Hugging Face releases HOPE, a MoE expert pruning method
What happened
On 9 November 2026, Hugging Face proposed HOPE (Higher-Order Pruning of Experts) on its official blog, a second-order MoE expert pruning method that accounts for pairwise interactions between experts. According to the report, at a 50% pruning rate HOPE achieved the best average rank among all methods and improved by up to 6.1% over the next-best pruning method on agentic coding tasks. The work is currently at the method-release stage, with no independent reproduction or third-party evaluation reported yet.
Written by AI from the reports · updated 6 d ago
Timeline
Follow the reports to see the event from each side.
- Hugging Face BlogYour Experts Have Partners. There's HOPE for Keeping Them Together
Higher-Order Pruning of Experts in Mixture-of-Experts Language Models Introduction Mixture-of-Experts (MoE) models have enabled state-of-the-art LLMs to be scaled to hundreds of billions of parameters, but they come with a fundamental and costly caveat: every expert MLP must occupy memory at inference time, even though the vast majority are idle for any given token.
Heat of this event
Current heat 3·Peak in the comparable range 9(Nov 10 00:00)·Change over 24 hours in the comparable range -51%
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.