Ka Leong Cheng
2 papers · Latest:
Computer Vision
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
CausalCine is a real-time autoregressive framework for generating multi-shot video narratives, enabling interactive, coherent storytelling across shot changes.
2605.12496
Computer VisionGeometric Context Transformer for Streaming 3D Reconstruction
LingBot-Map introduces a Geometric Context Transformer for streaming 3D reconstruction, achieving efficient, accurate, and stable performance over long sequences.
2604.14141
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.