APIUp to 25% cheaper than official pricesTry the API →
Hermes
APIModelsCases
Back to News
paperReasoningPost Training

TU Delft's FMER Trains Robot Policies 7x Faster on Sparse Tasks

FMER swaps diffusion for flow matching in online RL, delivering tractable entropy, mirror descent updates, and up to 7x faster training.

TU Delft's FMER Trains Robot Policies 7x Faster on Sparse Tasks
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read

FMER swaps diffusion for flow matching in online RL, delivering tractable entropy, mirror descent updates, and up to 7x faster training.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

Perplexity and NVIDIA's JOLT Beats GRPO Using 6.5x Fewer Training Tokens
Perplexity · news

Perplexity and NVIDIA's JOLT Beats GRPO Using 6.5x Fewer Training Tokens

LoopRPT Teaches AI to Think Smarter With Every Recurrent Pass
AlphaSignal · paper

LoopRPT Teaches AI to Think Smarter With Every Recurrent Pass

Shanghai AI Lab's RePro Cuts Reasoning Tokens 47% While Boosting Math Scores
AlphaSignal · paper

Shanghai AI Lab's RePro Cuts Reasoning Tokens 47% While Boosting Math Scores