Ruiqi Wang (@RuiqisNotes) header
Ruiqi Wang (@RuiqisNotes) profile picture

phd @sfu_cs_ai, perception & reasoning; prev: @nvidia @awscloud @MMLabNTU @AmazonScience @ourANU

Vancouver, British Columbia
Joined January 2014
Photo by Ruiqi Wang (@RuiqisNotes)Photo by Ruiqi Wang (@RuiqisNotes)Photo by Ruiqi Wang (@RuiqisNotes)Photo by Ruiqi Wang (@RuiqisNotes)Photo by Ruiqi Wang (@RuiqisNotes)Photo by Ruiqi Wang (@RuiqisNotes)Photo by Ruiqi Wang (@RuiqisNotes)Photo by Ruiqi Wang (@RuiqisNotes)
Ruiqi Wang retweeted
Coding agents can now operate graphics tools. How will they change the way we design graphics algorithms and conduct graphics research? Join the discussion at the 1st Workshop on Agentic Graphics on Dec 1 afternoon at #SIGGRAPHAsia2026! 🔗 siga26.agentic-graphics.com
2
14
46
1,602
Tired of black box image editing? Regain some control through 3D. VETI is a geometry grounded image tuner. Simple idea with fun results. A course project under @yagizaksoy wrapped up as a SIG Asia poster. All is available at: yaksoy.github.io/VETI/
6
20
1,464
Symmetry! Symmetry! Symmetry! Meet SymTRELLIS, symmetry-enforced 3D asset generation. Rotational, reflectional or polyhedral, have them under your control without retraining. SIGGRAPH ASIA 2026 Paper, code & demo available at: symtrellis.github.io/
2
3
1
8
1,279
Ruiqi Wang retweeted
1/8 Good morning Malmö 🇸🇪! #ECCV2026 Have you wondered how far we are from building interactable 3D worlds? Come join our FAI workshop and hear the world’s leading researchers’ opinions! Today, 9 Sept · 14:00–17:35 CEST Malmö Arena · Palissad East Talk details follow!
1
4
1
18
1,473
Ruiqi Wang retweeted
🚀 Tomorrow at #ECCV2026: FAI Workshop — Functionality, Articulation & Interaction! 🌟 Talks by Andrea Vedaldi, Wei-Chiu Ma, Evangelos Kalogerakis, Angela Dai & Mikaela Uy! 💬 And don’t miss our Closing Panel featuring our invited speakers + @richardzhangsfu!!
Join us for the Functionality, Articulation & Interaction workshop at #ECCV2026 tomorrow! Our incredible lineup: - Andrea Vedaldi (@Oxford_VGG) - Wei-Chiu Ma (@weichiuma) - Evangelos Kalogerakis (@EvangelosKalog1) - Angela Dai (@angelaqdai) - Mikaela Angelina Uy (@mikacuy)
1
2
7
1,403
Please join us tomorrow (Sept. 9) afternoon, 2:00pm, at Malmö Arena Palissad East! I will open the workshop. We have a fantastic line-up of invited speakers, a poster session, and a closing panel session at 4:55pm.
Join us for the Functionality, Articulation & Interaction workshop at #ECCV2026 tomorrow! Our incredible lineup: - Andrea Vedaldi (@Oxford_VGG) - Wei-Chiu Ma (@weichiuma) - Evangelos Kalogerakis (@EvangelosKalog1) - Angela Dai (@angelaqdai) - Mikaela Angelina Uy (@mikacuy)
4
9
636
Ruiqi Wang retweeted
Function2Scene turns functional design briefs into 3D indoor layouts Instead of placing furniture from object lists, it parses who uses a room and what they do into 17 ergonomic and spatial constraints. Iterative refinement with geometric, LLM, and VLM checks wins 94.3% over baselines.
1
4
20
1,872
I will be giving two workshop talks at #ECCV2026 (stay tuned) and opening a third on Functionality, Articulation, and Interaction (diliash.github.io/fai_eccv_w…). Please also check out our oral paper on PADFormer (arxiv.org/abs/2608.04210) on Friday.
We are heading to #ECCV2026 in Malmö 🇸🇪 Come find us there Sept 8–13! 🎊 @eccvconf
4
8
661
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”。 プロジェクトページなどは🧵から
1
3
1
17
3,034
Ruiqi Wang retweeted
🎬Ultra-Long Egocentric Video Reasoning🎬 😎Ego-R1😎 reasons over ultra-long (i.e., in weeks) egocentric videos, which leverages a **Chain-of-Tool-Thought (CoTT)** process trained via reinforcement learning (RL) - Project: egolife-ai.github.io/Ego-R1/ - Code: github.com/egolife-ai/Ego-R1
Ego-R1 Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
15
1
80
7,400
Ego-R1, a novel framework for reasoning over ultra-long (i.e.,in days and weeks) egocentric videos, which leverages a structured Chain-of-Tool-Thought (CoTT) process, orchestrated by an Ego-R1 Agent trained via reinforcement learning (RL). Inspired by human problem-solving strategies, CoTT decomposes complex reasoning into modular steps, with the RL agent invoking specific tools, one per step, to iteratively and collaboratively answer sub-question stackling such tasks as temporal retrieval and multi-modal understanding. Paper Title: Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning Project: egolife-ai.github.io/Ego-R1/ Link: arxiv.org/abs/2506.13654 #AI #video #GenerativeAI #AIイケメン部
3
7
1,220
Ruiqi Wang retweeted
Ego-R1 Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
4
37
3
163
29,341
Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning Reasoning over weeks-long video, with a mix of CoT and using tools
1
9
26
2,275