[CVPR25] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"

Mobile-VideoGPT: Fast and Accurate Video Understanding Language Model

An encyclopedia of jailbreaking techniques to make AI models safer.

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!

Scaling Vision Pre-Training to 4K Resolution

[icml, iclr, cvpr, neurips, eccv, iccv]: browse through whole conference by just reading a book of abstract. My fingers hurt having to click each paper. We want to read everything lol. So, i took t…

RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO & designed for fine-tuning.

Implementation of paper EditCLIP: Representation Learning for Image Editing

Practical tips for effective AI-assisted software development

Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

History-Aware Transformation of ReID Features for Multiple Object Tracking

A curated list of Person Re-Identification papers and BibTeX entries

A personal list of papers and resources of image matching and pose estimation, including perspective images and panoramas.

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Bringing BERT into modernity via both architecture changes and scaling

Assessing Context-Aware Creative Intelligence in MLLMs

A curated list of temporal action localization/detection and related area (e.g. temporal action proposal) resources.

Temporal Action Detection & Weakly Supervised Temporal Action Detection & Temporal Action Proposal Generation

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Segment-anything related awesome extensions/projects/repos.

Tracking and collecting papers/projects/others related to Segment Anything.

General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX

The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling

[CVPR 2024] Real-Time Open-Vocabulary Object Detection