arXiv Computer Vision
No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 4
Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video Continuation
The paper introduces Statebench, a benchmark for evaluating how well video generators track world states across segments, focusing on past-visible, occluded-process, and complex-transition states. It also proposes Stateagent, a method that maintains an explicit entity-state representation, updates it with new prompts, and uses the resulting state to guide video continuation. Experiments show Stateagent raises the overall state score from 45.2 to 69.3 and improves one‑minute story generation.
arXiv Computer Vision
Sep 22
Rethinking Streaming Video Diffusion Model: Context, Execution, and Training
arXiv:2609.22283v1 Announce Type: new Abstract: Understanding the design space of streaming video diffusion is essential to exploring its potential for generation quality and computational efficiency...
arXiv AI
Jun 8
Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding
arXiv:2606. 06991v1 Announce Type: cross Abstract: Online Video Large Language Models (Video-LLMs) have advanced toward seamless human-AI interaction through frame-by-frame processing and proactive responding.
arXiv AI
4d ago
Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning
The paper introduces Watch-Think-Interact (WTI), a closed-loop framework for multi-question streaming video reasoning that maintains compact natural-language memory entries linked to video time ranges. WTI decides whether to answer, continue watching, or recall relevant past intervals for each question, avoiding replay of the full history. The authors build a large dataset, WTI-82K, and a training method, Stream-GDPO, achieving state‑of‑the‑art performance on StreamingBench and OVO-Bench.
arXiv Machine Learning
Sep 17
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control
Zing-0.5 is a 5B autoregressive world model that enables users to explore and influence generated worlds through joint keyboard and online text control. It integrates unified action and text conditioning, event-scale supervision for incremental generation, and low-cost real-time interaction, achieving high scores on WBench Navigation. The authors release model weights, inference code, and a serving implementation to support further research on playable generated worlds.
arXiv AI
Sep 1
CineForge: Self-Improving Agents for Long-Horizon Video Generation
arXiv:2608.29621v1 Announce Type: cross Abstract: Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt con...