Search: diffusion models

More than 1,000 papers match: here are the 1,000 most recent, ranked by relevance.

• Forward-Free Diffusion Language Models

  Haotian Sun, Rushi Qiang, Yuqian Zheng, Bo Dai · 9 June 2026 · Large Language Models

  Diffusion language models generate text through iterative denoising, offering a powerful alternative to autoregressive generation. However, discrete language spaces lack a natural neighborhood structure for defining effective perturbations, so some artificial corruption schemes are proposed in the f…

• The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

  Zanlin Ni, Shenzhi Wang, Yang Yue, Tianyu Yu, Weilin Zhao, Yeguo Hua, Tianyi Chen, Jun Song, Cheng Yu, Bo Zheng, Gao Huang · 9 June 2026 · Large Language Models

  Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility implies a solution space that strictly supersets the fixed autoregressive trajectory, theoretically unlocking superior re…

• Unified Energy for Invariant and Independent Decoding in Diffusion Language Models

  Yuchen Yan, Minkai Xu, Zaiquan Yang, Yatao Bian · 9 June 2026 · Speech Recognition and Synthesis

  Diffusion Language Models (DLMs) enable parallel text generation by iteratively denoising a full sequence, offering attractive flexibility compared to auto-regressive (AR) decoding. However, existing methods fail to fully capture token relationships, leading to a performance gap relative to AR basel…

• Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks

  Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun, Farshad Khorrami · 9 June 2026 · Reinforcement Learning in Robotics

  Visual world models have shown great potential in learning complex system dynamics. Recent advancements leverage these models as transition functions within Model Predictive Control (MPC) frameworks to solve various control tasks. When applied to robotics, however, they are limited to single-stage t…

• TimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering

  Ryandito Diandaru, Ikhlasul Akmal Hanif, Fadli Aulawi Al Ghiffari, Ahmed Elshabrawy, Alham Fikri Aji · 9 June 2026 · Large Language Models

  We extend activation steering to diffusion language models (DLMs) and study a novel problem that arose due to the inference mechanism of DLMs: Modifying a text in-place to manifest a different concept. We propose TimpaTeks, an automatic in-place text modification mechanism using DLMs. Experiments on…

• Enabling KV Caching of Shared Prefix for Diffusion Language Models

  Younghun Go, Jaehoon Han, Changyong Shin, Chuk Yoo, Gyeongsik Yang · 9 June 2026 · Large Language Models

  Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM) serving, but it faces critical challenges in emerging diffusion language models (DLMs). In DLMs, bidirectional attention means that updating any token dynamically alters the entire context and its …

• Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

  Xingyu Su, Jacob Helwig, Shubham Parashar, Atharv Chagi, Lakshmi Jotsna, Degui Zhi, James Caverlee, Dileep Kalathil, Shuiwang Ji · 8 June 2026 · Large Language Models

  We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs). Rather than pretraining from scratch, prior work replaces the causal attention in ARLMs with bidirectional attention and then trains the resulting model using a DLM objective. However, these approache…

• NAVIRA: Decoupled Stochastic Remasking for Masked Diffusion Language Models

  Andrey Fomenko, Maksim Kryzhanovskiy, Svetlana Glazyrina, Roman Ischenko · 5 June 2026 · Language and cultural evolution

  Masked diffusion language models generate text by iteratively unmasking many tokens in parallel, but this speed comes with a correction problem: tokens generated in the same step are predicted from marginal distributions, and early local dependency errors can later contaminate the context. PRISM add…

• Self-Augmenting Retrieval for Diffusion Language Models

  Paul J\"unger, Justin Lovelace, Linxi Zhao, Dongyoung Go, Kilian Q. Weinberger · 5 June 2026 · Large Language Models

  Discrete diffusion language models generate text by iteratively denoising an entire response in parallel. At each step, they predict tentative tokens for every masked position, committing the confident predictions to the output and discarding the unconfident ones. We show that the discarded tokens a…

• Adapting Diffusion Language Models for Lossless Pixel-Level Image Transmission

  Tianqi Ren, Rongpeng Li, Xianfu Chen, Yingyu Li, Zhifeng Zhao · 5 June 2026 · Advanced Data Compression Techniques

  Lossless pixel-level image transmission is a fundamental regime beyond semantic communications, because exact recovery requires both accurate symbol probability modeling and reliable delivery over noisy channels. This paper proposes DDM-SSCC, a discrete-diffusion-model-based separate source-channel …

• Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models

  Anant Khandelwal, Manish Gupta · 4 June 2026 · Large Language Models

  Diffusion large language models (dLLMs) generate responses by iteratively unmasking and revising many positions in parallel. This process leaves a rich denoising trace depicting which tokens become confident, which remain unstable, and when commitments form. Existing dLLM reinforcement learning meth…

• Global Sketch-Based Watermarking for Diffusion Language Models

  Daniel Zhao · 4 June 2026 · Speech Recognition and Synthesis

  Watermarking methods for language models have been studied extensively in the autoregressive setting, where tokens are generated sequentially. These works largely focus on local-context schemes that perturb the next token's distribution as a function of its preceding tokens. In diffusion language mo…

