Stanford open-sources Memorilla, a latent memory module for frozen LLMs
A 194M-parameter module gives a frozen Qwen3-8B 16 tokens and beat full context on FactKG with 108x fewer document tokens.
48
AI model
Qwen3-Embedding-4B
- Mentions · 7d1
- Mentions · 30d2
- All mentions2
- First seenOct 23, 2026
- Last mentioned3h ago
Timeline
2 articles · newest firstYalda Embedding released as a 595.8M Persian retrieval model
Adapted from Qwen3-Embedding-0.6B on more than one million pairs, it scores 0.5488 macro-average on eight FaMTEB tasks.
48
Appears with
- Qwen3-4Bai model · 1
- Stanford Universityorganization · 1
- Qwen3-Embedding-0.6Bai model · 1
- F2LLM-v2-0.6Bai model · 1
- Yalda Embeddingai model · 1
- SNAPorganization · 1
- Memorillaai model · 1
- Qwen3-8Bai model · 1
- F2LLM-v2-8Bai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.