SituationalLLM: Proactive language models with scene awareness for dynamic, contextual task guidance Paper • 2406.13302 • Published Jun 19, 2024
Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies Paper • 2409.20237 • Published Sep 30, 2024
Continual Human Pose Estimation for Incremental Integration of Keypoints and Pose Variations Paper • 2409.20469 • Published Sep 30, 2024
FocusCLIP: Multimodal Subject-Level Guidance for Zero-Shot Transfer in Human-Centric Tasks Paper • 2403.06904 • Published Mar 11, 2024