All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
-
Updated
Sep 21, 2026 - Python
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
Compile and explore a curated list of 350+ loss functions with papers, formulas, and code across deep learning and machine learning fields.
Orchestrate ML experiments and production pipelines with Tangle's flexible, run-anywhere system.
Download manga from Comick.io and beyond with blazing-fast concurrent downloads, a beautiful CLI & GUI, and support for Windows, macOS, and Linux.
Build AI chat components for Flutter with source code ownership and shadcn/ui-style patterns
Contrastive pre-training for technology-agnostic single-cell representations beyond reconstruction
A Time-Aware Self-Supervised Framework for Anomaly Detection in Temporal Graphs
A python library for self-supervised learning on images.
Code for "Mask- and Contrast-Enhanced Spatio-Temporal Learning for Urban Flow Prediction" (CIKM 2023)
Code for "Spatio-temporal fusion and contrastive learning for urban flow prediction" (Knowledge-Based Systems 2023)
Enhance BERT fine-tuning for intent classification using supervised contrastive learning, LoRA, and layer-wise learning rate decay for better accuracy and efficiency
Explore limitations of contrastive SAE steering in identifying causal consciousness features and introduce delta-steering to improve experiment validity.
🔍 Implement SimSiam for self-supervised contrastive learning on CIFAR-10, comparing its performance against supervised and multi-task models.
This repository is the official implementation of 'DrIM: Context-Driven Nearest Neighbor Imputation using Language Representation' with PyTorch (PAKDD 2026).
A custom-built deep learning system for multimodal malware detection. It features an attention-based BiLSTM for threat intelligence extraction and a CNN for visual malware representations, joined via cross-modal contrastive learning to achieve MITRE ATT&CK-aligned explainability.
Contrastive representation learning for polymer informatics
This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]
Recommend music using a contrastive learning model and acoustic feature vectors to improve discovery.
Adapt network parameters dynamically to improve 3D scene understanding performance.
Apply known function prototypes to indirect CALL instructions in IDA Pro to improve decompiler and disassembler accuracy for runtime APIs.
To associate your repository with the contrastive-learning topic, visit your repo's landing page and select "manage topics."