[0] Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales[cs.CV] 标题：超越准确度：确保正确预测和合理充分的解释 作者：Tang Li, Mengmeng Ma, Xi Peng 链接：http://arxiv.org/abs/2411.00132 代码：https://github.com/deep-real/DCP 备注：In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
[1] Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking[cs.CV] 标题：行人轨迹预测中缺失数据的处理：数据集、插值和基准测试 作者：Pranav Singh Chib, Pravendra Singh 链接：http://arxiv.org/abs/2411.00174 代码：https://github.com/Pranav-chib/TrajImpute 备注：Accepted at NeurIPS 2024
[2] Inducing Semi-Structured Sparsity by Masking for Efficient Model Inference in Convolutional Networks[cs.CV] 标题：通过掩码诱导半结构化稀疏性以提高卷积网络中模型推理效率 作者：David A. Danhofer 链接：http://arxiv.org/abs/2411.00288 备注：15 pages, 3 figures; this work will be presented at the NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability (FITML)
[3] Right this way: Can VLMs Guide Us to See More to Answer Questions?[cs.CV] 标题：正是这条路：VLMs能引导我们看到更多，以求解问题吗？ 作者：Li Liu, Diji Yang, Sijia Zhong, Kalyana Suma Sree Tholeti, Lei Ding, Yi Zhang, Leilani H. Gilpin 链接：http://arxiv.org/abs/2411.00394 备注：NeurIPS 2024
[4] ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization[cs.CV] 标题：概念工厂：通过物体概念化促进3D对象知识标注 作者：Jianhua Sun, Yuxuan Li, Longfei Xu, Nange Wang, Jiude Wei, Yining Zhang, Cewu Lu 链接：http://arxiv.org/abs/2411.00448 备注：NeurIPS 2024 Track on Datasets and Benchmarks
[5] Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions[cs.CV] 标题：面向对抗性点云转换的靶向引导对抗识别以防现实世界干扰 作者：Jie Wang, Tingfa Xu, Lihe Ding, Jianan Li 链接：http://arxiv.org/abs/2411.00462 代码：https://github.com/Roywangj/APCT 备注：Accepted by NeurIPS 2024; code: this https URL
[6] 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction[cs.CV] 标题：三个月等变姿态回归通过直接Wigner-D谐波预测 作者：Jongmin Lee, Minsu Cho 链接：http://arxiv.org/abs/2411.00543 备注：Accepted to NeurIPS 2024, Project webpage at this http URL
[7] Tracking one-in-a-million: Large-scale benchmark for microbial single-cell tracking with experiment-aware robustness metrics[cs.CV] 标题：追随百万分之一：大规模基准测试针对微生物单细胞跟踪的实验感知鲁棒性指标 作者：J. Seiffarth, L. Blöbaum, R. D. Paul, N. Friederich, A. J. Yamachui Sitcheu, R. Mikut, H. Scharr, A. Grünberger, K. Nöh 链接：http://arxiv.org/abs/2411.00552 备注：17 pages, 4 figures, 3 tables, BioImage Computing @ ECCV 2024
[8] Is Multiple Object Tracking a Matter of Specialization?[cs.CV] 标题：多目标跟踪是否是专业化的产物？ 作者：Gianluca Mancusi, Mattia Bernardi, Aniello Panariello, Angelo Porrello, Rita Cucchiara, Simone Calderara 链接：http://arxiv.org/abs/2411.00553 备注：NeurIPS 2024
[9] On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDAR[cs.CV] 标题：关于使用车内3D激光雷达实现的几何和语义场景理解深度学习 作者：Li Li 链接：http://arxiv.org/abs/2411.00600
备注：PhD thesis (Durham University, Computer Science), 149 pages (the 2024 BMVA Sullivan Doctoral Thesis Prize runner-up). Includes published content from arXiv:2407.10159 (ECCV 2024 ORAL), arXiv:2303.11203 (CVPR 2023), and arXiv:2406.10068 (3DV 2021), with minor revisions to the examined version: this https URL
[10] pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization[cs.CV] 标题：PCAGAN：通过主成分正则化改进后验抽样cGAN 作者：Matthew C. Bendel, Rizwan Ahmad, Philip Schniter 链接：http://arxiv.org/abs/2411.00605 代码：https://github.com/matt-bendel/pcaGAN 备注：To appear at NeurIPS 2024
[11] PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding[cs.CV] 标题：PCoTTA：多任务点云理解的持续测试时自适应 作者：Jincen Jiang, Qianyu Zhou, Yuhang Li, Xinkui Zhao, Meili Wang, Lizhuang Ma, Jian Chang, Jian Jun Zhang, Xuequan Lu 链接：http://arxiv.org/abs/2411.00632 备注：Accepted to NeurIPS 2024
[12] Event-guided Low-light Video Semantic Segmentation[cs.CV] 标题：事件引导的低光照视频语义分割 作者：Zhen Yao, Mooi Choo Chuah 链接：http://arxiv.org/abs/2411.00639 备注：12 pages, 5 figures, Accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025
