Understanding the Transformer Neural Network Model

Overview of the Transformer architecture: self-attention, multi-head attention, positional encoding, encoder-decoder stacks, and implications for distributed model training.

How Computer Systems Address Challenges of Large AI Models

Dr. Mao Yang examines how computer systems must evolve - ultra-large-scale computing, cloud redesign, and distributed systems - to support large models and next-gen AI

AI Infrastructure Drives Three Waves of Industrial Change

Technical overview of AI 2.0: how generative AI drives demand for large-scale compute, data pipelines, and Model-as-a-Service (MaaS) to enable industry deployments.

Popular LLM Inference Stacks and Setups

Survey of LLM inference stacks covering throughput, latency and cost; explains hardware constraints, KV cache, quantization, paged/grouped attention, and practical optimizations.

Practical Tricks for Reward Models

Technical overview of methods to improve reward model robustness for RLHF: quantify preference strength, flip/soften labels, apply adaptive margins, contrastive learning and MetaRM

Visualization Techniques for Machine Learning

Guide to machine learning visualization techniques covering model structure, performance plots (ROC, confusion matrix), feature importance, and practical analysis.

Survey of Deep Metric Learning

Survey of deep metric learning: formulations, sample selection and metric loss functions (contrastive, triplet, N?pair), architectures and applications in vision, audio, and text.

12 Core Machine Learning Interview Questions

Overview of 12 deep learning interview questions highlighting core concepts and training considerations, including batch normalization and practical model evaluation.

Can LLMs Reason and Plan?

Analysis of recent research evaluating whether LLMs can plan or reason, showing limited autonomous planning and that apparent emergent capabilities stem from in-context learning.

F-Learning: Forget-then-Learn for LLM Knowledge Updates

F-Learning: a parameter-based fine-tuning paradigm that subtracts knowledge parameter deltas to forget outdated facts, then fine-tunes (LoRA or full-model) to update LLM knowledge.

Using AI Tools to Improve IC Design Efficiency

Synopsys.ai and Microsoft extend Copilot into EDA with Azure OpenAI, adding GenAI features for RTL generation, formal verification assertions, and validated design workflows.

Implicit Harmful Outputs in Large Language Models

Tsinghua study analyzes implicit harmful content in LLMs, showing how SFT and RLHF can induce subtle abusive outputs that evade harmful-content detectors.

RL-Designed GPU Arithmetic Circuits at NVIDIA

PrefixRL uses deep reinforcement learning to optimize parallel prefix circuits, producing smaller, lower-latency adders and mapping Pareto trade-offs between area and latency.

Retrieval-Augmented In-Context Learning for Domain Adaptation

DAICL: a retrieval-augmented in-context learning framework for unsupervised domain adaptation that retrieves target examples and jointly optimizes task and LM.

Simplifying Transformer Blocks

Simplifying Transformer blocks by removing skip connections, projections and normalization; introduces Simplified Attention to reduce parameters and raise training throughput.

Mamba: New Selective State Space Model vs Transformer

Mamba: a selective SSM state-space model that generalizes S4 to enable linear long-context scaling, million-token sequences, and improved language modeling.

Building a Multilingual Open-Ended QA Dataset

OMGEval presents an open-source multilingual open-ended QA benchmark (804 Chinese prompts) localized from AlpacaEval, using Text-Davinci-003 baseline and GPT-4 evaluation.

Memory Interface Chips for AI Servers

Technical overview of AI server interconnects and components: DGX H100 architecture, PCIe switches and Retimers, and DDR5 memory interface chip trends.

What Is AI Computation and How Does It Work?

AI overview with latent space representations and practical applications in manufacturing and semiconductor manufacturing, including predictive maintenance and quality assurance.

GPT and Neural Networks: Underlying Mechanisms

Technical overview of neural networks and GPT: how images and text are vectorized, forward/backpropagation, gradient descent training, activations, and prediction.