Victor Escorcia
@escorciav.bsky.social
Father. AI Freelancer @ 🇮🇹. Ph.D. @KAUST_AEx. @AdobeResearch @Qualcomm_EU @samsungresearch Wandering Caribbean 🇨🇴, ☮️❤️❌⚔️
😂 at this pace we will get a AGI fruto di bosco 🍓🫐...
"The car wash is only 50m from my house. I want to get my car washed. Should I walk or drive there?"
Credits to @giffmana.ai ...
"The car wash is only 50m from my house. I want to get my car washed. Should I walk or drive there?"
Credits to @giffmana.ai ...
February 13, 2026 at 3:11 AM
😂 at this pace we will get a AGI fruto di bosco 🍓🫐...
"The car wash is only 50m from my house. I want to get my car washed. Should I walk or drive there?"
Credits to @giffmana.ai ...
"The car wash is only 50m from my house. I want to get my car washed. Should I walk or drive there?"
Credits to @giffmana.ai ...
@ziv_ravid 1/2 🧵
"Mat is right that something big is happening. But the examples, lawyers, analysts, managers, are elite knowledge work. That's maybe 20% of jobs.
Most work ...
"Mat is right that something big is happening. But the examples, lawyers, analysts, managers, are elite knowledge work. That's maybe 20% of jobs.
Most work ...
February 12, 2026 at 8:36 PM
Reposted by Victor Escorcia
Our grad-level "Deep Learning" course (MIT's 6.7960) is now freely available online through OpenCourseWare: ocw.mit.edu/courses/6-79...
Lecture videos, psets, and readings are all provided.
Had a lot of fun teaching this with @sarameghanbeery.bsky.social and @jeremybernste.in!
Lecture videos, psets, and readings are all provided.
Had a lot of fun teaching this with @sarameghanbeery.bsky.social and @jeremybernste.in!
February 11, 2026 at 5:52 PM
Our grad-level "Deep Learning" course (MIT's 6.7960) is now freely available online through OpenCourseWare: ocw.mit.edu/courses/6-79...
Lecture videos, psets, and readings are all provided.
Had a lot of fun teaching this with @sarameghanbeery.bsky.social and @jeremybernste.in!
Lecture videos, psets, and readings are all provided.
Had a lot of fun teaching this with @sarameghanbeery.bsky.social and @jeremybernste.in!
Reposted by Victor Escorcia
Knowing which questions to ask is often the hardest part of science. Today we're releasing AutoDiscovery in AstaLabs, an AI system that starts with your data and generates its own hypotheses. 🧪
February 12, 2026 at 4:06 PM
Knowing which questions to ask is often the hardest part of science. Today we're releasing AutoDiscovery in AstaLabs, an AI system that starts with your data and generates its own hypotheses. 🧪
Am I the only one curious to hear from a #CVPR2026 AC how many papers (s)he is considering to reject based on the claim below?
Hit ❤️ &/Or 🔁 who knows perhaps @cvprconference.bsky.social PCs will disclose such stats during the event 😉
Hit ❤️ &/Or 🔁 who knows perhaps @cvprconference.bsky.social PCs will disclose such stats during the event 😉
#KostasThoughts: The ends don’t justify the means. Simply achieving state-of-the-art results is not grounds for acceptance. Claims and methods must also be coherent.
February 12, 2026 at 8:31 PM
Am I the only one curious to hear from a #CVPR2026 AC how many papers (s)he is considering to reject based on the claim below?
Hit ❤️ &/Or 🔁 who knows perhaps @cvprconference.bsky.social PCs will disclose such stats during the event 😉
Hit ❤️ &/Or 🔁 who knows perhaps @cvprconference.bsky.social PCs will disclose such stats during the event 😉
Reposted by Victor Escorcia
Introducing MolmoSpaces, a large-scale, fully open platform + benchmark for embodied AI research. 🤖
230k+ indoor scenes, 130k+ object models, & 42M annotated robotic grasps—all in one ecosystem.
230k+ indoor scenes, 130k+ object models, & 42M annotated robotic grasps—all in one ecosystem.
