AI Papers Academy
3.6만
구독자
84
영상
최근 영상
The End of Standard Attention in LLMs? | DeepSeek-V4 Paper Explained
The End of Frozen LLMs? (Google’s Hope Explained)
GDPO Explained: NVIDIA Fixes GRPO for LLM Reinforcement Learning
mHC Explained: How DeepSeek Rewires LLMs for 2026
Why Reinforcement Learning Unlocks Reasoning in LLMs (Aha Moments Explained)
Tiny Recursive Model (TRM) Paper Explained
DINOv3 Paper Explained: The Computer Vision Foundation Model
The Era of Hierarchical Reasoning Models
Reinforcement Pre-Training (RPT) By Microsoft Explained
Darwin Gödel Machine Explained: Self-Improving AI Agents
Continuous Thought Machines (CTMs) - The Era of AI Beyond Transformers?
Perception Language Models (PLMs) by Meta – A Fully Open SOTA VLM
GRPO Reinforcement Learning Explained (DeepSeekMath Paper)
GRPO 2.0? DAPO LLM Reinforcement Learning Explained
Cheating LLMs & How (Not) To Stop Them | OpenAI Paper Explained
START by Alibaba: Teaching LLMs to Debug Their Thinking with Python
SWE-RL by Meta — Reinforcement Learning for Software Engineering LLMs
Large Language Diffusion Models - The Era Of Diffusion LLMs?
CoCoMix by Meta AI - The Future of LLMs Pretraining?
s1: Simple Test-Time Scaling - Can 1k Samples Rival o1-Preview?
DeepSeek Janus-Pro: DeepSeek's Revolution in Multimodal AI?
DeepSeek-R1 Paper Explained - A New RL LLMs Era in AI?
Titans by Google: The Era of AI After Transformers?
rStar-Math by Microsoft: Can SLMs Beat OpenAI o1 in Math?
Large Concept Models (LCMs) by Meta: The Era of AI After LLMs?
Byte Latent Transformer (BLT) by Meta AI - A Tokenizer-free LLM
Coconut by Meta AI - LLM Reasoning With Chain of Continuous Thought
Hymba by NVIDIA: A Hybrid Mamba-Transformer SOTA Small LM
LLaMA-Mesh by Nvidia: LLM for 3D Mesh Generation
Tokenformer: The Next Generation of Transformers?