Cover Image

Diffusion Beats Autoregressive in Data-Constrained Settings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Prabhudesai, Mihir, Wu, Mengning, Zadeh, Amir, Fragkiadaki, Katerina, Pathak, Deepak
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Aligning Text-to-Image Diffusion Models with Reward Backpropagation
by: Prabhudesai, Mihir, et al.
Published: (2023)

Unified Multimodal Discrete Diffusion
by: Swerdlow, Alexander, et al.
Published: (2025)

Video Diffusion Alignment via Reward Gradients
by: Prabhudesai, Mihir, et al.
Published: (2024)

Iterative Refinement Improves Compositional Image Generation
by: Jaiswal, Shantanu, et al.
Published: (2026)

Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
by: Prabhudesai, Mihir, et al.
Published: (2026)

3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
by: Ke, Tsung-Wei, et al.
Published: (2024)

RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
by: Wang, Yufei, et al.
Published: (2023)

Self-Questioning Language Models
by: Chen, Lili, et al.
Published: (2025)

Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
by: Gkanatsios, Nikolaos, et al.
Published: (2023)

ODIN: A Single Model for 2D and 3D Segmentation
by: Jain, Ayush, et al.
Published: (2024)

RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation
by: Jangir, Yash, et al.
Published: (2025)

Neural MP: A Generalist Neural Motion Planner
by: Dalal, Murtaza, et al.
Published: (2024)

SAPG: Split and Aggregate Policy Gradients
by: Singla, Jayesh, et al.
Published: (2024)

IFG: Internet-Scale Guidance for Functional Grasping Generation
by: Liu, Ray Muxin, et al.
Published: (2025)

FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning
by: Liu, Jason Jingzhou, et al.
Published: (2025)

TransForSeg: A Multitask Stereo ViT for Joint Stereo Segmentation and 3D Force Estimation in Catheterization
by: Fekri, Pedram, et al.
Published: (2025)

Maximizing Confidence Alone Improves Reasoning
by: Prabhudesai, Mihir, et al.
Published: (2025)

Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation
by: Kuang, Yuxuan, et al.
Published: (2026)

ViPRA: Video Prediction for Robot Actions
by: Routray, Sandeep, et al.
Published: (2025)

Adaptive Mobile Manipulation for Articulated Objects In the Open World
by: Xiong, Haoyu, et al.
Published: (2024)

Bimanual Dexterity for Complex Tasks
by: Shaw, Kenneth, et al.
Published: (2024)

DriveGPT: Scaling Autoregressive Behavior Models for Driving
by: Huang, Xin, et al.
Published: (2024)

Continuously Improving Mobile Manipulation with Autonomous Real-World RL
by: Mendonca, Russell, et al.
Published: (2024)

SPIN: Simultaneous Perception, Interaction and Navigation
by: Uppal, Shagun, et al.
Published: (2024)

CRAFT: Video Diffusion for Bimanual Robot Data Generation
by: Chen, Jason, et al.
Published: (2026)

D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation
by: Liu, I-Chun Arthur, et al.
Published: (2025)

DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies
by: Tao, Tony, et al.
Published: (2025)

Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments
by: Yang, Jiahui, et al.
Published: (2025)

Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification
by: Mohammadi, Marzieh, et al.
Published: (2024)

Robustness Is a Function, Not a Number: A Factorized Comprehensive Study of OOD Robustness in Vision-Based Driving
by: Mallak, Amir, et al.
Published: (2026)

Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encoding
by: Mohammadi, Marzieh, et al.
Published: (2025)

Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet
by: Saeid, Mohammad, et al.
Published: (2025)

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
by: Liu, Songming, et al.
Published: (2024)

Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning
by: Vosylius, Vitalis, et al.
Published: (2024)

Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning
by: Mohan, Rohit, et al.
Published: (2025)

The Ingredients for Robotic Diffusion Transformers
by: Dasari, Sudeep, et al.
Published: (2024)

Seeking Physics in Diffusion Noise
by: Tang, Chujun, et al.
Published: (2026)

Fractional Diffusion Bridge Models
by: Nobis, Gabriel, et al.
Published: (2025)

RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration
by: Alama, Omar, et al.
Published: (2025)

RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation
by: Kim, Seungchan, et al.
Published: (2025)