EPS Dashboard

Authors: Haohui Zhang, Zhiye Wang, Xiaoying Gan et al.

Summary

The authors speed up inference in diffusion language models (dLLMs) by identifying tokens that converge early in the denoising process but don't yet meet the usual confidence thresholds. Their LEAP method uses lookahead filtering (checking future denoising steps) and multi-sequence superposition to detect these early-converging tokens and decode them in parallel without waiting for high confidence. This reduces denoising steps by ~30% on average and achieves 7.2 tokens per step on GSM8K while preserving accuracy.

Main takeaways:

Existing dLLM parallelism relies on high-confidence thresholds, which are overly conservative: many tokens converge correctly early but don't reach the threshold.
LEAP detects early-converging tokens by looking ahead at future denoising steps and checking alignment across multiple sequences.
Training-free, plug-and-play method that reduces average denoising steps by ~30% compared to confidence-based decoding.
On GSM8K, combines with dParallel to decode 7.2 tokens per step while preserving model precision.
Breaks the reliance on high-confidence priors, offering a new paradigm for parallel decoding in diffusion language models.

Relevance

Not directly related to my persona/midtraining work — this is about inference-time optimization for diffusion language models, a different architecture from the autoregressive transformers I work with, though the general theme of parallelizing generation has no obvious connection to behavioral installation or persona mechanics.

Threat model

Potential threat/caveat for clean result "Fine-tuning one persona on a two-marker chunk and another on the start marker plants the end marker at every donor answer's end, not chained to the start (LOW confidence)": this item discusses benchmark.

Abstract

arXiv:2605.10980v1 Announce Type: new Abstract: Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the assumption of conditional independence at high confidence levels, which ensures negligible discrepancy between the marginal and joint distributions. However, the stringent confidence thresholds required to preserve accuracy severely constrain the scalability of parallelism. Through systematic token-level statistical analysis, we reveal that a substantial proportion of tokens converge to their correct predictions early in the denoising process yet fail to reach standard confidence thresholds, confirming that current confidence-based criteria are overly conservative. In response, we introduce LEAP (Lookahead Early-Convergence Token Detection for Accelerated Parallel Decoding). LEAP is a training-free, plug-and-play method that leverages future context filtering and multi-sequence superposition to detect early-converging tokens. By validating the alignment between early convergence and correctness, we enable reliable early decoding of these tokens. Benchmarking across diverse domains demonstrates that LEAP significantly lowers inference latency and decoding steps. Compared to confidence-based decoding, the average number of denoising steps is reduced by about 30%. On the GSM8K dataset, combining LEAP with dParallel accelerates decoding to 7.2 tokens per step while preserving model precision. LEAP effectively breaks the reliance on high-confidence priors, offering a novel paradigm for parallel decoding.