Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models

• URL: http://arxiv.org/abs/2512.02636v1
• Date: Tue, 02 Dec 2025 10:48:20 GMT
• Title: Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models
• Authors: Xinyue Ai, Yutong He, Albert Gu, Ruslan Salakhutdinov, J Zico Kolter, Nicholas Matthew Boffi, Max Simchowitz,
• Abstract summary: Some of today's best generative models still require hundreds to thousands of neural function evaluations to compute a single likelihood.<n>We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude.<n>F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head.
• Score: 100.28111930893188
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Log-likelihood evaluation enables important capabilities in generative models, including model comparison, certain fine-tuning objectives, and many downstream applications. Yet paradoxically, some of today's best generative models -- diffusion and flow-based models -- still require hundreds to thousands of neural function evaluations (NFEs) to compute a single likelihood. While recent distillation methods have successfully accelerated sampling to just a few steps, they achieve this at the cost of likelihood tractability: existing approaches either abandon likelihood computation entirely or still require expensive integration over full trajectories. We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude. Our key insight is that in continuous normalizing flows, the coupled ODEs for sampling and likelihood are computed from a shared underlying velocity field, allowing us to jointly distill both the sampling trajectory and cumulative divergence using a single model. F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head. Experiments demonstrate F2D2's capability of achieving accurate log-likelihood with few-step evaluations while maintaining high sample quality, solving a long-standing computational bottleneck in flow-based generative models. As an application of our approach, we propose a lightweight self-guidance method that enables a 2-step MeanFlow model to outperform a 1024 step teacher model with only a single additional backward NFE.

Related papers

• FlowConsist: Make Your Flow Consistent with Real Trajectory [99.22869983378062]
  We argue that current fast-flow training paradigms suffer from two fundamental issues.<n> conditional velocities constructed from randomly paired noise-data samples introduce systematic trajectory drift.<n>We propose FlowConsist, a training framework designed to enforce trajectory consistency in fast flows.
  arXiv  Detail & Related papers  (2026-02-06T03:24:23Z)
• PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models [24.911180095603658]
  $texttPairFlow$ is a lightweight preprocessing step for training Discrete Flow Models (DFMs)<n>DFMs suffer from slow sampling due to their iterative nature.<n>$texttPairFlow$ matches or even surpasses the performance of two-stage training involving finetuning.
  arXiv  Detail & Related papers  (2025-12-23T05:31:56Z)
• FALCON: Few-step Accurate Likelihoods for Continuous Flows [78.37361800856583]
  We propose Few-step Accurate Likelihoods for Continuous Flows (FALCON), which allows for few-step sampling with a likelihood accurate enough for importance sampling applications.<n>We show FALCON outperforms state-of-the-art normalizing flow models for molecular Boltzmann sampling and is two orders of magnitude faster than the equivalently performing CNF model.
  arXiv  Detail & Related papers  (2025-12-10T18:47:25Z)
• TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows [25.487712175353035]
  We propose TwinFlow, a framework for training 1-step generative models.<n>Our method achieves a GenEval score of 0.83 in 1-NFE on text-to-image tasks.<n>Our approach matches the performance of the original 100-NFE model on GenEval and DPG-Bench benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T07:45:46Z)
• Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching [60.37045080890305]
  We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
  arXiv  Detail & Related papers  (2025-12-01T05:14:25Z)
• GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models [42.15046750300825]
  We introduce GLASS Flows, a new sampling paradigm that simulates a "flow matching model" to sample Markov transitions.<n>On large-scale text-to-image models, we show that GLASS Flows eliminate the trade-off between evolution and efficiency.
  arXiv  Detail & Related papers  (2025-09-29T17:58:36Z)
• Align Your Flow: Scaling Continuous-Time Flow Map Distillation [63.927438959502226]
  Flow maps connect any two noise levels in a single step and remain effective across all step counts.<n>We extensively validate our flow map models, called Align Your Flow, on challenging image generation benchmarks.<n>We show text-to-image flow map models that outperform all existing non-adversarially trained few-step samplers in text-conditioned synthesis.
  arXiv  Detail & Related papers  (2025-06-17T15:06:07Z)
• Mean Flows for One-step Generative Modeling [64.4997821467102]
  We propose a principled and effective framework for one-step generative modeling.<n>A well-defined identity between average and instantaneous velocities is derived and used to guide neural network training.<n>Our method, termed the MeanFlow model, is self-contained and requires no pre-training, distillation, or curriculum learning.
  arXiv  Detail & Related papers  (2025-05-19T17:59:42Z)
• Neural Flow Samplers with Shortcut Models [19.81513273510523]
  Continuous flow-based neural samplers offer a promising approach to generate samples from unnormalized densities.<n>We introduce an improved estimator for these challenging quantities, employing a velocity-driven Sequential Monte Carlo method.<n>Our proposed Neural Flow Shortcut Sampler empirically outperforms existing flow-based neural samplers on both synthetic datasets and complex n-body system targets.
  arXiv  Detail & Related papers  (2025-02-11T07:55:41Z)
• Flow map matching with stochastic interpolants: A mathematical framework for consistency models [15.520853806024943]
  Flow Map Matching is a principled framework for learning the two-time flow map of an underlying generative model.<n>We show that FMM unifies and extends a broad class of existing approaches for fast sampling.
  arXiv  Detail & Related papers  (2024-06-11T17:41:26Z)
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [56.38386580040991]
  Consistency Trajectory Model (CTM) is a generalization of Consistency Models (CM) CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance. Unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods.
  arXiv  Detail & Related papers  (2023-10-01T05:07:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.