February 11, 2026 at 7:47 PM
Introducing MolmoSpaces, a large-scale, fully open platform + benchmark for embodied AI research. 🤖
230k+ indoor scenes, 130k+ object models, & 42M annotated robotic grasps—all in one ecosystem.
230k+ indoor scenes, 130k+ object models, & 42M annotated robotic grasps—all in one ecosystem.
Reposted by Victor Escorcia
Need a crash course on the fundamental concepts and algorithms of machine learning?
Consider visiting Genoa 🇮🇹 this summer for the MaLGa Machine Learning Crash Course!
Suitable for undergrad/grad students, as well as professionals.
📅 June 15-19
📍 MaLGa Center, Genova 🇮🇹
🔗 https://bit.ly/4rddwRq
Consider visiting Genoa 🇮🇹 this summer for the MaLGa Machine Learning Crash Course!
Suitable for undergrad/grad students, as well as professionals.
📅 June 15-19
📍 MaLGa Center, Genova 🇮🇹
🔗 https://bit.ly/4rddwRq
February 11, 2026 at 4:21 PM
Need a crash course on the fundamental concepts and algorithms of machine learning?
Consider visiting Genoa 🇮🇹 this summer for the MaLGa Machine Learning Crash Course!
Suitable for undergrad/grad students, as well as professionals.
📅 June 15-19
📍 MaLGa Center, Genova 🇮🇹
🔗 https://bit.ly/4rddwRq
Consider visiting Genoa 🇮🇹 this summer for the MaLGa Machine Learning Crash Course!
Suitable for undergrad/grad students, as well as professionals.
📅 June 15-19
📍 MaLGa Center, Genova 🇮🇹
🔗 https://bit.ly/4rddwRq
@ziv_ravid 1/2 🧵
"Mat is right that something big is happening. But the examples, lawyers, analysts, managers, are elite knowledge work. That's maybe 20% of jobs.
Most work ...
"Mat is right that something big is happening. But the examples, lawyers, analysts, managers, are elite knowledge work. That's maybe 20% of jobs.
Most work ...
February 12, 2026 at 7:13 AM
@ziv_ravid 1/2 🧵
"Mat is right that something big is happening. But the examples, lawyers, analysts, managers, are elite knowledge work. That's maybe 20% of jobs.
Most work ...
"Mat is right that something big is happening. But the examples, lawyers, analysts, managers, are elite knowledge work. That's maybe 20% of jobs.
Most work ...
Reposted by Victor Escorcia
We're pleased to share that the much awaited Anny-One dataset is now available!
Download ➡️ tinyurl.com/anny-one
*⃣ 800K images
🚀Multi-view & multi-person
🏠Indoor 3D scenes
📷Wild cameras
🔥Anny format! github.com/naver/anny
Download ➡️ tinyurl.com/anny-one
*⃣ 800K images
🚀Multi-view & multi-person
🏠Indoor 3D scenes
📷Wild cameras
🔥Anny format! github.com/naver/anny
February 10, 2026 at 11:27 AM
We're pleased to share that the much awaited Anny-One dataset is now available!
Download ➡️ tinyurl.com/anny-one
*⃣ 800K images
🚀Multi-view & multi-person
🏠Indoor 3D scenes
📷Wild cameras
🔥Anny format! github.com/naver/anny
Download ➡️ tinyurl.com/anny-one
*⃣ 800K images
🚀Multi-view & multi-person
🏠Indoor 3D scenes
📷Wild cameras
🔥Anny format! github.com/naver/anny
Reposted by Victor Escorcia
LLMs often generate step-by-step instructions, from real-world tasks (how do I file taxes?) to plans for AI agents. Improving this is hard: outputs can sound fluent for steps that don't work, and current datasets cover few domains.
How2Everything evals/trains for this at scale. 🧵
How2Everything evals/trains for this at scale. 🧵
February 10, 2026 at 4:53 PM
LLMs often generate step-by-step instructions, from real-world tasks (how do I file taxes?) to plans for AI agents. Improving this is hard: outputs can sound fluent for steps that don't work, and current datasets cover few domains.
How2Everything evals/trains for this at scale. 🧵
How2Everything evals/trains for this at scale. 🧵
Reposted by Victor Escorcia
📣 Upcoming Workshop! Join the ELIAS, ELLIOT & ENFIELD TDW on Trustworthy AI to explore the technical, ethical, & environmental challenges of deploying reliable, fair, and sustainable AI systems.
📅 Mar 6
📍 Paris/Hybrid
🔗 https://bit.ly/4bMMiME
@elliot-eu.bsky.social · @horizonenfield.bsky.social
📅 Mar 6
📍 Paris/Hybrid
🔗 https://bit.ly/4bMMiME
@elliot-eu.bsky.social · @horizonenfield.bsky.social
February 10, 2026 at 9:57 AM
📣 Upcoming Workshop! Join the ELIAS, ELLIOT & ENFIELD TDW on Trustworthy AI to explore the technical, ethical, & environmental challenges of deploying reliable, fair, and sustainable AI systems.
📅 Mar 6
📍 Paris/Hybrid
🔗 https://bit.ly/4bMMiME
@elliot-eu.bsky.social · @horizonenfield.bsky.social
📅 Mar 6
📍 Paris/Hybrid
🔗 https://bit.ly/4bMMiME
@elliot-eu.bsky.social · @horizonenfield.bsky.social
@KL_Div repost after @hanshengchen acknowledge a connection 1/4 🧵
"Thanks for pointing out the similarity between drifting and Implicit Maximum Likelihood Estimation!
I worked out the mathematical connection - the crux is that drifting fields are similar to the gradient of a soft version of the
"Thanks for pointing out the similarity between drifting and Implicit Maximum Likelihood Estimation!
I worked out the mathematical connection - the crux is that drifting fields are similar to the gradient of a soft version of the
Sergio Charles @eigentopology 1/10
"Thread: Drifting Models - The Math Behind Training-Time Evolution 🧵
New paradigm for generative modeling from Kaiming He's team. Let's break down the mathematics.
Paper: arxiv.org/abs/2602.04770
...
"Thread: Drifting Models - The Math Behind Training-Time Evolution 🧵
New paradigm for generative modeling from Kaiming He's team. Let's break down the mathematics.
Paper: arxiv.org/abs/2602.04770
...
Generative Modeling via Drifting
Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference...
arxiv.org
February 10, 2026 at 7:08 AM
@KL_Div repost after @hanshengchen acknowledge a connection 1/4 🧵
"Thanks for pointing out the similarity between drifting and Implicit Maximum Likelihood Estimation!
I worked out the mathematical connection - the crux is that drifting fields are similar to the gradient of a soft version of the
"Thanks for pointing out the similarity between drifting and Implicit Maximum Likelihood Estimation!
I worked out the mathematical connection - the crux is that drifting fields are similar to the gradient of a soft version of the
@isskoro 1/5 🧵
"The recent Drifting Models paper from Kaiming's group got very hyped as a new generative modeling paradigm, but it's basically a scaled-up/generalized version of 2015 GMMN (authors acknowledge this in App. C.2 — GMMN = Drifting for particular kernel). Very skeptical about
...
"The recent Drifting Models paper from Kaiming's group got very hyped as a new generative modeling paradigm, but it's basically a scaled-up/generalized version of 2015 GMMN (authors acknowledge this in App. C.2 — GMMN = Drifting for particular kernel). Very skeptical about
...
Sergio Charles @eigentopology 1/10
"Thread: Drifting Models - The Math Behind Training-Time Evolution 🧵
New paradigm for generative modeling from Kaiming He's team. Let's break down the mathematics.
Paper: arxiv.org/abs/2602.04770
...
"Thread: Drifting Models - The Math Behind Training-Time Evolution 🧵
New paradigm for generative modeling from Kaiming He's team. Let's break down the mathematics.
Paper: arxiv.org/abs/2602.04770
...
Generative Modeling via Drifting
Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference...
arxiv.org
February 10, 2026 at 6:53 AM
@isskoro 1/5 🧵
"The recent Drifting Models paper from Kaiming's group got very hyped as a new generative modeling paradigm, but it's basically a scaled-up/generalized version of 2015 GMMN (authors acknowledge this in App. C.2 — GMMN = Drifting for particular kernel). Very skeptical about
...
"The recent Drifting Models paper from Kaiming's group got very hyped as a new generative modeling paradigm, but it's basically a scaled-up/generalized version of 2015 GMMN (authors acknowledge this in App. C.2 — GMMN = Drifting for particular kernel). Very skeptical about
...
Today I woke up with a sentiment particularly from far right/left & against institutions 🇪🇺
😡🤬🙃
😡🤬🙃
February 10, 2026 at 6:41 AM
Today I woke up with a sentiment particularly from far right/left & against institutions 🇪🇺
😡🤬🙃
😡🤬🙃
Sergio Charles @eigentopology 1/10
"Thread: Drifting Models - The Math Behind Training-Time Evolution 🧵
New paradigm for generative modeling from Kaiming He's team. Let's break down the mathematics.
Paper: arxiv.org/abs/2602.04770
...
"Thread: Drifting Models - The Math Behind Training-Time Evolution 🧵
New paradigm for generative modeling from Kaiming He's team. Let's break down the mathematics.
Paper: arxiv.org/abs/2602.04770
...
Generative Modeling via Drifting
Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference...
arxiv.org
February 10, 2026 at 4:39 AM
Sergio Charles @eigentopology 1/10
"Thread: Drifting Models - The Math Behind Training-Time Evolution 🧵
New paradigm for generative modeling from Kaiming He's team. Let's break down the mathematics.
Paper: arxiv.org/abs/2602.04770
...
"Thread: Drifting Models - The Math Behind Training-Time Evolution 🧵
New paradigm for generative modeling from Kaiming He's team. Let's break down the mathematics.
Paper: arxiv.org/abs/2602.04770
...
(according to you) What's the most enticing driver behind humanity pursuing AGI?
📽️ Sci-fi
🧞♂️ Spiritual
🧪 Science & Eng ~= Maker
❌ None ~= nihilism/realism
💬 ...
📽️ Sci-fi
🧞♂️ Spiritual
🧪 Science & Eng ~= Maker
❌ None ~= nihilism/realism
💬 ...
February 10, 2026 at 3:17 AM
(according to you) What's the most enticing driver behind humanity pursuing AGI?
📽️ Sci-fi
🧞♂️ Spiritual
🧪 Science & Eng ~= Maker
❌ None ~= nihilism/realism
💬 ...
📽️ Sci-fi
🧞♂️ Spiritual
🧪 Science & Eng ~= Maker
❌ None ~= nihilism/realism
💬 ...
Reposted by Victor Escorcia
A bit late due to the flu 😅 but still very worth sharing: China open source highlights for January 2026🔥
huggingface.co/collections/...
huggingface.co/collections/...
2026 January⛄️ - China Open Source Highlights - a zh-ai-community Collection
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
February 9, 2026 at 10:04 PM
A bit late due to the flu 😅 but still very worth sharing: China open source highlights for January 2026🔥
huggingface.co/collections/...
huggingface.co/collections/...
📢 𝑪𝒂𝒍𝒍 𝒇𝒐𝒓 𝑷𝒂𝒑𝒆𝒓𝒔: @cvprconference.bsky.social 2026 Workshop on AI for Creative Visual Content Generation, Editing, and Understanding (CVEU)!
We are thrilled to invite submissions to the 9th installment of the CVEU workshop at CVPR 2026 in Denver!
We are thrilled to invite submissions to the 9th installment of the CVEU workshop at CVPR 2026 in Denver!
February 10, 2026 at 1:46 AM
📢 𝑪𝒂𝒍𝒍 𝒇𝒐𝒓 𝑷𝒂𝒑𝒆𝒓𝒔: @cvprconference.bsky.social 2026 Workshop on AI for Creative Visual Content Generation, Editing, and Understanding (CVEU)!
We are thrilled to invite submissions to the 9th installment of the CVEU workshop at CVPR 2026 in Denver!
We are thrilled to invite submissions to the 9th installment of the CVEU workshop at CVPR 2026 in Denver!
Reposted by Victor Escorcia
Bubble Crasher (S05E19)
February 9, 2026 at 2:17 PM
Bubble Crasher (S05E19)
Reposted by Victor Escorcia
I made a map of 3.4 million Bluesky users - see if you can find yourself!
bluesky-map.theo.io
I've seen some similar projects, but IMO this seems to better capture some of the fine-grained detail
bluesky-map.theo.io
I've seen some similar projects, but IMO this seems to better capture some of the fine-grained detail
Bluesky Map
Interactive map of 3.4 million Bluesky users, visualised by their follower pattern.
bluesky-map.theo.io
February 8, 2026 at 10:59 PM
I made a map of 3.4 million Bluesky users - see if you can find yourself!
bluesky-map.theo.io
I've seen some similar projects, but IMO this seems to better capture some of the fine-grained detail
bluesky-map.theo.io
I've seen some similar projects, but IMO this seems to better capture some of the fine-grained detail
Reposted by Victor Escorcia
I'm thinking of building a logged in version of the For You playground: linklonk.com/bluesky
It could have some personal stats and settings.
What would you like to see/do on that page?
It could have some personal stats and settings.
What would you like to see/do on that page?
Bluesky "For You" feed playground
linklonk.com
February 7, 2026 at 9:39 PM
I'm thinking of building a logged in version of the For You playground: linklonk.com/bluesky
It could have some personal stats and settings.
What would you like to see/do on that page?
It could have some personal stats and settings.
What would you like to see/do on that page?
@yaroslavvb.bsky.social 1/3 🧵
"People ask me what I think about AGI. I think modern AGI discourse defies the voice of reason. Thankful to 5-hour "walks" with Ian Goodfellow and Shubho Sengupta that motivated me to put this down, had a lot of fun writing this essay...
speakerdeck.com/yaroslavvb/g...
"People ask me what I think about AGI. I think modern AGI discourse defies the voice of reason. Thankful to 5-hour "walks" with Ian Goodfellow and Shubho Sengupta that motivated me to put this down, had a lot of fun writing this essay...
speakerdeck.com/yaroslavvb/g...
God_Gold_and_GPUs.pdf
speakerdeck.com
February 8, 2026 at 7:30 PM
@yaroslavvb.bsky.social 1/3 🧵
"People ask me what I think about AGI. I think modern AGI discourse defies the voice of reason. Thankful to 5-hour "walks" with Ian Goodfellow and Shubho Sengupta that motivated me to put this down, had a lot of fun writing this essay...
speakerdeck.com/yaroslavvb/g...
"People ask me what I think about AGI. I think modern AGI discourse defies the voice of reason. Thankful to 5-hour "walks" with Ian Goodfellow and Shubho Sengupta that motivated me to put this down, had a lot of fun writing this essay...
speakerdeck.com/yaroslavvb/g...
@JitendraMalikCV:
"It's great to see the excitement these days about world models and their applications in robotics. World models predate deep learning, and if you're curious, here's my history talk starting from Craik (1943) & Kalman (1960)"
www.youtube.com/watch?v=9B4k...
"It's great to see the excitement these days about world models and their applications in robotics. World models predate deep learning, and if you're curious, here's my history talk starting from Craik (1943) & Kalman (1960)"
www.youtube.com/watch?v=9B4k...
2748 Robust and Interactable World Models in Computer Vision
YouTube video by ComputerVisionFoundation Videos
www.youtube.com
February 8, 2026 at 6:07 AM
@JitendraMalikCV:
"It's great to see the excitement these days about world models and their applications in robotics. World models predate deep learning, and if you're curious, here's my history talk starting from Craik (1943) & Kalman (1960)"
www.youtube.com/watch?v=9B4k...
"It's great to see the excitement these days about world models and their applications in robotics. World models predate deep learning, and if you're curious, here's my history talk starting from Craik (1943) & Kalman (1960)"
www.youtube.com/watch?v=9B4k...
Reposted by Victor Escorcia
@mariaa.bsky.social and I have been building a custom client that we'd like to make public in the near-term BUT we want to make sure we've gotten the security right. Anyone with some expertise open to helping us out a bit?
February 8, 2026 at 3:34 AM
@mariaa.bsky.social and I have been building a custom client that we'd like to make public in the near-term BUT we want to make sure we've gotten the security right. Anyone with some expertise open to helping us out a bit?