Astrmira幻梦星芒A wonderful star / ASTRMIRA
Seek the unknown. Build beyond the horizon.
From first principles to real-world intelligence.
We study foundational questions in data, computation, and intelligence,
then turn rigorous ideas into systems people can use.
Our research
We frame questions, build methods, and test ideas through derivation and experiment, letting each finding become the beginning of the next inquiry.
Research, in the open
From foundational problems to new findings across different fields, this is where we record our papers and research progress.
Research at a glance
When Does Low-Bit Quantization Preserve the Decisions of Vector Search?
Places quantization error inside the ranking and graph-pruning decisions that vector search actually makes, relating reliability to comparison margins, correlated residuals, and execution traces.
Explore this researchResearch at a glance
Contextual Utility of Quantization Moves in Extreme Low-Bit LLMs
Studies the real utility of a discrete move in extreme low-bit LLMs by evaluating the move along its own path and combining decisions in an evolving model state.
Explore this researchResearch at a glance
Covariance Structure and Coordinate Heterogeneity Govern Binary Quantization of Contrastive Embeddings
Explains low-bit ranking behavior through covariance structure and coordinate heterogeneity, including why an extra magnitude bit and random rotation help different representations in different ways.
Explore this researchResearch at a glance
QuIVer: Rethinking ANN Graph Topology via Training-Free Binary Quantization
Builds, prunes, and navigates an ANN graph in a training-free two-bit space, reading full vectors only for final reranking and exposing the data regimes where compact topology works.
Explore this researchOur practice
Foundational research expands what is possible. Building systems lets real problems answer back.
Ideas, made tangible
From data foundations and intelligent companions to a workspace for working with agents.
An AI-native embedded database in Rust that unifies vectors, property graphs, and documents for agent memory and local knowledge.
An open-source runtime for AI companions, connecting long-term memory, context, and tools while powering persistent conversation and desktop interaction.
An open-source workspace for AI agents. Models, tools, files, and projects meet in one place, with a native Rust runtime and clients for desktop, web, and mobile.
A note on our name
Stars change. Curiosity continues.
Astr evokes the distant sky; Mira is a real variable star; Mirage is an imagined horizon still to be reached. These images come together in our Chinese name, 幻梦星芒.
Mira changes in brightness and leaves a long ultraviolet tail. It reminds us to preserve imagination around the unknown and leave a trail that others can continue.
Name inspiration · NASA ↗Let’s ask the next question
Databases and intelligent systems · Research collaboration · University partnerships
Begin a meaningful collaboration with one real problem.