Developing #causal #tensor framework -TensorFaces, Human Motion Signatures | Alumna @MIT, @UofT | #womenwhocode
Joined April 2009
- Tweets 6,480
- Following 1,568
- Followers 2,428
- Likes 16,901
1,047 Photos and videos
Pinned Tweet
May 10
If your empathy gives you permission to silence dissent, create blacklists, assassinate careers, ruin lives, or kill concrete human beings, it is not empathy.
It is cruelty with better PR.
(The ends do not justify the means.)
1
1
3
271
M. Alex O. Vasilescu retweeted
Jensen Huang, Founder and CEO of @NVIDIA, reflects on the connection between the immigrant experience and the entrepreneurial mindset.
He speaks with @CondoleezzaRice about why America offers an unmatched opportunity to turn ambition into achievement: youtu.be/ZEL0EAVtCTY
Jun 10
Today, @NVIDIA is widely recognized as the most consequential technology company in the world. But when Founder and CEO Jensen Huang hatched the idea more than three decades ago, it was viewed as little more than an incredibly risky bet on a new approach to computing.
How did Huang, an immigrant from working class roots in Taiwan, build this company into what it is today? In the first installment of the Hoover Institution's Only in America series, @CondoleezzaRice sits down with Huang to explore why his rise—and that of NVIDIA—couldn't have happened anywhere else.
04:42 Jensen Huang's journey to the US
07:54 Jensen's experience at boarding school in Kentucky
14:23 How Jensen came to Silicon Valley
17:23 Founding NVIDIA
23:40 The evolution and growth of NVIDIA
27:08 Sustaining motivation amid challenges
29:01 America's exceptional tech sector
32:28 Why Huang is a "cautious optimist" on AI
35:10 Jensen Huang's Only in America story
4
7
25
8,967
M. Alex O. Vasilescu retweeted
Jun 13
🥇 CVPR BEST PAPER: D4RT 🏆
• New state of the art across 4D reconstruction tasks
• One transformer encodes a video into a global scene representation that a lightweight decoder reads to jointly infer depth, motion, and camera.
• You can query the 3D position of any pixel at any time independently — skipping dense decoding and making it fast and scalable.
3
17
127
8,247
M. Alex O. Vasilescu retweeted
#LLM are a Revolution in Library Science!
They are an automated management systems for human records that can interpolate and extrapolate. Current #AI does not create new explanatory conceptual schemas. It operates based on inherited schemas.
#causality #tensors #statistics #ML #xAI
2
1
4
322
M. Alex O. Vasilescu retweeted
Jun 13
When software hallucinates, call it consciousness.
When accountability arrives, call for regulation.
----
It is much more glamorous for a CEO to testify before Congress about "safeguarding the future of conscious digital life" than it is to answer why their product hallucinates false medical advice.
1
68
M. Alex O. Vasilescu retweeted
Jun 11
#AISafety Safeguards or Completive Sabotage?
""Anthropic's powerful new models deliberately become less helpful when they detect users are working on AI research, according to technical disclosures that are already sparking controversy across the industry.
In a system card for Mythos 5 and Fable 5 published Tuesday, Anthropic said it limited the models' usefulness for tasks related to developing frontier large language models.
The company said the measures stem from concerns that advanced AI systems could accelerate the development of competing models without equivalent safety protections.
Unlike safeguards used for cybersecurity, biology, or chemistry-related risks, Anthropic said these interventions are intentionally invisible to users. Rather than refusing requests or switching to another model, Mythos may subtly modify its responses through techniques such as altering user prompts.
...."
1
1
1
201
M. Alex O. Vasilescu retweeted
Absolutely packed at
It’s Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models
tldr: recover diversity in trained
T2I diffusion models w/o retraining by optimizing noise latents directly
#CVPR2026
@annekharrington @ASophiaKoepke @ShyamgopalKart1
10
75
6,891
M. Alex O. Vasilescu retweeted
Very nice work from @KadirYilmaz_CV. A fully Transformer-based 3D encoder that removes the need for sparse convolutions and their (painful) dependencies.
Apr 22
Could this be the ViT moment for 3D scene understanding? 🚀
We revisit the good old Transformer architecture and apply it to 3D scene understanding with minimal modifications. #Volt ⚡️
Project page: yilmazkadir.github.io/Volt/
Arxiv link: arxiv.org/abs/2604.19609
(1/5)
2
10
92
10,964
M. Alex O. Vasilescu retweeted
Jun 3
After a few years of heads down building @Waabi_ai , I’m back at @CVPR !
