语言大模型 / LLM - arXivDaily 专题

2409.20467 2024-10-01 cs.CL cs.AI 62%

A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Media

Dung Ha Nguyen, Anh Thi Hoang Nguyen, Kiet Van Nguyen

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

2409.19532 2024-10-01 cs.CV cs.CL cs.LG cs.MM 62%

Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding

Xiao Wang, Jianlong Wu, Zijia Lin, Fuzheng Zhang, Di Zhang, Liqiang Nie

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

Comments Under peer review

2310.15961 2024-09-25 cs.CL cs.LG 62%

Mixture of Tokens: Continuous MoE through Cross-Example Aggregation

Szymon Antoniak, Michał Krutul, Maciej Pióro, Jakub Krajewski, Jan Ludziejewski, Kamil Ciebiera, Krystian Król, Tomasz Odrzygóźdź, Marek Cygan, Sebastian Jaszczur

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

2409.14200 2024-09-24 cs.CL cs.CR cs.LG 62%

Data-centric NLP Backdoor Defense from the Lens of Memorization

Zhenting Wang, Zhizhi Wang, Mingyu Jin, Mengnan Du, Juan Zhai, Shiqing Ma

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

2409.13920 2024-09-24 cs.CL cs.LG 62%

One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks

Sebastian Nehrdich, Oliver Hellwig, Kurt Keutzer

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

2404.16193 2024-09-23 cs.CV cs.AI cs.LG cs.MM eess.IV 62%

Improving Multi-label Recognition using Class Co-Occurrence Probabilities

Samyak Rawlekar, Shubhang Bhatnagar, Vishnuvardhan Pogunulu Srinivasulu, Narendra Ahuja

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

Comments Accepted to ICPR 2024, CVPR workshops 2024

2407.03995 2024-09-20 cs.LG cs.AI cs.RO 62%

ROER: Regularized Optimal Experience Replay

Changling Li, Zhang-Wei Hong, Pulkit Agrawal, Divyansh Garg, Joni Pajarinen

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

Journal ref Reinforcement Learning Journal, vol. 4, 2024, pp. 1598-1618

2409.12175 2024-09-19 cs.LG cs.AI 62%

Expanding Expressivity in Transformer Models with MöbiusAttention

Anna-Maria Halacheva, Mojtaba Nayyeri, Steffen Staab

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

2409.08719 2024-09-16 cs.CL cs.AI 62%

Distilling Monolingual and Crosslingual Word-in-Context Representations

Yuki Arase, Tomoyuki Kajiwara

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

2409.07424 2024-09-12 cs.CL cs.CY cs.LG 62%

Towards Fairer Health Recommendations: finding informative unbiased samples via Word Sense Disambiguation

Gavin Butts, Pegah Emdad, Jethro Lee, Shannon Song, Chiman Salavati, Willmar Sosa Diaz, Shiri Dori-Hacohen, Fabricio Murai

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

Comments Accepted for long presentation at the FAcctRec @ Recsys 2024

2402.06784 2024-09-11 cs.CV cond-mat.dis-nn cs.AI cs.LG cs.NA math.NA 62%

Transfer learning with generative models for object detection on limited datasets

Matteo Paiano, Stefano Martina, Carlotta Giannelli, Filippo Caruso

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

Comments 28 pages, 16 figures, 1 table

Journal ref 2024 Mach. Learn.: Sci. Technol. 5 035041

2402.12189 2024-09-04 cs.CL cs.CR cs.LG 62%

Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships

Myung Gyo Oh, Hong Eun Ahn, Leo Hyun Park, Taekyoung Kwon

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

Comments 20 pages, 6 figures, 15 tables

2304.01762 2024-09-02 cs.LG cs.AI stat.ML 62%

Incorporating Unlabelled Data into Bayesian Neural Networks

Mrinank Sharma, Tom Rainforth, Yee Whye Teh, Vincent Fortuin

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

Comments Published in the Transactions on Machine Learning Research

2408.15793 2024-08-29 cs.CL cs.LG 62%

Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough

Konstantin Dobler, Gerard de Melo

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

Comments WANT@ICML 2024

2408.11243 2024-08-28 cs.LG cs.AI 62%

Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?

