Search Results for author:
Found 8 papers, 4 papers with code
INDUS: Effective and Efficient Language Models for Scientific Applications
The suite of models include: (1) an encoder model trained using domain-specific vocabulary and corpora to address NLP tasks, (2) a contrastive-learning based text embedding model trained using a diverse set of datasets to address information retrieval tasks and (3) smaller versions of these models created using knowledge distillation for applications which have latency or resource constraints.
Accelerating Production LLMs with Combined Token/Embedding Speculators
This technical report describes the design and training of novel speculative decoding draft models, for accelerating the inference speeds of large language models in a production environment.
SudokuSens: Enhancing Deep Learning Robustness for IoT Sensing Applications using a Generative Approach
To incorporate sufficient diversity into the IoT training data, one therefore needs to consider a combinatorial explosion of training cases that are multiplicative in the number of objects considered and the possible environmental conditions in which such objects may be encountered.
Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners
Existing approaches generally assume that the shot number at test time is known in advance.
Few-Shot Classification with Feature Map Reconstruction Networks
In this paper we reformulate few-shot classification as a reconstruction problem in latent space.
Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
We aim to build image generation models that generalize to new domains from few examples.
Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e. g., birds) based on a few images alone.
Few-Shot Learning with Localization in Realistic Settings
Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones.
