Public KG record
HOPE
Recorded overview
A second-order pruning method for MoE that minimizes a quadratic surrogate error
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: gains of up to +6.1% on agentic coding tasks over the next-best pruning method at 50% pruning
- Performance: +6.1% on agentic coding tasks
- Performance: +6.1% gains on agentic coding tasks over the next-best pruning method
- Performance: gains of up to +6.1% on agentic coding tasks over the next-best pruning method
Evidence coverage
The KG currently records 8 known information dimensions and has 11 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Mixture-of-Experts — applied to
- Mixture-of-Experts — improves
- expert pruning — is a
- First-order pruning — outperforms