Foyer study: logistic regression beats LLMs on inbox routing
On about 200 labels, logistic regression led every field, while the most accurate system ignored 18% of emails needing action.
34
AI model
Gemma 4 31B
- Mentions · 7d0
- Mentions · 30d1
- All mentions4
- First seenSep 11, 2026
- Last mentioned19d ago
Timeline
4 articles · newest firstReal Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute
Researchers store encrypted KV cache on NVMe so Gemma 4 recalls facts across 50 million tokens without recompute.
58
Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost
Galahad caches byte-exact KV state so repeated LLM document reading becomes a one-time cost.
52
Cohere Releases North Small Translate: A 218B MoE Translation Model That Scores 83.6 on WMT26 Across 50 Languages
Cohere released North Small Translate, an open-weight 218B MoE (25B active) translation model scoring 83.6 on WMT26 across 50 languages.
55
Appears with
- vLLMproduct · 2
- Cohere Labsorganization · 1
- Coherevendor · 1
- NVIDIAvendor · 1
- Qwen 3.5 397B A17Bai model · 1
- RWSorganization · 1
- GPT-5.6-Solai model · 1
- Command A Translateai model · 1
- North Small Translateproduct · 1
- Cohereorganization · 1
- Chat V2 APIproduct · 1
- galahad-kvproduct · 1
- Gemma 4 12Bai model · 1
- RAGFlowproduct · 1
- North Small Translateai model · 1
- Foyerproduct · 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.