A team of researchers released ORL on Oct 14, 2026 — a training recipe that makes diffusion language models (which generate many tokens at once, then refine) about 6.9x faster at serving, without…
AspireAI community · arxiv.org
A team of researchers released ORL on Oct 14, 2026 — a training recipe that makes diffusion language models (which generate many tokens at once, then refine) about 6.9x faster at serving, without losing quality.
ORL works by letting a diffusion LM learn from its own residual predictions as it denoises, instead of only from fixed trajectories. The team pairs the recipe with a custom inference engine called dlmrt and ships both on Hugging Face.
On a single H100, the 4B QwenDLM-ORL model decodes at over 5,000 tokens per second; on a consumer RTX 5090, the team reports about 2,800 tokens per second. Code, weights and training data are open.
The trade-off: speed gains depend on a custom runtime — not a drop-in upgrade for existing pipelines.
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.