ML applications

MiniMax Sparse Attention (MSA): a Two-Branch Block-Sparse Attention Trained on a 109B-Parameter MoE With a 3T-Token Budget

ML applications

8 Min Read

MiniMax Sparse Attention (MSA): a Two-Branch Block-Sparse Attention Trained on a 109B-Parameter MoE With a 3T-Token Budget

By Editorial Team

June 17, 2026

Read Article

How to Build Memory-Efficient Transformers with xFormers Using Packed Sequences, GQA, ALiBi, SwiGLU, and Causal Attention

ML applications

2 Min Read

How to Build Memory-Efficient Transformers with xFormers Using Packed Sequences, GQA, ALiBi, SwiGLU, and Causal Attention

By Editorial Team

June 17, 2026

Read Article

Google Cloud Introduces Open Knowledge Format (OKF): A Vendor-Neutral Markdown Spec for Giving AI Agents Curated Context

ML applications

6 Min Read

Google Cloud Introduces Open Knowledge Format (OKF): A Vendor-Neutral Markdown Spec for Giving AI Agents Curated Context

By Editorial Team

June 16, 2026

Read Article

Z.ai Launches GLM-5.2 With a Usable 1M-Token Context, Two Thinking-Effort Levels, and No Benchmarks at Launch

ML applications

5 Min Read

Z.ai Launches GLM-5.2 With a Usable 1M-Token Context, Two Thinking-Effort Levels, and No Benchmarks at Launch

By Editorial Team

June 15, 2026

Read Article

A Coding Hands-On on FineWeb for Streaming, Filtering, Deduplication, Tokenization, and Large-Scale Web Corpus Analytics

ML applications

2 Min Read

A Coding Hands-On on FineWeb for Streaming, Filtering, Deduplication, Tokenization, and Large-Scale Web Corpus Analytics

By Editorial Team

June 14, 2026

Read Article

A Coding Implementation on Spatial Graph Neural Networks for Urban Function Inference Using city2graph, OSMnx, and PyTorch Geometric

ML applications

2 Min Read

A Coding Implementation on Spatial Graph Neural Networks for Urban Function Inference Using city2graph, OSMnx, and PyTorch Geometric

By Editorial Team

June 13, 2026

Read Article

Moonshot AI Releases Kimi K2.7-Code: a Coding Model Reporting +21.8% on Kimi Code Bench v2 Over K2.6

ML applications

6 Min Read

Moonshot AI Releases Kimi K2.7-Code: a Coding Model Reporting +21.8% on Kimi Code Bench v2 Over K2.6

By Editorial Team

June 13, 2026

Read Article

Zyphra Release Zamba2-VL: Hybrid Mamba2–Transformer Vision-Language Models That Cut Time-to-First-Token by About an Order of Magnitude

ML applications

7 Min Read

Zyphra Release Zamba2-VL: Hybrid Mamba2–Transformer Vision-Language Models That Cut Time-to-First-Token by About an Order of Magnitude

By Editorial Team

June 12, 2026

Read Article

Meet ‘North Mini Code’: Cohere’s 30B Open-Weight Mixture-of-Experts Model With 3B Active Parameters for Agentic Coding

ML applications

8 Min Read

Meet ‘North Mini Code’: Cohere’s 30B Open-Weight Mixture-of-Experts Model With 3B Active Parameters for Agentic Coding

By Editorial Team

June 11, 2026

Read Article

Google AI Releases DiffusionGemma, a 26B MoE Open Model Using Text Diffusion for Up to 4x Faster Generation

ML applications

8 Min Read

Google AI Releases DiffusionGemma, a 26B MoE Open Model Using Text Diffusion for Up to 4x Faster Generation

By Editorial Team

June 10, 2026

Read Article

Popular Posts

AI chip maker SambaNova raises $1B at $11B valuation, 5 months after last mega round

NVIDIA Releases Audex (Nemotron-Labs-Audex-30B-A3B): A Unified Audio-Text LLM That Preserves the Text Intelligence of Its

Final extension: Startup Battlefield Australia applications now close July 20

Liquid AI Open-Sources Antidoom: A Final Token Preference Optimization (FTPO) Method that Reduces Doom Loops

ML applications

MiniMax Sparse Attention (MSA): a Two-Branch Block-Sparse Attention Trained on a 109B-Parameter MoE With a 3T-Token Budget

How to Build Memory-Efficient Transformers with xFormers Using Packed Sequences, GQA, ALiBi, SwiGLU, and Causal Attention

Google Cloud Introduces Open Knowledge Format (OKF): A Vendor-Neutral Markdown Spec for Giving AI Agents Curated Context

Z.ai Launches GLM-5.2 With a Usable 1M-Token Context, Two Thinking-Effort Levels, and No Benchmarks at Launch

A Coding Hands-On on FineWeb for Streaming, Filtering, Deduplication, Tokenization, and Large-Scale Web Corpus Analytics

A Coding Implementation on Spatial Graph Neural Networks for Urban Function Inference Using city2graph, OSMnx, and PyTorch Geometric

Moonshot AI Releases Kimi K2.7-Code: a Coding Model Reporting +21.8% on Kimi Code Bench v2 Over K2.6

Zyphra Release Zamba2-VL: Hybrid Mamba2–Transformer Vision-Language Models That Cut Time-to-First-Token by About an Order of Magnitude

Meet ‘North Mini Code’: Cohere’s 30B Open-Weight Mixture-of-Experts Model With 3B Active Parameters for Agentic Coding

Google AI Releases DiffusionGemma, a 26B MoE Open Model Using Text Diffusion for Up to 4x Faster Generation

Recent Posts

Archives

Categories