
Stream-T1: Test-Time Scaling for Streaming Video Generation
From Daily Paper Cast by Jingwen Liang, Gengyu Wang
May 8, 2026 · 22 min · Episode 1841
About this episode
This episode discusses the Stream-T1 framework for enhancing streaming video generation through test-time scaling.
🤗 Upvotes: 94 | cs.CV Authors: Yijing Tu, Shaojin Wu, Mengqi Huang, Wenchuan Wang, Yuxin Wang, Chunxiao Liu, Zhendong Mao Title: Stream-T1: Test-Time Scaling for Streaming Video Generation Arxiv: http://arxiv.org/abs/2605.04461v1 Abstract: While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration costs and lack temporal guidance. To address these structural bottlenecks, we propose shifting the focus to streaming video generation. We identify that its chunk-level synthesis and few denoising steps are intrinsically suited for TTS, significantly lowering computational overhead while enabling fine-grained temporal control. Driven by this insight, we introduced Stream-T1, a pioneering comprehensive TTS framework exclusively tailored for streaming video generation. Specifically, Stream-T1 is composed of three units: (1) Stream -Scaled Noise Propagation, which actively refines the initial latent noise of the generating chunk using historically proven, high-quality previous chunk noise, effectively…
People in this episode
Hosts: Jingwen Liang, Gengyu Wang
Topics covered
- video generation
- test-time scaling
- streaming video
- diffusion models
- computational efficiency
Keywords
- Stream-T1
- test-time scaling
- streaming video generation
- diffusion models
- temporal control
Mentioned in this episode
Organizations: arxiv
More episodes of Daily Paper Cast
- EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
- MiniMax Sparse Attention · June 13, 2026 · 26 min
- SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
- InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
- FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
- Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min
Explore listener stats, chart rankings, contacts and more on the Daily Paper Cast podcast page.