Manjunath @_ssmanjunath

Joined January 2015

Tweets

218
Followers

149
Following

3K
Likes

1K

Sebastian Raschka @rasbt

7 months ago

Following up on my reasoning model article, I just read the new "s1: Simple Test-Time Scaling" paper, which describes an interesting method for improving reasoning models using a combination of pure supervised finetuning (SFT) and scaling inference compute. In short, their…

15 78 400 25K 274

Download Image

Ai2 @allen_ai

7 months ago

Here is Tülu 3 405B 🐫 our open-source post-training model that surpasses the performance of DeepSeek-V3! The last member of the Tülu 3 family demonstrates that our recipe, which includes Reinforcement Learning from Verifiable Rewards (RVLR) scales to 405B - with performance on…

153 377 2K 446K 678

Download Image

Jiayi Pan @jiayi_pirate

7 months ago

We reproduced DeepSeek R1-Zero in the CountDown game, and it just works Through RL, the 3B base LM develops self-verification and search abilities all on its own You can experience the Ahah moment yourself for < $30 Code: github.com/Jiayi-Pan/Tiny… Here's what we learned 🧵

194 1K 6K 1.7M 6K

Download Image

Philipp Schmid @_philschmid

8 months ago

For those trying to understand @deepseek_ai Group Relative Policy Optimization (GRPO). Here, in simple steps: 1️⃣ Generate multiple outputs for each prompt using the current policy 2️⃣ Score these outputs using a reward model (rule or outcome) 3️⃣ Average the rewards and use it as…

8 43 273 17K 190

Download Image

Sayak Paul @RisingSayak

9 months ago

Introducing a high-quality open-preference dataset to further this line of research for image generation. Despite being such an inseparable component for modern image generation, open preference datasets are a rarity! So, we decided to work on one with the community!

3 19 103 5K 34

Download Image

Yuchen Jin @Yuchenj_UW

9 months ago

The highest-scored paper at ICLR 2025 with full scores, 10, 10, 10, 10! The first time in ICLR history? IC-Light is designed to control image lighting. They managed to collect >10 million images for training illumination editing models, with amazing results on SDXL and Flux…

12 193 2K 214K 1K

Download Image

Devendra Chaplot @dchaplot

11 months ago

We just released Pixtral 12B paper on Arxiv: arxiv.org/abs/2410.07073

21 216 2K 88K 463

Download Image

Pedro Domingos @pmddomingos

11 months ago

Physicists think AI is physics. Statisticians think AI is statistics. Mathematicians think AI is mathematics. Psychologists think AI is psychology. Neuroscientists think AI is neuroscience. And they’re all right.

298 865 6K 352K 649

Qian Liu @sivil_taram

a year ago

📚Introduction to a new paper "Performance Law of Large Language Models"🤖 This paper presents a new empirical equation that directly predicts the performance (i.e., MMLU score) of LLMs by fitting a law on top of several hyper-parameters ⬇️. Leveraging❗️10 open-source models…

3 29 141 16K 101

Download Image

Gradio @Gradio

a year ago

🚀 Scribble SDXL ControlNet with Gradio ImageEditor component works like magic! Check out the model and cool Spaces👇

1 29 127 16K 96

Download Video

Philipp Schmid @_philschmid

a year ago

Llama 3 released! 🚨🔔@AIatMeta just released their best open LLM! 👑🚀 Llama 3 is the next iteration of Llama with a ~10% relative improvement to its predecessor! 🤯 Llama 3 comes in 2 different sizes 8B and 70B with a new extended tokenizer and commercially permissive license!…

6 62 259 27K 45

Download Image

clem 🤗 @ClementDelangue

a year ago

The new @MistralAI is now #1 on the openLLM leaderboard. Apache 2.0 license too! 🔥🔥🔥

11 69 442 78K 76

Download Image

Philipp Schmid @_philschmid

a year ago

New Instances, New Region, New Capabilities! 🧠 @Google Cloud is now generally available on @huggingface! 🤗 We are excited to launch @GoogleCloudTech as an official backend for Inference Endpoints, offering you more options to power your Generative AI applications. 🚀 🌍 New…

2 37 118 23K 34

Download Image

OpenAI @OpenAI

2 years ago

Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. openai.com/sora Prompt: “Beautiful, snowy…

9K 31K 133K 97.9M 36K

Download Video

Philipp Schmid @_philschmid

2 years ago

Code Llama 70B Instruct available in Hugging Chat! 💬 Try and experiment with @AIatMeta new Code Llama 70B for free in the @huggingface chat! 😍 👉 huggingface.co/chat?model=cod… Share your experience in this thread! 🤗

3 26 121 18K 32

Download Image

Santiago @svpino

2 years ago

You can now access AI directly from your database! Here is a step-by-step demo that uses GPT-4 to classify customer reviews from a MySQL dataset. And I'm only writing SQL instructions! You have to see it! The model acts as another table in the database. I can query it and join…

25 146 978 209K 1K

Download Video

Santiago @svpino

2 years ago

Another deep learning breakthrough: Deep TDA, a new algorithm using self-supervised learning, overcomes the limitations of traditional dimensionality reduction algorithms. t-SNE and UMAP have long been the favorites. Deep TDA might change that forever. Here are the details:

47 668 4K 1.1M 3K

Download Image

Aran Komatsuzaki @arankomatsuzaki

2 years ago

Training Diffusion Models with Reinforcement Learning Presents an RL-based framework for training denoising diffusion models to directly optimize a variety of reward functions arxiv.org/abs/2305.13301

1 14 54 7K 11

Download Image

Philipp Schmid @_philschmid

2 years ago

New open-source chat-GPT model alert! 🚨 @togethercompute released a new version of their chatGPT-NeoX 20B model with higher quality by fine-tuning on user feedback. 🚀🔥 Demo: huggingface.co/spaces/togethe… Model: huggingface.co/togethercomput…

4 88 435 86K 196

Download Image

Nikhil Kamath @nikhilkamathcio

2 years ago

Everyone I know who has visited a western economy in the last few months can't stop comparing how bleak everything is compared to #India. Incredible that Indian innovation could power critical backbones of foreign economies; kudos to the Indian govt and all involved in #UPI.