Merged
Conversation
- Created si_guide.md: Complete mapping of all 17 SI algorithms to code - Annotated RFD3_diffusion_module.py: Algorithm 5 (diffusion forward pass) - Added bilingual comments to all methods - Documented EDM preconditioning, recycling, and coordinate updates - Annotated encoders.py: Algorithms 3, 4, 12 - TokenInitializer: Token and atom initialization with detailed steps - DiffusionTokenEncoder: Distogram embedding and recycling - Added comprehensive docstrings and inline comments in Chinese/English
- Annotated Algorithm 13: SinusoidalDistEmbed - Sinusoidal distance embedding for pairwise positions - Detailed step-by-step comments for frequency calculation and embedding - Annotated Algorithm 14: PositionPairDistEmbedder - Inverse pairwise distance encoding with mask embedding - Support for both full 3D distance frame and simple inverse distance - Annotated Algorithm 15: OneDFeatureEmbedder - Additive aggregation of multiple 1D feature embeddings - Used for both token-level and atom-level feature initialization - Annotated Algorithm 9: Downcast - Pools atom-level features to token-level using cross-attention or mean pooling - Comprehensive documentation of grouping, pooling, and residual operations - Annotated Algorithm 6: LocalTokenTransformer - SL2 sparse attention (sequence-local + structure-local) at token level - Detailed explanation of attention indices creation and transformer blocks All annotations include bilingual Chinese/English comments with algorithm step references
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.