cross-modal Consistency Guidance for Robust Emotion Control in Auto-Regressive TTS Models
Introduces CCG-CFG with inconsistency-based dynamic scales and hard-sample mining distillation to boost emotional alignment in auto-regressive TTS, reporting up to 12% absolute gains in emotion recognition accuracy.
-
Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
ARFM adaptively adjusts a scaling factor in the flow-matching loss so that offline RL advantage signals are preserved while gradient variance is controlled, improving VLA robot policy fine-tuning.
-
Room Impulse Response Generation Conditioned on Acoustic Parameters
MaskGIT conditioned on acoustic parameters, operating on Descript Audio Codec tokens, generates room impulse responses that outperform StoRIR and FastRIR in objective and MUSHRA evaluations.
-
Normalizing Flows are Capable Models for Continuous Control
A simple normalizing flow policy matches or outperforms diffusion and autoregressive baselines across imitation learning, offline RL, goal-conditioned RL, and unsupervised RL on 82 tasks.
-
AffinityFlow: Guided Flows for Antibody Affinity Maturation
AffinityFlow guides AlphaFlow structure generation toward low Rosetta binding energy, then inverse-folds the structures to propose antibody mutations, and reports top scores on a computational affinity maturation benchmark.
-
Local MAP Sampling for Diffusion Models
LMAPS frames reverse-diffusion inverse-problem solving as repeated local MAP estimation, unifying existing optimization-based solvers, and achieves strong PSNR gains on tasks like motion deblurring, JPEG restoration, ...
-
Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
Blending a base diffusion model with its RL-finetuned version at sampling time lets users dial alignment strength, with the blend weight corresponding to the KL-regularization coefficient beta/w.
-
Reinforcement Learning: From Algorithms To Foundation Models
A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.
Discussion (0). Continue with ORCID to comment.