paper-with-me

홈 › Papers

A Comparison between Pre-training and Large-scale Back-translation for Neural Machine Translation

2021-08-01 · Findings (ACL) 2021 8 · Dandan Huang, Kun Wang, Yue Zhang
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Training Language Models with Language Feedback at Scale

2023-03-28 · Jérémy Scheurer, Jon Ander Campos, Tomasz Korbak, Jun Shern Chan 외

Pretrained language models often generate outputs that are not in line with human preferences, such as harmful text or factually incorrect summaries. Recent work approaches the above issues by learning from a simple form…

Bayesian InferenceImitation LearningLanguage ModelingLanguage Modelling

Dialogue Response Ranking Training with Large-Scale Human Feedback Data

2020-09-15 · EMNLP 2020 11 · Xiang Gao, Yizhe Zhang, Michel Galley, Chris Brockett 외

Existing open-domain dialog models are generally trained to minimize the perplexity of target human responses. However, some human replies are more engaging than others, spawning more followup interactions. Current conve…

Conversational Response SelectionOpen-Domain Dialog

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

2025-03-19 · Federico Cocchi, Nicholas Moratelli, Davide Caffagni, Sara Sarto 외

Recent progress in Multimodal Large Language Models (MLLMs) has highlighted the critical roles of both the visual backbone and the underlying language model. While prior work has primarily focused on scaling these compon…

Instruction FollowingMultimodal Reasoning

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

2023-10-30 · NeurIPS 2023 11 · Micah Goldblum, Hossein Souri, Renkun Ni, Manli Shu 외

Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an ImageNet-trained convolutional neural n…

Benchmarkingobject-detectionObject DetectionSelf-Supervised Learning

Reward Learning from Multiple Feedback Types

2025-02-28 · Yannick Metz, András Geiszl, Raphaël Baur, Mennatallah El-Assady

Learning rewards from preference feedback has become an important tool in the alignment of agentic models. Preference-based feedback, often implemented as a binary comparison between multiple completions, is an establish…