Stories by omarsar

Can LLMs generate good questions?

LLMs for AGI

The Overthinking of O1-Like LLMs

DeepSeek-VL2

Gemini 2.0 as an AI Research Assistant

Asynchronous LLM Function Calling

Granite Guardian Models (From IBM)

Training LLMs to Reason in a Continuous Latent Space

Transformers Struggle to Learn to Search

OpenAI O1 Capabilities Tested

Auto-RAG

LLMOps Database

Reverse Thinking Makes LLMs Stronger Reasoners

A Survey of LLM-Brained GUI Agents

A Survey on LLM-as-a-Judge

Generating Science from AI-Powered Automated Falsification

The Dawn of GUI Agent

A Taxonomy of AgentOps

HtmlRAG: HTML is Better than Plain Text

LLM Evaluation Course

1
2
3
4
5
6