{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/reconstruction-vs-generation-taming-1","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","arxiv_id":"2501.01423","date":"2025-01-02","proceeding":"CVPR 2025 1","authors":["Jingfeng Yao","Xinggang Wang"],"abstract":"Latent diffusion models with Transformer architectures excel at generating high-fidelity images. However, recent studies reveal an optimization dilemma in this two-stage design: while increasing the per-token feature dimension in visual tokenizers improves reconstruction quality, it requires substantially larger diffusion models and more training iterations to achieve comparable generation performance. Consequently, existing systems often settle for sub-optimal solutions, either producing visual artifacts due to information loss within tokenizers or failing to converge fully due to expensive computation costs. We argue that this dilemma stems from the inherent difficulty in learning unconstrained high-dimensional latent spaces. To address this, we propose aligning the latent space with pre-trained vision foundation models when training the visual tokenizers. Our proposed VA-VAE (Vision foundation model Aligned Variational AutoEncoder) significantly expands the reconstruction-generation frontier of latent diffusion models, enabling faster convergence of Diffusion Transformers (DiT) in high-dimensional latent spaces. To exploit the full potential of VA-VAE, we build an enhanced DiT baseline with improved training strategies and architecture designs, termed LightningDiT. The integrated system achieves state-of-the-art (SOTA) performance on ImageNet 256x256 generation with an FID score of 1.35 while demonstrating remarkable training efficiency by reaching an FID score of 2.11 in just 64 epochs--representing an over 21 times convergence speedup compared to the original DiT. Models and codes are available at: https://github.com/hustvl/LightningDiT.","url_abs":"https://arxiv.org/abs/2501.01423v2","url_pdf":"https://arxiv.org/pdf/2501.01423v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"reconstruction-vs-generation-taming-1","repo_url":"https://github.com/hustvl/LightningDiT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reconstruction-vs-generation-taming-1","repo_url":"https://github.com/westlake-repl/leanvae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"LightningDiT + VA-VAE (with the guidance interval)","rank_in_archive_order":14,"of":94,"metrics":{"FID":"1.35"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.01423","atlas_url":"https://app.syntology.ai/?focus=2501.01423","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2501.01423"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2501.01423\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2501.01423"},"call":"get_concepts_for_paper(arxiv_id=\"2501.01423\")"}],"by_repo":[{"repo":"hustvl/LightningDiT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.10356"],"harvested_for_calls":[{"arxiv_id":"2410.10356","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.10356"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.10356\")"}]},{"repo":"westlake-repl/leanvae","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2503.14325"],"harvested_for_calls":[{"arxiv_id":"2503.14325","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.14325"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.14325\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"59acd9bae5a55d3faf337efc9ff6e6423c2b3cba31ad2077e1bd5cc25fb18baa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}