Fenchel Tilting: Weighted Correction for Efficient Finetuning of Generative Models

arXiv:2609.40030 · cs.LG, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-30

Updated: 2026-10-01

Code: https://github.com/zifan-5528/TFFT

Terminology

• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes

Sources

• Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generation
• FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
• Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization
• On the Guidance of Flow Matching
• Atomic Design Transformer: Scaffold-Conditioned 3D Molecule Generation via xTB-Reward Reinforcement Learning
• Flow Matching Guide and Code
• DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
• Tilt Matching for Scalable Sampling and Fine-Tuning
• Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond
• Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
• ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
• Diffusion Controller: Framework, Algorithms and Parameterization
• Energy-Weighted Flow Matching for Offline Reinforcement Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks