SEGA adaptively scales RoPE attention components using spectral-energy guidance from the latent to improve structural coherence and fine details in high-resolution DiT synthesis.
Ultravico: Breaking extrapolation limits in video diffusion transformers
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
FlowLong generates videos several times longer than native model windows by blending adjacent predictions with Tweedie matching to enforce manifold and temporal consistency while using stochastic noise injection early and deterministic sampling later.
WM-DAgger uses world models with corrective action synthesis and consistency-guided filtering to aggregate OOD recovery data for imitation learning, reporting 93.3% success in soft bag pushing with five demonstrations.
Salt improves low-step video generation quality by adding endpoint-consistent regularization to distribution matching distillation and using cache-conditioned feature alignment for autoregressive models.
citing papers explorer
-
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
SEGA adaptively scales RoPE attention components using spectral-energy guidance from the latent to improve structural coherence and fine details in high-resolution DiT synthesis.
-
FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching
FlowLong generates videos several times longer than native model windows by blending adjacent predictions with Tweedie matching to enforce manifold and temporal consistency while using stochastic noise injection early and deterministic sampling later.
-
WM-DAgger: Enabling Efficient Data Aggregation for Imitation Learning with World Models
WM-DAgger uses world models with corrective action synthesis and consistency-guided filtering to aggregate OOD recovery data for imitation learning, reporting 93.3% success in soft bag pushing with five demonstrations.
-
Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
Salt improves low-step video generation quality by adding endpoint-consistent regularization to distribution matching distillation and using cache-conditioned feature alignment for autoregressive models.