语言大模型 / LLM - arXivDaily 专题

2310.09518 2024-06-18 cs.CL cs.AI cs.LG 82%

Instruction Tuning with Human Curriculum

Bruce W. Lee, Hyunsoo Cho, Kang Min Yoo

专题命中指令微调：instruction tuning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NAACL 2024

2406.08762 2024-06-17 cs.SI cs.CY 82%

LGB: Language Model and Graph Neural Network-Driven Social Bot Detection

Ming Zhou, Dan Zhang, Yuandong Wang, Yangli-ao Geng, Yuxiao Dong, Jie Tang

专题命中指令微调：language model(title,abstract)；SFT(abstract)

2406.05432 2024-06-11 cs.CV 82%

Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models

Minho Park, Sunghyun Park, Jooyeol Yun, Jaegul Choo

专题命中指令微调：language model(title,abstract)；post-training(abstract)

Comments Preprint. Under review

2406.01843 2024-06-05 cs.CV 82%

L-MAGIC: Language Model Assisted Generation of Images with Coherence

Zhipeng Cai, Matthias Mueller, Reiner Birkl, Diana Wofk, Shao-Yen Tseng, JunDa Cheng, Gabriela Ben-Melech Stan, Vasudev Lal, Michael Paulitsch

专题命中指令微调：language model(title,abstract)；large language model(abstract)

Comments accepted to CVPR 2024

2402.02801 2024-06-04 cs.CL cs.AI cs.LG 82%

KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models

Fei Yuan, Chang Ma, Shuai Yuan, Qiushi Sun, Lei Li

专题命中指令微调：language model(title)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

2402.10896 2024-06-04 cs.CV 82%

PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter

Junfei Xiao, Zheng Xu, Alan Yuille, Shen Yan, Boyu Wang

专题命中指令微调：language model(title,abstract)；large language model(abstract)

Comments Technical report, 15 pages; v2 fix typos, add additional results in appendix

2402.07865 2024-05-31 cs.CV cs.AI cs.CL cs.LG 82%

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

Siddharth Karamcheti, Suraj Nair, Ashwin Balakrishna, Percy Liang, Thomas Kollar, Dorsa Sadigh

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published at ICML 2024. 22 pages, 11 figures. Training code and models: https://github.com/TRI-ML/prismatic-vlms. Evaluation code: https://github.com/TRI-ML/vlm-evaluation

2404.18848 2024-05-28 cs.LG cs.AI cs.CL 82%

FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decomposition

Yuxuan Yan, Qianqian Yang, Shunpu Tang, Zhiguo Shi

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2310.03744 2024-05-17 cs.CV cs.AI cs.CL cs.LG 82%

Improved Baselines with Visual Instruction Tuning

Haotian Liu, Chunyuan Li, Yuheng Li, Yong Jae Lee

专题命中指令微调：instruction tuning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Camera ready, CVPR 2024 (highlight). LLaVA project page: https://llava-vl.github.io

2312.05677 2024-04-29 cs.LG cs.AI cs.CL 82%

Batched Low-Rank Adaptation of Foundation Models

Yeming Wen, Swarat Chaudhuri

专题命中指令微调：foundation model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 16 pages, 3 figures

2404.08080 2024-04-15 cs.LG cs.AI cs.CL math.OC 82%

Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models

Tanmay Gautam, Youngsuk Park, Hao Zhou, Parameswaran Raman, Wooseok Ha

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 29 pages, 25 tables, 9 figures

2404.05674 2024-04-09 cs.CV 82%

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

Kunpeng Song, Yizhe Zhu, Bingchen Liu, Qing Yan, Ahmed Elgammal, Xiao Yang

专题命中指令微调：LLM(title)；large language model(abstract)；language model(abstract)

2403.14119 2024-04-02 cs.CV cs.AI cs.CL cs.LG 82%

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion

Hee Suk Yoon, Eunseop Yoon, Joshua Tian Jin Tee, Mark Hasegawa-Johnson, Yingzhen Li, Chang D. Yoo

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICLR 2024

2403.18025 2024-03-29 cs.CL cs.AI cs.IR cs.LG 82%

Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NER

Micheal Abaho, Danushka Bollegala, Gary Leeming, Dan Joyce, Iain E Buchan

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Paper alrerady accepted for publishing by the NAACL 2024 conference (main conference paper)

2403.16915 2024-03-28 cs.IR cs.AI cs.CL cs.LG 82%

Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models

Atsushi Keyaki, Ribeka Keyaki

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at LREC-COLING 2024

2311.11202 2024-03-26 cs.LG cs.AI cs.CL cs.CY 82%

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

Zhaowei Zhu, Jialu Wang, Hao Cheng, Yang Liu

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICLR 2024

2403.14783 2024-03-25 cs.CV cs.AI cs.CL cs.LG cs.MA 82%

Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering

Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, Camillo J. Taylor

专题命中指令微调：foundation model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments A full version of the paper will be released soon. The codes are available at https://github.com/bowen-upenn/Multi-Agent-VQA

