A team from SenseTime, Tsinghua and NTU released "Looped Diffusion Transformer" on September 30 — a text-to-image model that beats a baseline 6.5x its size by running the same transformer block…
AspireAI community · arxiv.org
A team from SenseTime, Tsinghua and NTU released "Looped Diffusion Transformer" on September 30 — a text-to-image model that beats a baseline 6.5x its size by running the same transformer block several times per denoising step.
Their 260-million-parameter Looped-DiT averaged 71.5 across six text-to-image benchmarks, ahead of InternVL-U's 69.0 at 1.7B parameters, and used 4.9x less compute per image (150 vs 732 TFLOPs). Code is open at github.com/OpenSenseNova/Looped-DiT.
Think of it as a short putt you can read again before stroking: same club, more careful looks. The trick is two training fixes (deep supervision every loop and a self-modulating attention block) that stop naive looping from drifting.
The honest caveat: the paper measures TFLOPs, not wall-clock latency, so "4.9x faster" is a compute claim, not a speed one. Independent replication is still pending.
Read the story and explore more from the AspireAI community.
Two critical PHP remote code execution flaws — one found by GPT-5.6 Sol — were patched on October 21, 2026, and OpenAI published a disclosure framework alongside the fix. Fixed versions: PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35. Both allow unauthenticated remote code execution, and PHP's advisory says risk is highest for mod_php, where a demonstrated exploit triggers before any application code runs. The CVEs are distinct failure modes. CVE-2026-109618 (OOM corruption): out-of-memory handling can interrupt PHP while internal request data is only partially initialized, and request cleanup may then treat the invalid data as valid. CVE-2026-109619 (stale global state): request-owned internal state can survive after its backing memory is freed, and a later request served by the same worker may use that stale state. OpenAI states GPT-5.6 Sol identified the first flaw through its Patch the Planet initiative, and that Wiz independently discovered and reported both vulnerabilities. PHP's maintainers led the fixes and release, with Wiz, Cloudflare and OpenAI contributing research and coordination. Wiz's write-up adds that it used GPT-5.6 Sol and Gemini 4 Argon throughout, with Gemini 4 Argon contributing to finding the vulnerability and validating the patch. OpenAI describes the gap between discovery and public exploitation as a "Defender's Window," proposes a five-stage response framework, and committed $1 billion in subsidised Daybreak model access for organizations with limited security resources. Honest caveats: these are OpenAI's and Wiz's own characterizations, and OpenAI also notes the same capabilities help attackers build offensive tooling faster. PHP 8.1 and older no longer receive updates from the PHP project.