Search Results for author:
Found 11 papers, 4 papers with code
Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation
Intuitively, the MC-GNN layer substitutes a self-attention layer at the encoder side of a transformer-based machine translation model.
Bellman Optimal Stepsize Straightening of Flow-Matching Models
This paper introduces Bellman Optimal Stepsize Straightening (BOSS) technique for distilling flow-matching generative models: it aims specifically for a few-step efficient image sampling while adhering to a computational budget constraint.
Ranked #1 on
Image Generation
on LSUN Churches 256 x 256
(clean-FID metric)
Flow Matching in Latent Space
In this work, we propose to apply flow matching in the latent spaces of pretrained autoencoders, which offers improved computational efficiency and scalability for high-resolution image synthesis.
Ranked #4 on
Image Generation
on CelebA-HQ 256x256
Application of Self-Supervised Learning to MICA Model for Reconstructing Imperfect 3D Facial Structures
In this study, we emphasize the integration of a pre-trained MICA model with an imperfect face dataset, employing a self-supervised learning approach.
Ontology-based Solution for Building an Intelligent Searching System on Traffic Law Documents
In this paper, an ontology-based approach is used to organize the knowledge base of legal documents in road traffic law.
Co-Factorization Model for Collaborative Filtering with Session-based Data
Despite that MF is a powerful method, it suffers from not be able to identifying strong associations of closely related items.
Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging
However, there are still difficulties in standardizing the output of ASR such as capitalization and punctuation restoration for long-speech transcription.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Bayesian Active Learning With Abstention Feedbacks
We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate.
Learning Representations from Product Titles for Modeling Shopping Transactions
In this paper, we propose BASTEXT, an efficient model of shopping baskets and the texts associated with the products (e. g., product titles).
Hyperledger Fabric: A Distributed Operating System for Permissioned Blockchains
Fabric is a modular and extensible open-source system for deploying and operating permissioned blockchains and one of the Hyperledger projects hosted by the Linux Foundation (www. hyperledger. org).
Distributed, Parallel, and Cluster Computing Cryptography and Security
Bayesian Pool-based Active Learning With Abstention Feedbacks
We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate.
