Heinsen Routing + RoBERTa Large

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Sentiment AnalysisonSST-5 Fine-grained classification
Accuracy· 2022-11-20
59.8
best: 62.27 (Llama-3.3-70B + CAPO)
SOTA
An Algorithm for Routing Vectors in Sequences arXiv:2211.11754
Sentiment AnalysisonIMDb
Accuracy· 2022-11-20
96.2
best: 96.68 (RoBERTa-large with LlamBERT)
An Algorithm for Routing Vectors in Sequences arXiv:2211.11754