Di Wu

xiaowu0162

·

https://xiaowu0162.github.io/

xiaowu0162

AI & ML interests

Natural Language Processing

Recent Activity

upvoted a paper about 14 hours ago

OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

upvoted a paper 28 days ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

new activity 5 months ago

xiaowu0162/longmemeval-v2:Improve dataset card: add task metadata, links, and citation

View all activity

Organizations

Papers 9

arxiv:2410.10813

arxiv:2407.00377

arxiv:2407.00191

arxiv:2406.13692

models 4

xiaowu0162/repoformer-16b

Updated Oct 12, 2024 • 6 • 1

xiaowu0162/repoformer-7b

Updated Oct 12, 2024 • 10

xiaowu0162/repoformer-3b

Updated Oct 12, 2024 • 34

xiaowu0162/repoformer-1b

Updated Oct 12, 2024 • 4

datasets 3

xiaowu0162/longmemeval-v2

Viewer • Updated May 17 • 29 • 5.09k • 6

xiaowu0162/longmemeval-cleaned

Updated Sep 19, 2025 • 30.4k • 38

xiaowu0162/longmemeval

Updated Sep 19, 2025 • 8.46k • 23