• D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

  Liyuan Zhang, Jiarui Zhang, Jinwei Yao, Ran Yan, Yuchen Yang, Jiahao Zhang, Tongkai Yang, Yi Wu, Binhang Yuan · 4 June 2026 · Large Language Models

  Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward pass. Recent diffusion-based drafters generate an entire block of tokens in parallel but usually commit to a single draft sequence per verifi…

• Supportive Token Revealing for Fast Diffusion Language Model Decoding

  Giries Abu Ayoub, Mario Barbara, Llu\'is Pastor-P\'erez, Tanja Bien, Aneesh Barthakur, Alaa Maalouf, Loay Mualem · 4 June 2026 · Large Language Models

  Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off. Aggressive decoding may commit mutually dependent tokens too early, while conservative decoding requires many denoising ste…

• Knowledge Editing in Masked Diffusion Language Models

  Haewon Park, Yohan Jo · 3 June 2026 · Large Language Models

  Knowledge editing aims to update or correct factual knowledge in a language model. A widely used approach, locate-then-edit, does this in two steps: it first localizes a fact within the model, then edits the weights there. To date, such methods have been developed exclusively on autoregressive model…

• An Attention-Based Denoising Model for Diffusion Weighted Imaging

  Prithviraj Verma, Pawan Kumar, Chandan Deshani, Prasun Chandra Tripathi · 3 June 2026 · Advanced Neuroimaging Techniques and Applications

  Diffusion-weighted imaging (DWI) is used for whole-body cancer screening, but it typically requires a long acquisition time. When the scan time is reduced, the image quality often suffers, leading to increased noise in the scans. Magnitude reconstruction in DWI introduces signal-dependent Rician noi…

• Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method

  Yan Zeng, Masanori Suganuma, Takayuki Okatani · 3 June 2026 · Generative Adversarial Networks and Image Synthesis

  This paper studies the problem of inverting the DDIM image generation process to recover latent variables, particularly the initial noise map, from a generated image. Existing methods often struggle with accuracy in this task. We propose a novel hybrid approach that combines direct inversion via gra…

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

  Longxuan Yu, Shaorong Zhang, Yu Fu, Hui Liu, Yue Dong, Greg Ver Steeg · 2 June 2026 · Large Language Models

  Masked diffusion language models (MDLMs) re-predict every position at each denoising step, but standard samplers commit tokens once revealed, leaving this revision capability unused. Existing approaches either add heuristic or learned mechanisms to revise committed tokens, or remask them back to [MA…

• Reconsidering Positional Supervision in Masked Diffusion Language Model Training

  Mengyu Ye, Keito Kudo, Ryosuke Takahashi, Jun Suzuki · 2 June 2026 · Language and cultural evolution

  Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive language models. They can be viewed as parallel decoders trained with a position-wise cross-entropy (CE) loss, the same setup as non-autoregressive trans…

• d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation

  Guanghan Wang, Gilad Turok, Yair Schiff, Marianne Arriola, Volodymyr Kuleshov · 2 June 2026 · Natural Language Processing Techniques

  While diffusion language models (DLMs) have achieved competitive performance in text generation, improving their reasoning ability with reinforcement learning remains an active research area. Here, we introduce d2, a reasoning framework tailored for masked DLMs. Central to our framework is a new pol…

• Error Bounds for a Diffusion Model-Based Drift Estimator

  Ioar Casado-Telletxea, Omar Rivasplata · 2 June 2026 · Stochastic processes and financial applications

  Parameter estimation in stochastic differential equations is a classical statistical problem of much importance in many scientific fields. Recent work of Tapia Costa et al. (2026) introduced a novel technique for estimating the drift when the diffusion parameter is known, using discrete samples from…

• SimSD: Simple Speculative Decoding in Diffusion Language Models

  Junxia Cui, Haotian Ye, Runchu Tian, Hongcan Guo, Jinya Jiang, Haoru Li, Chaojie Ren, Yiming Huang, Kaijie Zhu, Zhongkai Yu, Kun Zhou, Jingbo Shang · 2 June 2026 · Large Language Models

  Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding. However, their masked language modeling formulation remains incompatible with standard token-level speculative decod…

• EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models

  Hyundong Jin, Yo-Sub Han · 2 June 2026 · Natural Language Processing Techniques

  Controlling language model outputs is essential for ensuring structural validity, reliability, and downstream usability, and diffusion language models are no exception. Recent advances in diffusion language model decoding have extended output control beyond regular constraints to context-free gramma…

• DLLM-JEPA: Joint Embedding Predictive Architectures for Masked Diffusion Language Models

  Sangdae Nam · 2 June 2026 · Domain Adaptation and Few-Shot Learning

  Joint Embedding Predictive Architectures (JEPAs) have reshaped self-supervised representation learning in vision. The recent LLM-JEPA ported JEPA to autoregressive language models but inherited two steep costs from the causal-attention substrate: it demands explicit multi-view data (e.g., text-code …

• Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models

  Heqiang Qi, Wei Huang, Mingyuan Bai, Xiangming Meng · 29 May 2026 · Natural Language Processing Techniques

  Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level granularity. We revisit this granularity and observe that reliable predictions ofte…