http://y-ichen.github.io/icon.png 子喵的个人博客 2024-01-08T08:28:21.935Z http://y-ichen.github.io/ Yichen Hexo http://y-ichen.github.io/2024/01/08/2024-01-08%20[Daily%20Trend]%2015e37de0064e4bb78fb79debedb40727/ 2024-01-07T16:16:29.000Z 2024-01-08T08:28:21.935Z

<h1 id="【1】VideoPoet-A-Large-Language-Model-for-Zero-Shot-Video-Generation"><a

http://y-ichen.github.io/2023/12/15/2023-12-15%20[Daily%20Trend]%20746e872198ac4e9986732ca946ee6a5d/ 2023-12-14T16:18:35.000Z 2023-12-15T10:35:44.760Z

<h1 id="【1】MVDream-Multi-view-Diffusion-for-3D-Generation"><a href="#【1】MVDream-Multi-view-Diffusion-for-3D-Generation" class="headerlink"

http://y-ichen.github.io/2023/12/12/2023-12-12%20[Daily%20Trend]%208188c6b976a9495daa564f385dfc6026/ 2023-12-11T16:18:37.000Z 2023-12-12T10:37:54.628Z

<h1 id="【1】Sequential-Modeling-Enables-Scalable-Learning-for-Large-Vision-Models"><a

http://y-ichen.github.io/2023/12/04/2023-12-04%20[Daily%20Trend]%206955e249abe745aa9dc053890151d4e3/ 2023-12-03T16:11:28.000Z 2023-12-04T03:28:55.004Z

<h2 id="【1】Think-before-you-speak-Training-Language-Models-With-Pause-Tokens"><a

http://y-ichen.github.io/2023/11/29/2023-11-29%20[Daily%20Trend]%20744dda0cdf6743a39763020f8766e5c9/ 2023-11-28T16:15:09.000Z 2023-11-29T07:09:22.307Z

<h2 id="【1】Stable-Video-Diffusion-Scaling-Latent-Video-Diffusion-Models-to-Large-Datasets"><a

http://y-ichen.github.io/2023/11/24/2023-11-24%20[Daily%20Trend]%205aa09d6a9fb84207a167a753499bca12/ 2023-11-23T16:09:41.000Z 2023-11-24T01:41:45.070Z

<h2 id="【1】Vision-Transformers-Need-Registers"><a href="#【1】Vision-Transformers-Need-Registers" class="headerlink" title="【1】Vision

http://y-ichen.github.io/2023/11/23/2023-11-23%20[Daily%20Trend]%204ac1840f3c34484ea3886e94d5ed704a/ 2023-11-22T16:10:40.000Z 2023-11-23T02:40:27.078Z

<h2 id="【1】Video-LLaVA-Learning-United-Visual-Representation-by-Alignment-Before-Projection"><a

http://y-ichen.github.io/2023/11/22/2023-11-22%20[Daily%20Trend]%20a222620bde6c4b1c8e982424af087a4e/ 2023-11-21T16:09:21.000Z 2023-11-22T01:21:24.917Z

<h2 id="【1】Learning-Unsupervised-World-Models-for-Autonomous-Driving-via-Discrete-Diffusion"><a

http://y-ichen.github.io/2023/11/21/2023-11-21%20[Daily%20Trend]%20b471bf9a6fdb4ed093df8dae68eda4aa/ 2023-11-20T16:09:08.000Z 2023-11-21T06:37:36.941Z

<h2 id="【1】Emu-Video-Factorizing-Text-to-Video-Generation-by-Explicit-Image-Conditioning"><a

http://y-ichen.github.io/2023/11/17/2023-11-17%20[Daily%20Trend]%20d243dd83ede648efa4e4a4b078b27b36/ 2023-11-16T16:09:08.000Z 2023-11-17T01:08:15.729Z

