arxiv:2506.03569
Dawei Zhu
dwzhu
AI & ML interests
natural language processing
Recent Activity
upvoted a paper 3 days ago
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself upvoted a paper 4 months ago
Useful Memories Become Faulty When Continuously Updated by LLMsOrganizations
models 15
dwzhu/e5rope-base
Sentence Similarity • 0.1B • Updated • 697 • 18
dwzhu/e5-base-4k
Sentence Similarity • Updated • 9.08k • • 14
dwzhu/nomic-bert-2048
Feature Extraction • Updated • 9
dwzhu/LLaMA2-7B-PoSE-YaRN-16k
Text Generation • Updated • 17 • 5
dwzhu/Baichuan2-7B-PoSE-YaRN-16k
Text Generation • Updated • 19 • 1
dwzhu/Baichuan2-7B-PoSE-NTK-16k
Text Generation • Updated • 21 • 1
dwzhu/LLaMA-7B-PoSE-Linear-16k
Text Generation • Updated • 9 • 1
dwzhu/LLaMA-7B-PoSE-YaRN-16k
Text Generation • Updated • 10 • 2
dwzhu/LLaMA-7B-PoSE-YaRN-96k
Text Generation • Updated • 9 • 1
dwzhu/LLaMA2-7B-PoSE-NTK-16k
Text Generation • Updated • 14 • 2
datasets 6
dwzhu/PaperBananaBench
Viewer • Updated • 1.09k • 1.71k • 25
dwzhu/PaperBananaDiagramPDFs
Viewer • Updated • 600 • 9 • 4
dwzhu/DocLensDatasets
Preview • Updated • 664 • 1
dwzhu/LongEmbed
Viewer • Updated • 29.6k • 2.28k • 8
dwzhu/needle_in_a_haystack_retrieval
Updated • 21 • 1
dwzhu/PoSE-Datasets
Preview • Updated • 86 • 7