ConvLLaVA

non-profit

AI & ML interests

Large Multimodal Models

authored 2 papers over 1 year ago

Instruction-Guided Visual Masking

Paper • 2405.19783 • Published May 30, 2024 • 2

VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI

Paper • 2410.11623 • Published Oct 15, 2024 • 49

authored 3 papers almost 2 years ago

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models

Paper • 2403.07714 • Published Mar 12, 2024 • 1

Can Vision-Language Models Think from a First-Person Perspective?

Paper • 2311.15596 • Published Nov 27, 2023 • 3

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Paper • 2309.11235 • Published Sep 20, 2023 • 15

updated 9 models almost 2 years ago

ConvLLaVA/ConvLLaVA-sft-1536

Text Generation • Updated May 28, 2024 • 16

ConvLLaVA/ConvLLaVA-sft-1024

Text Generation • Updated May 28, 2024 • 48

ConvLLaVA/ConvLLaVA-sft-768

Text Generation • Updated May 28, 2024 • 2 • 1

ConvLLaVA/ConvLLaVA-pretrain-1536

Text Generation • Updated May 28, 2024 • 7 • 2

ConvLLaVA/ConvLLaVA-pretrain-1024

Text Generation • Updated May 28, 2024 • 5

ConvLLaVA/ConvLLaVA-pretrain-768

Text Generation • Updated May 28, 2024 • 4 • 1

ConvLLaVA/ConvLLaVA-ConvNeXt-1536

Updated May 28, 2024 • 25 • 1

ConvLLaVA/ConvLLaVA-ConvNeXt-768

Updated May 28, 2024 • 81

ConvLLaVA/ConvLLaVA-ConvNeXt-1024

Updated May 28, 2024 • 74

authored a paper almost 2 years ago

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

Paper • 2405.15738 • Published May 24, 2024 • 46

authored a paper almost 2 years ago

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

Paper • 2405.15738 • Published May 24, 2024 • 46

updated a model almost 2 years ago

ConvLLaVA/LAION-CLIP-ConvNeXt-Large-512

Zero-Shot Image Classification • Updated May 26, 2024 • 1