Stories by GaggiX

MeshLRM: Large Reconstruction Model for High-Quality Meshes

Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

Bringing generative AI to video editing workflows in Adobe Premiere Pro

Open model Command R+ beats GPT-4 in the LMSYS Chatbot Arena

Mixture-of-Depths: Dynamically allocating compute in transformer language models

Qwen1.5-Moe: Matching 7B Model Performance with 1/3 Activated Parameters

VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild

Claude 3 Haiku is ranked #6 on LLM arena

A new way to search and connect. Only on Android

Possible Mistral Medium model leak?

Moe-LLaVA: Mixture of Experts for Large Vision-Language Models

SupIR: Revolutionizing image restoration with cutting-edge large-scale AI

AutoRT: Foundation Models for Large Scale Orchestration of Robotic Agents

Midjourney V6 photorealistic images collection

Gemini vs GPT-4V: A Comparison and Combination of VLMs Through Qualitative Cases

CoSeR: Bridging Image and Language for Cognitive Super-Resolution

VecFusion: Vector Font Generation with Diffusion

ReconFusion: 3D Reconstruction with Diffusion Priors

Music ControlNet: Multiple Time-Varying Controls for Music Generation

Instant3D: Fast Text-to-3D with Sparse-View Generation

1
2
3
4
5