[0] Time-Resolved MNIST Dataset for Single-Photon Recognition[cs.CV] 标题:快速瞬态MNIST数据集用于单光子识别 作者:Aleksi Suonsivu, Lauri Salmela, Edoardo Peretti, Leevi Uosukainen, Radu Ciprian Bilcu, Giacomo Boracchi 链接:http://arxiv.org/abs/2410.16744 备注:12 pages, 4 figures. Accepted for Workshop on Synthetic Data for Computer Vision at ECCV 2024
[1] One-Step Diffusion Distillation through Score Implicit Matching[cs.CV] 标题:一步扩散蒸馏通过评分隐式匹配 作者:Weijian Luo, Zemin Huang, Zhengyang Geng, J. Zico Kolter, Guo-jun Qi 链接:http://arxiv.org/abs/2410.16794 期刊:NeurIPS 2024 备注:Accepted by NeurIPS 2024
[2] Hierarchical Clustering for Conditional Diffusion in Image Generation[cs.CV] 标题:图像生成中的条件扩散分层聚类 作者:Jorge da Silva Goncalves, Laura Manduchi, Moritz Vandenhirtz, Julia E. Vogt 链接:http://arxiv.org/abs/2410.16910 备注:25 pages, submitted to ICLR 2025
[3] LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization[cs.CV] 标题:从多个专家学习领域泛化的简单框架:LFME 作者:Liang Chen, Yong Zhang, Yibing Song, Zhiqiang Shen, Lingqiao Liu 链接:http://arxiv.org/abs/2410.17020 代码:https://github.com/liangchen527/LFME 备注:Accepted by NeurIPS 2024
[4] Masked Differential Privacy[cs.CV] 标题:掩码差分隐私 作者:David Schneider, Sina Sajadmanesh, Vikash Sehwag, Saquib Sarfraz, Rainer Stiefelhagen, Lingjuan Lyu, Vivek Sharma 链接:http://arxiv.org/abs/2410.17098 期刊:Proceedings of the 2nd International Workshop on Privacy-Preserving Computer Vision, ECCV 2024
自然语言处理会议: 12篇
[0] Susu Box or Piggy Bank: Assessing Cultural Commonsense Knowledge between Ghana and the U.S[cs.CL] 标题:斯苏盒或储蓄罐:评估加纳和美国之间的文化常识知识 作者:Christabel Acquaye, Haozhe An, Rachel Rudinger 链接:http://arxiv.org/abs/2410.16451 备注:Accepted to EMNLP 2024
[1] To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning[cs.CL] 标题:《走向世界(TTG):语言驱动确保旅行规划》 作者:Da JU, Song Jiang, Andrew Cohen, Aaron Foss, Sasha Mitts, Arman Zharmagambetov, Brandon Amos, Xian Li, Justine T Kao, Maryam Fazel-Zarandi, Yuandong Tian 链接:http://arxiv.org/abs/2410.16456 期刊:EMNLP 2024 Demo Track
[3] Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method[cs.CL] 标题:正确解答后:基于后处理方法的跨段落问答增强
作者:Jiayi Lin, Chenyang Zhang, Haibo Tong, Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Junli Wang 链接:http://arxiv.org/abs/2410.16788 备注:Accepted by EMNLP 2024 Findings
[4] Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning[cs.CL] 标题:可信的通过强化学习实现检索增强的大型语言模型的校准 作者:Zongmeng Zhang, Yufeng Shi, Jinhua Zhu, Wengang Zhou, Xiang Qi, Peng Zhang, Houqiang Li 链接:http://arxiv.org/abs/2410.16843 期刊:Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59827-59850, 2024 备注:ICML 2024
[5] Learning Mathematical Rules with Large Language Models[cs.CL] 标题:利用大型语言模型学习数学规则 作者:Antoine Gorceix, Bastien Le Chenadec, Ahmad Rammal, Nelson Vadori, Manuela Veloso 链接:http://arxiv.org/abs/2410.16973 备注:4th MATH-AI Workshop at NeurIPS'24
[7] Human-LLM Hybrid Text Answer Aggregation for Crowd Annotations[cs.CL] 标题:人类与大型语言模型混合文本答案汇聚用于众包标注 作者:Jiyi Li 链接:http://arxiv.org/abs/2410.17099 备注:Accepted in EMNLP 2024
[8] Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?[cs.CL] 标题:可以通用的大型语言模型泛化到英语-泰语机器翻译吗? 作者:Jirat Chiaranaipanich, Naiyarat Hanmatheekuna, Jitkapat Sawatphol, Krittamate Tiankanon, Jiramet Kinchagawat, Amrest Chinkamol, Parinthapat Pengpun, Piyalitt Ittichaiwong, Peerat Limkonchotiwat 链接:http://arxiv.org/abs/2410.17145 备注:Accepted in GenBench EMNLP 2024
[9] Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy[cs.CL] 标题:微调大型语言模型以合理地基于语义熵避免特定内容 作者:Benedict Aaron Tjandra, Muhammed Razzak, Jannik Kossen, Kunal Handa, Yarin Gal 链接:http://arxiv.org/abs/2410.17234 备注:Accepted to NeurIPS Safe Generative AI Workshop 2024
[10] Towards Reliable Evaluation of Behavior Steering Interventions in LLMs[cs.CL] 标题:迈向可靠评估LLM中的行为引导干预措施 作者:Itamar Pres, Laura Ruis, Ekdeep Singh Lubana, David Krueger 链接:http://arxiv.org/abs/2410.17245 备注:Accepted to the NeurIPS 2024 - Workshop on Foundation Model Interventions
[11] Altogether: Image Captioning via Re-aligning Alt-text[cs.CV] 标题:整体:通过重新对齐Alt文本来进行图文描述 作者:Hu Xu, Po-Yao Huang, Xiaoqing Ellen Tan, Ching-Feng Yeh, Jacob Kahn, Christine Jou, Gargi Ghosh, Omer Levy, Luke Zettlemoyer, Wen-tau Yih, Shang-Wen Li, Saining Xie, Christoph Feichtenhofer 链接:http://arxiv.org/abs/2410.17251 备注:accepted by EMNLP 2024; MetaCLIPv2