Efficient Training

5 pages

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Paper ZGCM-1: How a 7B Dense Model Trades Blows with 235B Frontiers — A Fully Open, Ultra-Efficient Foundation Model Design ReportTL;DR — …

September 16, 2026

KV Cache Long Context Efficient Inference Efficient Training Chain-of-Thought Open-Source LLM

Miles v0.1: Production-Level Post-Training

Paper Miles v0.1: A “verified, clean, and scalable” full-stack system for frontier RL post-trainingTL;DR: Miles is a full-stack …

September 10, 2026

Reinforcement Learning Efficient Training Distributed Computing Mixture of Experts Quantization Large Language Models

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Paper Two Designs That Make Speculative Decoding Practical for Large-Scale, Long-Context RL Post-TrainingTL;DR : Rollout generation …

September 10, 2026

Speculative Decoding Long Context Reinforcement Learning Distributed Computing Efficient Training Inference Acceleration

[Paper Review] Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

[Paper Review] Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Paper Link Structured State Space Duality: Unifying SSMs and Attention with Mamba-2 for 2–8× AccelerationTL;DRStructured State-Space Duality …

October 3, 2025

Mamba SSM Transformer Long Context Efficient Training FlashAttention GPU Acceleration

Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Paper Janus-Pro 7B: Dual-Encoder Multimodal LLM That Outsmarts Bigger ModelsOne-line summary (TL;DR)By fully separating the SigLIP …

DeepSeek Dual Encoder Multimodal Learning Vision-Language Models Large Language Models Efficient Training