AgentDish directory
long-context
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
#380
↓ -3
KRLabsOrg/verbatim-rag-modern-bert-v2
A 150M ModernBERT-based token classification model that extracts verbatim evidence spans for RAG and related pipelines, reducing the need for an LLM call to highlight answers. |
AI Model / Text Extraction / RAG | 88 | ↓ -3 | 127 days ago | Details |
#2433
→ 0
Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute
A Hugging Face paper page describing a memory layer for LLMs that stores KV state to encrypted NVMe and reloads it later without recomputing, with results from 50M-token experiments on Gemma models. |
Research / AI Memory / Long-Context | 71 | → 0 | 7 days ago | Details |