[5] Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning[cs.CV] 标题：视频2奖励：生成奖励函数以用于地面机器人行为学习 作者：Runhao Zeng, Dingjie Zhou, Qiwei Liang, Junlin Liu, Hui Li, Changxin Huang, Jianqiang Li, Xiping Hu, Fuchun Sun 链接：http://arxiv.org/abs/2412.05515 期刊：Proceedings of the 27th European Conference on Artificial Intelligence (ECAI 2024), Santiago de Compostela, Spain, October 19-24, 2024. Frontiers in Artificial Intelligence and Applications, vol. 392, IOS Press, pp. 4369-4376 备注：8 pages, 6 figures, ECAI2024
[6] Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis[cs.CV] 标题：无模板的自由连接高斯喷溅实时可重用动态视点合成 作者：Diwen Wan, Yuxiang Wang, Ruijie Lu, Gang Zeng 链接：http://arxiv.org/abs/2412.05570 备注：Accepted by NeurIPS 2024
[7] TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances[cs.CV] 标题：TB-HSU：基于情境能力的层次化三维场景理解 作者：Wenting Xu, Viorela Ila, Luping Zhou, Craig T. Jin 链接：http://arxiv.org/abs/2412.05596 备注：Submitted to AAAI2025
[8] Self-Supervised Learning with Probabilistic Density Labeling for Rainfall Probability Estimation[cs.CV] 标题：基于概率密度标签的自监督学习在降雨概率估计中的应用 作者：Junha Lee, Sojung An, Sujeong You, Namik Cho 链接：http://arxiv.org/abs/2412.05825 代码：https://github.com/joonha425/SSLPDL 备注：Accepted by WACV 2025
[9] LVP-CLIP:Revisiting CLIP for Continual Learning with Label Vector Pool[cs.CV] 标题：LVP-CLIP：重新审视CLIP以实现连续学习的标签向量池 作者：Yue Ma, Huantao Ren, Boyu Wang, Jingang Jin, Senem Velipasalar, Qinru Qiu 链接：http://arxiv.org/abs/2412.05840 备注：submitted to CVPR2025
[11] HSDA: High-frequency Shuffle Data Augmentation for Bird's-Eye-View Map Segmentation[cs.CV] 标题：HSDA：高频洗牌数据增强技术用于鸟瞰图地图分割 作者：Calvin Glisson, Qiuxiao Chen 链接：http://arxiv.org/abs/2412.06127 代码：https://github.com/Zarhult/HSDA 备注：Accepted for publication at the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 8 pages excluding references, 5 figures
[12] Data Free Backdoor Attacks[cs.CV] 标题：数据无关后门攻击 作者：Bochuan Cao, Jinyuan Jia, Chuxuan Hu, Wenbo Guo, Zhen Xiang, Jinghui Chen, Bo Li, Dawn Song 链接：http://arxiv.org/abs/2412.06219 备注：24 pages, 8 figures, accepted by NeurIPS 2024
[13] No Annotations for Object Detection in Art through Stable Diffusion[cs.CV] 标题：无标注通过稳定扩散进行艺术作品中对象检测 作者：Patrick Ramos, Nicolas Gonthier, Selina Khan, Yuta Nakashima, Noa Garcia 链接：http://arxiv.org/abs/2412.06286 代码：https://github.com/patrick-john-ramos/nada 备注：8 pages, 6 figures, to be published in WACV 2025
[14] LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations[cs.CV] 标题：LLaVA-SpaceSGG：开放词汇场景图生成中的视觉指令微调与增强空间关系 作者：Mingjie Xu, Mengyang Wu, Yuzhi Zhao, Jason Chun Lok Li, Weifeng Ou 链接：http://arxiv.org/abs/2412.06322 代码：https://github.com/Endlinc/LLaVA-SpaceSGG 备注：Accepted by the WACV 2025, including supplementary material
[15] Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation[cs.CV] 标题：智能体超脱RGB之旅：揭露适用于视觉-语言导航的混合语义-空间环境表示 作者：Xuesong Zhang, Yunbo Xu, Jia Li, Zhenzhen Hu, Richnag Hong 链接：http://arxiv.org/abs/2412.06465 备注：underreview in CVPR 2025
[16] Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation[cs.CV] 标题：基于上下文采样和一对多熵的主动学习用于语义分割 作者：Fei Wu, Pablo Marquez-Neila, Hedyeh Rafi-Tarii, Raphael Sznitman 链接：http://arxiv.org/abs/2412.06470 备注：WACV 2025, 8 pages
[17] BATseg: Boundary-aware Multiclass Spinal Cord Tumor Segmentation on 3D MRI Scans[cs.CV] 标题：BATseg：基于3D MRI扫描的边界感知多类脊髓肿瘤分割 作者：Hongkang Song, Zihui Zhang, Yanpeng Zhou, Jie Hu, Zishuo Wang, Hou Him Chan, Chon Lok Lei, Chen Xu, Yu Xin, Bo Yang 链接：http://arxiv.org/abs/2412.06507 代码：https://github.com/vLAR-group/BATseg 备注：ECCV 2024 Workshop on BioImage Computing. Code and data are available at: this https URL
[19] Class Balance Matters to Active Class-Incremental Learning[cs.CV] 标题：类平衡对主动类增量学习很重要
作者：Zitong Huang, Ze Chen, Yuanze Li, Bowen Dong, Erjin Zhou, Yong Liu, Rick Siow Mong Goh, Chun-Mei Feng, Wangmeng Zuo 链接：http://arxiv.org/abs/2412.06642 代码：https://github.com/1170300714/CBS 备注：ACM MM 2024
