Felipe Ferreira @feliferrgo

AI Researcher at https://t.co/MWMcoX32Ey | PhD Student at PUC-Rio linkedin.com/in/feliferr Rio de Janeiro, Brazil Joined October 2009

Tweets

302
Followers

115
Following

219
Likes

2K

ICLR 2026 @iclr_conf

a month ago

ICLR 2026 will take place in 📍Rio de Janeiro, Brazil 📅 April 23–27, 2026 Save the date - see you in Rio! #ICLR2026

9 100 1K 81K 144

Download Image

If you're getting into LLMs, PyTorch is essential. And lot of folks asked for beginner-friendly material, so I put this together: PyTorch in One Hour: From Tensors to Multi-GPU Training (sebastianraschka.com/teaching/pytor…) 📖 ~1h to read through 💡 Maybe the perfect weekend project!? I’ve…

49 433 3K 145K 4K

elvis @omarsar0

3 months ago

Future of Work with AI Agents Stanford's new report analyzes what 1500 workers think about working with AI Agents. What types of AI Agents should we build? A few surprises! Let's take a closer look:

28 286 2K 298K 3K

Download Image

elvis @omarsar0

6 months ago

Thinking Machines: A Survey of LLM-based Reasoning Strategies Great survey to catch up on LLM-based reasoning strategies. It provides an overview and comparison of existing reasoning techniques and presents a systematic survey of reasoning-imbued language models.

8 129 651 68K 698

Download Image

Avi Chawla @_avichawla

6 months ago

Generative vs. discriminative models in ML: Generative models: - learn the distribution so they can generate new samples. - possess discriminative properties—we can use them for classification. Discriminative models don't have generative properties.

5 160 786 51K 569

Download Image

Avi Chawla @_avichawla

7 months ago

Transformer vs. Mixture of Experts in LLMs, clearly explained (with visuals):

32 217 2K 517K 3K

Math Cafe @Riazi_Cafe_en

7 months ago

MIT's "Matrix Calculus for Machine Learning" 🗒️Lecture Notes: ocw.mit.edu/courses/18-s09… 📽️Lecture Videos: youtube.com/playlist?list=…

1 158 873 34K 697

Download Image

Valeriy M., PhD, MBA, CQF @predict_addict

7 months ago

Step-by-Step Diffusion: An Elementary Tutorial

5 120 645 37K 644

Download Image

Aran Komatsuzaki @arankomatsuzaki

7 months ago

Apple presents: Distillation Scaling Laws Presents a distillation scaling law that estimates distilled model performance based on a compute budget and its allocation between the student and teacher

16 205 1K 134K 1K

Download Image

AmishMagic @MagicAmish

7 months ago

Like everyone, I've been a bit distracted exploring @deepseek_ai R1 and experimenting with it locally. I've spoken to a few people recently who don't know how to run local LLMs - this thread will cover a few different tools to get up and running easily.

61 842 6K 759K 11K

Download Image

Akshay 🚀 @akshay_pachaar

8 months ago

DeepSeekV3, Gemini, Mixtral and many others are all Mixture of Experts (MoEs). But what exactly are MoEs? 🤔 A Mixture of Experts (MoE) is a machine learning framework that resembles a team of specialists, each adept at handling different aspects of a complex task. It's like…

16 211 867 74K 722

Download Image

Andrew Ng @AndrewYNg

10 months ago

Announcing new open-source Python package: aisuite! This makes it easy for developers to use large language models from multiple providers. When building applications I found it a hassle to integrate with multiple providers. Aisuite lets you pick a "provider:model" just by…

146 1K 6K 436K 4K

Download Image

AK @_akhaliq

a year ago

Tora Trajectory-oriented Diffusion Transformer for Video Generation Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based diffusion models for

1 37 185 26K 56

Download Video

zed @zmkzmkz

a year ago

it's 1:28AM and I just finished this abomination. fully illustrated toy calculation of 1 transformer layer. why would I make this? idk ask my thesis advisor, "not everyone knows how a transformer works, you have to give an example"

120 324 4K 404K 3K

Download Image

Dr. April Khademi, PEng @aprilkhademi

a year ago

I love this tutorial on the self-attention mechanism used in transformers. It shows how all matrices are computed, along with the matrix sizes and code to implement it. sebastianraschka.com/blog/2023/self…

6 90 320 35K 365

Akshay 🚀 @akshay_pachaar

2 years ago

What is a Mixture-of-Experts (MoE)? A Mixture of Experts (MoE) is a machine learning framework that resembles a team of specialists, each adept at handling different aspects of a complex task. It's like dividing a large problem into smaller, more manageable parts and assigning…

13 188 919 78K 775

Download Image

Sumit @_reachsumit

2 years ago

Is Cosine-Similarity of Embeddings Really About Similarity? Netflix cautions against blindly using cosine similarity as a measure of semantic similarity between learned embeddings, as it can yield arbitrary and meaningless results. 📝arxiv.org/abs/2403.05440

28 385 2K 373K 2K

Download Image

Saining Xie @sainingxie

2 years ago

Here's my take on the Sora technical report, with a good dose of speculation that could be totally off. First of all, really appreciate the team for sharing helpful insights and design decisions – Sora is incredible and is set to transform the video generation community. What we…

42 533 3K 1.3M 2K

Download Image

Jon Barron @jon_barron

2 years ago

We just finished a joint code release for CamP (camp-nerf.github.io) and Zip-NeRF (jonbarron.info/zipnerf/). As far as I know, this code is SOTA in terms of image quality (but not speed) among all the radiance field techniques out there. Have fun! github.com/jonbarron/camp…

22 150 910 195K 494

Download Video

Gedas Bertasius @gberta227

2 years ago

What makes modern Video-Language (VidL) perform well? Check out our #CVPR2023 paper "VindLU: A Recipe for Effective Video-and-Language Pretraining" where we demystify the most critical factors in the VidL model design. klauscc.github.io/vindlu.html @fncheng2333 @jayleicn @mohitban47