arXiv (All)
open access
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation
Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that their gradients exhibit distinct patterns and systematic negative alignment, hi
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SGF+: Decoupling Gradient Flows for Autoregressive Video Generation#1252657
- ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation#1076579
- Enhancing Autoregressive Video Generation via Representation Adversarial Distillation#1145204
- Self-Representation Alignment in Diffusion Models for Video Background Music Generation#1326825
- Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation#1325449
Record · ID 1234854
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive