AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge

Juntong Shi, Brian L. Trippe, Jure Leskovec, Stefano Ermon, Minkai Xu

ICML 2026 · Large language models › Language, safety and interpretability · approach: Parallel and early-exit decoding · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add importance sampling over K=4 candidates (ablation)PoE-Bridge · GSM8Kaccuracy: 95.20 -> 95.30Improved
add importance sampling over K=4 candidates (ablation)PoE-Bridge · MATHaccuracy: 73.86 -> 74.42Improved
add importance sampling over K=4 candidates (ablation)PoE-Bridge · HumanEvalaccuracy: 80.69 -> 79.47Hurt
add importance sampling over K=4 candidates (ablation)PoE-Bridge · MBPPaccuracy: 72.20 -> 73.20Improved
add importance sampling over K=4 candidates (ablation)PoE-Bridge · MATHthroughput (tokens/s): 99.49 -> 94.94Hurt
replace direct DLM-to-AR speculative decoding (w=0.0) with PoE bridge w=0.3 (ablation)PoE-Bridge · HumanEval (K=1)throughput (tokens/s): 56.55 -> 84.82Improved
replace direct DLM-to-AR speculative decoding (w=0.0) with PoE bridge w=0.3 (ablation)PoE-Bridge · HumanEval (K=1)% all-reject steps: 17.15 -> 4.53Improved
raise PoE weight w from 0.3 to 0.9 (ablation)PoE-Bridge · HumanEval (K=1)accuracy: 80.69 -> 30.49Hurt
raise PoE weight w from 0.3 to 0.9 (ablation)PoE-Bridge · HumanEval (K=1)throughput (tokens/s): 84.82 -> 168.35Improved
use Elastic Rejection Window V=32 instead of disabled (V=inf), K=4 (ablation)PoE-Bridge · MATHthroughput (tokens/s): 39.46 -> 94.94Improved
use Elastic Rejection Window V=32 instead of V=8, K=1 (ablation)PoE-Bridge · MATHthroughput (tokens/s): 66.22 -> 99.49Improved
use mixed-temperature candidates instead of uniform temperature with increasing K (ablation)PoE-Bridge · MATH and MBPPaccuracy: at least one-third of the remaining gap closedImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy