The memory of contemporary Large Language Models is bound by a physical paradox: as they learn, they fill up. The linear accumulation (O(N)) of Key-Value states...
The serverless computing paradigm offers compelling advantages for deploying Large Language Model (LLM) inference services, including elastic scaling and pay-pe...
The advances of large language models (LLMs) have paved the way for automated software vulnerability repair approaches, which iteratively refine the patch until...
Multi-agent systems have extended the capability of agentic AI. Instead of single inference passes, multiple agents perform collective reasoning to derive high ...
Distributed Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental operation in numerous high-performance computing and deep learning applications. The maj...
For nearly two decades, population protocols have been extensively studied, yielding efficient solutions for central problems in distributed computing, includin...
Evolutionary Neural Architecture Search (ENAS) has gained attention for automatically designing neural network architectures. Recent studies use a neural predic...
Matrix Product State (MPS) is a versatile tensor network representation widely applied in quantum physics, quantum chemistry, and machine learning, etc. MPS sam...
Most computational accounts of cognitive maps assume that stability is achieved primarily through sensory anchoring, with self-motion contributing to incrementa...
Point-based Differentiable Rendering (PBDR) enables high-fidelity 3D scene reconstruction, but scaling PBDR to high-resolution and large scenes requires efficie...
Metaheuristic algorithms for cardinality-constrained portfolio optimization require repair operators to map infeasible candidates onto the feasible region. Stan...
Deep representations across modalities are inherently intertwined. In this paper, we systematically analyze the spectral characteristics of various semantic and...
