The AI Timeline
Follow The Latest Cutting Edge AI Research
Connect
#27 | Latest AI Research Explained Simply
Training Large Language Models to Reason in a Continuous Latent Space, and [MASK] is All You Need
DeMo: Decoupled Momentum Optimization, and Densing Law of LLMs
O1 Replication Journey, and LLMs Don't Implicitly Reason
#32 | Latest AI Research Explained Simply
Plus more about Transformer2 and Kimi k1.5
Plus more about RWKV-7 "Goose" with Expressive Dynamic State Evolution and Measuring AI Ability to Complete Long Tasks
Plus more about Generalized Kullback-Leibler Divergence Loss and Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Plus more about Optimal Hyperparameter Scaling Law in Large Language Model Pretraining and PokéChamp: an Expert-level Minimax Language Agent
Plus more about SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution and Reasoning with Latent Thoughts: On the Power of Looped Transformers
Plus more about Mixture of Block Attention for Long-Context LLMs, and Idiosyncrasies in Large Language Models
Plus more about Continuous Concepts (CoCoMix), and Distillation scaling laws
Plus more about OmniHuman-1, and Simple test-time scaling
Plus more about Supervised Fine-Tuning (SFT) vs Reinforcement Learning (RL), and Janus-Pro
Plus more about MiniMax-01 and Scaling LLM Test-Time Compute
Plus more about Towards System 2 Reasoning in LLMs and Memory Layers at Scale
Plus more about ModernBERT, and Qwen 2.5 Technical Report
