College application research evidence · understanding and original contribution · Seoul and online
Project courseThe student keeps the work and the record they made.
Columbia AI: Predicting What Happens Next
Grades 9-12: AI that predicts the next scene, prediction...
- Free consultation and level check
- Apgujeong classroom or online
- One-to-one or small group
- Registered academy no. 11882
Is Columbia AI: Predicting What Happens Next a good fit for high school students in Grades 9-12?
Columbia AI: Predicting What Happens Next is a good fit for students in grades 9-12 who are interested in AI that predicts the next scene and prediction versus physics simulation. CIT offers online or in-person lessons in Apgujeong, Gangnam, Seoul, in one-to-one or small-group formats. Students make a side-by-side scene comparison tool, a color-coded error view, and code that flags the first mismatch.
The course starts from open research published by Columbia. When a student pushes an object with the keyboard, an AI model predicts the next scene. Using a prepared model and a simple pushing scene, students play the AI prediction beside a physics calculation and measure how far the two diverge as the prediction runs longer. They then build a feature that stops automatically when the difference passes a set limit and finds the first moment of mismatch, along with a screen that color-codes position differences and accumulated error. The student then designs and tests an extension of their own: a new question, feature, model, interface, or solution. In an application or interview, the student separates the source research from their own decisions, results, failed attempts, revisions, and limits.
Google sign-in is required. Existing account permissions determine access.
My child found the AI classes interesting and stayed with them. It made for a worthwhile school break. Thank you for teaching so attentively.
- Age group
- Grades 9-12
- Academic subject
- AI & Data, Engineering & Robotics, Physics & SpaceBrowse subject
- Course type
- Course
- Format
- Online or Apgujeong in person · one-to-one or small group
- Teaching language
- Korean by default, with complete English materials
- Curriculum status
- Lesson-readyEvery learning item includes the evidence, worked example, practical work, and tutor guidance required by CIT's lesson-ready standard.
From open research to student-owned work
Students inspect a relevant public source, reproduce the idea, then add an original question, feature, or test. Every source is public, and each lesson names the exact page it opens.
How can I explain this course to my child?
If questions about AI that predicts the next scene or prediction versus physics simulation keep making you ask why, Columbia AI: Predicting What Happens Next lets you investigate the question with evidence, then build and defend an extension of your own.
Which interests suggest this course?
- AI that predicts the next scene
- prediction versus physics simulation
- errors that grow over time
What does the student finish?A side-by-side scene comparison tool, a color-coded error view, and code that flags the first mismatch.
Is this a good fit?
A strong fit for students who want to understand, build, test, or responsibly use AI systems.
Course placement follows current subject and coding readiness.
Students should be ready to document sources, methods, and limits.
Advanced tools are introduced after a clear baseline.
What will my child learn?
- Explain, with a working example, how far into the future a next-scene prediction model looks.
- Move objects with the keyboard and compare the AI prediction with the physics calculation under the same conditions.
- Change only the prediction length and chart how position differences and accumulated error grow.
- Decide on a stopping threshold for finding the first mismatch and build it into a feature.
How does the course progress?
- 1Understanding the Research Question and Baseline Behavior
Check the prepared AI model, data, and computer requirements, then drive a simple pushing scene with the keyboard.
- 2Connecting Sensors, Actions, and Measurements
Move objects with the keyboard and set the AI prediction beside the physics calculation to record the error.
- 3Building a Feature and Control Screen from Evidence
Change only the prediction length to compare error, then build a feature that stops past a set limit and finds the first mismatch.
- 4Testing the Integrated App and Explaining the Design
Add optional large language model (LLM) review questions, drawn only from chosen numbers and notes, to a synced screen and test the tool.
What counts as useful evidence?
A side-by-side scene comparison tool, a color-coded error view, and code that flags the first mismatch.
What should an admissions reader be able to see?
The course starts from open research published by Columbia. The student works out what those researchers were trying to learn, why the question matters, and how they tested it, then designs and tests an extension of their own: a new question, feature, model, interface, or solution. In an application or interview, the student separates the source research from their own decisions, results, failed attempts, revisions, and limits.
Useful evidence may include a documented dataset, baseline comparison, model evaluation, error analysis, and a clear record of the student's own decisions.
These names identify who published the open project the course starts from. The evidence an application reads is what the student understood, completed, and can explain.
