laolao's picture

3 31 5

laolao

laolao77

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 16 days ago

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

upvoted a paper about 1 month ago

ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning

upvoted a paper about 1 month ago

ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation

View all activity

Organizations

New activity in osmosis-ai/Osmosis-Structure-0.6B 7 months ago

SGLang inference Error

#4 opened 7 months ago by

New activity in laolao77/MMDU over 1 year ago

Thank you for sharing datasets

#2 opened over 1 year ago by

commented 2 papers over 1 year ago

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

Paper • 2406.11833 • Published Jun 17, 2024 • 63 •

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

Paper • 2406.11833 • Published Jun 17, 2024 • 63 •