ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2605.28456· 16 results

cs.CLcs.AIRecentMay 31, 2026

DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs

Longxuan Yu, Yunshu Wu, Yu Fu, Siheng Xiong +4 more

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…

View →
cs.CLcs.AIRecentJun 1, 2026

SimSD: Simple Speculative Decoding in Diffusion Language Models

Junxia Cui, Haotian Ye, Runchu Tian, Hongcan Guo +8 more

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…

View →
cs.LGcs.AIRecentMay 28, 2026

BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference

Xiaoyou Wu, Cheng-Jhih Shih, Binfei Ji, Yong Liu +1 more

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…

View →
cs.CLRecentMay 29, 2026

Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation

Zekai Li, Ji Liu, Yiqing Huang, Ziqiong Liu +2 more

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…

View →
cs.AIRecentMay 28, 2026

NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs

Shuaidi Wang, Zhan Zhuang, Ruping Huang, Yu Zhang

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

View →
cs.CLRecentMay 29, 2026

dMoE: dLLMs with Learnable Block Experts

Sicheng Feng, Zigeng Chen, Gongfan Fang, Xinyin Ma +1 more

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…

View →
cs.LGcs.AIRecentJun 1, 2026

FLARE: Diffusion for Hybrid Language Model

Yuchen Zhu, Jing Shi, Chongjian Ge, Hao Tan +8 more

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…

View →
cs.CLcs.AIRecentMay 28, 2026

DLM-SWAI: Steering Diffusion Language Models Before They Unmask

Hyeseon An, Yo-Sub Han

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…

View →
cs.CLRecentMay 31, 2026

Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models

Longxuan Yu, Shaorong Zhang, Yu Fu, Hui Liu +2 more

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…

View →
cs.CLcs.AIRecentMay 30, 2026

MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models

Ravil Mussabayev, Rustam Mussabayev

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…

View →
cs.CLcs.AIeess.ASRecentMay 31, 2026

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects

Sicheng Yang, Shulan Ruan, Shiwei Wu, Yu Liu +3 more

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…

View →
cs.CLRecentMay 31, 2026

Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreading

Lin Yao

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…

View →
cs.CLcs.AIRecentMay 29, 2026

What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation

Qing Wang, Jacob Devasier, Chengkai Li

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…

View →
cs.LGcs.CRRecentMay 19, 2026

Backdooring Masked Diffusion Language Models

Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou, Chengyu Huang +2 more

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.

View →
cs.AIcs.CLRecentMay 27, 2026

The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models

Dueun Kim, Albert No

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…

View →
cs.CVcs.AIRecentMay 28, 2026

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral, Adil Kaan Akan +3 more

VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput f…

View →