ML applications

Microsoft Releases Agent Lightning: A New AI Framework that Enables Reinforcement Learning (RL)-based Training of LLMs for Any AI Agent

ML applications

5 Min Read

Microsoft Releases Agent Lightning: A New AI Framework that Enables Reinforcement Learning (RL)-based Training of LLMs for Any AI Agent

By Editorial Team

October 30, 2025

Read Article

Liquid AI Releases LFM2-ColBERT-350M: A New Small Model that brings Late Interaction Retrieval to Multilingual and Cross-Lingual RAG

ML applications

4 Min Read

Liquid AI Releases LFM2-ColBERT-350M: A New Small Model that brings Late Interaction Retrieval to Multilingual and Cross-Lingual RAG

By Editorial Team

October 29, 2025

Read Article

5 Common LLM Parameters Explained with Examples

ML applications

8 Min Read

5 Common LLM Parameters Explained with Examples

By Editorial Team

October 27, 2025

Read Article

Meet ‘kvcached’: A Machine Learning Library to Enable Virtualized, Elastic KV Cache for LLM Serving on Shared GPUs

ML applications

6 Min Read

Meet ‘kvcached’: A Machine Learning Library to Enable Virtualized, Elastic KV Cache for LLM Serving on Shared GPUs

By Editorial Team

October 27, 2025

Read Article

An Implementation on Building Advanced Multi-Endpoint Machine Learning APIs with LitServe: Batching, Streaming, Caching, and Local Inference

ML applications

6 Min Read

An Implementation on Building Advanced Multi-Endpoint Machine Learning APIs with LitServe: Batching, Streaming, Caching, and Local Inference

By Editorial Team

October 25, 2025

Read Article

Google AI Introduces FLAME Approach: A One-Step Active Learning that Selects the Most Informative Samples for Training and Makes a Model Specialization Super Fast

ML applications

5 Min Read

Google AI Introduces FLAME Approach: A One-Step Active Learning that Selects the Most Informative Samples for Training and Makes a Model Specialization Super Fast

By Editorial Team

October 24, 2025

Read Article

Microsoft AI Proposes BitNet Distillation (BitDistill): A Lightweight Pipeline that Delivers up to 10x Memory Savings and about 2.65x CPU Speedup

ML applications

5 Min Read

Microsoft AI Proposes BitNet Distillation (BitDistill): A Lightweight Pipeline that Delivers up to 10x Memory Savings and about 2.65x CPU Speedup

By Editorial Team

October 19, 2025

Read Article

Weak-for-Strong (W4S): A Novel Reinforcement Learning Algorithm that Trains a weak Meta Agent to Design Agentic Workflows with Stronger LLMs

ML applications

5 Min Read

Weak-for-Strong (W4S): A Novel Reinforcement Learning Algorithm that Trains a weak Meta Agent to Design Agentic Workflows with Stronger LLMs

By Editorial Team

October 19, 2025

Read Article

Google AI Releases C2S-Scale 27B Model that Translate Complex Single-Cell Gene Expression Data into ‘cell sentences’ that LLMs can Understand

ML applications

4 Min Read

Google AI Releases C2S-Scale 27B Model that Translate Complex Single-Cell Gene Expression Data into ‘cell sentences’ that LLMs can Understand

By Editorial Team

October 17, 2025

Read Article

Baidu’s PaddlePaddle Team Releases PaddleOCR-VL (0.9B): a NaViT-style + ERNIE-4.5-0.3B VLM Targeting End-to-End Multilingual Document Parsing

ML applications

3 Min Read

Baidu’s PaddlePaddle Team Releases PaddleOCR-VL (0.9B): a NaViT-style + ERNIE-4.5-0.3B VLM Targeting End-to-End Multilingual Document Parsing

By Editorial Team

October 17, 2025

Read Article

Popular Posts

The Minneapolis tech community holds strong during ‘tense and difficult time’

Sudo’s maintainer needs resources to keep utility updated • The Register

How to Build Advanced Quantum Algorithms Using Qrisp with Grover Search, Quantum Phase Estimation, and

An ‘Intimacy Crisis’ Is Driving the Dating Divide

ML applications

Microsoft Releases Agent Lightning: A New AI Framework that Enables Reinforcement Learning (RL)-based Training of LLMs for Any AI Agent

Liquid AI Releases LFM2-ColBERT-350M: A New Small Model that brings Late Interaction Retrieval to Multilingual and Cross-Lingual RAG

5 Common LLM Parameters Explained with Examples

Meet ‘kvcached’: A Machine Learning Library to Enable Virtualized, Elastic KV Cache for LLM Serving on Shared GPUs

An Implementation on Building Advanced Multi-Endpoint Machine Learning APIs with LitServe: Batching, Streaming, Caching, and Local Inference

Google AI Introduces FLAME Approach: A One-Step Active Learning that Selects the Most Informative Samples for Training and Makes a Model Specialization Super Fast

Microsoft AI Proposes BitNet Distillation (BitDistill): A Lightweight Pipeline that Delivers up to 10x Memory Savings and about 2.65x CPU Speedup

Weak-for-Strong (W4S): A Novel Reinforcement Learning Algorithm that Trains a weak Meta Agent to Design Agentic Workflows with Stronger LLMs

Google AI Releases C2S-Scale 27B Model that Translate Complex Single-Cell Gene Expression Data into ‘cell sentences’ that LLMs can Understand

Baidu’s PaddlePaddle Team Releases PaddleOCR-VL (0.9B): a NaViT-style + ERNIE-4.5-0.3B VLM Targeting End-to-End Multilingual Document Parsing

Recent Posts

Archives

Categories