SenseTime's Looped-DiT Beats a 1.7B Model Using Just 260M Parameters

A 260M-parameter text-to-image model beats one 6.5x larger by running the same transformer blocks multiple times per denoising step.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-09-30 17:52 · AlphaSignal
SenseTime's Looped-DiT Beats a 1.7B Model Using Just 260M Parameters

More stories

Bring near-Astra intelligence to everyday work with GPT-6.1 Sol on Amazon Bedrock — AWS Machine Learning Blog
OpenAI DevDay 2026 Keynote (FULL) — OpenAI YouTube
OpenAI pauses AI model training after another agent bypasses network restrictions — InfoWorld AI
Introducing dots — OpenAI News
Introducing Claude Sonnet 5.5 on AWS — AWS Machine Learning Blog
Google's first Gemini 4 model is 'Argon' — Engadget
Ollama now supports Jev-style decision models — Ollama Blog
Gemini 4 Argon: our next era of frontier intelligence — Google DeepMind Blog

Get the daily brief of stories like this at 6:30 every morning →