From Transformers to DeepSeek‑R1: The 2017‑2025 Evolution of Large Language Models

This article chronicles the rapid development of large language models from the 2017 Transformer breakthrough through the rise of BERT, GPT‑3, ChatGPT, multimodal systems like GPT‑4V/o, and the recent cost‑efficient DeepSeek‑R1, highlighting key architectural innovations, scaling trends, alignment techniques, and their transformative impact on AI research and industry.

AI AlignmentBERTCost‑Efficient Inference

0 likes · 26 min read

From Transformers to DeepSeek‑R1: The 2017‑2025 Evolution of Large Language Models

AI Frontier Lectures

May 9, 2025 · Artificial Intelligence

How Tiny Inference Model Tina Cuts Training Costs by 99.6% with LoRA‑RL

Researchers from ShanghaiTech and USC introduced the compact inference model Tina, which leverages low‑rank adaptation and reinforcement learning to achieve comparable or superior performance to large SOTA models while reducing post‑training and evaluation costs to just $9, a 99.6% savings over traditional approaches.

AICost‑Efficient Inferencelow-rank adaptation

0 likes · 12 min read

How Tiny Inference Model Tina Cuts Training Costs by 99.6% with LoRA‑RL

AI Frontier Lectures

Mar 7, 2025 · Artificial Intelligence

From Transformers to DeepSeek‑R1: Tracing the Evolution of Large Language Models (2017‑2025)

This article chronicles the rapid development of large language models from the 2017 Transformer breakthrough through successive milestones such as BERT, GPT‑3, ChatGPT, multimodal GPT‑4 variants, open‑weight releases, and the cost‑efficient DeepSeek‑R1, highlighting key architectural innovations, training paradigms, alignment techniques, and industry impact.

Cost‑Efficient InferenceModel AlignmentReasoning Models

0 likes · 27 min read

From Transformers to DeepSeek‑R1: Tracing the Evolution of Large Language Models (2017‑2025)