AI & ML interests
Machine Learning, Computer Vision, Embodied AI
Recent Activity
ViSpeak: Visual Instruction Feedback in Streaming Videos
(ICCV 2025) ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations
EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding
LOVE-R1: Advancing Long Video Understanding with Adaptive Zoom-in Mechanism via Multi-Step Reasoning
-
LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
Paper • 2509.24786 • Published • 7 -
iSEE-Laboratory/love-r1-train
Preview • Updated • 28 • 1 -
iSEE-Laboratory/love-r1-stage1
8B • Updated • 5 -
iSEE-Laboratory/love-r1-stage2
8B • Updated • 1
[NeurIPS 2024] Grasp as You Say: Language-guided Dexterous Grasp Generation
LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models
-
fushh7/LLMDet
Zero-Shot Object Detection • Updated • 23 -
LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models
Paper • 2501.18954 • Published -
iSEE-Laboratory/llmdet_tiny
Zero-Shot Object Detection • 0.2B • Updated • 752 • 6 -
iSEE-Laboratory/llmdet_base
Zero-Shot Object Detection • 0.2B • Updated • 410k • 9
ViSpeak: Visual Instruction Feedback in Streaming Videos
LOVE-R1: Advancing Long Video Understanding with Adaptive Zoom-in Mechanism via Multi-Step Reasoning
-
LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
Paper • 2509.24786 • Published • 7 -
iSEE-Laboratory/love-r1-train
Preview • Updated • 28 • 1 -
iSEE-Laboratory/love-r1-stage1
8B • Updated • 5 -
iSEE-Laboratory/love-r1-stage2
8B • Updated • 1
(ICCV 2025) ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations
[NeurIPS 2024] Grasp as You Say: Language-guided Dexterous Grasp Generation
EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding
LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models
-
fushh7/LLMDet
Zero-Shot Object Detection • Updated • 23 -
LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models
Paper • 2501.18954 • Published -
iSEE-Laboratory/llmdet_tiny
Zero-Shot Object Detection • 0.2B • Updated • 752 • 6 -
iSEE-Laboratory/llmdet_base
Zero-Shot Object Detection • 0.2B • Updated • 410k • 9