机器之心 & ArXiv Weekly
参与：楚航、罗若天、梅洪源
本周论文包括给视频中人物或物体添加特效的新人工智能模型「Gen-1」，以及约翰斯·霍普金斯大学和剑桥大学制作的迄今为止最先进的昆虫大脑图谱。
Composer: Creative and Controllable Image Synthesis with Composable Conditions Structure and Content-Guided Video Synthesis with Diffusion Models The connectome of an insect brain Uncertainty-driven dynamics for active learning of interatomic potentials Combinatorial synthesis for AI-driven materials discovery Masked Images Are Counterfactual Samples for Robust Fine-tuning One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale ArXiv Weekly Radiostation：NLP、CV、ML 更多精选论文（附音频）
作者：Lianghua Huang 等 论文地址：https://arxiv.org/pdf/2302.09778v2.pdf
作者：Patrick Esser 等 论文地址：https://arxiv.org/pdf/2302.03011.pdf
作者：MICHAEL WINDING 等 论文地址：https://www.science.org/doi/10.1126/science.add9330
作者：Maksim Kulichenko 等 论文地址：https://www.nature.com/articles/s43588-023-00406-5
作者：John M. Gregoire 等 论文地址：https://www.nature.com/articles/s44160-023-00251-4
作者：Yao Xiao 等 论文地址：https://arxiv.org/abs/2303.03052
作者：Fan Bao 等 论文地址：https://ml.cs.tsinghua.edu.cn/diffusion/unidiffuser.pdf
1. GLEN: General-Purpose Event Detection for Thousands of Types. (from Martha Palmer, Jiawei Han)
2. An Overview on Language Models: Recent Developments and Outlook. (from C.-C. Jay Kuo)
3. Learning Cross-lingual Visual Speech Representations. (from Maja Pantic)
4. Translating Radiology Reports into Plain Language using ChatGPT and GPT-4 with Prompt Learning: Promising Results, Limitations, and Potential. (from Ge Wang)
5. A Picture is Worth a Thousand Words: Language Models Plan from Pixels. (from Honglak Lee)
6. Do Transformers Parse while Predicting the Masked Word?. (from Sanjeev Arora)
7. The Learnability of In-Context Learning. (from Amnon Shashua)
8. Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?. (from Yuji Matsumoto)
9. ChatGPT Participates in a Computer Science Exam. (from Ulrike von Luxburg)
10. Team SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification. (from Kalina Bontcheva)
本周 10 篇 CV 精选论文是：
1. From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning. (from Matti Pietikäinen, Li Liu)
2. Category-Level Multi-Part Multi-Joint 3D Shape Assembly. (from Wojciech Matusik, Leonidas Guibas)
3. PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision. (from Leonidas Guibas)
4. Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception. (from Xiangyu Zhang)
5. Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation. (from Bing Liu)
6. Unified Visual Relationship Detection with Vision and Language Models. (from Ming-Hsuan Yang)
7. Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank. (from Huan Liu)
8. InstMove: Instance Motion for Object-centric Video Segmentation. (from Xiang Bai, Alan Yuille)
9. ViTO: Vision Transformer-Operator. (from George Em Karniadakis)
10. A Simple Framework for Open-Vocabulary Segmentation and Detection. (from Jianfeng Gao, Lei Zhang)
本周 10 篇 ML 精选论文是：
1. Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap. (from Bernhard Schölkopf)
2. AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks. (from Jure Leskovec)
3. Relational Multi-Task Learning: Modeling Relations between Data and Tasks. (from Jure Leskovec)
4. Interpretable Outlier Summarization. (from Samuel Madden)
5. Visual Prompt Based Personalized Federated Learning. (from Dacheng Tao)
6. Interpretable Joint Event-Particle Reconstruction for Neutrino Physics at NOvA with Sparse CNNs and Transformers. (from Pierre Baldi)
7. FedLP: Layer-wise Pruning Mechanism for Communication-Computation Efficient Federated Learning. (from Fei Wang, Khaled B. Letaief)
8. Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors. (from Sepp Hochreiter)
9. Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning. (from Thomas Hofmann)
10. Steering Prototype with Prompt-tuning for Rehearsal-free Continual Learning. (from Dimitris N. Metaxas)
© THE END
转载请联系本公众号获得授权
投稿或寻求报道：content@jiqizhixin.com