MiniMax-M1 Collection MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. • 4 items • Updated 7 days ago • 97
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention Paper • 2506.13585 • Published 10 days ago • 236
SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond Paper • 2505.19641 • Published about 1 month ago • 66
One-RL-to-See-Them-All Collection One RL to See Them All: Visual Triple Unified Reinforcement Learning. GitHub: https://github.com/MiniMax-AI/One-RL-to-See-Them-All • 5 items • Updated 16 days ago • 27
One RL to See Them All: Visual Triple Unified Reinforcement Learning Paper • 2505.18129 • Published May 23 • 59
Running 94 94 MiniMax Speech Tech Report 🎙 Generate high-quality speech from text with MiniMax-Speech
MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder Paper • 2505.07916 • Published May 12 • 124
MiniMax-01: Scaling Foundation Models with Lightning Attention Paper • 2501.08313 • Published Jan 14 • 295