attract-repel
by nmrksic
The Attract-Repel algorithm presented in (Mrkšić et al., TACL 2017), with accompanying resources.
AI summary
Vector tuner
An algorithm for fine-tuning word vector spaces using linguistic constraints
- stars
- 64
- forks
- 17
- watching
- 9
Similar projects
Found by comparing what the projects do, not just their names.
Vector updater
A tool to update word vectors to align with linguistic constraints
roboflow/maestro1.4K
fine-tuner
A tool to streamline fine-tuning of multimodal models for vision-language tasks
Vector inducer
Tools and code for inducing custom semantic vector representations from text data
Noisy label solver
Develops a robust learning framework to handle noisy labels in multimodal data and improve cross-modal retrieval.
Data cleaner
Automated tool to detect and flag spatial and temporal errors in biological data
Model fine-tuner
Provides guidance on fine-tuning pre-trained models for image classification tasks using PyTorch.
NLP vectors
A repository providing pre-built non-distributional word vector representations for NLP tasks
Tracer
Generates vector maps by tracing raster images.
Model optimizer
Enables the creation of smaller neural network models through efficient pruning and quantization techniques
Attention calibrator
This project proposes a novel method for calibrating attention distributions in multimodal models to improve contextualized representations of image-text pairs.
Safety fine-tuner
Improves safety and helpfulness of large language models by fine-tuning them using safety-critical tasks
Domain adaptation model
This project implements a deep learning-based approach to adapt semantic segmentation models from one domain to another.
Numerical stabilizer
Improves numerical stability in Haskell code by automatically rewriting floating point computations.
NMPC solver
An automatic code generator and solver for nonlinear model predictive control (NMPC) problems.
Parser
A markdown parser designed to produce high-quality error messages and offer extensions for customizing its behavior
