Intelligence & Reliability
Latent-space computation, causal credit assignment, feature detection, and runtime assurance for embodied AI.
RESEARCH · BUILD · CREATE
LancerSiyao Lan
Beijing · China University of Geosciences, Beijing
Undergraduate in Computer Science and Technology · Class entering in 2025
Researching intelligence. Building tools. Creating stories.
I study representation, reasoning, and reliability in AI. My recent work focuses on automated research, search, and continual improvement.
Beyond research, I write long-form fiction, develop learning materials, and stay curious about music, history, and philosophy.
RESEARCH × CREATIVE WORK
Between intelligence and imagination.
Asking questions. Building tools. Imagining worlds worth entering.
Explore my workResearch interests
Representation & Reasoning
Exploring latent computation, causal credit, and the limits of model learning.
Research Automation
Connecting question discovery, search, structural reorganization, and experimental validation.
Research, as a process of understanding.
Connecting questions, evidence, search, and experiments.
Selected research
View all
Attractor-JEPA
Causal attractors in latent computation
Studying local transitions, causal dependencies, and state recovery in latent representations to explore compositional long-horizon computation.
Explore research
Sentinel-EVC
Final-action validation and verifiable execution
Between policy and controller: final-action validation, single-use authorization, and independently verifiable evidence.
Explore research
Auto Research · Sustained Exploration
Automated research and recursive improvement
Connecting questions, literature, search, refutation, and frozen experiments so that sustained exploration accumulates evidence future work can build on.
Explore researchTools in development
View all
EulerForge / Archimedes
Developing a research idea into a plan with traceable sources, strong controls, behavioral evidence, and replay records.
Explore project
LSMFC
Connecting research facts, arguments, paragraphs, and figures so that manuscripts and scientific visuals can be cross-checked.
Explore projectWriting & Reflections
View all
WRITING & REFLECTION
Another way to understand the world.
Research notes, long-form stories, and reading give questions different forms of expression.
Why does computation in hidden states need a causal order?
The ability to execute local operations does not imply the ability to discover a long-horizon program independently.
Read the essayLet every exploration leave evidence to build on
A good research workflow should also preserve why an idea failed.
Read the essayEducation & Experience
Full backgroundCUGB
China University of Geosciences, Beijing
Undergraduate studies in Computer Science · Entered 2025
Studying AI, while continuing to learn through literature, music, and expression.
LET’S CONNECT
Let's explore questions worth pursuing.
I welcome conversations about AI, automated research, literature, and sharing knowledge.
Get in touch