【2024/11/27】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
312 回再生
いいね数
13 いいね
この動画の内容
この動画は、2024年11月27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】
Learning_3D_Representations_from_Procedural_3D_Programs
https://arxiv.org/pdf/2411.17467
Pathways_on_the_Image_Manifold-Image_Editing_via_Video_Generation
https://arxiv.org/pdf/2411.16819
TEXGen-a_Generative_Diffusion_Model_for_Mesh_Textures
https://arxiv.org/pdf/2411.14740
FINECAPTION-Compositional_Image_Captioning_Focusing_on_Wherever_You_Want_at_Any_Granularity
https://arxiv.org/pdf/2411.15411
SALOVA-Segment-Augmented_Long_Video_Assistant_for_Targeted_Retrieval_and_Routing_in_Long-Form_Video_Analysis
https://arxiv.org/pdf/2411.16173
Low-Bit_Quantization_Favors_Undertrained_LLMs-Scaling_Laws_for_Quantized_LLMs_with_100T_Training_Tokens
https://arxiv.org/pdf/2411.17691
Controllable_Human_Image_Generation_with_Personalized_Multi-Garments
https://arxiv.org/pdf/2411.16801
Star_Attention-Efficient_LLM_Inference_over_Long_Sequences
https://arxiv.org/pdf/2411.17116
VLRewardBench-A_Challenging_Benchmark_for_Vision-Language_Generative_Reward_Models
https://arxiv.org/pdf/2411.17451
MME-Survey-A_Comprehensive_Survey_on_Evaluation_of_Multimodal_LLMs
https://arxiv.org/pdf/2411.15296
SAR3D-Autoregressive_3D_Object_Generation_and_Understanding_via_Multi-scale_3D_VQVAE
https://arxiv.org/pdf/2411.16856
SketchAgent-Language-Driven_Sequential_Sketch_Generation
https://arxiv.org/pdf/2411.17673
Rethinking_Token_Reduction_in_MLLMs-Towards_a_Unified_Paradigm_for_Training-Free_Acceleration
https://arxiv.org/pdf/2411.17686
MolReFlect-Towards_In-Context_Fine-grained_Alignments_between_Molecules_and_Texts
https://arxiv.org/pdf/2411.14721
AnchorCrafter-Animate_CyberAnchors_Saling_Your_Products_via_Human-Object_Interacting_Video_Generation
https://arxiv.org/pdf/2411.17383
ShowUI-One_Vision-Language-Action_Model_for_GUI_Visual_Agent
https://arxiv.org/pdf/2411.17465
DreamMix-Decoupling_Object_Attributes_for_Enhanced_Editability_in_Customized_Image_Inpainting
https://arxiv.org/pdf/2411.17223
【タイムスタンプ】
00:00 イントロ
00:39 Learning_3D_Representations_from_Procedural_3D_Programs
03:04 Pathways_on_the_Image_Manifold-Image_Editing_via_Video_Generation
05:50 TEXGen-a_Generative_Diffusion_Model_for_Mesh_Textures
08:09 FINECAPTION-Compositional_Image_Captioning_Focusing_on_Wherever_You_Want_at_Any_Granularity
10:58 SALOVA-Segment-Augmented_Long_Video_Assistant_for_Targeted_Retrieval_and_Routing_in_Long-Form_Video_Analysis
13:53 Low-Bit_Quantization_Favors_Undertrained_LLMs-Scaling_Laws_for_Quantized_LLMs_with_100T_Training_Tokens
16:16 Controllable_Human_Image_Generation_with_Personalized_Multi-Garments
18:52 Star_Attention-Efficient_LLM_Inference_over_Long_Sequences
21:12 VLRewardBench-A_Challenging_Benchmark_for_Vision-Language_Generative_Reward_Models
24:11 MME-Survey-A_Comprehensive_Survey_on_Evaluation_of_Multimodal_LLMs
26:36 SAR3D-Autoregressive_3D_Object_Generation_and_Understanding_via_Multi-scale_3D_VQVAE
29:08 SketchAgent-Language-Driven_Sequential_Sketch_Generation
31:34 Rethinking_Token_Reduction_in_MLLMs-Towards_a_Unified_Paradigm_for_Training-Free_Acceleration
33:56 MolReFlect-Towards_In-Context_Fine-grained_Alignments_between_Molecules_and_Texts
36:31 AnchorCrafter-Animate_CyberAnchors_Saling_Your_Products_via_Human-Object_Interacting_Video_Generation
38:46 ShowUI-One_Vision-Language-Action_Model_for_GUI_Visual_Agent
40:31 DreamMix-Decoupling_Object_Attributes_for_Enhanced_Editability_in_Customized_Image_Inpainting
#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)