The real research project this course reads
- WangYixuan12/interactive_world_sim
- pinned commit
3ba69b41d070 - commit date 2026-03-10
- licence MIT
- text files 144
The student compares an AI's predicted scene with the real motion and finds where the prediction starts to slip. In class the project is separated into five boxes (input, memory, process, output, control). The lesson opens one of them, changes one value, and leaves the rest closed.
- InputWhat comes in?
Video of a robot handling objects, and the action values recorded alongside it
- MemoryWhat persists?
The scene squeezed into a short set of values, and the model numbers training settled on
- Processopened hereWhat transforms?
The generation step that takes the current scene and an action and draws the next scene
- OutputWhat leaves, and who uses it?
The predicted video, and the score for how far it sits from what really happened
- ControlWhat decides when anything runs?
The settings that say how many steps ahead to predict, and when to train again
InputVideo and actions
interactive_world_sim/datasets/latent_dynamics/sim_aloha_dataset.pyinteractive_world_sim/datasets/latent_dynamics/real_aloha_dataset.py
MemoryLatent and weights
interactive_world_sim/algorithms/latent_dynamics/latent_world_model.pyinteractive_world_sim/algorithms/models/cm_decoder.py
ProcessMaking the next
interactive_world_sim/algorithms/common/diffusion_helper.pyinteractive_world_sim/algorithms/latent_dynamics/models/cm_latent_dynamics.py
OutputPrediction, score
interactive_world_sim/algorithms/common/metrics/fvd.pyinteractive_world_sim/algorithms/common/metrics/lpips.py
ControlHorizon settings
configurations/algorithm/latent_world_model.yamlconfigurations/experiment/exp_latent_dyn.yaml
The files the lesson opens, by name. The course is not a walk through the repository; it opens a chosen few and says which.
One value moves and everything else stays. The right-hand column is the prediction written before the run, not a result; the work is reconciling the two.
On a narrow screen, swipe the picture sideways.
The universities and labs named here made the open projects this course reads. CIT designed the course independently; it is not an official, affiliated, or endorsed course.
Questions parents search before choosing this course
Is Columbia AI: Predicting What Happens Next a good fit for high school students in Grades 9-12?
Columbia AI: Predicting What Happens Next is a good fit for students in grades 9-12 who are interested in AI that predicts the next scene and prediction versus physics simulation. CIT offers online or in-person lessons in Apgujeong, Gangnam, Seoul, in one-to-one or small-group formats. Students make a side-by-side scene comparison tool, a color-coded error view, and code that flags the first mismatch.
Can my child take Columbia AI: Predicting What Happens Next online or in person, one-to-one or in a small group?
Yes. CIT offers online and in-person lessons at its Apgujeong academy in Gangnam, Seoul, with one-to-one and small-group options. A readiness consultation confirms the available format and starting point for the course.
Does my child need prior subject knowledge or coding experience for Columbia AI: Predicting What Happens Next?
Course placement follows current subject and coding readiness. Students should be ready to document sources, methods, and limits. Advanced tools are introduced after a clear baseline.
What will my child make or practice in Columbia AI: Predicting What Happens Next?
The main evidence is a side-by-side scene comparison tool, a color-coded error view, and code that flags the first mismatch. Students also document decisions, tests, feedback, and limits in age-appropriate language.
How can Columbia AI: Predicting What Happens Next show research understanding in a college application?
The course starts from open research published by Columbia. The student works out what those researchers were trying to learn, why the question matters, and how they tested it, then designs and tests an extension of their own: a new question, feature, model, interface, or solution. In an application or interview, the student separates the source research from their own decisions, results, failed attempts, revisions, and limits. Useful evidence may include a documented dataset, baseline comparison, model evaluation, error analysis, and a clear record of the student's own decisions.
How are the schedule and tuition for Columbia AI: Predicting What Happens Next determined?
CIT confirms the student's readiness, goal, location, class size, and current availability before recommending a course plan. The consultation and level check are free; tuition is explained before enrollment.
When should a student start?
There is no fixed intake month. CIT reviews the student's current school term, readiness, and available hours, then names the point in the course where they should begin.
I appreciated that a simple early idea was extended into an 'AI debate tool'. My child has always been interested in debate and social issues, so seeing that interest connect to the project makes me expect a more complete and distinctive result.
Where else parents check CIT
Choose the course after a readiness check
CIT can compare this course with nearby options by age, subject, and current preparation.