Archive

All Posts

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

/

Feb 18, 2025

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Plus more about Continuous Concepts (CoCoMix), and Distillation scaling laws

Fully Autonomous AI Agents Should Not be Developed

/

Feb 11, 2025

Fully Autonomous AI Agents Should Not be Developed

Plus more about OmniHuman-1, and Simple test-time scaling

Large Language Models Think Too Fast To Explore Effectively

/

Feb 4, 2025

Large Language Models Think Too Fast To Explore Effectively

Plus more about Supervised Fine-Tuning (SFT) vs Reinforcement Learning (RL), and Janus-Pro

DeepSeek-R1 Explained

/

Jan 28, 2025

DeepSeek-R1 Explained

Plus more about Transformer2 and Kimi k1.5

Titans: Learning to Memorize at Test Time

/

Jan 21, 2025

Titans: Learning to Memorize at Test Time

Plus more about MiniMax-01 and Scaling LLM Test-Time Compute

Agent Laboratory: Using LLM Agents as Research Assistants

/

Jan 14, 2025

Agent Laboratory: Using LLM Agents as Research Assistants

Plus more about Towards System 2 Reasoning in LLMs and Memory Layers at Scale

Alignment Faking In Large Language Models Explained

/

Jan 7, 2025

Alignment Faking In Large Language Models Explained

Plus more about ModernBERT, and Qwen 2.5 Technical Report

Byte Latent Transformer: The Future of LLM is Without Tokenization?

/

Dec 17, 2024

Byte Latent Transformer: The Future of LLM is Without Tokenization?

Training Large Language Models to Reason in a Continuous Latent Space, and [MASK] is All You Need

HunyuanVideo: A Systematic Framework For Large Video Generative Models

/

Dec 11, 2024

HunyuanVideo: A Systematic Framework For Large Video Generative Models

DeMo: Decoupled Momentum Optimization, and Densing Law of LLMs