Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning

• URL: http://arxiv.org/abs/2602.16796v1
• Date: Wed, 18 Feb 2026 19:00:59 GMT
• Title: Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
• Abstract summary: Fine-tuning pre-trained diffusion and flow models to optimize downstream utilities is central to real-world deployment.<n>We present Tail-aware Flow Fine-Tuning (TFFT), a principled and efficient distributional fine-tuning algorithm based on the Conditional Value-at-Risk (CVaR)
• Score: 40.79705260303773
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning pre-trained diffusion and flow models to optimize downstream utilities is central to real-world deployment. Existing entropy-regularized methods primarily maximize expected reward, providing no mechanism to shape tail behavior. However, tail control is often essential: the lower tail determines reliability by limiting low-reward failures, while the upper tail enables discovery by prioritizing rare, high-reward outcomes. In this work, we present Tail-aware Flow Fine-Tuning (TFFT), a principled and efficient distributional fine-tuning algorithm based on the Conditional Value-at-Risk (CVaR). We address two distinct tail-shaping goals: right-CVaR for seeking novel samples in the high-reward tail and left-CVaR for controlling worst-case samples in the low-reward tail. Unlike prior approaches that rely on non-linear optimization, we leverage the variational dual formulation of CVaR to decompose it into a decoupled two-stage procedure: a lightweight one-dimensional threshold optimization step, and a single entropy-regularized fine-tuning process via a specific pseudo-reward. This decomposition achieves CVaR fine-tuning efficiently with computational cost comparable to standard expected fine-tuning methods. We demonstrate the effectiveness of TFFT across illustrative experiments, high-dimensional text-to-image generation, and molecular design.

Related papers

• Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation [15.216413521560705]
  Test-time adaptation (TTA) aims to enhance the cross-domain performance of pre-trained models by adapting to unlabeled test data.<n>ZO methods rely only on forward computation, which can largely reduce the complexity and memory overhead of on-device deployment.<n>We propose an improved ZO method to substantially boost the performance of ZO optimization based TTA.
  arXiv  Detail & Related papers  (2026-08-12T17:17:40Z)
• Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning [8.422673935994451]
  consistency distillation has significantly accelerated the inference of diffusion models.<n>We propose Curvature-Adaptive Consistency Flow Matching to address the limitations of static sampling.<n>Our approach achieves new state-of-the-art results on large-scale models such as FLUX and SDXL.
  arXiv  Detail & Related papers  (2026-06-21T08:49:50Z)
• Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration [2.1016374925364616]
  Low-rank decomposition based on the singular value decomposition (SVD) provides a principled approach for model reduction.<n> Randomized alternatives such as randomized SVD (RSVD) improve efficiency, yet they suffer from poor approximation quality when the singular value spectrum decays slowly.<n>We propose randomized subspace (RSI) as a more effective alternative.
  arXiv  Detail & Related papers  (2026-04-03T02:47:03Z)
• Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization [76.38917994186733]
  Diff3R is a novel framework that bridges feed-forward prediction and test-time optimization.<n>We show that it can be seamlessly integrated into existing feed-forward 3DGS architectures for both pose-given and pose-free methods.
  arXiv  Detail & Related papers  (2026-04-01T15:40:20Z)
• Variational Entropic Optimal Transport [67.76725267984578]
  We propose Variational Entropic Optimal Transport (VarEOT) for domain translation problems.<n>VarEOT is based on an exact variational reformulation of the log-partition $log mathbbE[exp(cdot)$ as a tractable generalization over an auxiliary positive normalizer.<n> Experiments on synthetic data and unpaired image-to-image translation demonstrate competitive or improved translation quality.
  arXiv  Detail & Related papers  (2026-02-02T15:48:44Z)
• Parallel Diffusion Solver via Residual Dirichlet Policy Optimization [88.7827307535107]
  Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face significant image quality degradation under a low-dimensional budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as EPD-EPr), a novel ODE solver that mitigates these errors by incorporating multiple gradient parallel evaluations in each step.
  arXiv  Detail & Related papers  (2025-12-28T05:48:55Z)
• A Trainable Optimizer [18.195022468462753]
  We present a framework that jointly trains the full gradient estimator and the trainable weights of the model.<n>Pseudo-linear TO incurs negligible computational overhead, requiring only minimal additional multiplications.<n> Experiments demonstrate that TO methods converge faster than benchmark algorithms.
  arXiv  Detail & Related papers  (2025-08-03T14:06:07Z)
• To Theoretically Understand Transformer-Based In-Context Learning for Optimizing CSMA [26.87533852488578]
  The binary exponential backoff scheme is widely used in WiFi 7 and still incurs poor throughput performance under dynamic channel environments.<n>Recent model-based approaches simply optimize backoff strategies under a known and fixed node density.<n>This paper is the first to propose transformer-based in-context learning (ICL) theory for optimizing channel access.
  arXiv  Detail & Related papers  (2025-07-31T23:31:23Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Flow-GRPO: Training Flow Matching Models via Online RL [80.62659379624867]
  We propose Flow-GRPO, the first method to integrate online policy reinforcement learning into flow matching models.<n>Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation into an equivalent Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original number of inference steps.
  arXiv  Detail & Related papers  (2025-05-08T17:58:45Z)
• EXACT: How to Train Your Accuracy [6.144680854063938]
  We propose a new optimization framework by introducing ascentity to a model's output and optimizing expected accuracy. Experiments on linear models and deep image classification show that the proposed optimization method is a powerful alternative to widely used classification losses.
  arXiv  Detail & Related papers  (2022-05-19T15:13:00Z)
• Second-order step-size tuning of SGD for non-convex optimization [6.021787236982659]
  In view of a direct and simple improvement of vanilla SGD, this paper presents a fine-tuning of its step-sizes in the mini-batch case. One obtains a new first-order gradient method (Step-Tuned SGD) which can be seen as a version of the classical Barzilai-Borwein method.
  arXiv  Detail & Related papers  (2021-03-05T10:01:48Z)
• Efficient Semi-Implicit Variational Inference [65.07058307271329]
  We propose an efficient and scalable semi-implicit extrapolational (SIVI) Our method maps SIVI's evidence to a rigorous inference of lower gradient values.
  arXiv  Detail & Related papers  (2021-01-15T11:39:09Z)
• BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model [34.093978443640616]
  Recent methods have significantly reduced the performance of Binary Neural Networks (BNNs) guaranteeing the effective and efficient training of BNNs is an unsolved problem. We propose a BAMSProd algorithm with a key observation that the convergence property of optimizing deep binary model is strongly related to the quantization errors.
  arXiv  Detail & Related papers  (2020-09-29T06:12:32Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.