Knowledge Graph
Graph explorer
Search resolved entities, walk their edges, and read the sentence behind every one.
Entities25 of 207,987
- large language modeltechnology1,048 mentions
- robotic manipulationmarket834 mentions
- artificial intelligencetechnology739 mentions
- reinforcement learningtechnology492 mentions
- density-functional theorytechnology386 mentions
- Transformertechnology372 mentions
- vision-language-action modeltechnology355 mentions
- agentic AItechnology353 mentions
- Vision-Language Modeltechnology321 mentions
- U.S. Food and Drug Administrationorganization320 mentions
- Microsoftorganization291 mentions
- Googleorganization277 mentions
- NVIDIAorganization265 mentions
- Model Context Protocoltechnology232 mentions
- machine learningtechnology204 mentions
- MarketsandMarketsorganization199 mentions
- Claudeproduct192 mentions
- AI agenttechnology188 mentions
- ChatGPTproduct178 mentions
- Anthropicorganization177 mentions
- integrated sensing and communicationtechnology176 mentions
- Amazon Web Services, Inc.organization174 mentions
- OpenAIorganization172 mentions
- diffusion modeltechnology170 mentions
- IBMorganization163 mentions
Entity
sparse attention
technology10 mentionslast seen Nov 13, 2026
An attention mechanism optimization technique integrated into the DeepSeek-V4-Flash inference system.
Relationships 14
- sparse attentiondepends oncompact kernel90% confidence1 source
- SPLASHdepends onsparse attention90% confidence1 source
- learned gateapplies tosparse attention88% confidence1 source
- Transformerimplementssparse attention88% confidence1 source
- TempoNetcomposed ofsparse attention88% confidence1 source
- DeepSeek-V4-Flashimplementssparse attention85% confidence1 source
- random gateapplies tosparse attention85% confidence1 source
- hard top-k maskingimplementssparse attention82% confidence1 source
- hierarchical indexed sparse attentionimplementssparse attention82% confidence1 source
- sparse attentiondepends onMarkov chain82% confidence1 source
- Pre-hoc Sparsitycompetes withsparse attention80% confidence1 source
- sparse attentioncomposed ofattention head specialization80% confidence1 source
- sparse attentiondepends onHigh-Bandwidth Flash80% confidence1 source
- sparse attentioncompetes withadaptive two-stage attention70% confidence1 source
Relationship
sparse attentioncomposed ofattention head specialization
80% confidence1 supporting mentions
Either name opens that entity’s relationships.
Sources 1