几篇论文实现代码:
《One Chatbot Per Person: Creating Personalized Chatbots based on Implicit Profiles》(SIGIR 2021) GitHub:https:// github.com/zhengyima/DHAP
《Learning to Track with Object Permanence》(ICCV 2021) GitHub:https:// github.com/TRI-ML/permatrack [fig3]
《JoJoGAN: One Shot Face Stylization》(2021) GitHub:https:// github.com/mchong6/JoJoGAN [fig1]
《A Static Analyzer for Detecting Tensor Shape Errors in Deep Neural Network Training Code》(2021) GitHub:https:// github.com/ropas/pytea
《Towards a Unified View of Parameter-Efficient Transfer Learning》(2021) GitHub:https:// github.com/jxhe/unify-parameter-efficient-tuning [fig2]
《PantheonRL: A MARL Library for Dynamic Training Interactions》(2021) GitHub:https:// github.com/Stanford-ILIAD/PantheonRL
《Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark》(NeurIPS 2021) GitHub:https:// github.com/iamalexkorotin/Wasserstein2Benchmark [fig4]
《Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data》(2021) GitHub:https:// github.com/sberbank-ai/Real-ESRGAN
《FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark》(2021) GitHub:https:// github.com/mlii0117/FFA-IR
《The neural architecture of language: Integrative modeling converges on predictive processing》(2021) GitHub:https:// github.com/mschrimpf/neural-nlp
《One Chatbot Per Person: Creating Personalized Chatbots based on Implicit Profiles》(SIGIR 2021) GitHub:https:// github.com/zhengyima/DHAP
《Learning to Track with Object Permanence》(ICCV 2021) GitHub:https:// github.com/TRI-ML/permatrack [fig3]
《JoJoGAN: One Shot Face Stylization》(2021) GitHub:https:// github.com/mchong6/JoJoGAN [fig1]
《A Static Analyzer for Detecting Tensor Shape Errors in Deep Neural Network Training Code》(2021) GitHub:https:// github.com/ropas/pytea
《Towards a Unified View of Parameter-Efficient Transfer Learning》(2021) GitHub:https:// github.com/jxhe/unify-parameter-efficient-tuning [fig2]
《PantheonRL: A MARL Library for Dynamic Training Interactions》(2021) GitHub:https:// github.com/Stanford-ILIAD/PantheonRL
《Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark》(NeurIPS 2021) GitHub:https:// github.com/iamalexkorotin/Wasserstein2Benchmark [fig4]
《Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data》(2021) GitHub:https:// github.com/sberbank-ai/Real-ESRGAN
《FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark》(2021) GitHub:https:// github.com/mlii0117/FFA-IR
《The neural architecture of language: Integrative modeling converges on predictive processing》(2021) GitHub:https:// github.com/mschrimpf/neural-nlp
Now that the weather is a bit better, Dazzler has decided to meet up with a fellow elf as well as Irish wolfhounds Méabh and Saoirse to help show him some more sights that Clare has to offer. #FindDazzler
Mar gheall go bhfuil an aimsir beagáinín níos fearr anois, rinne Dazzler an cinneadh casadh le síogaí agus leis na cúnna faoil Méabh agus Saoirse chun cabhrú leis roinnt radhairc eile i gContae an Chláir a fheiceáil. #CáBhfuilDazzler
Mar gheall go bhfuil an aimsir beagáinín níos fearr anois, rinne Dazzler an cinneadh casadh le síogaí agus leis na cúnna faoil Méabh agus Saoirse chun cabhrú leis roinnt radhairc eile i gContae an Chláir a fheiceáil. #CáBhfuilDazzler
A spot of tea, go on, go on, go on and some very tourist sightseeing is just what Dazzler is looking for but can you tell Jingle and Jangle where to look? #FindDazzler
Taitníonn sé go mór le Dazzler a bheith ag ól tae, ólfaidh tú braon, ólfaidh tú braon, ólfaidh tú braon, ólfaidh tú braon! agus na rudaí deasa do thurasóirí a fheiceáil ach an féidir leat a insint do Jingle agus Jangle cár cheart dóibh cuardach dó? #CáBhfuilDazzler
Taitníonn sé go mór le Dazzler a bheith ag ól tae, ólfaidh tú braon, ólfaidh tú braon, ólfaidh tú braon, ólfaidh tú braon! agus na rudaí deasa do thurasóirí a fheiceáil ach an féidir leat a insint do Jingle agus Jangle cár cheart dóibh cuardach dó? #CáBhfuilDazzler
✋热门推荐