The paper introduces DSL-LLaDA, a method that lightly adapts a pre-trained masked diffusion language model to perform continuous denoising in embedding space, significantly improving text generation q…

The paper introduces SARDI, a novel, training-free framework that uses low-confidence 'lookahead' tokens generated during the denoising process of discrete diffusion language models to dynamically gui…

The paper proposes SimSD, a plug-and-play speculative decoding algorithm that adapts diffusion language models (dLLMs) to achieve fast, token-level acceleration by restoring causal masking capabilitie…

The paper introduces SHADOWMASK, the first systematic backdoor attack targeting Masked Diffusion Language Models (MDLMs), demonstrating near-100% attack success while preserving clean model utility.

The paper introduces DLM-SWAI, a training-free method that effectively steers diffusion language models (DLMs) toward desired textual styles or properties by biasing the token distribution at each den…

The paper proposes a novel global sketch-based watermarking technique for diffusion language models that controls the entire sequence's statistics, offering an order-agnostic and context-independent a…

WaveFilter is a novel, training-free framework that uses wavelet transforms to efficiently filter critical tokens in the KV cache, significantly improving the long-context performance of Diffusion LLM…

TAPS introduces a target-aware prefix selection method that optimizes the trade-off between draft tree acceptance and verification cost, achieving significant speedups in speculative decoding.

This paper analyzes the decoding process of masked diffusion models for graph-to-text generation, finding that structural fine-tuning disrupts natural entity-first generation and proposing a structura…

Divergence Decoding (DD) is a novel, effective, and inexpensive method that uses auxiliary models to steer LLM logits during inference, enabling the removal of memorized sensitive data without signifi…

The paper introduces D3IM, a novel parameter-free sampler that enables direct revision of visible tokens in Masked Diffusion Language Models, and proposes SCOPE to mitigate the model's tendency to per…

The paper introduces a novel, transferable learned attack (LT-MIA) that detects a universal 'signature of memorization' in language models, achieving high accuracy across diverse model architectures (…

The paper proposes a novel trace-aware decoding framework, combining Temporal-Spatial Parallel Decoding (TSPD) and Confidence Extrapolation (CE), to significantly accelerate the inference of diffusion…

Weak self-training on synthetic data can amplify a language model's existing capabilities, but this effect is strictly dependent on the compatibility between the source and student models, not on the…

The paper analyzes order-agnostic language models (OALMs), finding that their learned conditionals are not true factorizations and proposing a variance-based diagnostic to compare the quality of diffe…

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achiev…

MaskForge is a novel, adaptive, black-box attack framework that significantly improves jailbreaking diffusion large language models (dLLMs) by treating red-teaming as an optimized search over reusable…

The paper introduces BadDLM, a unified framework that demonstrates a new class of backdoor vulnerabilities in Diffusion Language Models (DLMs) by exploiting their forward masking process across divers…

The paper proposes EPIC, an efficient and parallel decoding framework that significantly speeds up the process of constraining diffusion language model outputs using Context-Free Grammars (CFG).