3 citations · 3 across the 4 of their papers we have counts for
Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory
Ruiqi Wu, Xuanhua He, Meng Cheng +8
We propose Infinite-World, a robust interactive world model capable of maintaining coherent visual memory over 1000+ frames in complex real-world environments. While existing world…
cs.CV2025
Active Intelligence in Video Avatars via Closed-loop World Modeling
Xuanhua He, Tianyu Yang, Ke Cao +6
Current video avatar generation methods excel at identity preservation and motion alignment but lack genuine agency, they cannot autonomously pursue long-term goals through adaptiv…
cs.CV2024★ 3 cited
Auto-selected Knowledge Adapters for Lifelong Person Re-identification
Xuelin Qian, Ruiqi Wu, Gong Cheng +1
Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations, ada…