田二
Tian2 builds with artificial intelligence the way it builds everything else — as craft kept to a standard. A suite of original coaching tools, a curriculum that teaches the field from first principles, and the mentored student research it all serves. Tools and teaching are Tian2's own work; student research is shown by field alone, names withheld.
The tools, the curriculum, and the animation work are Tian2's own — original, publishable, and credited to the studio. These are shown by name.
Student research belongs to the students. It appears here by field and method only — no names, no scores, no project identifiers. When in doubt, it is left out.
Tian-Skills is a working library of more than forty-five original Claude skills — small, reusable agents that run a bilingual coaching and publishing practice. Each one packages a real piece of the craft: how a science-fair poster is judged, how a Yau paper is structured, how a competition's past papers become a strategy, how a LaTeX manuscript becomes a searchable question bank. They span AP and olympiad coaching, ISEF and Yau award pathways, the studio's own design system, and the California and UC application essays — built as tools, not prompts, and curated down to original work only.
Reads a poster or slide deck, then runs parallel agents to check the science against current literature, score it against the official rubric, and return sixty-plus categorized judge questions with model strong and weak answers.
One of nine S.-T. Yau coaching skills. Guides a student to draft the research paper in their own voice — a different skeleton for a proof, an experiment, a CS system, or an economics model — bilingual, and written for the all-English finals defense.
Walks a project through ISEF's compliance questions — humans, animals, tissue, hazards, field work — and emits the exact forms, the correct review body, and the right timing, grounded in the official rules book.
Turns any contest's past papers into a tiered "how to score more" guide — key facts per theme, the most common trap, a year-by-year question map — and, where a build exists, a corrected and categorized preparation book.
Converts a LaTeX solution book into a searchable, reveal-on-click question bank that runs offline in a browser — protecting every math form, fractions and amsmath environments included, before a single line of text is touched.
Turns notes or an outline into a self-contained interactive slide deck — in-class handwriting annotation, one-slide-per-page PDF export, live canvas diagrams — all in the house design system and running by double-click, no server.
Two pieces of teaching built with and about AI. The first is a full ten-lesson curriculum that takes a high-school student from "what is a function" to a deployed speech system; the second uses AI-assisted animation to make physics move on the page. The curriculum design and the animation code are Tian2's own; the student project the course is built around is shown only in outline, its author withheld.
A bilingual course Tian2 designed and guided, built around a real student project: a Ningbo-dialect (Wu / 吴语) text-to-speech system for elder care. Rather than teach machine learning in the abstract, each lesson advances the same project — duration models, embeddings, attention, the physics of sound, modern neural speech, the ethics of data, and a responsible launch. It ships as ten lesson plans, ten lecture scripts, and ten interactive decks in the house design system.
A growing codebase that pairs AI with Manim — the programmatic animation library — to build animated physics lectures from scratch. The first unit, on kinematics, is complete: motion, velocity, and acceleration drawn as they actually behave, with lecture notes written alongside the code. It is early work, and openly so — a study in using AI to produce teaching material that holds to the same clean, unhurried standard as the printed books.
The last lesson of the curriculum is the one Tian2 cares about most: consent for elder subjects, audible AI-speech disclosure, audio watermarking, and the voice-spoofing law across three jurisdictions — because shipping responsibly is part of the syllabus, not an afterthought.
The projects below belong to the students who did them. They are described by field and method only — no names, no scores, no project identifiers, no review content. This is a sample of the kinds of AI-assisted research Tian2 mentors, not a roster.
Real-time video segmentation and document-image (OCR) pipelines — deep models built, trained, and evaluated against published baselines.
CVPR · Science FairClassification and risk-modeling projects on real scientific data — exoplanet detection from light curves, clinical risk estimation — with honest treatment of imbalance and uncertainty.
ISEF · Science FairBioinformatics and machine learning applied to cancer immunotherapy — sequence and expression analysis read for signal, framed for a research review.
ISEF · YauAgent-based and learned simulation — pedestrian evacuation dynamics — alongside dialect speech synthesis, where the modeling and the ethics are coached together.
ISEFThese archetypes are part of a wider mentoring practice across the sciences. See the full Research Mentoring section →
Not Tian2's work — open systems kept close and read for what they get right. Each one sits next to a part of the practice: autonomous research next to student mentoring, poster and slide generation next to competition coaching.
A fully autonomous research agent — hypothesis, experiment, analysis, manuscript — whose work first cleared peer review at an ICLR 2025 workshop. Studied as a mirror for how student research is structured and defended.
A multimodal system that generates a conference poster directly from a paper. Read closely for the same reason the studio coaches posters by hand: the hard part is deciding what to leave out.
A multilingual agent that drafts presentation slides across twenty-plus languages. A useful counterpoint to the studio's own design-first approach to teaching decks.
AI can draft a thing quickly. Keeping it correct, and honest, is still the work.
— The Tian2 Editors