语言大模型 / LLM - arXivDaily 专题

2411.00683 2024-11-04 cs.CV cs.AI cs.CL cs.LG 67%

TaxaBind: A Unified Embedding Space for Ecological Applications

Srikumar Sastry, Subash Khanal, Aayush Dhakal, Adeel Ahmad, Nathan Jacobs

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

Comments Accepted to WACV 2025

2407.17453 2024-11-04 cs.CV 67%

VILA$^2$: VILA Augmented VILA

Yunhao Fang, Ligeng Zhu, Yao Lu, Yan Wang, Pavlo Molchanov, Jan Kautz, Jang Hyun Cho, Marco Pavone, Song Han, Hongxu Yin

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

2403.06904 2024-10-30 cs.CV 67%

Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks

Muhammad Saif Ullah Khan, Muhammad Ferjad Naeem, Federico Tombari, Luc Van Gool, Didier Stricker, Muhammad Zeshan Afzal

专题命中预训练与数据：LLM(abstract)；pretraining(abstract)

2410.16163 2024-10-22 cs.CV 67%

Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models

Yufei Zhan, Hongyin Zhao, Yousong Zhu, Fan Yang, Ming Tang, Jinqiao Wang

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments This work has been submitted to the IEEE for possible publication. Codes and data will be later released at https://github.com/jefferyZhan/Griffon

2410.15509 2024-10-22 cs.LG cs.AI cs.CL cs.CV 67%

Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training

Rohan Saha, Abrar Fahim, Alona Fyshe, Alex Murphy

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

Comments CoNLL BabyLM Challenge 2024 camera ready

2404.01476 2024-10-22 cs.CV cs.AI cs.CL cs.LG 67%

TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering

Chuyi Shang, Amos You, Sanjay Subramanian, Trevor Darrell, Roei Herzig

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

Comments EMNLP 2024 (Main)

2410.13419 2024-10-18 cs.SD cs.MM eess.AS 67%

MeloTrans: A Text to Symbolic Music Generation Model Following Human Composition Habit

Yutian Wang, Wanyin Yang, Zhenrong Dai, Yilong Zhang, Kun Zhao, Hui Wang

专题命中预训练与数据：large language model(abstract)；language model(abstract)

2310.01166 2024-10-16 cs.SE cs.CR 67%

Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models

Zhou Yang, Zhipeng Zhao, Chenyu Wang, Jieke Shi, Dongsum Kim, Donggyun Han, David Lo

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments Accepted by IEEE Transactions on Software Engineering, Camera-Ready Version

2410.08325 2024-10-14 eess.AS 67%

Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer

Slava Shechtman, Avihu Dekel

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments You can download the model from DAC.speech.v1.0" target="_blank" rel="noopener">https://huggingface.co/ibm/DAC.speech.v1.0

Journal ref Proc. Interspeech 2024, 4174-4178

2311.07682 2024-10-11 cs.CL cs.AI cs.LG 67%

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion

Kerem Zaman, Leshem Choshen, Shashank Srivastava

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

Comments 21 pages, 12 figures, 7 tables; To appear at EMNLP 2024

2403.13248 2024-10-07 cs.CV 67%

Mora: Enabling Generalist Video Generation via A Multi-Agent Framework

Zhengqing Yuan, Yixin Liu, Yihan Cao, Weixiang Sun, Haolong Jia, Ruoxi Chen, Zhaoxu Li, Bin Lin, Li Yuan, Lifang He, Chi Wang, Yanfang Ye, Lichao Sun

专题命中预训练与数据：large language model(abstract)；language model(abstract)

2404.16538 2024-10-01 cs.CV 67%

OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images

Ye Mao, Junpeng Jing, Krystian Mikolajczyk

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

Comments 17 pages (Accepted by NeurIPS 2024)

2409.17943 2024-09-27 cs.CL cs.AI cs.LG 67%

On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms

Richard Yue, John E. Ortega, Kenneth Ward Church

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

Comments AMTA 2024 - The Association for Machine Translation in the Americas organizes biennial conferences devoted to researchers, commercial users, governmental and NGO users

