{"id":"arxiv:2604.09168","title":"ELT: Elastic Looped Transformers for Visual Generation","date":"2026-04-10","section":"Self-supervised learning and vision","quality":0.057548,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/","source_url":"https://arxiv.org/abs/2604.09168","text_available":true,"authors":["Sahil Goyal","Swayam Agrawal","Gautham Govind Anil","Prateek Jain"],"outgoing":[{"source":"arxiv:2604.09168","target":"arxiv:1807.03819","evidence":"id","id":"arxiv:1807.03819","title":"Universal Transformers","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1d843516d980c3404cb622a2a490edb535a3afe27a85a980335a54b5fcd2220a/"},{"source":"arxiv:2604.09168","target":"arxiv:2205.13147","evidence":"title","id":"arxiv:2205.13147","title":"Matryoshka Representation Learning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/803baa0a8ea7ba1bc63bee0ce80006bf4f403ca0db16ada95dd8198da9a4a899/"},{"source":"arxiv:2604.09168","target":"arxiv:2502.05171","evidence":"id","id":"arxiv:2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/24a6ab865777290627cecebd3f06ea3daef01622f102d32a95f7fb2a5a42880f/"},{"source":"arxiv:2604.09168","target":"arxiv:2507.10524","evidence":"id","id":"arxiv:2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7b25702c35f07446cea97d6a98afc489c8fdda54560c05fbeb1b3b139a9da622/"}],"incoming":[{"source":"arxiv:2605.12466","target":"arxiv:2604.09168","evidence":"id","id":"arxiv:2605.12466","title":"Solve the Loop: Attractor Models for Language and Reasoning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/eb46f81cd5718eb6b9256c583cf9dd2e97b793b4d14337e487c16285f96e2b9a/"}],"text_parts":[{"start":0,"end":15567,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-1.html"},{"start":15567,"end":31388,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-2.html"},{"start":31388,"end":40151,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-3.html"}],"contents":[{"title":"ELT: Elastic Looped Transformers for Visual Generation","offset":32,"level":1,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-1.html#text"},{"title":"Abstract","offset":90,"level":6,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-1.html#text"},{"title":"keywords","offset":1332,"level":6,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-1.html#text"},{"title":"1 Introduction","offset":1349,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-1.html#text"},{"title":"2 Related Work","offset":5857,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-1.html#text"},{"title":"3 Preliminaries","offset":10075,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-1.html#text"},{"title":"4 Method","offset":13755,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-1.html#text"},{"title":"5 Experiments and Results","offset":22896,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-2.html#text"},{"title":"5.1 Experimental Setup","offset":23288,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-2.html#text"},{"title":"5.2 Image Generation","offset":25694,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-2.html#text"},{"title":"5.3 Video Generation","offset":30578,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-2.html#text"},{"title":"5.4 Intra-Loop Self Distillation (ILSD) drives Elasticity","offset":31325,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-2.html#text"},{"title":"6 Conclusion","offset":32307,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-3.html#text"},{"title":"Appendix A Implementation Details","offset":34203,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-3.html#text"},{"title":"Appendix B Additional Experiments","offset":35831,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-3.html#text"},{"title":"Appendix C Limitations","offset":38020,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-3.html#text"},{"title":"Appendix D Acknowledgments","offset":38984,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-3.html#text"},{"title":"Instructions for reporting errors","offset":39187,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/part-3.html#text"}],"text_code_points":40151,"source_markdown":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/63d4e5f1a267b96ed4474fa233f7d3bb2171aae949c0139db37b58b4e45eca47/source.md"}