大模型对齐与安全

MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models

Yongzhu Miao, Shasha Li, Jintao Tang, Ting Wang

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

Comments The paper has been accepted by ICME 2023

Aardvark weather: end-to-end data-driven weather forecasting

Anna Vaughan, Stratis Markou, Will Tebbutt, James Requeima, Wessel P. Bruinsma, Tom R. Andersson, Michael Herzog, Nicholas D. Lane, Matthew Chantry, J. Scott Hosking, Richard E. Turner

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

FairyLandAI: Personalized Fairy Tales utilizing ChatGPT and DALLE-3

Georgios Makridis, Athanasios Oikonomou, Vasileios Koukos

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Comments 11 pages

Development of Cognitive Intelligence in Pre-trained Language Models

Raj Sanjay Shah, Khushi Bhardwaj, Sashank Varma

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

The Career Interests of Large Language Models

Meng Hua, Yuan Cheng, Hengshu Zhu

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Intelligent Multi-Document Summarisation for Extracting Insights on Racial Inequalities from Maternity Incident Investigation Reports

Georgina Cosma, Mohit Kumar Singh, Patrick Waterson, Gyuchan Thomas Jun, Jonathan Back

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

HiLight: Technical Report on the Motern AI Video Language Model

Zhiting Wang, Qiangong Zhou, Kangjie Yang, Zongyang Liu, Xin Mao

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

A Closer Look at Logical Reasoning with LLMs: The Choice of Tool Matters

Long Hei Matthew Lam, Ramya Keerthy Thatikonda, Ehsan Shareghi

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

Comments Code and data are publicly available at: https://github.com/Mattylam/Logic_Symbolic_Solvers_Experiment

Towards a text-based quantitative and explainable histopathology image analysis

Anh Tien Nguyen, Trinh Thi Le Vuong, Jin Tae Kwak

专题命中 其他安全 ：alignment(abstract)；分类 cs.LG

Comments MICCAI 2024 - Early acceptance (Top 11%)

4D Contrastive Superflows are Dense 3D Representation Learners

Xiang Xu, Lingdong Kong, Hui Shuai, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu, Qingshan Liu

专题命中 其他安全 ：alignment(abstract)；分类 cs.LG

Comments ECCV 2024; 36 pages, 11 figures, 11 tables; Code at https://github.com/Xiangxu-0103/SuperFlow

Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry

Jing Jiang, Yiran Ling, Binzhu Li, Pengxiang Li, Junming Piao, Yu Zhang

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Comments 13 pages, 7 figures

CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Zhihao Du, Qian Chen, Shiliang Zhang, Kai Hu, Heng Lu, Yexin Yang, Hangrui Hu, Siqi Zheng, Yue Gu, Ziyang Ma, Zhifu Gao, Zhijie Yan

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Comments work in progress. arXiv admin note: substantial text overlap with arXiv:2407.04051

The Solution for Language-Enhanced Image New Category Discovery

Haonan Xu, Dian Chao, Xiangyu Wu, Zhonghua Wan, Yang Yang

专题命中 其他安全 ：alignment(abstract)；分类 cs.LG

CausalOps -- Towards an Industrial Lifecycle for Causal Probabilistic Graphical Models

Robert Maier, Andreas Schlattl, Thomas Guess, Jürgen Mottok

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

The Mysterious Case of Neuron 1512: Injectable Realignment Architectures Reveal Internal Characteristics of Meta's Llama 2 Model

Brenden Smith, Dallin Baker, Clayton Chase, Myles Barney, Kaden Parker, Makenna Allred, Peter Hu, Alex Evans, Nancy Fulda

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

Comments 21 pages, 17 figures

Accompanied Singing Voice Synthesis with Fully Text-controlled Melody

Ruiqi Li, Zhiqing Hong, Yongqi Wang, Lichao Zhang, Rongjie Huang, Siqi Zheng, Zhou Zhao

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

Comments Working in progress

CoMadOut -- A Robust Outlier Detection Algorithm based on CoMAD

Andreas Lohrer, Daniyal Kazempour, Maximilian Hünemörder, Peer Kröger

专题命中 其他安全 ：alignment(abstract)；分类 cs.LG

Comments published in Springer Machine Learning Journal (MLJ)

Journal ref Machine Learning, Special Issue on Imbalanced Learning ISSN: 0885-6125 (Print) 1573-0565 (Online), 2024, Pages 1-75

Optimal Transport for Latent Integration with An Application to Heterogeneous Neuronal Activity Data

Yubai Yuan, Babak Shahbaba, Norbert Fortin, Keiland Cooper, Qing Nie, Annie Qu

专题命中 其他安全 ：alignment(abstract)；分类 cs.LG

Verifying the Generalization of Deep Learning to Out-of-Distribution Domains

Guy Amir, Osher Maayan, Tom Zelazny, Guy Katz, Michael Schapira

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments To appear in the Journal of Automated Reasoning (JAR), 2024. This is an extended version of a CAV 2023 paper, titled: "Verifying Generalization in Deep Learning"

Question Translation Training for Better Multilingual Reasoning

Wenhao Zhu, Shujian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, Alexandra Birch

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

Comments Accepted to Findings of ACL 2024

A Teacher Is Worth A Million Instructions

Nikhil Kothari, Ravindra Nayak, Shreyas Shetty, Amey Patil, Nikesh Garera

专题命中 其他安全 ：alignment(abstract)；分类 cs.LG

Comments 7 pages, 4 figures

Pre-Trained Vision-Language Models as Partial Annotators

Qian-Wei Wang, Yuqiu Xie, Letian Zhang, Zimo Liu, Shu-Tao Xia

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

DRAK: Unlocking Molecular Insights with Domain-Specific Retrieval-Augmented Knowledge in LLMs

Jinzhe Liu, Xiangsheng Huang, Zhuo Chen, Yin Fang

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Comments Ongoing work; 11 pages, 6 Figures, 2 Tables

Coarse-to-Fine Concept Bottleneck Models

Konstantinos P. Panousis, Dino Ienco, Diego Marcos

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR

Van Tung Pham, Yist Lin, Tao Han, Wei Li, Jun Zhang, Lu Lu, Yuxuan Wang

专题命中 其他安全 ：alignment(abstract)；分类 cs.LG

Vision-Language Consistency Guided Multi-modal Prompt Learning for Blind AI Generated Image Quality Assessment

Jun Fu, Wei Zhou, Qiuping Jiang, Hantao Liu, Guangtao Zhai

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Comments Accepted by IEEE Signal Processing Letter

UniCoder: Scaling Code Large Language Model via Universal Code

Tao Sun, Linzheng Chai, Jian Yang, Yuwei Yin, Hongcheng Guo, Jiaheng Liu, Bing Wang, Liqun Yang, Zhoujun Li

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

Comments Accepted by ACL 2024 (Main)

RecExplainer: Aligning Large Language Models for Explaining Recommendation Models

Yuxuan Lei, Jianxun Lian, Jing Yao, Xu Huang, Defu Lian, Xing Xie

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Comments 12 pages, 9 figures, 5 tables

Devil's Advocate: Anticipatory Reflection for LLM Agents

Haoyu Wang, Tao Li, Zhiwei Deng, Dan Roth, Yang Li

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Comments 13 pages, 6 figures

Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model

Wanting Xu, Yang Liu, Langping He, Xucheng Huang, Ling Jiang

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI