Arash (Ali) Mahdavi Amiri retweeted
Congrats to all the authors!!!!
Happy to see these papers accepted #Neurips2026 🎊 🎊 🎊
Please come and find us at the conference!
More details & links in 🧵
Arash (Ali) Mahdavi Amiri retweeted
3D models can look right and still fall apart.
Introducing Functionalization: graph completion adds missing structure and connectors to rectify motion and make models work.
SIGGRAPH Asia 2026
Paper, code, data available at: mingrui-zhao.github.io/Funct…
Arash (Ali) Mahdavi Amiri retweeted
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)
Arash (Ali) Mahdavi Amiri retweeted
You ask for a talking parrot, but the model makes the pirate talk AND gives him a beak! 🦜😮💨
-> Introducing The Attention Triangle in Audio-Video Models: how semantics leak between text, audio, and video, and how we steer them back. 🧵 [1/5]
Arash (Ali) Mahdavi Amiri retweeted
This entire game was built using Claude + Thrixel, an agentic 3D creation platform.
Thrixel: Generated high-quality, thematically consistent, editable 3D assets.
Claude: Assembled in Unity + wrote game logic.
1 /goal prompt + Thrixel Skills + <5 follow-ups
Repo coming👇
Arash (Ali) Mahdavi Amiri retweeted
Congratulations to Assistant Professor and Director Ali Mahdavi-Amiri on being named a recipient of the CHCCS 2026 Early Career Researcher Award (Graphics)!
Learn more about his research here: ow.ly/SiXe50Z3jPs
Arash (Ali) Mahdavi Amiri retweeted
Excited to share our work accepted to #SIGGRAPH2026 ! Video generation models struggle with something few talk about: their transformations don't evolve smoothly. You get long boring stretches... then a sudden semantic jump where everything "catches up" at once.
I really like this work. It’s very insightful about how RoPE influences the attention mechanisms. Please read if you are interested.
Shared attention is a powerful way to transfer style in diffusion models: let tokens attend to a reference image, and the model can pick up stylistic cues.
⚠️ But in RoPE-based DiTs, this often breaks badly.
Instead of transferring style, the model starts copying the reference content.
In this work, Untwisting RoPE, we explore how positional bias and semantic understanding become twisted together in DiTs, and how frequency control can untwist them.
I don’t know if calls for war by Iranians abroad had any impact. But if you protested for war, speak up now too: demand an end to attacks on civilians and essential infrastructure. One can achieve the same thing without such massive destructions.
Arash (Ali) Mahdavi Amiri retweeted
That’s a wrap on #3DV2026! 🎬
It has been an incredible four days in Vancouver exploring the frontiers of 3D vision. 🍁
Thank you to all the organizers, sponsors, reviewers, speakers, and attendees who make this community so wonderful! 🎉
"They knows our position. We knows their position."
Foreign minister of the Islamic Republic, ladies and gentlemen.
This is the level of stupidity we are dealing with.
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
1
171
Arash (Ali) Mahdavi Amiri retweeted
SFU Computing Science is hosting 3DV 2026! Explore the future of innovation at the leading venue for 3D computer vision and graphics research!
#SFU CS will be presenting several papers, with Professors @ManolisSavva and @arash_mham serving as Conference General Chair and Program Chair respectively.
Register here: ow.ly/bSjV50XYgvQ
Very interesting!
Replying to @docmilanfar
I published this in a 1-pager:
P. Milanfar, “A Persian Folk Method of Figuring Interest”, Mathematics Magazine, vol. 69, no. 5, Dec. 1996
My late dad refused to be a co-author. But when it appeared, he printed it out, framed it, and hung it on the wall of the house 🙂
4/4
178
Arash (Ali) Mahdavi Amiri retweeted
صحبتهای احساسی مارک لوین، مجری محافظهکار سرشناس آمریکایی درباره اوضاع ایرانیان
@marklevinshow
@seanhannity
Arash (Ali) Mahdavi Amiri retweeted
The risk of AI for education is not students cheating in exams, it is people in general cheating themselves into believing they understand things they don’t.
I believe things will change for the better in Iran soon. I hope that in this new Iran, we can stand each other and try to live together peacefully. If you are a Muslim/Jew/Christian, or an atheist, we should all be able to tolerate each other. That’s how we grow as a nation.
Arash (Ali) Mahdavi Amiri retweeted
As millions of Iranians stand up for their freedom, the silence of Barack Obama, Joe Biden, John Kerry, Ben Rhodes, Wendy Sherman, Robert Malley, Jen Psaki and all the rest is deafening
Arash (Ali) Mahdavi Amiri retweeted
[1/4] Sync about it… 💭✨
Editing a portrait video yet keeping it fully synced with the original across the entire sequence.
Read more about Sync-LoRA: sagipolaczek.github.io/Sync-… 🚀
Arash (Ali) Mahdavi Amiri retweeted
Advances in 4D Representation: Geometry, Motion, and Interaction
Abstract (excerpt)
Instead of offering an exhaustive enumeration of many works, we take a more selective approach by focusing on representative works to highlight both the desirable properties and ensuing challenges of each representation under different computation, application, and data scenarios.
The main take-away message we aim to convey to the readers is how to select and then customize the appropriate 4D representations for their tasks. Organizationally, we separate the 4D representations based on three key pillars: geometry, motion, and interaction. Our discourse will not only encompass the most popular representations of today, such as neural radiance fields (NeRFs) and 3D Gaussian Splatting (3DGS), but also bring attention to relatively under-explored representations in the 4D context, such as structured models and long-range motions.
Throughout our survey, we will reprise the role of large language models (LLMs) and video foundational models (VFMs) in a variety of 4D applications, while steering our discussion towards their current limitations and how they can be addressed. We also provide dedicated coverage on what 4D datasets are currently available, as well as what is lacking, to drive the subfield forward.
Arash (Ali) Mahdavi Amiri retweeted
📢📢📢 "ASIA" @ #SIGGRAPHAsia2025. 😉
We segment 3D shapes into possibly non-semantic and non-text describable parts using only a few annotated in-the-wild images as references!
👉Project Page: sairajk.github.io/asia/
📄Paper: arxiv.org/abs/2509.24288
































