Picture for Lewei Lu

Lewei Lu

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

Jun 13, 2024
Viaarxiv icon

OmniCorpus: An Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

Add code
Jun 12, 2024
Viaarxiv icon

VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks

Add code
Jun 12, 2024
Viaarxiv icon

Needle In A Multimodal Haystack

Add code
Jun 11, 2024
Viaarxiv icon

Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning

Add code
Jun 11, 2024
Viaarxiv icon

Parameter-Inverted Image Pyramid Networks

Add code
Jun 06, 2024
Viaarxiv icon

Learning 1D Causal Visual Representation with De-focus Attention Networks

Add code
Jun 06, 2024
Viaarxiv icon

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Add code
Apr 29, 2024
Figure 1 for How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Figure 2 for How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Figure 3 for How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Figure 4 for How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Viaarxiv icon

Masked AutoDecoder is Effective Multi-Task Vision Generalist

Add code
Mar 14, 2024
Figure 1 for Masked AutoDecoder is Effective Multi-Task Vision Generalist
Figure 2 for Masked AutoDecoder is Effective Multi-Task Vision Generalist
Figure 3 for Masked AutoDecoder is Effective Multi-Task Vision Generalist
Figure 4 for Masked AutoDecoder is Effective Multi-Task Vision Generalist
Viaarxiv icon

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

Add code
Mar 07, 2024
Figure 1 for Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
Figure 2 for Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
Figure 3 for Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
Figure 4 for Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
Viaarxiv icon