<h2 id="【1】ZeroNVS-Zero-Shot-360-Degree-View-Synthesis-from-a-Single-Real-Image"><a

http://y-ichen.github.io/2023/11/16/2023-11-16%20[Daily%20Trend]%207dcc30c54b3b44179124971ca541cf05/ 2023-11-15T16:10:58.000Z 2023-11-16T02:58:19.947Z

<h2 id="【1】MARS-An-Instance-aware-Modular-and-Realistic-Simulator-for-Autonomous-Driving"><a

http://y-ichen.github.io/2023/11/15/2023-11-15%20[Daily%20Trend]%2087d3b3e92e424da5af4c3ae16ade036b/ 2023-11-14T16:19:43.000Z 2023-11-15T11:43:22.770Z

<h2 id="【1】LRM-Large-Reconstruction-Model-for-Single-Image-to-3D"><a href="#【1】LRM-Large-Reconstruction-Model-for-Single-Image-to-3D"

http://y-ichen.github.io/2023/11/09/2023-11-09%20[Daily%20Trend]%20309662a582584d0f9cc678aa20c4aac2/ 2023-11-08T16:17:10.000Z 2023-11-09T09:10:34.691Z

<h2 id="【1】RoboGen-Towards-Unleashing-Infinite-Data-for-Automated-Robot-Learning-via-Generative-Simulation"><a

http://y-ichen.github.io/2023/11/03/2023-11-03%20[Daily%20Trend]%20a1537a0aed924c5aa8776d517d634754/ 2023-11-02T16:18:09.000Z 2023-11-03T10:09:34.014Z

<h2 id="【1】FreeNoise-Tuning-Free-Longer-Video-Diffusion-via-Noise-Rescheduling"><a

http://y-ichen.github.io/2023/11/02/2023-11-02%20[Daily%20Trend]%2020ffdf85a5154c1dbc515665fe16462b/ 2023-11-01T16:18:39.000Z 2023-11-02T10:39:48.790Z

<h2 id="【1】Frozen-Transformers-in-Language-Models-Are-Effective-Visual-Encoder-Layers"><a

http://y-ichen.github.io/2023/11/01/2023-11-01%20[Daily%20Trend]%20cb7feb9f64a149f58a13c6e4bd5db31b/ 2023-10-31T16:18:27.000Z 2023-11-01T10:27:36.255Z

<h2 id="【1】VideoCrafter1-Open-Diffusion-Models-for-High-Quality-Video-Generation"><a

http://y-ichen.github.io/2023/10/27/2023-10-27%20[Daily%20Trend]%20f6fed0095a76434aadd7ae24f0d51e09/ 2023-10-26T16:18:14.000Z 2023-10-27T10:15:00.746Z

<h2 id="【1】Zero123-a-Single-Image-to-Consistent-Multi-view-Diffusion-Base-Model"><a

http://y-ichen.github.io/2023/10/25/2023-10-25%20[Daily%20Trend]%20c3f17d22438a4bfaa23d09964da359f4/ 2023-10-24T16:16:05.000Z 2023-10-25T08:05:59.662Z

<h2 id="【1】TACo-Token-aware-Cascade-Contrastive-Learning-for-Video-Text-Alignment"><a

http://y-ichen.github.io/2023/10/24/2023-10-24%20[Daily%20Trend]%20360a1abe051e481d8c09f1fecdb9461f/ 2023-10-23T16:17:33.000Z 2023-10-24T09:34:44.897Z

<h2 id="【1】ConsistNet-Enforcing-3D-Consistency-for-Multi-view-Images-Diffusion"><a

http://y-ichen.github.io/2023/10/23/2023-10-23%20[Daily%20Trend]%20564c273d5b7a4b3d9bcee58272f1634b/ 2023-10-22T16:17:47.000Z 2023-10-24T09:34:52.118Z

<h2 id="【1】World-Models"><a href="#【1】World-Models" class="headerlink" title="【1】World Models"></a>【1】World Models</h2><p>【URL】<a