DAVIAN Lab. Seminar (2023)
Time: Monday 19:00 - 21:00
| Date | Topic | Presenters | Slides | Videos |
|---|---|---|---|---|
| 6th July, 2023 | DINO: Emerging Properties in Self-Supervised Vision Transformers | μ΅μλ―Έ | Slide | Video |
| 6th July, 2023 | On the duality between contrastive and non-contrastive SSL | μ΄νΈμ€ | Slide | Video |
| 29th June, 2023 | ConvNext v2: Extension of masked Image Modeling | μ΄μν | Slide | Video |
| 29th June, 2023 | Extension of Sample-Contrastive Learning | λ°μ€μ° | Slide | Video |
| 22th June, 2023 | GigaGAN: Scaling up GANs for Text-to-Image Synthesis | ꡬκ΅μ | Slide | Video |
| 22th June, 2023 | A survey of Neural Talking Heads | μ΄μ¬μ± | Slide | Video |
| 15th June, 2023 | Aligning Text-to-Image models with Human preference | νμ€ν | Slide | Video |
| 15th June, 2023 | Survey on Multimodal with LLM | λ°±μν | Slide | Video |
| 8th June, 2023 | Unsupervised Model Selection for Time Series Anomaly Detection | κΉμ§ν¬ | Slide | Video |
| 8th June, 2023 | Encoding Recurrent into Transformers | κΉνμ± | Slide | Video |
| 1th June, 2023 | Do you know AI bandoche? | μ‘°μμ° | Slide | Video |
| 1th June, 2023 | WebFace260M: A benchmark for Million scale Deep Face Recognition | μ΄λμ¬ | Slide | Video |
| 25th May, 2023 | LIMA: Less Is More for Alignment | μ΅λ―Όμ | Slide | Video |
| 25th May, 2023 | DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature | Chaehoon Park | Slide | Video |
| 18th May, 2023 | Pretraining, Instructing, Reasoning, Planning | Hojun Cho | Slide | Video |
| 11th May, 2023 | Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time | Minho Park | Slide | Video |
| 4th May, 2023 | Symbolic Discovery of Optimization Algorithms | Jooyeol Yun | Slide | Video |
| 13th April, 2023 | Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning |
Jimin Hong | Slide | Video |
| 6th April, 2023 | DenseNet Strikes Back | Donghyun Kim | Slide | Video |
| 6th April, 2023 | TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis | Junwoo Park | Slide | Video |
| 30th March, 2023 | Deep Active Learning for Computer Vision: Past and Future | Sejik Park | Slide | Video |
| 30th March, 2023 | P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks | Taehee Kim | Slide | Video |
| 23th March, 2023 | Image as Set of Points | Dongmin Choi | Slide | Video |
| 23th March, 2023 | Generative Neural Articulated Radiance Fields | Gyumin Sim | Slide | Video |
| 9th March, 2023 | Robust Object Detection With Inaccurate Bounding Boxes | Sohyun Jeong | Slide | Video |
| 9th March, 2023 | Learning Fair Classifiers with Partially Annotated Group Labels | Jinho Choi | Slide | Video |
| 23th February, 2023 | GLIGEN: Open-Set Grounded Text-to-Image Generation | Youngjoo Jo | Slide | Video |
| 23th February, 2023 | Interesting approaches to utilizing prompts for few-shot NER | Daniel Rim | Slide | Video |
| 16th February, 2023 | Recipe for a General, Powerful, Scalable Graph Transformer (GPS): A review on 2022 GT-research and how did we get here | Rodrigo Hormazabal | Slide | Video |
| 16th February, 2023 | Introduction to Vision-Language model | Koanho Lee | Slide | Video |
| 9th February, 2023 | Label-aware global consistency for multi-label learning with single positive labels | Huiwon Yun | Slide | Video |
| 9th February, 2023 | Sequence to sequence text generation with diffusion models | Seungil Lee | Slide | Video |
| 2nd February, 2023 | Bringing Old Films Back to Life | Ganbat Munkhsoyol | Slide | Video |
| 2nd February, 2023 | DropMix: A Textual Data Augmentation Combining Dropout with Mixup | Soyoung Yang | Slide | Video |
| 26th January, 2023 | Multi-Concept Customization of Text-to-Image Diffusion | Seunghwan Choi | Slide | Video |
| 16th January, 2023 | Image restoration: As a point of view of the inverse problem | Sangheyon Lee | Slide | Video |
| 9th January, 2023 | Learned Initializations for Optimizing Coordinate-Based Neural Representations | Minjung Kim | Slide | Video |
| 9th January, 2023 | Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation | Junha Hyung | Slide | Video |
| 2nd January, 2023 | Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency | Yeojeong Park | Slide | Video |
| 2nd January, 2023 | Context and Attribute-Aware Sequential Recommendation via Cross-Attention | Chung Park | Slide | Video |
| ~ 2022 | Link |