I-DLM is the first diffusion language model to match AR quality. It achieves 69.6 on AIME-24 and 45.7 on LiveCodeBench-v6, outperforming LLaDA-2.1-mini (16B) with 2.9-4.1x higher throughput.

Hacker News is a community-driven platform for sharing and discussing technology news, startups, and programming-related topics. Through user submissions and comments, Hacker News offers insights into emerging technology trends, industry developments, and entrepreneurial ventures. Readers can participate in discussions, share their insights, and stay informed about the latest advancements in technology and innovation.

Hacker News

I-DLM (Introspective Diffusion Language Model) is a new approach to diffusion-based language models that closes the quality gap with autoregressive (AR) models. The core insight is that existing DLMs lack 'introspective consistency' — they generate tokens without verifying them as AR models implicitly do. I-DLM introduces Introspective Strided Decoding (ISD), which generates new tokens and verifies prior ones in a single forward pass using a p/q acceptance criterion. The 8B model is claimed to be the first DLM to match same-scale AR quality, outperforming LLaDA-2.1-mini (16B) by +26 on AIME-24 and +15 on LiveCodeBench-v6 while delivering 2.9–4.1x throughput at high concurrency. A lossless variant (R-ISD) using gated LoRA guarantees bit-for-bit identical output to the base AR model. The model integrates directly into SGLang with no custom infrastructure, and code, models, and benchmarks are publicly available.

I-DLM: Introspective Diffusion Language Models