2405.10610 2024-09-24 cs.CV 67%

Harnessing Vision-Language Pretrained Models with Temporal-Aware Adaptation for Referring Video Object Segmentation

Zikun Zhou, Wentao Xiong, Li Zhou, Xin Li, Zhenyu He, Yaowei Wang

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

2409.03055 2024-09-11 cs.SD eess.AS 67%

SymPAC: Scalable Symbolic Music Generation With Prompts And Constraints

Haonan Chen, Jordan B. L. Smith, Janne Spijkervet, Ju-Chiang Wang, Pei Zou, Bochen Li, Qiuqiang Kong, Xingjian Du

专题命中预训练与数据：language model(abstract)；prompting(abstract)

Comments ISMIR 2024

2404.13993 2024-09-06 cs.MM cs.CV 67%

Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion

Yingxuan Li, Ryota Hinami, Kiyoharu Aizawa, Yusuke Matsui

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments Accepted to ACM Multimedia 2024. Project page: https://liyingxuan1012.github.io/zeroshot-speaker-prediction ; Github repo: https://github.com/liyingxuan1012/zeroshot-speaker-prediction

2311.01020 2024-09-04 cs.SE 67%

Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on GitHub and Stack Overflow

Xiyu Zhou, Peng Liang, Beiqi Zhang, Zengyang Li, Aakash Ahmad, Mojtaba Shahin, Muhammad Waseem

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments Preprint accepted for publication in Journal of Systems and Software, 2024

2211.07712 2024-09-01 cs.CL cs.AI cs.LG 67%

Cloning Ideology and Style using Deep Learning

Omer Beg, Muhammad Nasir Zafar, Waleed Anjum

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

Comments 11 pages, 7 figures, 3 tables

2408.14259 2024-08-27 cs.SE 67%

Towards Synthetic Trace Generation of Modeling Operations using In-Context Learning Approach

Vittoriano Muttillo, Claudio Di Sipio, Riccardo Rubei, Luca Berardinelli, MohammadHadi Dehghani

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments Accepted at the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024)

2408.13788 2024-08-27 cs.CV 67%

3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing

Shichao Dong, Ze Yang, Guosheng Lin

专题命中预训练与数据：language model(abstract)；foundation model(abstract)

2203.11702 2024-08-26 cs.CL cs.AI cs.LG 67%

BERT-ASC: Auxiliary-Sentence Construction for Implicit Aspect Learning in Sentiment Analysis

Murtadha Ahmed, Bo Wen, Shengfeng Pan, Jianlin Su, Luo Ao, Yunfeng Liu

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

Comments under review

2408.10734 2024-08-21 cs.IR 67%

Vector Symbolic Open Source Information Discovery

Cai Davies, Sam Meek, Philip Hawkins, Benomy Tutcher, Graham Bent, Alun Preece

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Journal ref Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications VI, vol. 13051, pp. 380-390. SPIE, 2024

2408.05729 2024-08-13 cs.CV 67%

A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot

Haoxuan Ding, Qi Wang, Junyu Gao, Qiang Li

专题命中预训练与数据：large language model(abstract)；language model(abstract)