Come and chat after my talks today:
→ 10:35 AM: Deployment of Foundation Models for Embodied AI: wdfm-eai.github.io/CVPR26/
→ 4:30 PM: Workshop on Autonomous Driving: cvpr2026.wad.vision/
This community has always pushed the frontier of what's possible in computer vision and AI and these conversations have never felt more relevant.
if you're looking to work on the most exiting problems in PhysicalAI, we are hiring: waabi.ai/cvpr-2026
2
10
33
1,607
M. Alex O. Vasilescu retweeted
CONGRATULATIONS to our GRASP Lab members on receiving BOTH the ICRA 2026 Best Paper Award on Planning and Control AND the Best Conference Paper Award!!!
#GRASP #GRASPLab #ICRA2026 #BestPaper
1
5
48
3,526
M. Alex O. Vasilescu retweeted
Jun 3
@DerekHoiem_UofI prediction of our next bitter lesson!
Jun 2
Start your #CVPR2026 with a coffee and some hard truths ☕
Tomorrow morning, we're talking 'Bitter Lessons' -- hard-won wisdom our field has accumulated but rarely discusses
Come be part of a candid conversation👇
sites.google.com/view/Bitter…
Wed, 8:45am, Four Seasons Ballroom 4
2
7
41
6,495
M. Alex O. Vasilescu retweeted
Jun 4
After the break (all bigmacs have been eaten), we continue with @HildeKuehne on RL for MLLMs. First VOLD, how reasoning capabilities can be transferred from text-only LLMs to MLLMs without using image data, super cool work. Also for reasoning with other modalities like audio. Finally test-time RL for video.
Her work really shows what we can get by taking innovations from LLM space to CV.
3
18
1,175
M. Alex O. Vasilescu retweeted
We have @dana_arad4 talking now. We are super excited !!!
Come catch her talk at room EF in milehigh ballroom
1
4
7
608
M. Alex O. Vasilescu retweeted
One hour to go: join us in mile high 4AB for AI for Visual Arts Workshop and Challenges at 8:30 AM. You won’t want to miss this with the keynotes, orals and posters we have selected. @CVPR
5
9
1,403
M. Alex O. Vasilescu retweeted
Jun 4
Georgia Gkioxari in room 111 now presenting at MULA workshop
1
3
15
1,193
M. Alex O. Vasilescu retweeted
we got the best paper award at the @CogVLWorkshop 🧠!!
but what made me happier was this photo with almost all authors!!
it's not often that people from so many different places come together, at the same time, and taking photo together like this 🥹
thank youu @CVPR #CVPR2026❤️
relsim has been accepted to #CVPR 2026; yay!!
hope to see you in Denverr
thaoshibe.github.io/relsim/
4
5
54
6,482
M. Alex O. Vasilescu retweeted
3
7
1,469
M. Alex O. Vasilescu retweeted
Jun 3
Just arrived at Denver for CVPR!
I will be presenting LoGeR at e2e3d.github.io/poster.html 5pm today and 4dvisionworkshop.github.io 4:30pm tomorrow (oral talk). Stop by if you are interested!
1
3
42
2,347
✈️ Denver bound for #CVPR2026!
Bringing a set of projects pushing toward interactive embodied agents: spanning dexterous bimanual motion, generative priors for whole-body control, and humanoid sim-to-real.
Looking forward to conversations, questions, and new ideas! Here’s where to find me:
InterPrior
🔗 sirui-xu.github.io/InterPrio…
🕟 Jun 6 (Sat), 16:15–18:45
📍 ExHall A & F 194
HandX
🔗 handx-project.github.io/
🕥 Jun 5 (Fri), 10:15–12:45
📍 ExHall A & F 210
I’ll also be around several workshops, including:
Spotlight Talk @ H2R
🔗 agents-in-interactions.githu…
🕝 Jun 4 (Thu), 15:00–15:15
📍 Mile High 2A
Come say hi! 🚀
1
15
85
5,627
M. Alex O. Vasilescu retweeted
Jun 4
Noah Snavely @Jimantha is currently giving a talk at the 4D Vision workshop! Happening at room 506.
Jun 2
The 2nd 4D Vision Workshop at CVPR is happening this Thursday afternoon in Room 506!
Come join us to see the latest progress in modeling the dynamic world. Looking forward to seeing you there! #CVPR2026 #CVPR
2
3
24
4,170