12 primary articles · 1 secondary mentions
Problem The paper addresses the limitations in existing mathematical proof systems, particularly in competition-level settings, where the ability to generate, verify, and refine proofs is critical. Prior works have not...
Problem This paper addresses the gap in understanding the relationship between Gaussian-process upper confidence bound (GP-UCB) methods and decision-estimation-coefficient (DEC) methods within the context of frequentist Reproducing Kernel Hilbert Space...
Problem This work addresses the gap in sequential decision-making under uncertainty in partially observable environments, specifically in the context of partially observable Markov games (POMGs). The challenge arises from the...
MiniMax, a rising player in the Chinese AI landscape, is preparing for a public listing in Shanghai, aiming to capitalize on the growing interest in artificial intelligence investments. This move...
Chinese AI company MiniMax has unveiled its latest model, M3, which is being touted as a groundbreaking advancement in the AI landscape. This model is notable for being the first...
MiniMax, an emerging player in the AI sector, is planning a public listing in China, aiming to bolster its competitive stance against established rivals like DeepSeek. This move comes at...
MiniMax, a prominent player in the AI sector, has announced its plans to launch an initial public offering (IPO) in China, aiming to bolster its competitive edge against local rivals...
MiniMax has unveiled its upcoming M3 model, which features a groundbreaking sparse attention mechanism that promises to enhance long-context response speeds by an impressive 15.6 times. This development is particularly...
Problem This paper addresses the vulnerability of machine learning models to distillation attacks, which exploit the outputs of models to create imitative versions. The authors highlight a significant gap in...
Problem This paper addresses the limitations of Joint Embedding Predictive Architectures (JEPAs), which typically regularize one-view embeddings towards an isotropic Gaussian distribution. The authors argue that this isotropic assumption is...
Problem This paper addresses the theoretical gap in understanding the conditions under which sign-based optimization algorithms, specifically SignSGD, outperform traditional Stochastic Gradient Descent (SGD). Despite empirical evidence of SignSGD’s effectiveness...
Problem This paper addresses a significant gap in the literature regarding unbiased mean estimation in the single-message shuffle model under local differential privacy (LDP). While minimax-optimal mechanisms for LDP are...
