5 papers
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory
Zihao Tang, Xin Yu, Ziyu Xiao +9
AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-R…
Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and A Fourier Kolmogorov-Arnold Framework
Linfei Li, Lin Zhang, Zhong Wang +3
Although Coordinate-MLP-based implicit neural representations have excelled in representing radiance fields, 3D shapes, and images, their application to audio signals remains under…
Sublinear-Time Algorithms for Diagonally Dominant Systems and Applications to the Friedkin-Johnsen Model
Weiming Feng, Zelin Li, Pan Peng
We study sublinear-time algorithms for solving linear systems , where is a diagonally dominant matrix, i.e., for all $i \in…
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation
Ming Zhang, Yujiong Shen, Zelin Li +13
Evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error. Current medical benchmarks have three…
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
MiniMax, :, Aili Chen +125
We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combin…