MCGI adapts graph-based vector search to data manifolds via local intrinsic dimensionality to improve approximation quality and stability at billion scale.
Approximate nearest neighbors: towards removing the curse of dimensionality
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
JoyAI-LLM Flash delivers a 48B MoE LLM with 2.7B active parameters per token via FiberPO RL and dense multi-token prediction, released with checkpoints on Hugging Face.
citing papers explorer
-
MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search
MCGI adapts graph-based vector search to data manifolds via local intrinsic dimensionality to improve approximation quality and stability at billion scale.
-
JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
JoyAI-LLM Flash delivers a 48B MoE LLM with 2.7B active parameters per token via FiberPO RL and dense multi-token prediction, released with checkpoints on Hugging Face.