Search: diffusion models

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

• When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models

  Danny Wang, Ruihong Qiu, Zi Huang · 28 April 2026 · Large Language Models

  Discrete diffusion language models (dLLMs) enable parallel token updates with bidirectional attention, yet practical generation typically adopts blockwise semi-autoregressive decoding. This switch creates a training-inference mismatch: training denoises with full-sequence context, while inference co…

• BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models

  Liming Liu, Binxuan Huang, Zixuan Zhang, Xin Liu, Bing Yin, Tuo Zhao · 24 April 2026 · Large Language Models

  Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation quality. We propose BackPlay, a frozen-backbone self-correction framework that trains only a lightweight correction head…

• On the Quantization Robustness of Diffusion Language Models in Coding Benchmarks

  Aarav Gupta, Gururaj Deshpande, Chandreyi Chakraborty · 23 April 2026 · Speech Recognition and Synthesis

  Auto-regressive Large Language Models (LLMs) achieve strong performance on coding tasks, but incur high memory and inference costs. Diffusion-based language models (d-LLMs) offer bounded inference cost via iterative denoising, but their behavior under post-training quantization (PTQ) has been sparse…

• LogicDiff: Logic-Guided Denoising Improves Zero-Shot Reasoning in Masked Diffusion Language Models

  Shaik Aman · 21 April 2026 · Large Language Models

  Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens from a fully masked sequence. Their standard confidence-based unmasking strategy systematically defers high-entropy logical connective tokens, degrading reasoning performance. We introduce LogicDiff, an inference-…

• Stability-Weighted Decoding for Diffusion Language Models

  Yue Wu, Jian Huang · 21 April 2026 · Large Language Models

  Diffusion large language models (dLLMs) enable parallel text generation by iteratively denoising a fully masked sequence, unmasking a subset of masked tokens at each step. Existing decoding strategies rely on static confidence metrics computed at a single denoising step, ignoring temporal history an…

• When Earth Foundation Models Meet Diffusion: An Application to Land Surface Temperature Super-Resolution

  Yiheng Chen, Zihui Ma, Peishi Jiang, Yilong Dai, Qikai Hu, Xinyue Ye, Lingyao Li, Rita Sousa, Runlong Yu · 21 April 2026 · Urban Heat Island Mitigation

  Land surface temperature (LST) super-resolution is important for environmental monitoring. However, it remains challenging as coarse thermal observations severely underdetermine fine-scale structure. In this paper, we propose Earth Foundation Model-guided Diffusion (EFDiff), a novel framework for su…

• Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

  Jiaoyang Ruan, Xin Gao, Yinda Chen, Hengyu Zeng, Liang Du, Guanghao Li, Jie Fu, Jian Pu · 21 April 2026 · AI-based Problem Solving and Planning

  While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces remains a critical challenge. In this work, we propose a geometric perspective: Reasoning on the Manifold. We hypothesiz…

• Elucidating the SNR-t Bias of Diffusion Probabilistic Models

  Meng Yu, Lei Sun, Jianhao Zeng, Xiangxiang Chu, Kun Zhan · 20 April 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion Probabilistic Models have demonstrated remarkable performance across a wide range of generative tasks. However, we have observed that these models often suffer from a Signal-to-Noise Ratio-timestep (SNR-t) bias. This bias refers to the misalignment between the SNR of the denoising sample a…

• Mitigating Barren Plateaus in Quantum Denoising Diffusion Probabilistic Model

  Haipeng Cao, Kaining Zhang, Dacheng Tao, Zhaofeng Su · 16 April 2026 · Quantum Computing Algorithms and Architecture

  Quantum generative models exploit quantum superposition and entanglement to enhance learning efficiency for both classical and quantum data. Recently, inspired by classical diffusion frameworks, the quantum denoising diffusion probabilistic model (QuDDPM) has emerged as a powerful tool for learning …

• Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models

  Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen, Xiaoge Zhang, Tianyi Li, Kaiyu Tang, Xiao Li, Jing Li · 16 April 2026 · Large Language Models

  Diffusion language models (DLMs) have emerged as a promising paradigm for large language models (LLMs), yet the non-deterministic behavior of DLMs remains poorly understood. The existing non-determinism evaluations for LLMs predominantly rely on dataset-level metrics under fixed inference configurat…

• Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics

  Angelo Moroncelli, Matteo Rufolo, Gunes Cagin Aydin, Asad Ali Shahid, Loris Roveda · 16 April 2026 · Model Reduction and Neural Networks

  Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem and compare deterministic and generative sequence models fo…

• SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

  Chenyu Wang, Paria Rashidinejad, DiJia Su, Song Jiang, Sid Wang, Siyan Zhao, Cai Zhou, Shannon Zejiang Shen, Feiyu Chen, Tommi Jaakkola, Yuandong Tian, Bo Liu · 16 April 2026 · Machine Learning in Healthcare

  Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, aligning dLLMs with human preferences or task-specific rewards via reinforcement learning (RL) is challenging because their i…

• Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model

  Yihong Dong, Zhaoyu Ma, Xue Jiang, Zhiyuan Fan, Jiaru Qian, Yongmin Li, Jianha Xiao, Zhi Jin, Rongyu Cao, Binhua Li, Fei Huang, Yongbin Li, Ge Li · 16 April 2026 · Large Language Models

