大模型对齐与安全

Rail Crack Propagation Forecasting Using Multi-horizons RNNs

Sara Yasmine Ouerk, Olivier Vo Van, Mouadh Yagoubi

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Are Existing Out-Of-Distribution Techniques Suitable for Network Intrusion Detection?

Andrea Corsini, Shanchieh Jay Yang

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning

Yeming Chen, Siyu Zhang, Yaoru Sun, Weijian Liang, Haoran Wang

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

PEvoLM: Protein Sequence Evolutionary Information Language Model

Issar Arab

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

Comments 8

Black Box Few-Shot Adaptation for Vision-Language models

Yassine Ouali, Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos

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

Comments Published at ICCV 2023

Bio-SIEVE: Exploring Instruction Tuning Large Language Models for Systematic Review Automation

Ambrose Robinson, William Thorne, Ben P. Wu, Abdullah Pandor, Munira Essat, Mark Stevenson, Xingyi Song

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.AI

Drones4Good: Supporting Disaster Relief Through Remote Sensing and AI

Nina Merkle, Reza Bahmanyar, Corentin Henry, Seyed Majid Azimi, Xiangtian Yuan, Simon Schopferer, Veronika Gstaiger, Stefan Auer, Anne Schneibel, Marc Wieland, Thomas Kraft

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.CY

Harnessing the Web and Knowledge Graphs for Automated Impact Investing Scoring

Qingzhi Hu, Daniel Daza, Laurens Swinkels, Kristina Ūsaitė, Robbert-Jan 't Hoen, Paul Groth

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

Comments Presented at the KDD 2023 Workshop - Fragile Earth: AI for Climate Sustainability

A Machine Learning Method for Predicting Traffic Signal Timing from Probe Vehicle Data

Juliette Ugirumurera, Joseph Severino, Erik A. Bensen, Qichao Wang, Jane Macfarlane

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving

Ben Agro, Quinlan Sykora, Sergio Casas, Raquel Urtasun

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 19 pages, 13 figures

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 1379-1388

Multi-modal Machine Learning in Engineering Design: A Review and Future Directions

Binyang Song, Rui Zhou, Faez Ahmed

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

Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success

Jaemin Yoo, Tiancheng Zhao, Leman Akoglu

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

Comments Transactions on Machine Learning Research (TMLR)

SKTR: Trace Recovery from Stochastically Known Logs

Eli Bogdanov, Izack Cohen, Avigdor Gal

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

Comments Submitted version -- Accepted to the 5th International Conference on Process Mining (ICPM), 2023

TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network

Brandon Theodorou, Cao Xiao, Jimeng Sun

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

Llama 2: Open Foundation and Fine-Tuned Chat Models

Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez, Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.AI

Anticipating Technical Expertise and Capability Evolution in Research Communities using Dynamic Graph Transformers

Sameera Horawalavithana, Ellyn Ayton, Anastasiya Usenko, Robin Cosbey, Svitlana Volkova

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey

Md. Mahfuzur Rahman, Vince D. Calhoun, Sergey M. Plis

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 109 pages, 21 figures

ECS -- an Interactive Tool for Data Quality Assurance

Christian Sieberichs, Simon Geerkens, Alexander Braun, Thomas Waschulzik

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Unveiling the Potential of Knowledge-Prompted ChatGPT for Enhancing Drug Trafficking Detection on Social Media

Chuanbo Hu, Bin Liu, Xin Li, Yanfang Ye

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.AI

Flowchase: a Mobile Application for Pronunciation Training

Noé Tits, Zoé Broisson

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

Comments Interspeech 2023 - SLaTE workshop 2023 (Speech and Language Technology in Education)

Exploring the In-context Learning Ability of Large Language Model for Biomedical Concept Linking

Qinyong Wang, Zhenxiang Gao, Rong Xu

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

Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces

Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

A clustering and graph deep learning-based framework for COVID-19 drug repurposing

Chaarvi Bansal, Rohitash Chandra, Vinti Agarwal, P. R. Deepa

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Incorporating Graph Information in Transformer-based AMR Parsing

Pavlo Vasylenko, Pere-Lluís Huguet Cabot, Abelardo Carlos Martínez Lorenzo, Roberto Navigli

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

Comments ACL 2023. Please cite authors correctly using both lastnames ("Martínez Lorenzo", "Huguet Cabot")

Exploring Vision-Language Models for Imbalanced Learning

Yidong Wang, Zhuohao Yu, Jindong Wang, Qiang Heng, Hao Chen, Wei Ye, Rui Xie, Xing Xie, Shikun Zhang

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

Comments IJCV minor revision; 16 pages; code: https://github.com/Imbalance-VLM/Imbalance-VLM

Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration

Chenyang Lyu, Minghao Wu, Longyue Wang, Xinting Huang, Bingshuai Liu, Zefeng Du, Shuming Shi, Zhaopeng Tu

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

Comments Longyue Wang is the corresponding author. Our project page is at https://github.com/lyuchenyang/Macaw-LLM

Improving Zero-Shot Detection of Low Prevalence Chest Pathologies using Domain Pre-trained Language Models

Aakash Mishra, Rajat Mittal, Christy Jestin, Kostas Tingos, Pranav Rajpurkar

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

Comments 3 pages, 1 table, Medical Imaging with Deep Learning, Short Paper

Semantic-Based Neural Network Repair

Richard Schumi, Jun Sun

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure

Ke Liang, Yue Liu, Sihang Zhou, Wenxuan Tu, Yi Wen, Xihong Yang, Xiangjun Dong, Xinwang Liu

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

Comments This work has been accepted by IEEE for publication. Early access in IEEE Transactions on Knowledge and Data Engineering

Modality Influence in Multimodal Machine Learning

Abdelhamid Haouhat, Slimane Bellaouar, Attia Nehar, Hadda Cherroun

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

Comments 10 pages