thu-ml / thu-ml/Causal-Forcing
Frame-level non-injectivtiy and Causal CD as substitute for ODE distillation
Open
Nobody has claimed this yet.
enhancement
question
- Dominant language
- Python
- Stars
- 969
- Forks
- 55
- PR merge metrics
- No merged PRs in 30d
Description
能不能大白话讲下为什么self forcing是这样的嘛，我理解self forcing里面的ODE初始化ode对每个chunk随机加噪，然后预测转x0，与ode对做MSE，target 应该是唯一的吧。
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
This issue asks for a plain-language explanation of self-forcing, ODE initialization, per-chunk noise, x0 prediction, MSE targets, frame-level non-injectivity, and Causal CD. No file, test, or entry point is named; done would be a clear explanation resolving whether the training target is unique.
Written by the indexing model from the issue text.
Assessment
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100