Librarian Bot. I found the following papers similar to this paper.

\n

The following papers were recommended by the Semantic Scholar API

\n

\n
• Visual Generation Without Guidance (2025)
\n
• Beyond and Free from Diffusion: Invertible Guided Consistency Training (2025)
\n
• PQD: Post-training Quantization for Efficient Diffusion Models (2024)
\n
• History-Guided Video Diffusion (2025)
\n
• Weak Supervision Dynamic KL-Weighted Diffusion Models Guided by Large Language Models (2025)
\n
• Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening (2025)
\n
• Robust Representation Consistency Model via Contrastive Denoising (2025)
\n

\n

Please give a thumbs up to this comment if you found it helpful!

\n

If you want recommendations for any Paper on Hugging Face checkout this Space

\n

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-02-20T01:37:01.226Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7036259770393372},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2502.12154","authors":[{"_id":"67b400719ff3ff79dae14701","user":{"_id":"6372f265112fb535baf254c4","avatarUrl":"/avatars/9b821bc533175c7dded48cdb3a3e1a12.svg","isPro":false,"fullname":"tzco","user":"tzco","type":"user"},"name":"Zhicong Tang","status":"claimed_verified","statusLastChangedAt":"2025-02-18T09:31:45.361Z","hidden":false},{"_id":"67b400719ff3ff79dae14702","name":"Jianmin Bao","hidden":false},{"_id":"67b400719ff3ff79dae14703","name":"Dong Chen","hidden":false},{"_id":"67b400719ff3ff79dae14704","name":"Baining Guo","hidden":false}],"publishedAt":"2025-02-17T18:59:50.000Z","submittedOnDailyAt":"2025-02-18T21:28:34.838Z","title":"Diffusion Models without Classifier-free Guidance","submittedOnDailyBy":{"_id":"6372f265112fb535baf254c4","avatarUrl":"/avatars/9b821bc533175c7dded48cdb3a3e1a12.svg","isPro":false,"fullname":"tzco","user":"tzco","type":"user"},"summary":"This paper presents Model-guidance (MG), a novel objective for training\ndiffusion model that addresses and removes of the commonly used Classifier-free\nguidance (CFG). Our innovative approach transcends the standard modeling of\nsolely data distribution to incorporating the posterior probability of\nconditions. The proposed technique originates from the idea of CFG and is easy\nyet effective, making it a plug-and-play module for existing models. Our method\nsignificantly accelerates the training process, doubles the inference speed,\nand achieve exceptional quality that parallel and even surpass concurrent\ndiffusion models with CFG. Extensive experiments demonstrate the effectiveness,\nefficiency, scalability on different models and datasets. Finally, we establish\nstate-of-the-art performance on ImageNet 256 benchmarks with an FID of 1.34.\nOur code is available at https://github.com/tzco/Diffusion-wo-CFG.","upvotes":8,"discussionId":"67b400789ff3ff79dae147ee","githubRepo":"https://github.com/tzco/Diffusion-wo-CFG","githubRepoAddedBy":"auto","ai_summary":"Model-guidance improves diffusion model training by incorporating posterior probabilities, removing the need for Classifier-free guidance, and achieving faster inference and superior quality.","ai_keywords":["diffusion model","Classifier-free guidance","posterior probability","Model-guidance","ImageNet 256","FID"],"githubStars":171},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6351e5bb3734c6e8a5c1bec1","avatarUrl":"/avatars/a784a51b369b197398575c3afbd5ceab.svg","isPro":false,"fullname":"Han-Bit Kang","user":"hbkang","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"650c8bfb3d3542884da1a845","avatarUrl":"/avatars/863a5deebf2ac6d4faedc4dd368e0561.svg","isPro":false,"fullname":"Adhurim ","user":"Limi07","type":"user"},{"_id":"64f955c582673b2a07fbf0ad","avatarUrl":"/avatars/1c98c8be61f6580c1e4ee698fa5c0716.svg","isPro":false,"fullname":"hongyu","user":"learn12138","type":"user"},{"_id":"6342796a0875f2c99cfd313b","avatarUrl":"/avatars/98575092404c4197b20c929a6499a015.svg","isPro":false,"fullname":"Yuseung \"Phillip\" Lee","user":"phillipinseoul","type":"user"},{"_id":"6357e711df75af4a1a5e4c43","avatarUrl":"/avatars/a7a57125d90e9c214146b58e5a22c168.svg","isPro":false,"fullname":"Rho","user":"Kyeongha","type":"user"},{"_id":"66a422c559a6a2ef45e7845e","avatarUrl":"/avatars/e4a9402bb181c37399f6645ddf9aaeae.svg","isPro":false,"fullname":"Yu li","user":"Yukkkop","type":"user"},{"_id":"64226df9eaad1bcb28b4be92","avatarUrl":"/avatars/b2194d958208dc8fcfcddee479ded1fd.svg","isPro":false,"fullname":"Chuong Nguyen","user":"Chuong98vt","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">