[20] Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation[cs.CV] 标题：触觉幻融合：利用触觉感知进行3D生成 作者：Ruihan Gao, Kangle Deng, Gengshan Yang, Wenzhen Yuan, Jun-Yan Zhu 链接：http://arxiv.org/abs/2412.06785 代码：https://ruihangao.github.io/TactileDreamFusion/ 备注：Accepted to NeurIPS 2024. Project webpage: this https URL Code: this https URL
自然语言处理会议: 13篇
[0] CALICO: Conversational Agent Localization via Synthetic Data Generation[cs.CL] 标题：合成数据生成对话代理定位系统英文缩写翻译为中文：CALICO：通过合成数据生成实现的对话代理定位 作者：Andy Rosenbaum, Pegah Kharazmi, Ershad Banijamali, Lu Zeng, Christopher DiPersio, Pan Wei, Gokmen Oz, Clement Chung, Karolina Owczarzak, Fabian Triefenbach, Wael Hamza 链接：http://arxiv.org/abs/2412.05388 备注：Accepted to The 37th International Conference on Neural Information Processing Systems (NeurIPS 2023) December 10-16, 2023 - SyntheticData4ML Workshop, New Orleans, United States this https URL
[1] A polar coordinate system represents syntax in large language models[cs.CL] 标题：大型语言模型中的语法定义可以用极坐标系表示 作者：Pablo Diego-Simón, Stéphane D'Ascoli, Emmanuel Chemla, Yair Lakretz, Jean-Rémi King 链接：http://arxiv.org/abs/2412.05571 期刊：NeurIPS 2024
[2] On the effective transfer of knowledge from English to Hindi Wikipedia[cs.CL] 标题：关于英语到印地语维基百科知识有效迁移的研究 作者：Paramita Das, Amartya Roy, Ritabrata Chakraborty, Animesh Mukherjee 链接：http://arxiv.org/abs/2412.05708 备注：accepted at COLING Industry Track 2025
[3] Uncovering Uncertainty in Transformer Inference[cs.CL] 标题：揭示Transformer推理中的不确定性 作者：Greyson Brothers, Willa Mannering, Amber Tien, John Winder
链接：http://arxiv.org/abs/2412.05768 备注：Accepted poster at the 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Workshop on Foundation Model Interventions
[4] Speech Is Not Enough: Interpreting Nonverbal Indicators of Common Knowledge and Engagement[cs.CL] 标题：言语不足：诠释共同知识及参与的非语言指标 作者：Derek Palmer, Yifan Zhu, Kenneth Lai, Hannah VanderHoeven, Mariah Bradford, Ibrahim Khebour, Carlos Mabrey, Jack Fitzgerald, Nikhil Krishnaswamy, Martha Palmer, James Pustejovsky 链接：http://arxiv.org/abs/2412.05797 备注：3 pages, 2 figures, appearing at AAAI 2025 Demos Track
[5] 1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering[cs.CL] 标题：1-800-SHARED-TASKS在RegNLP中：语义检索的词汇重排序（LeSeR）用于监管问答 作者：Jebish Purbey, Drishti Sharma, Siddhant Gupta, Khawaja Murad, Siddartha Pullakhandam, Ram Mohan Rao Kadiyala 链接：http://arxiv.org/abs/2412.06009 备注：5 pages, Accepted to RegNLP @ COLING 2025
[6] Steering Large Language Models to Evaluate and Amplify Creativity[cs.CL] 标题：引导大型语言模型以评估和增强创造力 作者：Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Shao-yen Tseng, Vasudev Lal 链接：http://arxiv.org/abs/2412.06060 备注：(Spotlight) NeurIPS 2024 Workshop on Creativity & Generative AI. Authors 1 and 2 contributed equally
[7] Annotations for Exploring Food Tweets From Multiple Aspects[cs.CL] 标题：关于多角度探索食品推文的标注 作者：Matīss Rikters, Edison Marrese-Taylor, Rinalds Vīksna 链接：http://arxiv.org/abs/2412.06179 期刊：Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
[9] Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy[cs.CL] 标题：基于多样化的大量语言模型文本分类中的数据质量提升：揭示、困难与噪声 作者：Min Zeng, Caiquan Liu, Shiqi Zhang, Li Xie, Chen Sang, Xiaoxin Chen, Xiaoxin Chen 链接：http://arxiv.org/abs/2412.06575 备注：Accepted by COLING 2025(main, long paper)
[10] GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse Dictionary[cs.CL] 标题：GEAR：一种简单的生成、嵌入、平均和排名的无监督反向字典方法 作者：Fatemah Almeman, Luis Espinosa-Anke 链接：http://arxiv.org/abs/2412.06654 备注：9 pages, Accepted at COLING 2025
[11] I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token[cs.CL] 标题：我不知道：使用[我不确定]标记的显式不确定性建模 作者：Roi Cohen, Konstantin Dobler, Eden Biran, Gerard de Melo 链接：http://arxiv.org/abs/2412.06676 备注：Published at NeurIPS 2024
[12] JAPAGEN: Efficient Few/Zero-shot Learning via Japanese Training Dataset Generation with LLM[cs.CL] 标题：JAPAGEN：通过LLM生成日本语训练数据集实现的低/无样本学习高效方法 作者：Takuro Fujii, Satoru Katsumata 链接：http://arxiv.org/abs/2412.06738 备注：Accepted by PACLIC38 (2024)
