Xu Chen
3 papers · Latest:
Computer Vision
CurEvo: Curriculum-Guided Self-Evolution for Video Understanding
CurEvo introduces curriculum-guided self-evolution for video understanding, dynamically regulating task difficulty and data diversity for structured learning.
2604.26707
Information RetrievalLoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction
LoopCTR uses a loop scaling paradigm to efficiently train high-performing CTR models, achieving SOTA with zero-loop inference.
2604.19550
Computer VisionGrasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions
GraG rapidly reconstructs dynamic 3D hand-object interactions from monocular video using a compact Sum-of-Gaussians representation.
2604.12929
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.