Loading...

ÇмúÇà»ç

Korean AI Association

  >   ÇмúÇà»ç   >   ±¹³»Çмú´ëȸ

±¹³»Çмú´ëȸ

ÇÁ·Î±×·¥
 ¡Ø  Æ©Å丮¾ó ¼¼¼Ç 2ÀÇ ±è½Â·æ ±³¼ö´Ô °­¿¬ÀÌ ¿¬»çºÐ »çÁ¤À¸·Î 16:00~18:00·Î º¯°æµÇ¾ú½À´Ï´Ù.
      ºÎµð Âø¿À ¾øÀ¸½Ã±â ¹Ù¶ó¸ç Âü°¡ÀںеéÀÇ ³Ê¸¥ ¾çÇظ¦ ºÎŹµå¸³´Ï´Ù.
 
11¿ù 23ÀÏ(¸ñ) <¿Â¶óÀÎ °³ÃÖ>
³»¿ë ½Ã°£ ¼¼ºÎ³»¿ë
Æ©Å丮¾ó ¼¼¼Ç 1 13:00-15:00                          Robot Learning                         / ÀÓÀçȯ ±³¼ö(KAIST)        3D-aware Image Generation and Editing                         Approaches and Applications                       / ÁÖÀç°É ±³¼ö(KAIST)   Fairness in Machine Learning: Challenges,                       Analysis, and Solutions                           / ¼Û°æ¿ì ±³¼ö(¿¬¼¼´ë)
ÈÞ½Ä 15:00-15:20 ÈÞ½Ä
Æ©Å丮¾ó ¼¼¼Ç 2
15:20-17:20
* 16:00-18:00 
   Recent Trends of Distillation Methods in                              Diffusion Models                             / ±èµ¿ÁØ ¹Ú»ç(Stanford)
 Injecting output constraints and  dependencies                          into neural models                           / ÀÌÀçÀ± ±³¼ö(¼­¿ï´ë)          * Recent Advances in Language-driven                          Computer Vision Tasks                       / ±è½Â·æ ±³¼ö(°í·Á´ë)
11¿ù 24ÀÏ(±Ý) Àå¼Ò : ³×À̹ö 1784 28Ãþ ½ºÄ«ÀÌȦ
³»¿ë ½Ã°£ ¼¼ºÎ³»¿ë
°³È¸¼±¾ð 09:00-09:10                                                                                                       °³È¸¼±¾ð/ ±è¿ë´ë ȸÀå                                                                                                         Ãà»ç/ ÀÌÇö±Ô PM(IITP)
Special invited talk 1 09:10-10:00 Optimal Transport in Large-Scale Machine Learning Applications/ Prof. Nhat Ho(University of Texas at Austin)
±¹Á¦ÇÐȸ¿ì¼ö³í¹®¹ßÇ¥  10:00-10:20  Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching, ICLR 2023/ È«½ÂÈÆ ±³¼ö(KAIST)
10:20-10:40          H-Likelihood Approach to Deep Neural Networks with Temporal-Spatial Random Effects for High-Cardinality Categorical Features,                              ICML 2023/ ÀÌÇ׺ó ¹Ú»ç(¼­¿ï´ë), ÀÌ¿µÁ¶ ±³¼ö(¼­¿ï´ë)
ÈÞ½Ä 10:40-11:00  ÈÞ½Ä
¿ì¼ö³í¹® ½Ã»ó ¹× ÃÖ¿ì¼ö³í¹® ¹ßÇ¥ 11:00-11:30 ¿ì¼ö³í¹® ½Ã»ó ¹× ÃÖ¿ì¼ö³í¹® ¹ßÇ¥
Æ÷½ºÅÍ 11:30-12:00 Æ÷½ºÅÍ ¹ßÇ¥
Á¡½É 12:00-13:00 Á¡½É
Plenary Talk  13:00-13:50 Martingale Posterior Distributions/ Prof. Stephen G. Walker(University of Texas at Austin)
±âȹ¼¼¼Ç 1 13:50-14:50 ÀΰøÁö´É ÀÌ·Ð  Cascading Contextual Assortment Bandits/ ¿À¹Îȯ ±³¼ö(¼­¿ï´ë)
 Score-based Generative Models in Hilbert Spaces/ ÀÓ¼ººó ±³¼ö(°í·Á´ë)
 Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima/ À±Ã¶Èñ ±³¼ö(KAIST)
ÈÞ½Ä 14:50-15:05 ÈÞ½Ä
±âȹ¼¼¼Ç 2  15:05-16:05 ºñÁ¯  On the Training-Free Image Manipulation using Diffusion Probabilistic Models/ ÇѺ¸Çü ±³¼ö(¼­¿ï´ë)
 Multimodal Foundation Models for Video QA/ ±èÇö¿ì ±³¼ö(°í·Á´ë)
±âȹ¼¼¼Ç 3  16:05-17:05    ÀÚ¿¬¾î ¹× À½¼º  X-SNS: Cross-Lingual Transfer Prediction through Sub-Network Similarity/ ±èÅÂ¿í ±³¼ö(ÇѾç´ë)
 ÃֽŠÀ½¼ºÀÎ½Ä ¹× À½¼ºÇÕ¼º °¡¼ú¸®ºä/ ÀåÁØÇõ ±³¼ö(ÇѾç´ë)
ÈÞ½Ä 17:05-17:20   ÈÞ½Ä
Special invited talk 2 17:20-18:10 Controllable AI: Lessons from the Past & The Future of Conversational AI/ ÃÖÁøÈ£ ±³¼ö(Emory University)
ÃÊû°­¿¬  18:10-18:40  Hyperscale AI, ¿ì¸®ÀÇ °æÀï·Â/ ¼º³«È£ ÇÏÀÌÆÛ½ºÄÉÀÏ AI ±â¼úÃÑ°ý(³×À̹öŬ¶ó¿ìµå)
¸¸Âù 19:20 ¸¸Âù <¶ó¿Â½ºÄù¾î>
11¿ù 25ÀÏ (Åä) Private Session <³»ºÎ ¿öÅ©¼ó>
 
¡Ø ¸¸ÂùÀº ÀαÙÀÇ "¶ó¿Â½ºÄù¾î"¿¡¼­ ÁøÇàµË´Ï´Ù. Çà»çÀå¼Ò¿¡¼­ ÇÔ²² ¼ÅƲ¹ö½º·Î À̵¿¿¹Á¤ÀÔ´Ï´Ù.