weimeng's picture

weimeng

mengwei0427

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Representation Forcing for Bottleneck-Free Unified Multimodal Models

upvoted a paper about 1 month ago

MultiWorld: Scalable Multi-Agent Multi-View Video World Models

upvoted a paper about 2 months ago

OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks

View all activity

Organizations

Papers 1

arxiv:2507.05240

models 3

mengwei0427/StreamVLN_Video_qwen_1_5_r2r_rxr_envdrop_scalevln_v1_3

Text Generation • 8B • Updated Sep 28, 2025 • 199

mengwei0427/StreamVLN_Video_qwen_1_5_r2r_rxr_envdrop_scalevln_real_world

8B • Updated Jul 18, 2025 • 37

mengwei0427/StreamVLN_Video_qwen_1_5_r2r_rxr_envdrop_scalevln

Robotics • 8B • Updated Jul 18, 2025 • 38 • 2

datasets 0

None public yet