Related papers: Gradual Fine-Tuning for Flow Matching Models
While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between their pretraining performance and real-world deployment…
In the era of foundation models, fine-tuning pre-trained models for specific downstream tasks has become crucial. This drives the need for robust fine-tuning methods to address challenges such as model overfitting and sparse labeling.…
We propose a simple, scalable algorithm for using stochastic interpolants to sample from unnormalized densities and for fine-tuning generative models. The approach, Tilt Matching, arises from a dynamical equation relating the flow matching…
While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samples, leading to data inefficiency. To address this, we…
Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment. However, they often introduce visual hallucinations like over-optimized details and semantic misalignment. This work preliminarily explores why visual…
Controlling generative models is computationally expensive. This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires estimating the value function. This task demands access to…
Traditional supervised fine-tuning (SFT) strategies for sequence-to-sequence tasks often train models to directly generate the target output. Recent work has shown that guiding models with intermediate steps, such as keywords, outlines, or…
This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…
Guidance of generative models is typically achieved by modifying the probability flow vector field through the addition of a guidance field. In this paper, we instead propose the Source-Guided Flow Matching (SGFM) framework, which modifies…
We present Direct Reward Fine-Tuning (DRaFT), a simple and effective method for fine-tuning diffusion models to maximize differentiable reward functions, such as scores from human preference models. We first show that it is possible to…
Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative…
Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring it to a downstream task. Recently, projected gradient…
Boltzmann Generators have emerged as a promising machine learning tool for generating samples from equilibrium distributions of molecular systems using Normalizing Flows and importance weighting. Recently, Flow Matching has helped speed up…
Parameter-efficient fine-tuning (PEFT) has become a common method for fine-tuning large language models, where a base model can serve multiple users through PEFT module switching. To enhance user experience, base models require periodic…
This paper investigates the connections between rectified flows, flow matching, and optimal transport. Flow matching is a recent approach to learning generative models by estimating velocity fields that guide transformations from a source…
Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional…
Classifier-free guidance (CFG) is the workhorse for steering large diffusion models toward text-conditioned targets, yet its native application to rectified flow (RF) based models provokes severe off-manifold drift, yielding visual…
Recent text-driven motion generation methods span both discrete token-based approaches and continuous-latent formulations. MotionGPT3 exemplifies the latter paradigm, combining a learned continuous motion latent space with a diffusion-based…
Aligning features from different modalities, is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language models can achieve a general alignment between image and text, they often require…
Recommender systems are often asked to serve multiple recommendation scenarios or domains. Fine-tuning a pre-trained CTR model from source domains and adapting it to a target domain allows knowledge transferring. However, optimizing all the…