VIS-Ground: Video Interactive Storytelling with Contextual Grounding
cs.CV
Submitted: 2026-10-07
Updated: 2026-10-09
Project page: https://vis-ground.github.io
Terminology
Sources
- Genie: Generative Interactive Environments
- StoryBench: A Multifaceted Benchmark for Continuous Story Visualization
- Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
- ViMax: Agentic Video Generation
- Vid2World: Crafting Video Diffusion Models to Interactive World Models
- StreamDiT: Real-Time Streaming Text-to-Video Generation
- Trimming the Long-Tail of Visual World Modeling Evaluation
- Long-Horizon Embodied Decision-Making via Multimodal Memory Compression
- Co-Director: Agentic Generative Video Storytelling
- Automated Movie Generation via Multi-Agent CoT Planning
- MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio
- LongLive: Real-time Interactive Long Video Generation
- From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
- WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
- VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
- Where LLM Agents Fail and How They can Learn From Failures
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models