GitHubRepoSTRING[ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"long-context-transformersposition-encoding83PythonMIT24 mo agoHKUNLPShare or keepTake it
AI on my own machineRepoMileBenchThis repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"benchmarkcomputer-visiondeep-learning38PythonApache-2.02 y agoMileBenchShare or keepTake it
GitHubRepoRANRAN: Recurrent Attention Networks for Long-text Modeling | Findings of ACL23acl2023recurrent-networkslong-document-modeling23PythonMIT3 y ago4AIShare or keepTake it