/AI9h ago

IMLE Method Trains One-Step Generative Models On Mixed-Quality Trajectories

--0--
Comments
Ke Li 馃崄#1952
Original post
Ke Li 馃崄@KL_Div#1952inAI

Vanilla IMLE treats all trajectories in the training dataset equally despite their varying quality. Since our goal is to generate trajectories of high quality, we propose reward-weighted IMLE, which emphasizes trajectories with high reward more than those with low reward.

(4/7)

Ke Li 馃崄@KL_Div

Our method uses Implicit Maximum Likelihood Estimation (IMLE) to train a one-step generative model on trajectories of varying quality. IMLE works by having each trajectory in the training dataset pull the closest generated trajectory towards it.

(3/7)

10:19 PM 路 Jun 1, 2026 路 404 Views
Sentiment
Sentiment unavailable for this story.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS360LIKES1REPLIES1
Ke Li 馃崄@KL_Div

We demonstrate on offline reinforcement learning tasks that our IMLE model runs in real time on both the CPU and GPU and achieves an order-of-magnitude speedup relative to diffusion models.

(5/7)

Ke Li 馃崄@KL_Div

Vanilla IMLE treats all trajectories in the training dataset equally despite their varying quality. Since our goal is to generate trajectories of high quality, we propose reward-weighted IMLE, which emphasizes trajectories with high reward more than those with low reward.

(4/7)

9hViews 360Likes 1Bookmarks 0