←Back to NewsAI News/ImagepaperImageReasoningSenseTime's Looped-DiT Beats a 1.7B Model Using Just 260M ParametersA 260M-parameter text-to-image model beats one 6.5x larger by running the same transformer blocks multiple times per denoising step.SourceAlphaSignalPublishedSep 30, 2026, 5:52 PMAuthorAlphaSignal NewsroomRead1 min readA 260M-parameter text-to-image model beats one 6.5x larger by running the same transformer blocks multiple times per denoising step.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsAlphaSignal · modelMitsuba Squeezes a 27B Vision Model Into 7.3 GB for ComfyUIGoogle AI · newsGoogle's Gemini 4 Argon Pushes AI Agent Output to One Million TokensGoogle DeepMind · newsGoogle DeepMind's Gemini 4 Argon Shatters Output Limits With 1 Million Tokens
