[论文简析]Is Space-Time Attention All You Need for Video Understanding?[2102.05095]
发布人
打开封面 下载高清视频 观看高清视频 视频下载器
...
[论文简析]Keeping Your Eye on the Ball: Trajectory Attention...[2106.05392]
...
【全374集】2024最新清华内部版！终于把AI大模型（LLM）讲清楚了！全程干货讲解，通俗易懂，拿走不谢！
...
[论文简析]Per-Pixel Classification is Not All You Need for Semantic Seg[2107.06278]
...
[论文简析]MoCoGAN-HD: A Good Image Generator Is What You Need...[2104.15069]
...
[论文简析]BiFormer: Vision Transformer with Bi-Level Routing Attention[2303.08810]
...
[论文简析]Improving fine-grained understanding in image-text pre-training[2401.0986]
...
[论文简析]Location-Aware Self-Supervised Transformers for Semantic Seg.[2212.02400]
...
[论文夕拾]Diffusion Models for Robotics
...
[论文简析]Towards Better Understanding of Self-Supervised Representation[2203.01881]
...
【全126集】目前B站最系统的Transformer教程！入门到进阶，全程干货讲解！拿走不谢！（神经网络/NLP/注意力机制/大模型/GPT/RNN）
...
【MATLAB论文复现】研一研二必看！MATLAB论文如何从代码到公式完整复现？看完这个你就彻底懂了！草履虫都能学会！
...
[论文速览]Open Vocab. Semantic Seg. with Patch Aligned Contrastive...[2212.04994]
...
[论文简析]End-to-End Video-Language Transformers..Masked Visual-token..[2111.12681]
...
太强了！【GNN+Transformer】2024年最容易研究论文方向的内容！论文精讲+代码复现！小白都能轻松看懂！建议收藏！（图神经网络、机器学习、AI）
...
[论文简析]Toolformer: Language Models Can Teach Themselves to Use Tools[2302.04761]
...
B站最全的【Transformer教程】中科院58集付费课程，最适合新手入门Transformer模型实战系列，绝对通俗易懂，允许白嫖！
...
[论文速览]Token Turing Machines[2211.09119]
...
[论文简析]VATT: Video-Audio-Text Transformer[2104.11178]
...
B站强推！2024公认最通俗易懂的时间序列预测教程，从入门到精通！草履虫都能听懂！（LSTM/Informer/ARIMA/PandasTransformer）
...
[论文速览]EViT: Expediting Vision Transformers via Token Reorganizations[2202.07800]
...
这是我迄今为止见过将 Chat GPT 原理最好的可视化。具象化的展示了Transformer神经网络模型结构。像在四维看三维。
...
[论文简析]End-to-End Learning... from Uncurated Instructional Videos[1912.06430]
...
[论文简析]Point Transformer[2012.09164]
...
[论文速览]LoRA: Low-Rank Adaptation of Large Language Models[2106.09685]
...
[论文速览]GENIMA: Generative Image as Action Models[2407.07875]
...
[论文简析]VoxPoser: Composable 3D Value Maps for Robotic...[2307.05973]
...
完爆YOLOv11！Transformer+目标检测新算法性能无敌，狠狠拿捏CV顶会
...
[论文简析]Regularized Vector Quantization for Tokenized Image Synthesis[2303.06424]
...
[论文速览]Scalable Video Object Segmentation with Simplified Framework[2308.09903]
...
[论文简析]DCLGAN/SimDCL: Dual Contrastive Learning[2104.07689]
...
[论文简析]Object-Centric Learning with Slot Attention[2006.15055]
...
[论文简析]Learning by Aligning Videos in Time[2103.17260]
...
[论文简析]World Models[1803.10122]
...
[论文简析]Vision Transformers Need Registers[2309.16588]
...
北大新作：傅里叶分析神经网络，填补周期性特征建模缺陷，Transformer重要缺陷被揭示！
...
[论文简析]MaskGIT: Masked Generative Image Transformer[2202.04200]
...
[论文简析]NeRF: Representing Scenes as Neural Radiance Fields...[2003.08934]
...
[论文简析]Barlow Twins:Self-Supervised Learning via Redundancy Reduction[2103.03230]
...
[论文简析]VAE: Auto-encoding Variational Bayes[1312.6114]
...
[论文简析]SimCLR: A simple framework for contrastive learning[2002.05709]