Stories by saeedesmaili

M2UGen: Multi-Modal Music Understanding and Generation

V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs

RAGatouille

FunASR: Fundamental End-to-End Speech Recognition Toolkit

Anxiety

WhatsApp Is Finally Starting to Dominate in the United States

Surya: Multilingual Document OCR Toolkit

The Two Reacts

AnyText: Multilingual Visual Text Generation and Editing

Choose Optimism

Is the ChatGPT API Refusing to Summarize Academic Papers?

Stable Diffusion for Realistic Image Super-Resolution and Stylization

Parrot Captions Teach Clip to Spot Text

Retrieval-Augmented Generation for Large Language Models: A Survey

Is GPT-4 cost effective yet?

OpenVoice: Versatile Instant Voice Cloning

The Problem with Your Manager

Semantic Router

Developer Productivity for Humans, Part 7: Software Quality

1
2
3
4
5
6
7
8
9
10