Wakals/CoVT-LLaVA-13B-depth

Model

stars

commits

linked in READMEs

Dec 5, 2025

updated

llava_llama

safetensors

README

CoVT Checkpoint (Segmentation, Depth, and DINO Aligned)

Checkpoint of https://huggingface.co/papers/2511.19418.

Model Description

This CoVT checkpoint is aligned with 4 Depth tokens, based on LLaVA-v1.5-13B.
These task-specific tokens are integrated into the model’s embedding space to enhance 3D-awareness.

Contributors

Wakals

4 commits

Similar repos

Wakals/CoVT-7B-seg_depth_dino

Model

Wakals/CoVT-7B-seg_depth_dino_edge

Model

Wakals/CoVT-7B-depth

Model

Wakals/CoVT-7B-seg

Model

facebook/dinov3-vitl16-chmv2-dpt-head

cpystan/SD-VLM-7B

OliverHuang1998/3DRS

ChaimZhu/LLaVA-3D-7B

Linked in READMEs

Wakals/CoVT

[ECCV 2026] Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with…

399

README badge

FufenNan/covt_data

README badge

DDDaar/COVT

README badge

README

CoVT Checkpoint (Segmentation, Depth, and DINO Aligned)

Checkpoint of https://huggingface.co/papers/2511.19418.

Model Description

This CoVT checkpoint is aligned with 4 Depth tokens, based on LLaVA-v1.5-13B.
These task-specific tokens are integrated into the model’s embedding space to enhance 3D-awareness.