Model Detail
MiniMax-M2.7-NVFP4
—MiniMax-M2.7-NVFP4 is a code generation model with 65.2B parameters released by lukealonso. Distributed under the permissive mit license.
MiniMax-M2.7-NVFP4 ships with 65.2B parameters. Total weight footprint is approximately 130.4 GB, which is the relevant figure when planning local-inference VRAM. The mit license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
MiniMax-M2.7-NVFP4 is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Lower Bounds for Stochastic First-Order Algorithms with Variance Reduction in Nonconvex--Concave Minimax Optimization
arXiv:2610.01662v1 Announce Type: cross Abstract: We establish complexity lower bounds for stochastic first-order algorithms in nonconvex--concave minimax optimization, allowing algorithms to use variance reduction. Our main contribution is a lower bound for a zero-respecting algorithm class that pe
Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity
arXiv:2609.38659v2 Announce Type: replace-cross Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers. For $K$-armed bandits with $A$ optimal arms, we first provide a sharper analysis
Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness
arXiv:2610.01377v1 Announce Type: new Abstract: We study causal logistic bandits with counterfactual fairness constraints. The causal structure is given through known factual and counterfactual feature maps that share an unknown logistic reward parameter, but the learner observes only factual reward
Minimax Additive Regression under Unknown Dependent Designs
arXiv:2609.39212v1 Announce Type: cross Abstract: We study additive regression under a potentially non-product random design on $[0,1]^d$, allowing the dimension $d$ to grow with the sample size $n$. We introduce coupled smoothness classes that separately control the regularity of the marginal densi
Minimax rates for learning spectral Barron functions by deep ReLU neural networks
arXiv:2609.39020v1 Announce Type: cross Abstract: We study how well deep neural networks approximate and learn spectral Barron functions. Recent studies have shown that these function classes can be efficiently approximated by shallow neural networks without suffering from the curse of dimensionalit
Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
arXiv:2606.01708v2 Announce Type: replace Abstract: We study fixed-confidence best-action identification (BAI) in stochastic minimax trees. This problem is increasingly relevant in modern AI planning, where deep minimax search and Monte Carlo Tree Search (MCTS) with language model long rollouts face
