Temporal Network Noise Contrastive Estimation (teneNCE) for Dynamic Link Prediction
-
Updated
Aug 31, 2024 - Python
Temporal Network Noise Contrastive Estimation (teneNCE) for Dynamic Link Prediction
Comparing performance of different InfoNCE type losses used in contrastive learning.
Neural Audio Style Transfer between piano and violin using GAN-based Encoder-Decoder architecture based on Disentanglement of Latent Representations of the input in complex domain
Controlled benchmark comparing MLP and FT-Transformer-style EHR encoders for multimodal retrieval.
Minimal CLIP from scratch — ResNet-20 image encoder + Transformer text encoder + Symmetric InfoNCE on CIFAR-10 / PyTorch로 직접 구현한 미니 CLIP — ResNet-20 이미지 인코더 + Transformer 텍스트 인코더 + Symmetric InfoNCE 손실 (CIFAR-10)
Controlled benchmark for studying CXR-text contrastive retrieval, image-report alignment, and retrieval failure modes.
Controlled benchmark comparing standard InfoNCE and false-negative-aware contrastive learning for retrieval.
SciFact retrieval experiments with BM25, hard negatives, custom InfoNCE dual encoders, and reranking.
Grounding Spatial Representations via Visual World Models for Robust Autoregressive Drift Reduction in Low-Power Robot Telemetry
To associate your repository with the infonce topic, visit your repo's landing page and select "manage topics."