lol, I think I helped design it, and I think it looks clowntown from the lens of Tensor padding. F.pad was written as a consolidation of all the vision padding — for padding images, videos, etc. It consolidated nn.ReflectionPad2d, etc. from torch7. But looking at it from the
MACHINE LEARNING
-
AI and Data Analytics Driving Manufacturing Efficiency
By
–
Data is the fuel for manufacturing. Unlock the power of AI, analytics, and scalable data strategies to drive efficiency. Here’s how: https://
buff.ly/puvZYsD #sponsored #highbyte_iiot #Industry40 @Fogoross @lucianilie15 -
Harvey Weinstein thanked more often than God at Oscars
By
–
Was Harvey Weinstein thanked more often than God at the Oscars? https://
buff.ly/nVWj8wA #AI #MachineLearning #DeepLearning #LLMs #DataScience -
AlexNet Released Open Source: The AI Model That Started It All
By
–
AlexNet, the AI model that started it all, released in source code form – for all to download It was the shot heard 'round the world – a neural network that finally fulfilled decades of theoretical promise. https://
zdnet.com/article/alexne
t-the-ai-model-that-started-it-all-released-in-source-code-form-for-all-to-download/
… @geoffreyhinton @ilyasut -
DAPO: Open-Source RL Training for Qwen2.5-32B LLMs
By
–
Reinforcement learning for LLMs—fully open-sourced DAPO trains Qwen2.5-32B with RL, hitting 50 points on AIME 2024, outperforming DeepSeek-R1-Zero after just 50% of the training steps. Open-source code & dataset
Improved training stability Trending #1 on alphaXiv -
Hugging Face 2024: Datasets and Tools Outpace Models Usage
By
–
For the first time in 2024 on @huggingface
:
– usage on datasets/spaces/papers > usage on models
– usage on all other domains > usage on text
– usage from AI builders (software engineers,…) > usage from AI scientists Slowly but surely becoming the platform that all AI builders -
AI Models Cannot Learn During Interactions: Debate Impact Analysis
By
–
The cognitive dissonance here is that these models don't learn during interactions. No online learning: it's literally the most fruitless debate you can imagine for its participants. The debate only has real impact in the minds of humans reading it, if they exist. https://
x.com/LiorOnAI/statu
/LiorOnAI/status/1903017981632020682
… -
Asynchronous RL Agents Learn Faster, Achieve Higher Returns
By
–
A not-so-surprising finding: with asynchronous RL, agents learn faster and achieve significantly higher returns. Still, it's nice to see it empirically verified.
-
Stanford’s Gaussian Atlas: 3D Scene Representation Breakthrough
By
–
Project Page: https://
cs.stanford.edu/~xtiange/proje
cts/gaussianatlas/
…
Paper: https://
arxiv.org/abs/2503.15877 -
2D Diffusion Models Repurposed for 3D Object Generation
By
–
A team led by Dr. Li Fei-Fei @drfeifei found that pre-trained 2D diffusion models can be repurposed for 3D object generation. Their proposed GaussianAtlas enables fine-tuning of 2D diffusion models to generate 3D Gaussians. pic.twitter.com/D2mvz52C08
— 机器之心 JIQIZHIXIN (@jiqizhixin) 21 mars 2025A team led by Dr. Li Fei-Fei @drfeifei found that pre-trained 2D diffusion models can be repurposed for 3D object generation. Their proposed GaussianAtlas enables fine-tuning of 2D diffusion models to generate 3D Gaussians.