Add SparsePR to modality-temporal methods - #5
Draft
PardisTaghavi wants to merge 1 commit into
Draft
Conversation
Add a complete SparsePR entry with metadata, abstract, links, core innovation, and key results.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds SparsePR: Partition the Support, Reconstruct the Residual to the Modality + Temporal Consistency catalog using the repository’s full paper-entry format.
Core contribution
SparsePR combines response-coupled block partitioning with probe-fitted residual reconstruction to accelerate attention without training. Across four video generation and world models, it preserves generation quality at 22.0–26.0% executed-pair density and reports 1.48–2.61× end-to-end speedups.
Why it belongs here
The method has practical value for scalable inference in temporally coherent video generators and world models, and includes a public reference implementation.
Verified links