Why We Built VIBE Bench: Rethinking Evaluation for Real Workloads
• 8
AI & ML interests
Intelligence with Everyone
Recent Activity
View all activity
Articles
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
-
MiniMax M1
💬354Generate web page code from your description
-
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
Paper • 2506.13585 • Published • 276 -
MiniMaxAI/MiniMax-M1-80k
Text Generation • Updated • 858 • • 691 -
MiniMaxAI/MiniMax-M1-40k
Text Generation • Updated • 52.3k • 184
One RL to See Them All: Visual Triple Unified Reinforcement Learning. GitHub: https://github.com/MiniMax-AI/One-RL-to-See-Them-All
-
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Paper • 2505.18129 • Published • 62 -
One-RL-to-See-Them-All/Orsta-Data-47k
Updated • 254 • 17 -
One-RL-to-See-Them-All/Orsta-7B
Image-Text-to-Text • 8B • Updated • 22 • 12 -
One-RL-to-See-Them-All/Orsta-32B-0321
Image-Text-to-Text • 33B • Updated • 16 • 2
Towards Scalable Pre-training of Visual Tokenizers for Generation
-
MiniMaxAI/VTP-Small-f16d64
Image Feature Extraction • 0.2B • Updated • 277 • 14 -
MiniMaxAI/VTP-Base-f16d64
Image Feature Extraction • Updated • 87 • 20 -
MiniMaxAI/VTP-Large-f16d64
Image Feature Extraction • 0.7B • Updated • 499 • 15 -
Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper • 2512.13687 • Published • 106
Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
-
SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
Paper • 2505.19641 • Published • 68 -
MiniMaxAI/SynLogic
Viewer • Updated • 49.3k • 569 • 104 -
MiniMaxAI/SynLogic-7B
Text Generation • 8B • Updated • 285 • • 27 -
MiniMaxAI/SynLogic-Mix-3-32B
Text Generation • 33B • Updated • 186 • • 19
Towards Scalable Pre-training of Visual Tokenizers for Generation
-
MiniMaxAI/VTP-Small-f16d64
Image Feature Extraction • 0.2B • Updated • 277 • 14 -
MiniMaxAI/VTP-Base-f16d64
Image Feature Extraction • Updated • 87 • 20 -
MiniMaxAI/VTP-Large-f16d64
Image Feature Extraction • 0.7B • Updated • 499 • 15 -
Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper • 2512.13687 • Published • 106
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
-
MiniMax M1
💬354Generate web page code from your description
-
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
Paper • 2506.13585 • Published • 276 -
MiniMaxAI/MiniMax-M1-80k
Text Generation • Updated • 858 • • 691 -
MiniMaxAI/MiniMax-M1-40k
Text Generation • Updated • 52.3k • 184
Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
-
SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
Paper • 2505.19641 • Published • 68 -
MiniMaxAI/SynLogic
Viewer • Updated • 49.3k • 569 • 104 -
MiniMaxAI/SynLogic-7B
Text Generation • 8B • Updated • 285 • • 27 -
MiniMaxAI/SynLogic-Mix-3-32B
Text Generation • 33B • Updated • 186 • • 19
One RL to See Them All: Visual Triple Unified Reinforcement Learning. GitHub: https://github.com/MiniMax-AI/One-RL-to-See-Them-All
-
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Paper • 2505.18129 • Published • 62 -
One-RL-to-See-Them-All/Orsta-Data-47k
Updated • 254 • 17 -
One-RL-to-See-Them-All/Orsta-7B
Image-Text-to-Text • 8B • Updated • 22 • 12 -
One-RL-to-See-Them-All/Orsta-32B-0321
Image-Text-to-Text • 33B • Updated • 16 • 2