activity
20242026
collaborators

7 papers

cs.CV2026

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

David McAllister, Miika Aittala, Tero Karras +4

Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly impro…

cs.RO2026

Scalable Behavior Cloning with Open Data, Training, and Evaluation

Arthur Allshire, Himanshu Gaurav Singh, Ritvik Singh +15

We introduce ABC, a fully open-source stack for manipulation with behavior cloning. At its core is ABC-130K: the largest open-source teleoperation dataset to date, featuring 3,500…

cs.CV2026

LoV3D: Grounding Cognitive Prognosis Reasoning in Longitudinal 3D Brain MRI via Regional Volume Assessments

Zhaoyang Jiang, Zhizhong Fu, David McAllister +2

Longitudinal brain MRI is essential for characterizing the progression of neurological diseases such as Alzheimer's disease assessment. However, current deep-learning tools fragmen…

cs.RO2025

Visual Imitation Enables Contextual Humanoid Control

Arthur Allshire, Hongsuk Choi, Junyi Zhang +7

How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably, the simplest way is to just show them-casually capture a human…

cs.LG2025

Flow Matching Policy Gradients

David McAllister, Songwei Ge, Brent Yi +5

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization…

cs.CV2025

Decentralized Diffusion Models

David McAllister, Matthew Tancik, Jiaming Song +1

Large-scale AI model training divides work across thousands of GPUs, then synchronizes gradients across them at each step. This incurs a significant network burden that only centra…