Papers

Filtered to long-horizon extrapolation · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

Self Gradient Forcing: Native Long Video Extrapolation

30 upvotes · 22 JUL 2026 · Junhao Zhuang, Shiyi Zhang, Yuxuan Bian et al.

This paper proposes a new training method for autoregressive video diffusion models called Self Gradient Forcing, which helps them better remember and use past information to generate future frames. Practitioners might care about this because it could lead to more realistic and stable video extrapolation.

self-forcingautoregressive video diffusionlong-horizon extrapolationcontextual memorygenerative models