Imagen de Portada

A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Olausson, Theo X., Jazbec, Metod, Wang, Xi, Solar-Lezama, Armando, Naesseth, Christian A., Mandt, Stephan, Nalisnick, Eric
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Monitoring Risks in Test-Time Adaptation
por: Schirmer, Mona, et al.
Publicado: (2025)

Early-Exit Neural Networks with Nested Prediction Sets
por: Jazbec, Metod, et al.
Publicado: (2023)

Generative Uncertainty in Diffusion Models
por: Jazbec, Metod, et al.
Publicado: (2025)

Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning
por: Bui, Ha Manh, et al.
Publicado: (2026)

Fast yet Safe: Early-Exiting with Risk Control
por: Jazbec, Metod, et al.
Publicado: (2024)

Learning Unmasking Policies for Diffusion Language Models
por: Jazbec, Metod, et al.
Publicado: (2025)

Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
por: Wynn, Andrea, et al.
Publicado: (2025)

Is Self-Repair a Silver Bullet for Code Generation?
por: Olausson, Theo X., et al.
Publicado: (2023)

The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?
por: Gu, Alex, et al.
Publicado: (2024)

LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
por: Olausson, Theo X., et al.
Publicado: (2023)

Dynamic Mixture-of-Experts for Visual Autoregressive Model
por: Vincenti, Jort, et al.
Publicado: (2025)

Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning
por: Gupta, Kavi, et al.
Publicado: (2025)

On Continuous Monitoring of Risk Violations under Unknown Shift
por: Timans, Alexander, et al.
Publicado: (2025)

Max-Rank: Efficient Multiple Testing for Conformal Prediction
por: Timans, Alexander, et al.
Publicado: (2023)

Joint Model and Data Sparsification via the Marginal Likelihood
por: Timans, Alexander, et al.
Publicado: (2026)

Towards Fast Stochastic Sampling in Diffusion Generative Models
por: Pandey, Kushagra, et al.
Publicado: (2024)

Power Term Polynomial Algebra for Boolean Logic
por: Sansone, Emanuele, et al.
Publicado: (2026)

Lossy Image Compression with Conditional Diffusion Models
por: Yang, Ruihan, et al.
Publicado: (2022)

EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
por: Li, Zhening, et al.
Publicado: (2025)

Are vision language models robust to uncertain inputs?
por: Wang, Xi, et al.
Publicado: (2025)

Dynamic Vocabulary Pruning in Early-Exit LLMs
por: Vincenti, Jort, et al.
Publicado: (2024)

Advances in Diffusion-Based Generative Compression
por: Yang, Yibo, et al.
Publicado: (2026)

E-Valuating Classifier Two-Sample Tests
por: Pandeva, Teodora, et al.
Publicado: (2022)

When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
por: Li, Zhening, et al.
Publicado: (2024)

SPARLING: Learning Latent Representations with Extremely Sparse Activations
por: Gupta, Kavi, et al.
Publicado: (2023)

Progressive Compression with Universally Quantized Diffusion Models
por: Yang, Yibo, et al.
Publicado: (2024)

Neural Diffusion Models
por: Bartosh, Grigory, et al.
Publicado: (2023)

Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
por: Bartosh, Grigory, et al.
Publicado: (2024)

Amortizing Maximum Inner Product Search with Learned Support Functions
por: Olausson, Theo X., et al.
Publicado: (2026)

DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach
por: Fernández, Daniel Gallo, et al.
Publicado: (2024)

Improving Handshape Representations for Sign Language Processing: A Graph Neural Network Approach
por: Carbo, Alessa, et al.
Publicado: (2025)

MathDSL: A Domain-Specific Language for Concise Mathematical Solutions Via Program Synthesis
por: Anupam, Sagnik, et al.
Publicado: (2024)

The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise
por: Wang, Xi, et al.
Publicado: (2026)

An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
por: Sun, Mingzhong, et al.
Publicado: (2026)

Practical and Asymptotically Exact Conditional Sampling in Diffusion Models
por: Wu, Luhuan, et al.
Publicado: (2023)

MeMo: Meaningful, Modular Controllers via Noise Injection
por: Tjandrasuwita, Megan, et al.
Publicado: (2024)

Towards Latent Diffusion Suitable For Text
por: Midavaine, Nesta, et al.
Publicado: (2026)

VLMaterial: Procedural Material Generation with Large Vision-Language Models
por: Li, Beichen, et al.
Publicado: (2025)

Active Learning for Multilingual Fingerspelling Corpora
por: Wang, Shuai, et al.
Publicado: (2023)

Neural NeRF Compression
por: Pham, Tuan, et al.
Publicado: (2024)