Portrait of Siyao Lan

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.

Original concept artwork for intelligence and imagination

RESEARCH × CREATIVE WORK

Between intelligence and imagination.

Asking questions. Building tools. Imagining worlds worth entering.

Explore my work

Research interests

01

Intelligence & Reliability

Latent-space computation, causal credit assignment, feature detection, and runtime assurance for embodied AI.

02

Representation & Reasoning

Exploring latent computation, causal credit, and the limits of model learning.

03

Research Automation

Connecting question discovery, search, structural reorganization, and experimental validation.

AN OPENING

A small opening. A wider world.

Research and creation begin with a willingness to look again.

An opening · A 15-second film

Project Bedrock: mathematical foundations, research and open dialogue.

Learning & practice · Programme launch

Introducing Project Bedrock

A three-month initiative to deepen our mathematical understanding of AI through close reading, first-hand derivation, open-source practice and community dialogue. Build understanding through practice. Let real questions lead the next step.

Read the announcement →
InkTide editorial artwork

AutoResearch · Research update

Meet InkTide

InkTide brings inspected paper lessons, author evidence, original prose and figure design into a connected writing workflow, with a separate review of the result.

Read the update
Ariadne research thread

AutoResearch · Research update

Introducing Ariadne v7.5

Begin with a question. Let evidence guide exploration and criticism drive evolution. Ariadne v7.5 is a first step toward an autonomous research machine, developing directions worth testing.

Read the update
Structural networks unfold into a paper wing

AutoResearch · Research update

Past release: Daedalus v7.4

Past release: Daedalus v7.4: structural thinking across fields, research tools, constructive review and continued exploration within AutoResearch.

Read the update
Verifier-Bit Ledger concept artwork

Research & creation · Profile update

A current record of research, tools and creative work

Verifier-Bit Ledger is under review at ICLR, with an arXiv preprint forthcoming. DFO is a paper with submission to IEEE TEVC forthcoming. The portfolio also includes seven AutoResearch workstreams and original music for CIVILIZATION; the web CV and bilingual PDF share the current profile.

View the updated CV

Selected research

View all
Original concept artwork for this project

Representation & Reasoning·Ongoing research

Attractor-JEPA

Compositional computation in latent representations

Explores compositional computation in latent representations, focusing on reasoning depth, state stability and learning.

Explore research
Original concept artwork for this project

Embodied AI safety·v0.3 · Open-source execution verification workbench

Sentinel-EVC

Final-action validation and verifiable execution

Final-action checks, incremental certificate reuse, pre-motion integration checks and signed execution records.

Explore research
Verifier-Bit Ledger concept artwork

Information theory & reasoning · ICLR under review

The Verifier-Bit Ledger

Verifier-in-the-loop reasoning

How much improvement can verifier feedback buy? An information ledger connects uplift ceilings, ghost baselines and executable audits.

Explore research
Original AutoResearch concept illustration: a question, evidence cards and research actions.

Research Automation·Local workbench and controlled experiments in progress

AutoResearch

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 research
The mathematical and research foundations of Project Bedrock

INDEPENDENT INITIATIVE · LAUNCHED 2026.10.18

Project Bedrock

Deeper foundations. Further possibilities.

A three-month initiative to deepen our mathematical understanding of AI through close reading, first-hand derivation, open-source practice and community dialogue. Build understanding through practice. Let real questions lead the next step.

Tools in development

View all
Original concept artwork for this project
Joint compilation of scientific manuscripts and figures

LSMFC

Connecting research facts, arguments, paragraphs, and figures so that manuscripts and scientific visuals can be cross-checked.

Explore project
Themis Court
v14.3.0-alpha · Offline scaffold

Themis Court

The contribution-review and writing module in AutoResearch, connecting lens routing, independent critique, evidence profiles, and deterministic checks with research taste and author-guided writing.

Explore the module
Literature Review
Workflow & utilities · K-Dense toolkit

Literature Review

A structured route through source discovery, record processing, staged screening, thematic synthesis, and citation review, supporting evidence preparation within AutoResearch.

Explore the module
InkTide concept artwork

Scientific writing & figure design

InkTide

InkTide brings inspected paper lessons, author evidence, original prose and figure design into a connected writing workflow, with a separate review of the result.

Explore InkTide

Technical blog

View all

Writing & Reflections

View all
Original editorial illustration for literature and reflection

LITERATURE & LIFE

Another way to understand the world.

Stories, reading, and essays—attending to people and lived experience.

Education & Experience

Full background
CUGB

China University of Geosciences, Beijing

Undergraduate studies in Computer Science · Entered 2025

Studying AI, while continuing to learn through literature, music, and expression.

A constellation of AI collaboration

LANCER / HUMAN × AI

The Craft of AI Collaboration

Across Codex and Claude Code: a thousand-agent scale of practice, hundreds of agents within a task, and work connecting tools, engineering, and stories.

Read my story of collaboration ↗

LET’S CONNECT

Let's explore questions worth pursuing.

I welcome conversations about AI, automated research, literature, and sharing knowledge.

Get in touch