A 7B LVLM with 128K context window and 512K generalization through long-context continued pre-training
Zhaowei Wang
ZhaoweiWang
AI & ML interests
NLP
Recent Activity
authored a paper 9 days ago
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents upvoted a paper 9 days ago
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents upvoted a paper 2 months ago
LEGO-RL: Harness-Native Reinforcement Learning for Coding AgentsOrganizations
datasets 9
ZhaoweiWang/MMLongBench
Preview • Updated • 4.98k • 7
ZhaoweiWang/image_full_collection
Viewer • Updated • 3.4k • 8
ZhaoweiWang/image_collection
Preview • Updated • 780
ZhaoweiWang/DivScene-DivTraj
Viewer • Updated • 117k • 49
ZhaoweiWang/AbsPyramid
Preview • Updated • 36 • 3
ZhaoweiWang/Levy_Holt_dataset_jsonl
Viewer • Updated • 23.9k • 12
ZhaoweiWang/AbstractATOMIC
Viewer • Updated • 92.2k • 32 • 1
ZhaoweiWang/COPES
Preview • Updated • 26 • 1
ZhaoweiWang/SubeventWriter
Preview • Updated • 30 • 1