3 papers
cs.CV2026
PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstruction
Ju Shen, Chen Chen, Tam V. Nguyen +1
We propose PoseGaussian, a pose-guided Gaussian Splatting framework for high-fidelity human novel view synthesis. Human body pose serves a dual purpose in our design: as a structur…
cs.CV2025
UltraLight Med-Vision Mamba for Classification of Neoplastic Progression in Tubular Adenomas
Aqsa Sultana, Nordin Abouzahra, Ahmed Rahu +5
Identification of precancerous polyps during routine colonoscopy screenings is vital for their excision, lowering the risk of developing colorectal cancer. Advanced deep learning a…
cs.CL2025
MindFlow+: A Self-Evolving Agent for E-Commerce Customer Service
Ming Gong, Xucheng Huang, Ziheng Xu +1
High-quality dialogue is crucial for e-commerce customer service, yet traditional intent-based systems struggle with dynamic, multi-turn interactions. We present MindFlow+, a self-…