【2024/11/28】今日の最新AI論文をまとめて紹介
2024年11月28日更新
Youtubeチャンネル名
閲覧数
199 回再生
いいね数
6 いいね
この動画の内容
この動画は、2024年11月28日のAI論文を簡単にまとめた内容を紹介しています。
【お知らせ】
Twitter始めました。よかったらフォローしてね😊
https://twitter.com/JiroHarapeko
【論文リスト】
DreamCache-Finetuning-Free_Lightweight_Personalized_Image_Generation_via_Feature_Caching
https://arxiv.org/pdf/2411.17786
VideoLLM_Knows_When_to_Speak-Enhancing_Time-Sensitive_Video_Comprehension_with_Video-Text_Duet_Interaction_Format
https://arxiv.org/pdf/2411.17991
Interleaved_Scene_Graph_for_Interleaved_Text-and-Image_Generation_Assessment
https://arxiv.org/pdf/2411.17188
Draft_Model_Knows_When_to_Stop-A_Self-Verification_Length_Policy_for_Speculative_Decoding
https://arxiv.org/pdf/2411.18462
Omegance-A_Single_Parameter_for_Various_Granularities_in_Diffusion-Based_Synthesis
https://arxiv.org/pdf/2411.17769
Training_and_Evaluating_Language_Models_with_Template-based_Data_Generation
https://arxiv.org/pdf/2411.18104
ROICtrl-Boosting_Instance_Control_for_Visual_Generation
https://arxiv.org/pdf/2411.17949
Collaborative_Decoding_Makes_Visual_Auto-Regressive_Modeling_Efficient
https://arxiv.org/pdf/2411.17787
ChatRex-Taming_Multimodal_LLM_for_Joint_Perception_and_Understanding
https://arxiv.org/pdf/2411.18363
UniPose-A_Unified_Multimodal_Framework_for_Human_Pose_Comprehension,_Generation_and_Editing
https://arxiv.org/pdf/2411.16781
MARVEL-40M+-Multi-Level_Visual_Elaboration_for_High-Fidelity_Text-to-3D_Content_Creation
https://arxiv.org/pdf/2411.17945
Optimizing_Brain_Tumor_Segmentation_with_MedNeXt-BraTS_2024_SSA_and_Pediatrics
https://arxiv.org/pdf/2411.15872
DiffusionDrive-Truncated_Diffusion_Model_for_End-to-End_Autonomous_Driving
https://arxiv.org/pdf/2411.15139
Identity-Preserving_Text-to-Video_Generation_by_Frequency_Decomposition
https://arxiv.org/pdf/2411.17440
Make-It-Animatable-An_Efficient_Framework_for_Authoring_Animation-Ready_3D_Characters
https://arxiv.org/pdf/2411.18197
CAT4D-Create_Anything_in_4D_with_Multi-View_Video_Diffusion_Models
https://arxiv.org/pdf/2411.18613
Large_Language_Model-Brained_GUI_Agents-A_Survey
https://arxiv.org/pdf/2411.18279
【タイムスタンプ】
00:00 イントロ
00:39 DreamCache-Finetuning-Free_Lightweight_Personalized_Image_Generation_via_Feature_Caching
02:58 VideoLLM_Knows_When_to_Speak-Enhancing_Time-Sensitive_Video_Comprehension_with_Video-Text_Duet_Interaction_Format
05:23 Interleaved_Scene_Graph_for_Interleaved_Text-and-Image_Generation_Assessment
07:28 Draft_Model_Knows_When_to_Stop-A_Self-Verification_Length_Policy_for_Speculative_Decoding
09:29 Omegance-A_Single_Parameter_for_Various_Granularities_in_Diffusion-Based_Synthesis
12:15 Training_and_Evaluating_Language_Models_with_Template-based_Data_Generation
14:54 ROICtrl-Boosting_Instance_Control_for_Visual_Generation
17:13 Collaborative_Decoding_Makes_Visual_Auto-Regressive_Modeling_Efficient
19:31 ChatRex-Taming_Multimodal_LLM_for_Joint_Perception_and_Understanding
21:37 UniPose-A_Unified_Multimodal_Framework_for_Human_Pose_Comprehension,_Generation_and_Editing
23:51 MARVEL-40M+-Multi-Level_Visual_Elaboration_for_High-Fidelity_Text-to-3D_Content_Creation
26:37 Optimizing_Brain_Tumor_Segmentation_with_MedNeXt-BraTS_2024_SSA_and_Pediatrics
29:05 DiffusionDrive-Truncated_Diffusion_Model_for_End-to-End_Autonomous_Driving
31:04 Identity-Preserving_Text-to-Video_Generation_by_Frequency_Decomposition
33:30 Make-It-Animatable-An_Efficient_Framework_for_Authoring_Animation-Ready_3D_Characters
35:38 CAT4D-Create_Anything_in_4D_with_Multi-View_Video_Diffusion_Models
38:06 Large_Language_Model-Brained_GUI_Agents-A_Survey
#AI論文
#LLM
#生成AI
【注意】
この動画は誤った情報を含む可能性があります。
問題点や改善点があれば、コメントで教えてください。
音声ソフト：VOICEVOX(ずんだもん)