トップカンファレンス輪読会
概要
本勉強会では，特にトップカンファレンスと呼ばれる国際会議に採択された論文を中心に輪読を行う．
取得目標
- 1つの論文を詳しく読むことができる
- 良質なプレゼン資料を作成できる
- 自分の言葉で説明できるようになる
実施回
| 回数 | 論文タイトル | 学会 | 担当者 |
|---|---|---|---|
| 第0回 | ガイダンス | 吉丸 | |
| 第1回 | Omniobject3d: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generatio | CVPR2023 | 灰野 |
| Story Trees: Representing Documents using Topological Persistence | LREC2022 | 柄戸 | |
| Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models | ACL2023 | 安永 | |
| 第2回 | Alice and the Caterpillar: A more descriptive null model for assessing data mining results | ICDM2022 | 波多野 |
| Fair Graph Representation Learning via Diverse Mixture-of-Experts | WWW2023 | 平子 | |
| What the DAAM: Interpreting Stable Diffusion Using Cross Attention | ACL2023 | 森岡 | |
| 第3回 | Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning | EMNLP2023 | 原 |
| Network Shuffling: Privacy Amplification via Random Walks | SIGMOD2022 | 宮本 | |
| reveal: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory | KDD2023 | 森弘 | |
| 第4回 | sparseembed: Learning Sparse Lexical Representations with Contextual Embeddings for Retriev | SIGIR2023 | 灰野 |
| LipLearner: Customizable Silent Speech Interactions on Mobile Devices | CHI2023 | 前川 | |
| Auto-Tables : Synthesizing multi-step transformations to relationalize tables without using examples | VLDB2023 | 安永 | |
| 第5回 | OpenCV Based Real-Time Video Processing Using Android Smartphone | 波多野 | |
| Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations | RecSys2023 | 平子 | |
| Machine Mindset: An MBTI Exploration of Large Language Models | 柄戸 | ||
| 第6回 | Diffusemp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation | ACL 2023 | 森岡 |
| Multimodal Channel-Mixing: Channel and Spatial Masked AutoEncoder on Facial Action Unit Detectio | CVPR2022 | 森弘 | |
| Bao: Making Learned Query Optimization Practical | SIGMOD2021 | 原 | |
| 第7回 | Misspecifcation in Inverse Reinforcement Learning | AAAI2023 | 安永 |
| Towards Flexible Multi-modal Document Models | CVPR2023 | 前川 | |
| Efficient Hyperparameter Optimization under Multi-Source Covariate Shift | CIKM 2021 | 宮本 | |
| 第8回 | Lossy Image Compression with Quantized Hierarchical VAEs | WACV2023 | 波多野 |
| A Watermark for Large Language | ICML2023 | 灰野 | |
| 第9回 | ガイダンス2 | 吉丸 | |
| LoRA: Low-Rank Adaptation of Large Language Models | ICLR2022 | 柄戸 | |
| Automated Metrics for Medical Multi-Document Summarization Disagree with Human Evaluations | ACL2023 | 森岡 | |
| Towards Principled User-side Recommender Systems | CIKM2022 | 平子 | |
| 第10回 | local Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detectio | CVPR2023 | 森弘 |
| AutoExecutor: Predictive Parallelism for Spark SQL Queries | VLDB2023 | 原 | |
| Unit: Multimodal Multitask Learning with a Unified Transformer | ICCV2021 | 前川 | |
| 第11回 | patsql: Efficient Synthesis of SQL Queries from Example Tables with Quick Inference of Projected Columns | VLDB2021 | 宮本 |