语言大模型 / LLM

MOFI: Learning Image Representations from Noisy Entity Annotated Images

Wentao Wu, Aleksei Timofeev, Chen Chen, Bowen Zhang, Kun Duan, Shuangning Liu, Yantao Zheng, Jonathon Shlens, Xianzhi Du, Zhe Gan, Yinfei Yang

专题命中 预训练与数据 ：foundation model(abstract)；分类 cs.CL、cs.LG

Comments Accepted to ICLR 2024

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?

Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel

专题命中 预训练与数据 ：foundation model(abstract)；分类 cs.AI、cs.LG

Comments ICLR 2024 camera-ready version

Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost

Oana Ignat, Longju Bai, Joan Nwatu, Rada Mihalcea

专题命中 预训练与数据 ：foundation model(abstract)；分类 cs.CL、cs.AI

Comments accepted at COLING 2024

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

Hao Chen, Jindong Wang, Ankit Shah, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj

专题命中 预训练与数据 ：language model(abstract)；分类 cs.AI、cs.LG

Comments ICLR 2024 Spotlight

CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?

Ibrahim Alabdulmohsin, Xiao Wang, Andreas Steiner, Priya Goyal, Alexander D'Amour, Xiaohua Zhai

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments 32 pages, 20 figures, 7 tables

Journal ref ICLR 2024

Encodings for Prediction-based Neural Architecture Search

Yash Akhauri, Mohamed S. Abdelfattah

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

TinyLLaVA: A Framework of Small-scale Large Multimodal Models

Baichuan Zhou, Ying Hu, Xi Weng, Junlong Jia, Jie Luo, Xien Liu, Ji Wu, Lei Huang

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Our model weights and codes will be made public at https://github.com/DLCV-BUAA/TinyLLaVABench

LogicPrpBank: A Corpus for Logical Implication and Equivalence

Zhexiong Liu, Jing Zhang, Jiaying Lu, Wenjing Ma, Joyce C Ho

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments In the 5th AI4ED Workshop, held in conjunction with The 38th AAAI Conference on Artificial Intelligence, February 2024

Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs

Jonas Golde, Patrick Haller, Felix Hamborg, Julian Risch, Alan Akbik

专题命中 预训练与数据 ：LLM(abstract)；分类 cs.CL、cs.AI

Comments 3 Figures and 2 Tables

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, Christopher D. Manning

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.LG

Scaling laws for language encoding models in fMRI

Richard Antonello, Aditya Vaidya, Alexander G. Huth

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to the Thirty-seventh Annual Conference on Neural Information Processing Systems (NeurIPS 2023). Please cite NeurIPS version

Textual Entailment for Effective Triple Validation in Object Prediction

Andrés García-Silva, Cristian Berrío, José Manuel Gómez-Pérez

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ISWC'23 - The International Semantic Web Conference

Capturing Pertinent Symbolic Features for Enhanced Content-Based Misinformation Detection

Flavio Merenda, José Manuel Gómez-Pérez

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted at K-CAP'23: The 12th Knowledge Capture Conference

EMBRE: Entity-aware Masking for Biomedical Relation Extraction

Mingjie Li, Karin Verspoor

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.AI

Comments 5 pages, 1 figure

Higher-Order DeepTrails: Unified Approach to *Trails

Tobias Koopmann, Jan Pfister, André Markus, Astrid Carolus, Carolin Wienrich, Andreas Hotho

专题命中 预训练与数据 ：language model(abstract)；分类 cs.AI、cs.LG

Evaluating Self-Supervised Learning via Risk Decomposition

Yann Dubois, Tatsunori Hashimoto, Percy Liang

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments Oral at ICML 2023

A 3D super-resolution of wind fields via physics-informed pixel-wise self-attention generative adversarial network

Takuya Kurihana, Kyongmin Yeo, Daniela Szwarcman, Bruce Elmegreen, Karthik Mukkavilli, Johannes Schmude, Levente Klein

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 4 figures, NeurIPS 2023 Workshop: Tackling Climate Change with Machine Learning

High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models

Chunyu Qiang, Hao Li, Yixin Tian, Yi Zhao, Ying Zhang, Longbiao Wang, Jianwu Dang

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.AI

Comments Accepted by ICASSP 2024. arXiv admin note: substantial text overlap with arXiv:2307.15484; text overlap with arXiv:2309.00424

Data and Approaches for German Text simplification -- towards an Accessibility-enhanced Communication

Thorben Schomacker, Michael Gille, Jörg von der Hülls, Marina Tropmann-Frick

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Acoustic models of Brazilian Portuguese Speech based on Neural Transformers

Marcelo Matheus Gauy, Marcelo Finger

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.LG

Comments Under review at Journal of Brazilian Computer Society

A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning

Yinmin Zhang, Jie Liu, Chuming Li, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments Accepted at AAAI 2024

Ignorance is Bliss: Robust Control via Information Gating

Manan Tomar, Riashat Islam, Matthew E. Taylor, Sergey Levine, Philip Bachman

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2023

Binarized Neural Machine Translation

Yichi Zhang, Ankush Garg, Yuan Cao, Łukasz Lew, Behrooz Ghorbani, Zhiru Zhang, Orhan Firat

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.LG

Journal ref Published at NeurIPS 2023

From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces

Peter Shaw, Mandar Joshi, James Cohan, Jonathan Berant, Panupong Pasupat, Hexiang Hu, Urvashi Khandelwal, Kenton Lee, Kristina Toutanova

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.LG

Handwriting recognition and automatic scoring for descriptive answers in Japanese language tests

Hung Tuan Nguyen, Cuong Tuan Nguyen, Haruki Oka, Tsunenori Ishioka, Masaki Nakagawa

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Keywords: handwritten Japanese answers, handwriting recognition, automatic scoring, ensemble recognition, deep neural networks; Reported in IEICE technical report, PRMU2021-32, pp.45-50 (2021.12) Published after peer review and Presented in ICFHR2022, Lecture Notes in Computer Science, vol. 13639, pp. 274-284 (2022.11)

Mirror: A Universal Framework for Various Information Extraction Tasks

Tong Zhu, Junfei Ren, Zijian Yu, Mengsong Wu, Guoliang Zhang, Xiaoye Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Min Zhang

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.AI

Comments Accepted to EMNLP23 main conference

The Impact of Data Corruption on Named Entity Recognition for Low-resourced Languages

Manuel Fokam, Michael Beukman

专题命中 预训练与数据 ：language model(abstract)；分类 cs.CL、cs.AI

Adaptive Training Distributions with Scalable Online Bilevel Optimization

David Grangier, Pierre Ablin, Awni Hannun

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.CL、cs.LG

AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing

Namjoon Suh, Xiaofeng Lin, Din-Yin Hsieh, Merhdad Honarkhah, Guang Cheng

专题命中 预训练与数据 ：language model(abstract)；分类 cs.AI、cs.LG

Augmenting Unsupervised Reinforcement Learning with Self-Reference

Andrew Zhao, Erle Zhu, Rui Lu, Matthieu Lin, Yong-Jin Liu, Gao Huang

专题命中 预训练与数据 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments Preprint