🚀 Medial Secures Investment on Shark Tank India - Fueling the Future of Professional Social Networking. 🔥

News

Pods

Back

Bhoop singh Gurjar

AI Deep Explorer | f... • 20d

Want to learn AI the right way in 2025? Don’t just take courses. Don’t just build toy projects. Look at what’s actually being used in the real world. The most practical way to really learn AI today is to follow the models that are shaping the industry — and read the technical papers that power them. That’s where you see what works in practice, not just theory. Here's a curated list of the most impactful language models technical paper: 1️⃣GPT Series (OpenAI) GPT-1 → Improving Language Understanding by Generative Pre-Training(2018) https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf GPT-2 → Language Models are Unsupervised Multitask Learners (2019) https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf GPT-3 → Language Models are Few-Shot Learners(2020) https://arxiv.org/abs/2005.14165 ChatGPT :Trained with RLHF – Reinforcement Learning from Human Feedback (Ouyang et al., 2022) https://arxiv.org/abs/2203.02155 GPT-4 → GPT-4 Technical Report (2023) https://cdn.openai.com/papers/gpt-4.pdf 2️⃣Claude (Anthropic) Constitutional AI: Harmlessness from AI Feedback (2022) https://arxiv.org/pdf/2212.08073 3️⃣Gemini (Google DeepMind) Gemini: A Family of Highly Capable Multimodal Models (2023) https://arxiv.org/abs/2312.11805 Start building with Gemini 2.5 Flash(2025) https://developers.googleblog.com/en/start-building-with-gemini-25-flash/ 4️⃣Gemma (Google) Gemma: Open Models for Responsible AI(2024) https://arxiv.org/abs/2403.08295 Gemma 3 Technical Report(2025) https://arxiv.org/abs/2503.19786 5️⃣LLaMA Series (Meta AI) LLaMA: Open and Efficient Foundation Language Models(2023) https://arxiv.org/abs/2302.13971 LLaMA 2: Improved training and safety (2023) https://arxiv.org/pdf/2307.09288 Llama 3:The Llama 3 Herd of Models https://arxiv.org/abs/2407.21783 Llama 4:The beginning of a new era of natively multimodal AI innovation https://ai.meta.com/blog/llama-4-multimodal-intelligence/ 6️⃣Mistral AI(France) Mistral 7B: Grouped-query attention (2023) https://arxiv.org/abs/2310.06825 7️⃣Kimi by Moonshot AI (China) Scaling RL with LLMs: Technical Report of Kimi k1.5 (2025) https://arxiv.org/abs/2501.12599 8️⃣DeepSeek(China) DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models https://arxiv.org/abs/2402.03300 DeepSeek-V3 Technical Report (2024) https://arxiv.org/pdf/2412.19437 DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning https://arxiv.org/abs/2501.12948 9️⃣Qwen (China) Qwen Technical Report(2023) https://arxiv.org/pdf/2309.16609 Qwen2 Technical Report(2024) https://arxiv.org/pdf/2407.10671 Qwen2.5 Technical Report(2024) https://arxiv.org/pdf/2412.15115 Qwen2.5-Omni Technical Report Multimodel (2025) https://arxiv.org/pdf/2503.20215 Keep exploring, keep growing, and always give back!

0 replies9 likes

Recommendations from Medial

DK
•

Ride • 1y

https://arxiv.org/pdf/2404.07143.pdf Google has dropped possibly THE most important and future defining AI paper under 12 pages. Models can now have infinite context.

2 replies7 likes

ProgrammerKR

Founder & CEO of Pro... • 1m

Meta Unleashes Llama 4 AI Models Meta has officially launched its Llama 4 large language models, reinforcing its push into advanced AI systems and competing head-on with OpenAI and Google. #AI #MachineLearning #Meta #Llama4 #TechInnovation

0 replies4 likes

Sweekar Koirala

startups, technology... • 9m

Meta has introduced the Llama 3.1 series of large language models (LLMs), featuring a top-tier model with 405 billion parameters, as well as smaller variants with 70 billion and 8 billion parameters. Meta claims that Llama 3.1 matches the performance

1 replies4 likes

Anonymous

Hey I am on Medial • 9m

Huge announcement from Meta. Welcome Llama 3.1🔥 This is all you need to know about it: The new models: - The Meta Llama 3.1 family of multilingual large language models (LLMs) is a collection of pre-trained and instruction-tuned generative models

1 replies4 likes

Mohit Singh

18yo ✨ #developer le... • 1y

Meta's Llama 3 model scales open language models, boasting improved performance and various sizes. With a focus on addressing fatigue, it utilizes diverse training methods and achieves impressive results, strengthening the open LLM ecosystem

0 replies3 likes

SamCtrlPlusAltMan
•

OpenAI • 3m

AI TOOLS TO CHECKOUT 🥒 Pickle: Your AI body double for video calls. https://getpickle.ai/ 🦙 Prompt Llama: Gather high-quality text-to-image prompts and test the performance of different models with the same prompts. https://prompt-llama.com/ 🤖

2 replies9 likes

Parampreet Singh

Python Developer 💻 ... • 2m

3B LLM outperforms 405B LLM 🤯 Similarly, a 7B LLM outperforms OpenAI o1 & DeepSeek-R1 🤯 🤯 LLM: llama 3 Datasets: MATH-500 & AIME-2024 This has done on research with compute optimal Test-Time Scaling (TTS). Recently, OpenAI o1 shows that Test-

1 replies5 likes

Inactive

AprameyaAI • 9m

Meta has released Llama 3.1, the first frontier-level open source AI model, with features such as expanded context length to 128K, support for eight languages, and the introduction of Llama 3.1 405B. The model offers flexibility and control, enabli

0 replies9 likes

Vaibhav Babruwan Shingde

Student • 1y

Good Morning Everyone 🔆, Do you think that, Elon Musk's Grok Model is going to be big competition for models like GPT-4,Claude Models Sonet/Optus, Google's Gemini Model or Grok is lagging behind the competition? According to me, making a Model publ

4 replies8 likes

Haran Naresh K

Developer in trainin... • 9m

🚀 Breaking News: Meta Unleashes Its Biggest Open-Source AI Model Yet – Llama 3.1 with 405 Billion Parameters!Meta has taken a giant leap forward in AI development by releasing Llama 3.1, their most powerful open-source AI model to date, boasting an