Qifeng Chen
6 papers · Latest:
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.
MedHorizon: Towards Long-context Medical Video Understanding in the Wild
MedHorizon introduces a new benchmark for long-context medical video understanding, revealing current MLLMs struggle with sparse evidence retrieval and clinical reasoning.
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
This paper introduces a "levels x laws" taxonomy for agentic world models, synthesizing over 400 works and outlining a roadmap for future development.
Divide-then-Diagnose: Weaving Clinician-Inspired Contexts for Ultra-Long Capsule Endoscopy Videos
This paper introduces a new task, dataset (VideoCAP), and framework (DiCE) for diagnosis-driven summarization of ultra-long capsule endoscopy videos.
AnimationBench: Are Video Models Good at Character-Centric Animation?
AnimationBench is a new benchmark for evaluating image-to-video models' ability to generate character-centric animation, addressing limitations of realism-focused tools.
Switch: Learning Agile Skills Switching for Humanoid Robots
Switch is a hierarchical multi-skill system enabling humanoid robots to seamlessly transition between diverse locomotion skills using a skill graph and online scheduler.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.