Qian Ma, Haitao Mao, Jingzhe Liu, Zhehua Zhang, Chunlin Feng, Yu Song, Yihan Shao, Yao Ma

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

2408.08622 2024-08-19 cs.LG cs.AI 62%

DeepDFA: Automata Learning through Neural Probabilistic Relaxations

Elena Umili, Roberto Capobianco

专题命中预训练与数据：post-training(abstract)；分类 cs.AI、cs.LG

2302.01647 2024-08-13 cs.CV cs.AI cs.LG 62%

Blockwise Self-Supervised Learning at Scale

Shoaib Ahmed Siddiqui, David Krueger, Yann LeCun, Stéphane Deny

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

2408.02711 2024-08-07 cs.SD cs.AI cs.LG eess.AS 62%

Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion Models

Pushkar Jajoria, James McDermott

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

2407.21772 2024-08-06 cs.CL cs.LG 62%

ShieldGemma: Generative AI Content Moderation Based on Gemma

Wenjun Zeng, Yuchi Liu, Ryan Mullins, Ludovic Peran, Joe Fernandez, Hamza Harkous, Karthik Narasimhan, Drew Proud, Piyush Kumar, Bhaktipriya Radharapu, Olivia Sturman, Oscar Wahltinez

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

2408.00695 2024-08-02 cs.LG cs.AI 62%

Accelerating Full Waveform Inversion By Transfer Learning

Divya Shyam Singh, Leon Herrmann, Qing Sun, Tim Bürchner, Felix Dietrich, Stefan Kollmannsberger

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

2309.15169 2024-07-30 cs.LG cs.AI 62%

Revealing the Power of Masked Autoencoders in Traffic Forecasting

Jiarui Sun, Yujie Fan, Chin-Chia Michael Yeh, Wei Zhang, Girish Chowdhary

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

Comments Accepted by CIKM 2024

2407.18421 2024-07-29 cs.CL cs.LG 62%

Self-Directed Synthetic Dialogues and Revisions Technical Report

Nathan Lambert, Hailey Schoelkopf, Aaron Gokaslan, Luca Soldaini, Valentina Pyatkin, Louis Castricato

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

Comments 25 pages, 3 figures, 4 tables

2310.08320 2024-07-24 cs.LG cs.CL cs.CR cs.CV 62%

Defending Our Privacy With Backdoors

Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting

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

Comments Accepted at ECAI 2024

2407.14259 2024-07-22 cs.CL cs.LG 62%

Voices in a Crowd: Searching for Clusters of Unique Perspectives

Nikolas Vitsakis, Amit Parekh, Ioannis Konstas

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

2407.14145 2024-07-22 cs.CR cs.AI cs.CL 62%

PassTSL: Modeling Human-Created Passwords through Two-Stage Learning

Yangde Wang, Haozhang Li, Weidong Qiu, Shujun Li, Peng Tang

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

Journal ref Lecture Notes in Computer Science 14897 (2024) 404-423

2402.18286 2024-07-19 cs.CV cond-mat.mtrl-sci cs.AI cs.LG 62%

Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy

Bashir Kazimi, Karina Ruzaeva, Stefan Sandfeld

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

2407.12881 2024-07-19 cs.CL cs.AI 62%

BinaryAlign: Word Alignment as Binary Sequence Labeling

Gaetan Lopez Latouche, Marc-André Carbonneau, Ben Swanson

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

Comments Accepted to ACL 2024

2407.12669 2024-07-18 cs.CV cs.AI cs.LG 62%

Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data

Richard Osuala, Daniel M. Lang, Anneliese Riess, Georgios Kaissis, Zuzanna Szafranowska, Grzegorz Skorupko, Oliver Diaz, Julia A. Schnabel, Karim Lekadir

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

Comments Early Accept at MICCAI 2024 Deep-Breath Workshop

2404.07982 2024-07-18 cs.CL cs.LG 62%

The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments

Anton Schäfer, Shauli Ravfogel, Thomas Hofmann, Tiago Pimentel, Imanol Schlag

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

2407.11855 2024-07-17 cs.CL cs.CV cs.LG 62%

Scaling Sign Language Translation

Biao Zhang, Garrett Tanzer, Orhan Firat

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

1. 预训练与数据 12502 篇

A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Media

Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding

Mixture of Tokens: Continuous MoE through Cross-Example Aggregation

Data-centric NLP Backdoor Defense from the Lens of Memorization

One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks

Improving Multi-label Recognition using Class Co-Occurrence Probabilities

ROER: Regularized Optimal Experience Replay

Expanding Expressivity in Transformer Models with MöbiusAttention

Distilling Monolingual and Crosslingual Word-in-Context Representations

Towards Fairer Health Recommendations: finding informative unbiased samples via Word Sense Disambiguation

Transfer learning with generative models for object detection on limited datasets

Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships

Incorporating Unlabelled Data into Bayesian Neural Networks

Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough

Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?

DeepDFA: Automata Learning through Neural Probabilistic Relaxations

Blockwise Self-Supervised Learning at Scale

Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion Models

ShieldGemma: Generative AI Content Moderation Based on Gemma

Accelerating Full Waveform Inversion By Transfer Learning

Revealing the Power of Masked Autoencoders in Traffic Forecasting

Self-Directed Synthetic Dialogues and Revisions Technical Report

Defending Our Privacy With Backdoors

Voices in a Crowd: Searching for Clusters of Unique Perspectives

PassTSL: Modeling Human-Created Passwords through Two-Stage Learning

Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy

BinaryAlign: Word Alignment as Binary Sequence Labeling

Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data

The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments

Scaling Sign Language Translation