डेटाबेस अनुभाग · 12 records
रिसर्च
The papers the modern stack is built on — from the transformer to scaling laws, RLHF and reasoning models.
फील्ड नोट्स
एक दर्जन PDF एक ट्रिलियन डॉलर के इन्फ्रास्ट्रक्चर की नींव हैं। ये वे papers हैं जहाँ विचार पहली बार सामने आए — अधिकांश हैरानी की हद तक पठनीय हैं, और यहाँ हर रिकॉर्ड आपको बिना गणित के बताता है कि क्या मायने रखा।
इन तीन से शुरू करें
AI
Attention Is All You Need (2017)
आठ लेखक, एक आर्किटेक्चर, और तब से सब कुछ।
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
वह सुधार जिसने हर model के ट्रेनिंग के तरीके को बदल दिया।
DR
DeepSeek-R1 — Reasoning via RL (2025)
reasoning की खुली रेसिपी — जब प्रतिद्वंद्वियों ने अपनी गुप्त रखी, तब प्रकाशित।
Foundational papers
12
AI
Attention Is All You Need (2017)
The eight Google authors who invented the transformer.
A(
AlexNet (2012)
The ImageNet result that started the deep-learning era — on two gaming GPUs.
CA
Constitutional AI (2022)
Anthropic's method: models critique themselves against written principles.
DR
DeepSeek-R1 — Reasoning via RL (2025)
The open recipe for reasoning models — a Nature cover, from a hedge fund's lab.
DD
Denoising Diffusion Probabilistic Models (2020)
The DDPM paper behind every image and video generator.
F(
FlashAttention (2022)
The kernel trick that made long context affordable.
HA
Highly Accurate Protein Structure Prediction (2021)
AlphaFold 2 in Nature — the result that won a Nobel.
I—
InstructGPT — RLHF at Scale (2022)
How raw language models became assistants people can use.
LM
Language Models are Few-Shot Learners (2020)
The GPT-3 paper: capability from scale, tasks from prompts.
LL
LoRA: Low-Rank Adaptation (2021)
Fine-tuning for the GPU-poor — tiny adapters instead of full weights.
SL
Scaling Laws for Neural Language Models (2020)
Kaplan et al.: loss falls as a power law in compute — the investment thesis, quantified.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
DeepMind's correction: most models were undertrained on data.