Knowledge Graph
Graph explorer
Search resolved entities, walk their edges, and read the sentence behind every one.
Entities25 of 207,987
- large language modeltechnology1,043 mentions
- robotic manipulationmarket824 mentions
- artificial intelligencetechnology739 mentions
- reinforcement learningtechnology491 mentions
- density-functional theorytechnology386 mentions
- Transformertechnology371 mentions
- agentic AItechnology353 mentions
- vision-language-action modeltechnology350 mentions
- U.S. Food and Drug Administrationorganization320 mentions
- Vision-Language Modeltechnology318 mentions
- Microsoftorganization291 mentions
- Googleorganization276 mentions
- NVIDIAorganization264 mentions
- Model Context Protocoltechnology232 mentions
- machine learningtechnology204 mentions
- MarketsandMarketsorganization199 mentions
- Claudeproduct192 mentions
- AI agenttechnology188 mentions
- ChatGPTproduct178 mentions
- Anthropicorganization177 mentions
- integrated sensing and communicationtechnology175 mentions
- Amazon Web Services, Inc.organization174 mentions
- OpenAIorganization172 mentions
- diffusion modeltechnology169 mentions
- IBMorganization163 mentions
Entity
LoRA-CRAFT
technology5 mentionslast seen Nov 11, 2026
Parameter-efficient fine-tuning method using Tucker tensor decomposition on cross-layer pre-trained attention weights.
Relationships 16
- LoRA-CRAFTdepends onskill representation92% confidence1 source
- LoRA-CRAFTdepends onfederated learning90% confidence1 source
- LoRA-CRAFTdepends onTucker tensor decomposition90% confidence1 source
- LoRA-CRAFTdepends onlarge language model90% confidence1 source
- LoRA-CRAFTdepends oncounterfactual training90% confidence1 source
- LoRA-CRAFTapplies torobotic manipulation88% confidence1 source
- LACE-CRAFTcomposed ofLoRA-CRAFT85% confidence1 source
- LoRA-CRAFTdepends onparameter-efficient fine-tuning85% confidence1 source
- LoRA-CRAFTdepends onHigher-Order SVD85% confidence1 source
- LoRA-CRAFTdepends onlayer-wise adaptation85% confidence1 source
- LoRA-CRAFTdepends onKullback-Leibler penalty85% confidence1 source
- LoRA-CRAFTapplies tocontinual learning80% confidence1 source
- LoRA-CRAFTcompetes withLoRA80% confidence1 source
- LoRA-CRAFTcompetes withTucker decomposition with shared factor matrices75% confidence1 source
- LoRA-CRAFTsupersedesLoRA75% confidence1 source
- LoRA-CRAFTapplies tonatural language understanding70% confidence1 source
Sources
Select a relationship to read the sources behind it.