A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
Videorope: What makes for good video rotary position embedding?
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
LiteVSR performs video super-resolution on a completely frozen Diffusion Transformer via a lightweight State-Aware Adapter that uses dual-stream extraction and time-dependent cross-attention, reaching competitive quality with 11.25% trainable parameters after 12 GPU-hours.
Circle-RoPE achieves cross-modal positional disentanglement in VLMs by mapping 2D image tokens to a cone-like annulus orthogonal to the text axis, with PTD=0 eliminating RoPE geometric bias while preserving intra-image structure via alternating geometry encoding.
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.
Adaptive 3D-RoPE adapts rotary positional encoding to wireless channel physics via learnable 3D frequencies and dynamic CSI control, yielding up to 10.7 dB NMSE gains in scale extrapolation and 1 dB in zero-shot tasks.
citing papers explorer
-
Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models
Circle-RoPE achieves cross-modal positional disentanglement in VLMs by mapping 2D image tokens to a cone-like annulus orthogonal to the text axis, with PTD=0 eliminating RoPE geometric bias while preserving intra-image structure via alternating geometry encoding.
-
Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.