Nomic Embed: Training a Reproducible Long Context Text Embedder
Feb 25, 2025 · This technical report describes the training of nomic-embed-text-v1, the first fully reproducible, open-source, open-weights, open-data, 8192 context length English text embedding …
Abstract The Machine Learning (ML) community has wit-nessed explosive growth, with millions of ML models being published on the Web. Reusing ML model components has been prevalent nowadays. …
The evaluation of extremely long-context capabilities presents challenges, as existing benchmarks (Yang et al., 2018; Tay et al., 2021) no longer align with the advanced processing abilities of current …
Chaos as an interpretable benchmark for forecasting and data …
Oct 11, 2021 · We present a curated collection of chaotic dynamical systems for benchmarking and interpreting forecasting and data-driven modelling, which can be re-integrated to generate new …
Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands...
Jul 29, 2025 · Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies fail to …
Evaluating Open-QA Evaluation | OpenReview
Sep 26, 2023 · This study focuses on the evaluation of the Open Question Answering (Open-QA) task, which can directly estimate the factuality of large language models (LLMs). Current automatic …
NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep...
Sep 25, 2023 · Recently, the Deep Learning community has become interested in evolutionary optimization (EO) as a means to address hard optimization problems, e.g. meta-learning through …
NeoRL: A Near Real-World Benchmark for Offline Reinforcement …
Sep 16, 2022 · NeoRL presents conservative datasets for offline RL, highlights the complete pipeline for deploying offline RL in real-world applications, and also benchmarks recent offline RL algorithms on …
WRENCH: A Comprehensive Benchmark for Weak Supervision
Oct 11, 2021 · Abstract: Recent Weak Supervision (WS) approaches have had widespread success in easing the bottleneck of labeling training data for machine learning by synthesizing labels from …
Signatory: differentiable computations of the signature and...
Jan 12, 2021 · Signatory is a library for calculating and performing functionality related to the signature and logsignature transforms. The focus is on machine learning, and as such includes features such …