Generative AI

Liquid AI Releases LFM2.5: A Unified Family Model for Real AI on Device Agents

Liquid AI Releases LFM2.5: A Unified Family Model for Real AI on Device Agents

Liquid AI has introduced the LFM2.5, a new generation of basic micromodels built on the LFM2 architecture and focused on…
Marktechpost Releases 'AI2025Dev': A Standardized Intelligence Framework for AI Models, Benchmarks, and Ecosystem Indicators

Marktechpost Releases 'AI2025Dev': A Standardized Intelligence Framework for AI Models, Benchmarks, and Ecosystem Indicators

Marktechpost released AI2025Devits 2025 statistics platform (available to AI Devs and Researchers without registration or login) designed to turn a…
A Coding Guide to Designing and Orchestrating Advanced React-Based Multi-Agent Workflows with AgentScope and OpenAI

A Coding Guide to Designing and Orchestrating Advanced React-Based Multi-Agent Workflows with AgentScope and OpenAI

In this tutorial, we build an advanced multi-agent incident response system using AgentScope. We organize multiple ReAct agents, each with…
DeepSeek Researchers Introduce 1967 Matrix Normalization Algorithm to Correct Hyper-Correlation Instability

DeepSeek Researchers Introduce 1967 Matrix Normalization Algorithm to Correct Hyper-Correlation Instability

DeepSeek researchers are trying to solve a specific problem in large language model training. Residual connectivity made very deep networks…
Recursive Language Models (RLMs): From MIT's Blueprint to Prime Intellect's RLMEnv for Long Horizon LLM Agents

Recursive Language Models (RLMs): From MIT's Blueprint to Prime Intellect's RLMEnv for Long Horizon LLM Agents

Recursive Language Models aim to overcome the common trade-offs between context length, accuracy and cost of large language models. Instead…
Train Your Large Model on Multiple GPUs with Tensor Parallelism

Train Your Large Model on Multiple GPUs with Tensor Parallelism

import dataclasses import datetime import os   import datasets import tokenizers import torch import torch.distributed as dist import torch.nn as…
Cloudflare's tokio-quiche How to Make QUIC and HTTP/3 a First Class Citizen on Rust Backends

Cloudflare's tokio-quiche How to Make QUIC and HTTP/3 a First Class Citizen on Rust Backends

Cloudflare has an open source tokio-quiche, an asynchronous QUIC and HTTP/3 Rust library that wraps its battle-tested quiche implementation in…
Back to top button