long-context
18 posts tagged long-context.
- FP4 KV Cache Done Right: What BitDecoding-FP4 Changes for Long-Context Serving
- Zyphra's tree-structured attention aims at million-token-plus context
- LongZero trains long-context reasoning without outside documents
- LatComm makes long context reusable across models
- MiniMax M3.1 Flash puts Space Bunny back under test
- LeapQuant targets the hidden inference cost in linear attention
- NoPE attention is not position-blind if local layers carry recency
- KV-streams make long-agent training cheaper by not throwing memory away
- Long-context models can miss the answer sitting behind nearby noise
- The Harness Matters as Much as the Model in Coding Agents
- Declassified Daily Briefs Are a Better AI Test Than Another Toy Corpus
- ConvMem Turns Long-Context Reasoning Into a Tree Instead of a Chain
- Declarative attention lets models skip the context they do not need
- Sliding Window Attention vs Linear Attention: What the Baseline Test Actually Shows
- CorporateBench and the Gap Between Demo Scale and Company Scale
- Indexing by Entities, Not Chunks: What EnSI-RAG Changes About Long-Document QA
- When the Teacher and the Verifier Disagree: Fixing On-Policy Distillation for Long Context
- Long-context KV caches are getting selective