大模型对齐与安全

Mitigating Receiver Impact on Radio Frequency Fingerprint Identification via Domain Adaptation

Liu Yang, Qiang Li, Xiaoyang Ren, Yi Fang, Shafei Wang

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

Comments Accepted by IEEE Internet of Things Journal

Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization

Dave Van Veen, Cara Van Uden, Louis Blankemeier, Jean-Benoit Delbrouck, Asad Aali, Christian Bluethgen, Anuj Pareek, Malgorzata Polacin, Eduardo Pontes Reis, Anna Seehofnerova, Nidhi Rohatgi, Poonam Hosamani, William Collins, Neera Ahuja, Curtis P. Langlotz, Jason Hom, Sergios Gatidis, John Pauly, Akshay S. Chaudhari

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Comments 27 pages, 19 figures

Journal ref Nature Medicine, 2024

GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism

Shuzhou Yuan, Michael Färber

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

Comments NAACL 2024 Findings

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

Desai Xie, Jiahao Li, Hao Tan, Xin Sun, Zhixin Shu, Yi Zhou, Sai Bi, Sören Pirk, Arie E. Kaufman

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

Comments 22 pages, 16 figures. Our code, training and testing data, and video results are available at: https://desaixie.github.io/carve-3d. This paper has been accepted to CVPR 2024. v2: incorporated changes from the CVPR 2024 camera-ready version

$λ$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space

Maitreya Patel, Sangmin Jung, Chitta Baral, Yezhou Yang

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

Comments Project page: https://eclipse-t2i.github.io/Lambda-ECLIPSE/

VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection

Li-Ming Zhan, Bo Liu, Xiao-Ming Wu

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Comments COLING 2024

Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers

Libo Qin, Qiguang Chen, Yuhang Zhou, Zhi Chen, Yinghui Li, Lizi Liao, Min Li, Wanxiang Che, Philip S. Yu

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

Automated Lane Change Behavior Prediction and Environmental Perception Based on SLAM Technology

Han Lei, Baoming Wang, Zuwei Shui, Peiyuan Yang, Penghao Liang

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

ChipNeMo: Domain-Adapted LLMs for Chip Design

Mingjie Liu, Teodor-Dumitru Ene, Robert Kirby, Chris Cheng, Nathaniel Pinckney, Rongjian Liang, Jonah Alben, Himyanshu Anand, Sanmitra Banerjee, Ismet Bayraktaroglu, Bonita Bhaskaran, Bryan Catanzaro, Arjun Chaudhuri, Sharon Clay, Bill Dally, Laura Dang, Parikshit Deshpande, Siddhanth Dhodhi, Sameer Halepete, Eric Hill, Jiashang Hu, Sumit Jain, Ankit Jindal, Brucek Khailany, George Kokai, Kishor Kunal, Xiaowei Li, Charley Lind, Hao Liu, Stuart Oberman, Sujeet Omar, Ghasem Pasandi, Sreedhar Pratty, Jonathan Raiman, Ambar Sarkar, Zhengjiang Shao, Hanfei Sun, Pratik P Suthar, Varun Tej, Walker Turner, Kaizhe Xu, Haoxing Ren

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

Comments Updated results for ChipNeMo-70B model

SemGrasp: Semantic Grasp Generation via Language Aligned Discretization

Kailin Li, Jingbo Wang, Lixin Yang, Cewu Lu, Bo Dai

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

Integrating Explanations in Learning LTL Specifications from Demonstrations

Ashutosh Gupta, John Komp, Abhay Singh Rajput, Krishna Shankaranarayanan, Ashutosh Trivedi, Namrita Varshney

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments 21 Pages, 13 Page Appendix

SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining

Chull Hwan Song, Taebaek Hwang, Jooyoung Yoon, Shunghyun Choi, Yeong Hyeon Gu

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

Comments CVPR2024 Accepted

LLMs are Good Sign Language Translators

Jia Gong, Lin Geng Foo, Yixuan He, Hossein Rahmani, Jun Liu

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

Comments Accepted to CVPR 2024

FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual Clues

Shuang Li, Jiahua Wang, Lijie Wen

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

The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification

Norbert Tihanyi, Tamas Bisztray, Ridhi Jain, Mohamed Amine Ferrag, Lucas C. Cordeiro, Vasileios Mavroeidis

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments https://github.com/FormAI-Dataset PLEASE USE PUBLISHED VERSION FOR CITATION: https://doi.org/10.1145/3617555.3617874

Journal ref PROMISE 2023: Proceedings of the 19th International Conference on Predictive Models and Data Analytics in Software Engineering December 2023 Pages 33 to 43

Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence

Hsiu-Wei Yang, Abhinav Agrawal, Pavlos Fragkogiannis, Shubham Nitin Mulay

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

ViT-Lens: Towards Omni-modal Representations

Weixian Lei, Yixiao Ge, Kun Yi, Jianfeng Zhang, Difei Gao, Dylan Sun, Yuying Ge, Ying Shan, Mike Zheng Shou

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

Comments This work is a follow-up of arXiv:2308.10185. Accepted to CVPR2024

ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search

Zehan Li, Jianfei Zhang, Chuantao Yin, Yuanxin Ouyang, Wenge Rong

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

Comments Accepted to LREC-COLING 2024

Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning

Rao Fu, Jingyu Liu, Xilun Chen, Yixin Nie, Wenhan Xiong

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

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining

Yihong Liu, Peiqin Lin, Mingyang Wang, Hinrich Schütze

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

Comments NAACL 2024 Findings

Epistemology of Language Models: Do Language Models Have Holistic Knowledge?

Minsu Kim, James Thorne

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

LifeTox: Unveiling Implicit Toxicity in Life Advice

Minbeom Kim, Jahyun Koo, Hwanhee Lee, Joonsuk Park, Hwaran Lee, Kyomin Jung

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Comments 11 pages, 5 figures, NAACL 2024

Human-AI collaboration is not very collaborative yet: A taxonomy of interaction patterns in AI-assisted decision making from a systematic review

Catalina Gomez, Sue Min Cho, Shichang Ke, Chien-Ming Huang, Mathias Unberath

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

Comments 25 pages; 2 figures

Towards 3D Molecule-Text Interpretation in Language Models

Sihang Li, Zhiyuan Liu, Yanchen Luo, Xiang Wang, Xiangnan He, Kenji Kawaguchi, Tat-Seng Chua, Qi Tian

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

CaVE: A Cone-Aligned Approach for Fast Predict-then-optimize with Binary Linear Programs

Bo Tang, Elias B. Khalil

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

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization

Yann Fraboni, Martin Van Waerebeke, Kevin Scaman, Richard Vidal, Laetitia Kameni, Marco Lorenzi

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Conformal Predictions for Probabilistically Robust Scalable Machine Learning Classification

Alberto Carlevaro, Teodoro Alamo Cantarero, Fabrizio Dabbene, Maurizio Mongelli

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 19 pages, 6 figures, journal paper

Detecting Brain Tumors through Multimodal Neural Networks

Antonio Curci, Andrea Esposito

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Presented at NeroPRAI 2024 (co-located with ICPRAM 2024). This version did not undergo peer review: refer to the open access version of record (see DOI)

Journal ref Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2024) - NeroPRAI 2024

Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation

Bingqian Lin, Yi Zhu, Xiaodan Liang, Liang Lin, Jianzhuang Liu

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

Comments Accepted by AAAI 2023

Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation

Zicheng Zhang, Tong Zhang, Yi Zhu, Jianzhuang Liu, Xiaodan Liang, QiXiang Ye, Wei Ke

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