#Diffusion Models
Latest news articles tagged with "Diffusion Models". Follow the timeline of events, related topics, and entities.
Articles (6)
-
πΊπΈ Calibrated Test-Time Guidance for Bayesian Inference
[USA]
arXiv:2602.22428v1 Announce Type: cross Abstract: Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing appro...
Related: #Machine Learning, #Bayesian Inference -
πΊπΈ TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion
[USA]
arXiv:2602.22586v1 Announce Type: cross Abstract: Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy. Howeve...
Related: #Machine Learning, #Data Generation -
πΊπΈ Diffusion Modulation via Environment Mechanism Modeling for Planning
[USA]
arXiv:2602.20422v1 Announce Type: new Abstract: Diffusion models have shown promising capabilities in trajectory generation for planning in offline reinforcement learning (RL). However, conventional ...
Related: #Artificial Intelligence, #Machine Learning, #Reinforcement Learning -
πΊπΈ Sink-Aware Pruning for Diffusion Language Models
[USA]
arXiv:2602.17664v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics larg...
Related: #Machine Learning, #Natural Language Processing, #Model Compression, #Inference Efficiency -
πΊπΈ Token-Based Audio Inpainting via Discrete Diffusion
[USA]
arXiv:2507.08333v4 Announce Type: replace-cross Abstract: Audio inpainting seeks to restore missing segments in degraded recordings. Previous diffusion-based methods exhibit impaired performance when...
Related: #Audio Restoration, #Tokenization, #Generative Modeling, #Machine Learning -
πΊπΈ AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
[USA]
arXiv:2602.06771v2 Announce Type: replace-cross Abstract: Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. R...
Related: #AI Safety, #Concept Erasure, #Robustness