[CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

[ICCV'25 oral] Official Code for "LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"

[ICCV 2025] MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance

AI agents running research on single-GPU nanochat training automatically

[ACL 2026] Open-source framework for holistic, structured repository-level documentation across multilingual codebases

Pytorch implementation of convolutional neural network visualization techniques

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

OpenRSD: Towards Open-Prompt Object Detection in Remote Sensing

[ACL 2025] Mitigating Non-Representative Prototypes and Representation Bias in Few-Shot Continual Relation Extraction

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Official implementation of the paper: Mitigating Non-Representative Prototypes and Representation Bias in Few-Shot Continual Relation Extraction

Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity"

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]

Hyperbolic Hierarchical Clustering.

PyTorch Implementation of the CVPR'25 Paper "Fitted Neural Lossless Image Compression"

A curated list for Efficient Large Language Models

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

[ECCV'24/IJCV'26] Code repo for "Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning"

The source code of paper LearningtoPromptKnowledgeTransferforOpen-WorldContinualLearning (AAAI-24) will be released in the near future.

Code & Dataset repository for the paper "Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation"

[AAAI'25] Official Code for “Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community"

An Ensemble-of-Experts Framework for Rehearsal-free Continual Relation Extraction. Findings of ACL 2024

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

[ECCV2024 Oral] Official implementation of the paper "Relation DETR: Exploring Explicit Position Relation Prior for Object Detection"