Papers

Filtered to source fidelity · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

75 upvotes · 4 AUG 2026 · Yicheng Xiao, Wenxun Dai, Xinran Qin et al.

This paper presents a real-time video editing system that can generate video frames on the fly without access to future frames or a predefined video duration, allowing for open-ended editing. Practitioners might care about this system because it could enable more flexible and interactive video editing experiences.

autoregressive diffusionvideo editingreal-time processingcausal generationsource fidelitylong-term temporal consistency