AI Paper Atlas

Research map / Video / Video generation

NeRV-Diffusion: Diffuse Implicit Neural Representation for Video Synthesis

Yixuan Ren, Hanyu Wang, Bo He, Hao Chen, Abhinav Shrivastava

ICLR 2026 · Video › Video generation · approach: Efficient video diffusion models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use channel-wise INR parameterization instead of repeat modulation (ablation)NeRV autoencoder (S) · UCF-101gFVD: 741 -> 570Improved
Add multi-head affine mapping to reuse weight tokens across layers (ablation)NeRV autoencoder (S) · UCF-101gFVD: 570 -> 283Improved
Direct reuse of tokens without multi-head affines (ablation)NeRV autoencoder (S) · UCF-101gFVD: 570 -> 562No clear effect
Use 8x8 spatiotemporal input embedding instead of 1x1 (ablation)Generative NeRV (S) · UCF-101gFVD: 283 -> 254Improved
Use 16x16 spatial embedding rather than 8x8 (ablation)Generative NeRV (S) · UCF-101gFVD: 254 -> 277Hurt
Use transposed convolution instead of PixelShuffle (ablation)Generative NeRV (S) · UCF-101gFVD: 254 -> 248Improved
Add residual side connections (ablation)Generative NeRV (S) · UCF-101gFVD: 248 -> 219Improved
Increase number of weight tokens from 128 to 256 (ablation)NeRV-Diffusion-S · UCF-101gFVD: 184 -> 206Hurt
Use DiT denoiser instead of Latte (temporal attention) (ablation)Implicit diffusion · UCF-101gFVD: 342 -> 295Improved
Add Min-SNR-gamma loss weighting (ablation)Implicit DiT · UCF-101gFVD: 295 -> 238Improved
Add scheduled sampling (ablation)Implicit DiT · UCF-101gFVD: 295 -> 261Improved
Combine Min-SNR-gamma and scheduled sampling (ablation)Implicit DiT · UCF-101gFVD: 295 -> 184Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy