Pedro Garcia @CKPYT

Researcher on Multimedia Technology. Interests: Computer Vision, QoE, and Immersive Media. Brazil Joined February 2010

Tweets

5K
Followers

616
Following

116
Likes

6K

philip @philiptorr

a month ago

not so often I do computer vision papers these days, great work from Ishi Deb

naveen manwani @NaveenManwani17

a month ago

not so often I do computer vision papers these days, great work from Ishi Deb

1 5 19 14K 17

Download Video

2 5 45 11K 19

"Some "AI experts" claim that "making CNNs work" was as important as inventing them. But "making them work" largely depended on whether your lab was rich enough to buy the latest computers required to scale up the original work." people.idsia.ch/~juergen/who-i…

0 0 1 41 1

Bojan Tunguz @tunguz

a month ago

I don’t see a problem.

230 216 3K 380K 779

Download Image

Peyman Milanfar @docmilanfar

2 months ago

The representer theorem is fundamental in ML - it states that for a broad class of optimization problems, the optimal solution can always be expressed as a linear combination of certain (kernel) functions of the training data. Why is it useful & where did it originate? 1/5

10 73 807 60K 721

Download Image

Santiago @svpino

2 months ago

I just met a person who can't tell Python from C++. He has never written a single line of code in his life, yet he feels he can build anything he wants. He told me point-blank: "I challenge you to tell me something I can't build using AI." I tried to explain, but I couldn't…

2K 845 18K 2.6M 3K

Peyman Milanfar @docmilanfar

2 months ago

faculty sending their PhD grads to industry

28 571 14K 424K 1K

Download Image

Deedy @deedydas

2 months ago

Huge computer science result: A Tsinghua professor JUST discovered the fastest shortest path algorithm for graphs in 40yrs. This improves on Turing award winner Tarjan’s O(m + nlogn) with Dijkstra’s, something every Computer Science student learns in college.

247 2K 22K 1.7M 13K

Download Image

Kai Fall @kai_fall

2 months ago

friendly reminder

115 1K 16K 700K 1K

Download Image

Shruti @heyshrutimishra

2 months ago

This paper didn’t go viral but it should have. A tiny AI model called HRM just beat Claude 3.5 and Gemini. It doesn’t even use tokens. They said it was just a research preview. But it might be the first real shot at AGI. Here’s what really happened and why OpenAI should be…

350 1K 10K 1.3M 12K

Download Image

Fenil Doshi @fenildoshi009

3 months ago

🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Humans can spot the difference instantly! The question is can vision models do the same? 1/15

5 122 607 72K 430

Download Gif

AK @_akhaliq

3 months ago

Mirage UGC Game Engine Powered by Real-Time World Model

71 169 1K 272K 659

Download Video

Pedro Garcia @CKPYT

3 months ago

A National Passion

out of context brazil 🇧🇷 @oocbrazill

3 months ago

A National Passion

319 2K 29K 1.3M 2K

Download Video

0 0 0 54 0

Peyman Milanfar @docmilanfar

3 months ago

If your PhD advisor dressed like this, you probably didn't use neural nets in your thesis

31 33 964 81K 66

Download Image

George Toderici @george_toderici

5 months ago

🚀 The 2025 Challenge on Learned Image Compression is live! Join us at the Picture Coding Symposium in Aachen for #CLIC2025 — where humans, not just metrics, judge image/video compression quality. 🏆 Leaderboards open June 1. Let the coding begin! Web: compression.cc

1 1 2 163 0

Download Image

Publishing with Integrity @fake_journals

5 months ago

The digital erosion of intellectual integrity: why misuse of generative AI is worse than plagiarism - AI & SOCIETY buff.ly/utMR3U9

2 6 13 976 6

Download Image

ICLR 2026 @iclr_conf

5 months ago

That's a wrap for #ICLR2025! See you all next year in Brazil! Please all welcome @BharathHarihar3 as the new Senior Program Chair! (With @cvondrick continuing on as General Chair.)

7 60 689 128K 45

Download Image

Erik Meijer @headinthebox

5 months ago

I am convinced we are doing AI coding wrong. Completely wrong in fact. Humans need abstraction and code reuse to reduce costs and manage complexity. That is not true for AIs however. They can just brute force things. No reuse and abstractions needed. So instead of trying to…

233 55 764 136K 432

Download Image

OpenAI @OpenAI

6 months ago

We’re releasing PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research, as part of our Preparedness Framework. Agents must replicate top ICML 2024 papers, including understanding the paper, writing code, and executing experiments.