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 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…

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

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 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…

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 'infilling extraction' to accurately model training data memorization in Diffusion Language Models (DLMs), finding that bidirectional masking significantly increases the extractab…

BlockBatch introduces a novel framework that efficiently accelerates diffusion language model (dLLM) inference by simultaneously executing multiple block-size branches for a single request, achieving…

The paper proposes DLLM-VSR, a novel Diffusion Large Language Model framework for Visual Speech Recognition, achieving state-of-the-art performance by treating transcription as iterative masked denois…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

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…

The paper argues that using confidence-based decoding, which is optimized via training mask alignment, fundamentally misaligns Masked Diffusion Models (MDMs) from the logical flow needed for complex r…

The paper proposes MaskDiff-AD, a forward-only masked diffusion model trained on nominal data to achieve state-of-the-art anomaly detection across various categorical, mixed-type, and text datasets.

dMoE proposes a block-level Mixture-of-Experts (MoE) framework for Diffusion Large Language Models (dLLMs) that aggregates token-level expert distributions into a unified block-level distribution, sig…

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…

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…

This paper introduces GraphSteal, an attack framework demonstrating that Graph RAG systems can leak substantial portions of a hidden knowledge graph by treating them as structural oracles.