Ji Lin's PhD Defense, Efficient Deep Learning Computing: From TinyML to Large Language Model. @MIT

Ji Lin's PhD Defense, Efficient Deep Learning Computing: From TinyML to Large Language Model. @MIT
Share:

Download MP3


Similar Tracks

TinyChat Computer running Llama2-7B Jetson Orin Nano. Key technique: AWQ 4bit quantization. MIT HAN Lab
MIT PhD Defense: Practical Engineering Design Optimization w/ Computational Graph Transformations Peter Sharpe
Learning, Reasoning, and Planning with Neuro-Symbolic Concepts–Jiayuan Mao (MIT) Paul G. Allen School
A Hackers' Guide to Language Models Jeremy Howard
Trends in Deep Learning Hardware: Bill Dally (NVIDIA) Paul G. Allen School
Cybersecurity Architecture: Five Principles to Follow (and One to Avoid) IBM Technology
MIT Introduction to Deep Learning (2024) | 6.S191 Alexander Amini
Andrew Ng Explores The Rise Of AI Agents And Agentic Reasoning | BUILD 2024 Keynote Snowflake Inc.
HPCA 2025 | LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications MIT HAN Lab
LSTM is dead. Long Live Transformers! Seattle Applied Deep Learning
An introduction to Policy Gradient methods - Deep Reinforcement Learning Arxiv Insights
MIT Robotics - Robotics Worldwide Workshop MIT Robotics
Transformers (how LLMs work) explained visually | DL5 3Blue1Brown
What We See & What We Value, Prof. Fei-Fei Li Symposia at CSAIL
Jeff Dean (Google): Exciting Trends in Machine Learning Rice Ken Kennedy Institute
But what are Hamming codes? The origin of error correction 3Blue1Brown
AWQ for LLM Quantization MIT HAN Lab
EfficientML.ai Lecture 9 - Knowledge Distillation (MIT 6.5940, Fall 2023) MIT HAN Lab
Let's build GPT: from scratch, in code, spelled out. Andrej Karpathy
AI and Opportunity MIT Shaping the Future of Work Initiative