Cover Image

Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Autospeculation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Hengyuan, Das, Aniket, Sadigh, Dorsa, Anari, Nima
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Batch Active Learning of Reward Functions from Human Preferences
by: Bıyık, Erdem, et al.
Published: (2024)

Imitation Bootstrapped Reinforcement Learning
by: Hu, Hengyuan, et al.
Published: (2023)

Parallel Sampling via Autospeculation
by: Anari, Nima, et al.
Published: (2025)

Parallel Sampling via Counting
by: Anari, Nima, et al.
Published: (2024)

What's the Move? Hybrid Imitation Learning via Salient Points
by: Sundaresan, Priya, et al.
Published: (2024)

EXPO: Stable Reinforcement Learning with Expressive Policies
by: Dong, Perry, et al.
Published: (2025)

FASTER: Value-Guided Sampling for Fast RL
by: Dong, Perry, et al.
Published: (2026)

Efficient Data Collection for Robotic Manipulation via Compositional Generalization
by: Gao, Jensen, et al.
Published: (2024)

Value Flows
by: Dong, Perry, et al.
Published: (2025)

Policy Learning with a Language Bottleneck
by: Srivastava, Megha, et al.
Published: (2024)

TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
by: Dong, Perry, et al.
Published: (2026)

Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning
by: Ren, Juntao, et al.
Published: (2025)

The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler
by: Akhtar, Md Sahil, et al.
Published: (2026)

Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning
by: Sarkar, Bidipta, et al.
Published: (2025)

Adaptive-lambda Subtracted Importance Sampled Scores in Machine Unlearning for DDPMs and VAEs
by: Dini, MohammadParsa, et al.
Published: (2025)

Polychromic Objectives for Reinforcement Learning
by: Hamid, Jubayer Ibn, et al.
Published: (2025)

A Taxonomy for Evaluating Generalist Robot Manipulation Policies
by: Gao, Jensen, et al.
Published: (2025)

Contrastive Preference Learning: Learning from Human Feedback without RL
by: Hejna, Joey, et al.
Published: (2023)

ProVox: Personalization and Proactive Planning for Situated Human-Robot Collaboration
by: Grannen, Jennifer, et al.
Published: (2025)

Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections
by: Zha, Lihan, et al.
Published: (2023)

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
by: Reizinger, Patrik, et al.
Published: (2024)

The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind
by: DeLeeuw, Caleb, et al.
Published: (2025)

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
by: Karamcheti, Siddharth, et al.
Published: (2024)

Vocal Sandbox: Continual Learning and Adaptation for Situated Human-Robot Collaboration
by: Grannen, Jennifer, et al.
Published: (2024)

Exchangeability in Neural Network and its Application to Dynamic Pruning
by: Pu, et al.
Published: (2025)

Toward Grounded Commonsense Reasoning
by: Kwon, Minae, et al.
Published: (2023)

ML-Driven Approaches to Combat Medicare Fraud: Advances in Class Imbalance Solutions, Feature Engineering, Adaptive Learning, and Business Impact
by: Farahmandazad, Dorsa, et al.
Published: (2025)

ControlEchoSynth: Boosting Ejection Fraction Estimation Models via Controlled Video Diffusion
by: Kondori, Nima, et al.
Published: (2025)

Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism
by: Wang, Kunyun, et al.
Published: (2025)

Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
by: Selvam, Nikil Roashan, et al.
Published: (2024)

Your Absorbing Discrete Diffusion Secretly Models the Bayesian Posterior
by: Doyle, Cooper
Published: (2025)

Non-Exchangeable Conformal Language Generation with Nearest Neighbors
by: Ulmer, Dennis, et al.
Published: (2024)

Explore until Confident: Efficient Exploration for Embodied Question Answering
by: Ren, Allen Z., et al.
Published: (2024)

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
by: Van Nguyen, Chien, et al.
Published: (2026)

From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
by: Fu, Hengyu, et al.
Published: (2025)

GRPO is Secretly a Process Reward Model
by: Sullivan, Michael, et al.
Published: (2025)

Model Parallelism With Subnetwork Data Parallelism
by: Singh, Vaibhav, et al.
Published: (2025)

Superhuman AI for Stratego Using Self-Play Reinforcement Learning and Test-Time Search
by: Sokota, Samuel, et al.
Published: (2025)

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
by: Li, Chengshu, et al.
Published: (2023)

VLAD-Grasp: Zero-shot Grasp Detection via Vision-Language Models
by: Kulshrestha, Manav, et al.
Published: (2025)