Model Detail
MiniMax-H3
▲ 0.5%MiniMax-H3 is an AI model with 16.6B parameters released by MiniMaxAI. The model is registered under the image-text-to-video pipeline tag on Hugging Face, distributed under a other license.
MiniMax-H3 ships with 16.6B parameters. Total weight footprint is approximately 33.1 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the other license — review the exact terms before commercial deployment.
Downloads of MiniMax-H3 have moved +0.5% over the past 24 hours, +5.6% over the trailing seven days. The trend is mildly positive, consistent with a model that is being picked up incrementally rather than going viral. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
MiniMax-H3 is best fit for workloads that match the image-text-to-video pipeline tag. 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.
Minimax bounds for watermarked and masked recursive discrete distribution estimation
arXiv:2608.31091v1 Announce Type: cross Abstract: Watermarking has been proposed as a way to identify synthetic samples in estimation settings where no metadata is available to distinguish them from real samples, but its precise effects remain unexplored. In the absence of a distinguishing mechanism
Continuity-Free Near-Minimax Leading-Order Regret for CVaR-UCBVI
arXiv:2608.28960v1 Announce Type: new Abstract: For finite-horizon tabular CVaR reinforcement learning, prior work proves a $\widetilde{O}(\tau^{-1}\sqrt{SAK})$ leading regret bound for arbitrary normalized return laws and the sharper $\widetilde{O}(\sqrt{SAK/\tau})$ rate under a density lower bound
Cone Extended Rayleigh Quotients for Directed Graph Learning: Minimax Spectral Certificates, Sensitivity, and Adaptive Control
arXiv:2608.27122v1 Announce Type: new Abstract: Directed graph learning naturally leads to trainable nonsymmetric propagation operators with distinct right and left spectral structures. Building on the two-sided cone Rayleigh framework for generalized pencils \[ B_\theta-\lambda G, \] we develop a l
Sharp Minimax Regret for Infinite-Memory Logistic Prediction
arXiv:2608.26515v1 Announce Type: cross Abstract: We study online prediction for a specific finite-alphabet, exogenously driven source with infinite input memory. Independent Rademacher inputs $(U_t)$ are observed sequentially, and the next binary mark has logit $\sum_{j=1}^{t}\theta_jU_{t+1-j}$, wh
Minimax Alternating Regret for the Experts Problem and Online Convex Optimization
arXiv:2608.25182v1 Announce Type: cross Abstract: In this paper, we study alternating regret in online convex optimization (OCO), motivated by the success of alternating learning dynamics in two-player games. Although previous works have shown that $o(\sqrt{T})$ alternating regret is achievable unde
Functional linear regression from sparse to dense designs: a pooling-ridge method and minimax optimality
arXiv:2608.25468v1 Announce Type: cross Abstract: Functional data analysis is an important statistical field that treats data as random functions. In practice, the random functions are often not fully observed but instead measured at discrete times. While simpler problems, such as mean and covarianc
