
Ruiqi Wang
@RuiqisNotes
Followers
52
Following
89
Media
1
Statuses
9
PhD student @SFU GrUVi Lab, prev Intern @AmazonScience, Functionality, MLLMs, Reasoning :)
Vancouver, British Columbia
Joined January 2014
RT @taziku_co: 1週間分の一人称映像を“人間のように”理解するAI。. Ego-R1は、複雑な行動を「小さなステップ」に分解し、その都度ツールを使って推論する新型フレームワーク。強化学習で訓練されたエージェントが、映像の意味を“考えながら解く”。. プロジェクトペ….
0
3
0
RT @liuziwei7: 🎬Ultra-Long Egocentric Video Reasoning🎬. 😎Ego-R1😎 reasons over ultra-long (i.e., in weeks) egocentric videos, which leverage….
github.com
Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning - egolife-ai/Ego-R1
0
15
0
RT @ai_bites: Ego-R1, a novel framework for reasoning over ultra-long (i.e.,in days and weeks) egocentric videos, which leverages a structu….
0
3
0
This work was done during my visit at MMlab@NTU! 🇸🇬✨Special thanks to Prof Ziwei Liu @liuziwei7 for the amazing opportunity and to my supervisor Prof Richard Zhang @richardzhangsfu for his unconditional support! 🙏Grateful for such incredible mentorship that made this possible!.
0
0
7
🎉 Excited to share our new work: 👓Ego-R1!. We cracked ultra-long egocentric video reasoning! 🤯 Think days/weeks of footage processed efficiently with Chain-of-Tool-Thought ⛓️🔧.🌐
🎥 Video is already a tough modality for reasoning. Egocentric video? Even tougher! It is longer, messier, and harder. 💡 How do we tackle these extremely long, information-dense sequences without exhausting GPU memory or hitting API limits?. We introduce 👓Ego-R1: A framework
1
8
27
RT @Ar_Douillard: Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning. Reasoning over weeks-long video, with a mix of C….
0
9
0
We introduce the first active learning (AL) framework for high-accuracy instance segmentation of moveable parts from RGB images of real indoor scenes with a dataset contribution. @FenggenYu.
0
0
0
Learning part motions from real images is challenging due to data limitation. Today at #ECCV2024 (10/3, 4:30PM, #41) I will present our work, Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images. @richardzhangsfu
1
5
10