AI Papers Academy

Tokenformer: The Next Generation of Transformers?

Generative Reward Models: Merging the Power of RLHF and RLAIF for Smarter AI

Writing in the Margins: Better LLM Inference Pattern for Long Context Retrieval

Sapiens by Meta AI: Foundation for Human Vision Models

Mixture of Nested Experts by Google: Efficient Alternative To MoE?

Introduction to Mixture-of-Experts | Original MoE Paper Explained

Mixture-of-Agents (MoA) Enhances Large Language Model Capabilities

Arithmetic Transformers with Abacus Positional Embeddings | AI Paper Explained

CLLMs: Consistency Large Language Models | AI Paper Explained

ReFT: Representation Finetuning for Language Models | AI Paper Explained

Stealing Part of a Production Language Model | AI Paper Explained

The Era of 1-bit LLMs by Microsoft | AI Paper Explained

LCM-LoRA: From Diffusion Models to Fast SDXL with Latent Consistency Models

NExT-GPT: Any-to-Any Multimodal LLM

Consistency Models from OpenAI - Optimizing Diffusion Models Inference

FACET by Meta AI - Fairness in Computer Vision Evaluation Benchmark

StyleDrop from Google AI - Text-to-Image Generation in Any Style!

HTML Tables Tutorial | How To Create and Customize Tables with HTML

DeepSeek-R1 Paper Explained - A New RL LLMs Era in AI?

Fast Inference of Mixture-of-Experts Language Models with Offloading

V-JEPA by Meta AI - A Human-Like Computer Vision Video-based Model

Cheating LLMs & How (Not) To Stop Them | OpenAI Paper Explained

Introduction to HTML - What are Tags, Elements and Attributes | HTML Document Structure

Code Llama Paper Explained

Table-GPT by Microsoft: Empower LLMs To Understand Tables

CODEFUSION by Microsoft: A Pre-trained Diffusion Model for Code Generation

DeepSeek Janus-Pro: DeepSeek's Revolution in Multimodal AI?

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Carbon Programming Language - Classes, Inheritance, Interfaces and Generics in Carbon

Graphs Representations - Adjacency Lists vs Adjacency Matrix

Tiny Recursive Model (TRM) Paper Explained

LLaMA-Mesh by Nvidia: LLM for 3D Mesh Generation

Continuous Thought Machines (CTMs) - The Era of AI Beyond Transformers?

Perception Language Models (PLMs) by Meta – A Fully Open SOTA VLM

DINOv3 Paper Explained: The Computer Vision Foundation Model

GRPO Reinforcement Learning Explained (DeepSeekMath Paper)

GDPO Explained: NVIDIA Fixes GRPO for LLM Reinforcement Learning

Large Language Models As Optimizers - OPRO by Google DeepMind

DFS Algorithm | Depth First Search Algorithm for Graph Search With Animated Example

Microsoft Found Gradient Descent for AI Agent Skills

LongNet from Microsoft - 1B Tokens Transformer with Dilated Attention

Byte Latent Transformer (BLT) by Meta AI - A Tokenizer-free LLM

BFS Algorithm | Breadth First Search Algorithm for Graph Search

YOLO-NAS - A New Best Object Detection Model!

ImageBind from Meta AI - One Embedding Space To Bind Them All

Google HyperDreamBooth - HyperNetworks for Fast Personalization of Text-to-Image Models

Large Language Diffusion Models - The Era Of Diffusion LLMs?

Vision Transformers Need Registers - Fixing a Bug in DINOv2?