Image de couverture de livre

Improved off-policy training of diffusion samplers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sendera, Marcin, Kim, Minsu, Mittal, Sarthak, Lemos, Pablo, Scimeca, Luca, Rector-Brooks, Jarrid, Adam, Alexandre, Bengio, Yoshua, Malkin, Nikolay
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training
par: Berner, Julius, et autres
Publié: (2025)

Solving Bayesian inverse problems with diffusion priors and off-policy RL
par: Scimeca, Luca, et autres
Publié: (2025)

Amortizing intractable inference in diffusion models for vision, language, and control
par: Venkatraman, Siddarth, et autres
Publié: (2024)

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
par: Venkatraman, Siddarth, et autres
Publié: (2025)

Adaptive teachers for amortized samplers
par: Kim, Minsu, et autres
Publié: (2024)

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
par: Akhound-Sadegh, Tara, et autres
Publié: (2024)

In-Context Parametric Inference: Point or Distribution Estimators?
par: Mittal, Sarthak, et autres
Publié: (2025)

Improving and generalizing flow-based generative models with minibatch optimal transport
par: Tong, Alexander, et autres
Publié: (2023)

Machine learning and information theory concepts towards an AI Mathematician
par: Bengio, Yoshua, et autres
Publié: (2024)

On scalable and efficient training of diffusion samplers
par: Kim, Minkyu, et autres
Publié: (2025)

On Generalization for Generative Flow Networks
par: Krichel, Anas, et autres
Publié: (2024)

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
par: Rector-Brooks, Jarrid, et autres
Publié: (2024)

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
par: Scimeca, Luca, et autres
Publié: (2025)

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
par: Jiralerspong, Thomas, et autres
Publié: (2025)

Discrete Probabilistic Inference as Control in Multi-path Environments
par: Deleu, Tristan, et autres
Publié: (2024)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
par: Scimeca, Luca, et autres
Publié: (2023)

Discrete, compositional, and symbolic representations through attractor dynamics
par: Nam, Andrew, et autres
Publié: (2023)

Torsional-GFN: a conditional conformation generator for small molecules
par: Volokhova, Alexandra, et autres
Publié: (2025)

Expected flow networks in stochastic environments and two-player zero-sum games
par: Jiralerspong, Marco, et autres
Publié: (2023)

Local Search GFlowNets
par: Kim, Minsu, et autres
Publié: (2023)

A Comedy of Estimators: On KL Regularization in RL Training of LLMs
par: Shah, Vedant, et autres
Publié: (2025)

Ant Colony Sampling with GFlowNets for Combinatorial Optimization
par: Kim, Minsu, et autres
Publié: (2024)

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
par: Venkatraman, Siddarth, et autres
Publié: (2025)

Learning diverse attacks on large language models for robust red-teaming and safety tuning
par: Lee, Seanie, et autres
Publié: (2024)

Learning Decision Trees as Amortized Structure Inference
par: Mahfoud, Mohammed, et autres
Publié: (2025)

Amortizing intractable inference in large language models
par: Hu, Edward J., et autres
Publié: (2023)

Generative Recursive Reasoning
par: Baek, Junyeob, et autres
Publié: (2026)

Active Attacks: Red-teaming LLMs via Adaptive Environments
par: Yun, Taeyoung, et autres
Publié: (2025)

Improved Off-policy Reinforcement Learning in Biological Sequence Design
par: Kim, Hyeonah, et autres
Publié: (2024)

Action abstractions for amortized sampling
par: Boussif, Oussama, et autres
Publié: (2024)

PhyloGFN: Phylogenetic inference with generative flow networks
par: Zhou, Mingyang, et autres
Publié: (2023)

Can a Bayesian Oracle Prevent Harm from an Agent?
par: Bengio, Yoshua, et autres
Publié: (2024)

Simulation-free Schrödinger bridges via score and flow matching
par: Tong, Alexander, et autres
Publié: (2023)

Learning to Scale Logits for Temperature-Conditional GFlowNets
par: Kim, Minsu, et autres
Publié: (2023)

Offline Model-Based Optimization: Comprehensive Review
par: Kim, Minsu, et autres
Publié: (2025)

Baking Symmetry into GFlowNets
par: Ma, George, et autres
Publié: (2024)

Hi-fi functional priors by learning activations
par: Sendera, Marcin, et autres
Publié: (2025)

Revisiting the Equivalence of Bayesian Neural Networks and Gaussian Processes: On the Importance of Learning Activations
par: Sendera, Marcin, et autres
Publié: (2024)

Self-Evolving Curriculum for LLM Reasoning
par: Chen, Xiaoyin, et autres
Publié: (2025)

Delta-AI: Local objectives for amortized inference in sparse graphical models
par: Falet, Jean-Pierre, et autres
Publié: (2023)