Bohao Li's picture

Bohao Li

BreakLee

·

Bohao-Lee

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation

upvoted a paper 4 days ago

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

upvoted a paper 18 days ago

Reinforcement Pre-Training

View all activity

Organizations

authored 2 papers 3 months ago

VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI

Paper • 2410.11623 • Published Oct 15, 2024 • 49

Video-R1: Reinforcing Video Reasoning in MLLMs

Paper • 2503.21776 • Published Mar 27 • 79

authored a paper 7 months ago

AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?

Paper • 2412.02611 • Published Dec 3, 2024 • 24

authored 2 papers about 1 year ago

SEED-Bench-2: Benchmarking Multimodal Large Language Models

Paper • 2311.17092 • Published Nov 28, 2023

SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension

Paper • 2404.16790 • Published Apr 25, 2024 • 9

authored 2 papers over 1 year ago

SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Paper • 2307.16125 • Published Jul 30, 2023 • 7

Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners

Paper • 2303.02151 • Published Mar 3, 2023