  Diffusion language models (DLMs) are emerging as a powerful and promising alternative to the dominant autoregressive paradigm, offering inherent advantages in parallel generation and bidirectional context modeling. However, the performance of DLMs on code generation tasks, which have stronger struct…

• Diffusion Language Models for Speech Recognition

  Davyd Naveriani, Albert Zeyer, Ralf Schl\"uter, Hermann Ney · 16 April 2026 · Speech Recognition and Synthesis

  Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation. In this work, we explore variants for their use in speech recognition. Specifically, we introduce a comprehensive guide…

• Surrogate models for diffusion on graphs via sparse polynomials

  Giuseppe Alessio D'Inverno, Kylian Ajavon, Simone Brugiapaglia · 15 April 2026 · Advanced Mathematical Modeling in Engineering

  Diffusion kernels over graphs have been widely utilized as effective tools in various applications due to their ability to accurately model the flow of information through nodes and edges. However, there is a notable gap in the literature regarding the development of surrogate models for diffusion p…

• LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models

  Haocheng Xi, Harman Singh, Yuezhou Hu, Coleman Hooper, Rishabh Tiwari, Aditya Tomar, Minjae Lee, Wonjun Kang, Michael Mahoney, Chenfeng Xu, Kurt Keutzer, Amir Gholami · 15 April 2026 · Generative Adversarial Networks and Image Synthesis

  Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline. However, they still remain bottlenecked by memory-bound attention in long-context scenarios. Naive sparse attention fails on DLMs due to a KV I…

• CAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular Generation

  Yanting Li, Zhuoyang Jiang, Enyan Dai, Lei Wang, Wen-Cai Ye, Li Liu · 14 April 2026 · Computational Drug Discovery Methods

  Goal-directed molecular generation requires satisfying heterogeneous constraints such as protein--ligand compatibility and multi-objective drug-like properties, yet existing methods often optimize these constraints in isolation, failing to reconcile conflicting objectives (e.g., affinity vs. safety)…

• A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Models

  Theo X. Olausson, Metod Jazbec, Xi Wang, Armando Solar-Lezama, Christian A. Naesseth, Stephan Mandt, Eric Nalisnick · 14 April 2026 · Large Language Models

  Much work has been done on designing fast and accurate sampling for diffusion language models (dLLMs). However, these efforts have largely focused on the tradeoff between speed and quality of individual samples; how to additionally ensure diversity across samples remains less well understood. In thi…

• Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards

  Shaoan Xie, Lingjing Kong, Xiangchen Song, Xinshuai Dong, Guangyi Chen, Eric P. Xing, Kun Zhang · 14 April 2026 · Large Language Models

  Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training strategy for improving their performance; however, existing …

• Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models

  Jiyeon Kim, Sungik Choi, Yongrae Jo, Moontae Lee, Minjoon Seo · 14 April 2026 · Large Language Models

  Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel token generation and bidirectional context modeling. However, harnessing this flexibility for fully non-autoregressive decoding remains an open quest…

• Introspective Diffusion Language Models

  Yifan Yu, Yuqing Jian, Junxiong Wang, Zhongzhu Zhou, Donglin Zhuang, Xinyu Fang, Sri Yanamandra, Xiaoxia Wu, Qingyang Wu, Shuaiwen Leon Song, Tri Dao, Ben Athiwaratkun, James Zou, Fan Lai, Chenfeng Xu · 14 April 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR models agree with their own generations, while DLMs often do not. We define the introspective acceptance rate, which measu…

• Attention-Based Sampler for Diffusion Language Models

  Yuyan Zhou, Kai Syun Hou, Weiyu Chen, James Kwok · 13 April 2026 · Large Language Models

  Auto-regressive models (ARMs) have established a dominant paradigm in language modeling. However, their strictly sequential decoding paradigm imposes fundamental constraints on both inference efficiency and modeling flexibility. To address these limitations, diffusion-based large language models (dL…

• Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models

  Arth Singh · 13 April 2026 · Adversarial Robustness in Machine Learning

  Diffusion-based language models (dLLMs) generate text by iteratively denoising masked token sequences. We show that their safety alignment rests on a single fragile assumption: that the denoising schedule is monotonic and committed tokens are never re-evaluated. Safety-aligned dLLMs commit refusal t…

• DiffuMask: Diffusion Language Model for Token-level Prompt Pruning

  Caleb Zheng, Jyotika Singh, Fang Tu, Weiyi Sun, Sujeeth Bharadwaj, Yassine Benajiba, Sujith Ravi, Eli Shlizerman, Dan Roth · 9 April 2026 · Large Language Models

  In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may contain redundant information. Prompt compression based on pruning offers a practical solution, yet existing methods rely …

• $S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

  Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Asad Aali, Muhammad Usman Khanzada, Muhammad Usman Rafique, Zihao He, Emily Fox, Dean F. Hougen · 9 April 2026 · Large Language Models

  Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, naive best-of-$K$ sampling is fundamentally limited because it repeatedly draws from the same base diffusion distribution…