Search papers, labs, and topics across Lattice.
MiniMax
5
0
9
3
MSA slashes per-token attention compute by over 28x while maintaining competitive performance, revolutionizing how LLMs can handle ultra-long contexts.
MaxProof's innovative test-time scaling enables an AI to outperform human champions in mathematical proof competitions.
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
Forget data quantity, diversity is the secret sauce: scaling the variety of tool-use patterns in training data boosts LLM generalization by +22 points on OOD benchmarks, even with 4x less data.
Learning from a mix of real and simulated data can be effectively transferred to real-world robot tasks using progressive neural networks, enabling safer and more efficient online adaptation.