2307.09476 2024-03-13 cs.LG cs.AI cs.CL 82%

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2402.13851 2024-02-22 cs.CV 82%

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Jiawei Liang, Siyuan Liang, Man Luo, Aishan Liu, Dongchen Han, Ee-Chien Chang, Xiaochun Cao

专题命中指令微调：language model(title,abstract)；instruction tuning(abstract)

2402.05616 2024-02-09 cs.CL cs.AI cs.LG 82%

Pretrained Generative Language Models as General Learning Frameworks for Sequence-Based Tasks

Ben Fauber

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2402.00794 2024-02-09 cs.CL cs.AI cs.LG 82%

ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models

Zhixue Zhao, Boxuan Shan

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at AAAI24 workshop ReLM

2401.13220 2024-01-25 eess.IV cs.CV 82%

Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentation

Saiyang Na, Yuzhi Guo, Feng Jiang, Hehuan Ma, Junzhou Huang

专题命中指令微调：prompting(title,abstract)；foundation model(abstract)

2401.03201 2024-01-17 cs.CV cs.MM 82%

3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding

Zeju Li, Chao Zhang, Xiaoyan Wang, Ruilong Ren, Yifan Xu, Ruifei Ma, Xiangde Liu

专题命中指令微调：instruction tuning(title)；large language model(abstract)；language model(abstract)

Comments 9 pages, 5 figures

2312.10770 2023-12-19 cs.LG cs.AI cs.CL q-bio.BM 82%

Identification of Knowledge Neurons in Protein Language Models

Divya Nori, Shivali Singireddy, Marina Ten Have

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2312.08932 2023-12-15 cs.CV 82%

Influence of Prompting Strategies on Segment Anything Model (SAM) for Short-axis Cardiac MRI segmentation

Josh Stein, Maxime Di Folco, Julia A. Schnabel

专题命中指令微调：prompting(title,abstract)；foundation model(abstract)

2312.02153 2023-12-05 cs.CV 82%

Aligning and Prompting Everything All at Once for Universal Visual Perception

Yunhang Shen, Chaoyou Fu, Peixian Chen, Mengdan Zhang, Ke Li, Xing Sun, Yunsheng Wu, Shaohui Lin, Rongrong Ji

专题命中指令微调：prompting(title,abstract)；foundation model(abstract)

2312.01564 2023-12-05 cs.LG cs.AI cs.CL cs.CV 82%

APoLLo: Unified Adapter and Prompt Learning for Vision Language Models

Sanjoy Chowdhury, Sayan Nag, Dinesh Manocha

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at EMNLP 2023 (Main track)

2312.00438 2023-12-04 cs.CV 82%

Dolphins: Multimodal Language Model for Driving

Yingzi Ma, Yulong Cao, Jiachen Sun, Marco Pavone, Chaowei Xiao

专题命中指令微调：language model(title,abstract)；instruction tuning(abstract)

Comments The project page is available at https://vlm-driver.github.io/

2305.06988 2023-12-01 cs.CV cs.AI cs.CL cs.LG 82%

Self-Chained Image-Language Model for Video Localization and Question Answering

Shoubin Yu, Jaemin Cho, Prateek Yadav, Mohit Bansal

专题命中指令微调：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NeurIPS 2023; Our code and checkpoints are available at: https://github.com/Yui010206/SeViLA

2311.10791 2023-11-21 cs.MM cs.HC 82%

Modality-invariant and Specific Prompting for Multimodal Human Perception Understanding

Hao Sun, Ziwei Niu, Xinyao Yu, Jiaqing Liu, Yen-Wei Chen, Lanfen Lin

专题命中指令微调：prompting(title)；large language model(abstract)；language model(abstract)

1. 指令微调 11619 篇

Instruction Tuning with Human Curriculum

LGB: Language Model and Graph Neural Network-Driven Social Bot Detection

Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models

L-MAGIC: Language Model Assisted Generation of Images with Coherence

KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models

PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decomposition

Improved Baselines with Visual Instruction Tuning

Batched Low-Rank Adaptation of Foundation Models

Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion

Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NER

Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Pretrained Generative Language Models as General Learning Frameworks for Sequence-Based Tasks

ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models

Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentation

3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding

Identification of Knowledge Neurons in Protein Language Models

Influence of Prompting Strategies on Segment Anything Model (SAM) for Short-axis Cardiac MRI segmentation

Aligning and Prompting Everything All at Once for Universal Visual Perception

APoLLo: Unified Adapter and Prompt Learning for Vision Language Models

Dolphins: Multimodal Language Model for Driving

Self-Chained Image-Language Model for Video Localization and Question Answering

Modality-invariant and Specific Prompting for Multimodal Human Perception Understanding