2408.04641 2024-08-12 cs.CL cs.AI cs.LG 67%

GPT-3 Powered Information Extraction for Building Robust Knowledge Bases

Ritabrata Roy Choudhury, Soumik Dey

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

2402.09611 2024-08-09 cs.CL cs.AI cs.CV cs.LG 67%

Towards Privacy-Aware Sign Language Translation at Scale

Phillip Rust, Bowen Shi, Skyler Wang, Necati Cihan Camgöz, Jean Maillard

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

Comments ACL 2024

2406.11704 2024-08-08 cs.CL cs.AI cs.LG 67%

Nemotron-4 340B Technical Report

Nvidia, :, Bo Adler, Niket Agarwal, Ashwath Aithal, Dong H. Anh, Pallab Bhattacharya, Annika Brundyn, Jared Casper, Bryan Catanzaro, Sharon Clay, Jonathan Cohen, Sirshak Das, Ayush Dattagupta, Olivier Delalleau, Leon Derczynski, Yi Dong, Daniel Egert, Ellie Evans, Aleksander Ficek, Denys Fridman, Shaona Ghosh, Boris Ginsburg, Igor Gitman, Tomasz Grzegorzek, Robert Hero, Jining Huang, Vibhu Jawa, Joseph Jennings, Aastha Jhunjhunwala, John Kamalu, Sadaf Khan, Oleksii Kuchaiev, Patrick LeGresley, Hui Li, Jiwei Liu, Zihan Liu, Eileen Long, Ameya Sunil Mahabaleshwarkar, Somshubra Majumdar, James Maki, Miguel Martinez, Maer Rodrigues de Melo, Ivan Moshkov, Deepak Narayanan, Sean Narenthiran, Jesus Navarro, Phong Nguyen, Osvald Nitski, Vahid Noroozi, Guruprasad Nutheti, Christopher Parisien, Jupinder Parmar, Mostofa Patwary, Krzysztof Pawelec, Wei Ping, Shrimai Prabhumoye, Rajarshi Roy, Trisha Saar, Vasanth Rao Naik Sabavat, Sanjeev Satheesh, Jane Polak Scowcroft, Jason Sewall, Pavel Shamis, Gerald Shen, Mohammad Shoeybi, Dave Sizer, Misha Smelyanskiy, Felipe Soares, Makesh Narsimhan Sreedhar, Dan Su, Sandeep Subramanian, Shengyang Sun, Shubham Toshniwal, Hao Wang, Zhilin Wang, Jiaxuan You, Jiaqi Zeng, Jimmy Zhang, Jing Zhang, Vivienne Zhang, Yian Zhang, Chen Zhu

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

2407.15819 2024-07-23 cs.CV 67%

Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight

Ziyuan Huang, Kaixiang Ji, Biao Gong, Zhiwu Qing, Qinglong Zhang, Kecheng Zheng, Jian Wang, Jingdong Chen, Ming Yang

专题命中预训练与数据：large language model(abstract)；language model(abstract)

2403.15378 2024-07-23 cs.CV 67%

Long-CLIP: Unlocking the Long-Text Capability of CLIP

Beichen Zhang, Pan Zhang, Xiaoyi Dong, Yuhang Zang, Jiaqi Wang

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

Comments ECCV 2024. All codes and models are publicly available at https://github.com/beichenzbc/Long-CLIP

2407.13072 2024-07-19 cs.CY cs.ET 67%

Accuracy of training data and model outputs in Generative AI: CREATe Response to the Information Commissioner Office Consultation

Zihao Li, Weiwei Yi, Jiahong Chen

专题命中预训练与数据：large language model(abstract)；language model(abstract)

2403.11650 2024-07-18 cs.CV 67%

Prioritized Semantic Learning for Zero-shot Instance Navigation

Xinyu Sun, Lizhao Liu, Hongyan Zhi, Ronghe Qiu, Junwei Liang

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

Comments Accepted by ECCV 2024

1. 预训练与数据 12486 篇

TaxaBind: A Unified Embedding Space for Ecological Applications

VILA$^2$: VILA Augmented VILA

Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks

Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models

Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training

TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering

MeloTrans: A Text to Symbolic Music Generation Model Following Human Composition Habit

Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models

Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion

Mora: Enabling Generalist Video Generation via A Multi-Agent Framework

OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images

On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms

Harnessing Vision-Language Pretrained Models with Temporal-Aware Adaptation for Referring Video Object Segmentation

SymPAC: Scalable Symbolic Music Generation With Prompts And Constraints

Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion

Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on GitHub and Stack Overflow

Cloning Ideology and Style using Deep Learning

Towards Synthetic Trace Generation of Modeling Operations using In-Context Learning Approach

3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing

BERT-ASC: Auxiliary-Sentence Construction for Implicit Aspect Learning in Sentiment Analysis

Vector Symbolic Open Source Information Discovery

A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot

GPT-3 Powered Information Extraction for Building Robust Knowledge Bases

Towards Privacy-Aware Sign Language Translation at Scale

Nemotron-4 340B Technical Report

Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight

Long-CLIP: Unlocking the Long-Text Capability of CLIP

Accuracy of training data and model outputs in Generative AI: CREATe Response to the Information Commissioner Office Consultation

Prioritized Semantic Learning for Zero-shot Instance Navigation