[13] Towards High-fidelity Head Blending with Chroma Keying for Industrial Applications[cs.CV] 标题：朝着工业应用的高保真头混合与实时抠绿技术的研究 作者：Hah Min Lew, Sahng-Min Yoo, Hyunwoo Kang, Gyeong-Moon Park 链接：http://arxiv.org/abs/2411.00652 备注：Accepted by WACV 2025. Project page: this https URL
[14] TaxaBind: A Unified Embedding Space for Ecological Applications[cs.CV] 标题：物种绑定：生态应用的综合嵌入空间 作者：Srikumar Sastry, Subash Khanal, Aayush Dhakal, Adeel Ahmad, Nathan Jacobs 链接：http://arxiv.org/abs/2411.00683 备注：Accepted to WACV 2025
[15] Debiasify: Self-Distillation for Unsupervised Bias Mitigation[cs.CV] 标题：消融偏差：用于无监督偏置缓解的自蒸馏 作者：Nourhan Bayasi, Jamil Fayyad, Ghassan Hamarneh, Rafeef Garbi, Homayoun Najjaran 链接：http://arxiv.org/abs/2411.00711 备注：Accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV2025)
[16] B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable[cs.CV] 标题：B-可解释化：将深度神经网络转化为固有可解释 作者：Shreyash Arya, Sukrut Rao, Moritz Böhle, Bernt Schiele 链接：http://arxiv.org/abs/2411.00715 代码：https://github.com/shrebox/B-cosification 备注：31 pages, 9 figures, 12 tables, Neural Information Processing Systems (NeurIPS) 2024
[0] Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models[cs.CV] 标题：保持预训练表示空间：关于Prefix-tuning对大型多模态模型有效性的探讨 作者：Donghoon Kim, Gusang Lee, Kyuhong Shim, Byonghyo Shim 链接：http://arxiv.org/abs/2411.00029 备注：Findings of EMNLP 2024
[1] Topic-Conversation Relevance (TCR) Dataset and Benchmarks[cs.CL] 标题：主题-对话相关性数据集和基准 作者：Yaran Fan, Jamie Pool, Senja Filipi, Ross Cutler 链接：http://arxiv.org/abs/2411.00038 备注：To be published in 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks
[2] Generating Diverse Negations from Affirmative Sentences[cs.CL] 标题：从肯定句生成多样否定句 作者：Darian Rodriguez Vasquez, Afroditi Papadaki 链接：http://arxiv.org/abs/2411.00056 代码：https://github.com/DarianRodriguez/NegVerse 备注：Accepted at "Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning" workshop at NeurIPS 2024
[3] LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction[cs.CL] 标题：LLM4Mat-Bench：材料属性预测的大型语言模型基准测试 作者：Andre Niyongabo Rubungo, Kangming Li, Jason Hattrick-Simpers, Adji Bousso Dieng 链接：http://arxiv.org/abs/2411.00177 代码：https://github.com/vertaix/LLM4Mat-Bench 备注：Accepted at NeurIPS 2024-AI4Mat Workshop. The Benchmark and code can be found at: this https URL
[4] Learning to Rank Salient Content for Query-focused Summarization[cs.CL] 标题：学习为查询聚焦总结排序显著内容 作者：Sajad Sotudeh, Nazli Goharian 链接：http://arxiv.org/abs/2411.00324 备注：Long paper accepted at EMNLP 2024 (Main)
[5] STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing[cs.CL] 标题：STEM-POM：评估文档解析中语言模型对数学符号推理的能力评估 作者：Jiaru Zou, Qing Wang, Pratyush Thakur, Nickvash Kani 链接：http://arxiv.org/abs/2411.00387 备注：Accepted to NeurIPS Math-AI 2024
[6] GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domains[cs.CL] 标题：GDTB：面向跨模态、文本类型和领域的英语浅层对话解析的语料库 作者：Yang Janet Liu, Tatsuya Aoyama, Wesley Scivetti, Yilun Zhu, Shabnam Behzad, Lauren Elizabeth Levine, Jessica Lin, Devika Tiwari, Amir Zeldes 链接：http://arxiv.org/abs/2411.00491 备注：Accepted to EMNLP 2024 (main, long); camera-ready version
[7] Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models[cs.CL] 标题：多专家提示优化大型语言模型的可靠性、安全性和实用性 作者：Do Xuan Long, Duong Ngoc Yen, Anh Tuan Luu, Kenji Kawaguchi, Min-Yen Kan, Nancy F. Chen 链接：http://arxiv.org/abs/2411.00492 备注：EMNLP 2024 Main Conference
[9] Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models[cs.CL] 标题：潜在释义：层扰动提升语言模型中的知识注入 作者：Minki Kang, Sung Ju Hwang, Gibbeum Lee, Jaewoong Cho 链接：http://arxiv.org/abs/2411.00686 备注：NeurIPS 2024
[10] Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis[cs.CL] 标题：利用大型语言模型进行情感分析中代码混合数据增强 作者：Linda Zeng 链接：http://arxiv.org/abs/2411.00691 备注：17 pages, 4 figures, 11 tables, To be published in the Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024), co-located with EMNLP 2024
