Discrete Diffusion in Large Language and Multimodal Models: A Survey
Paper
•
2506.13759
•
Published
•
29
Discrete Diffusion LLM & MLLM
An collection of research/models in discrete diffusion large language and multimodal models
-
-
GSAI-ML/LLaDA-8B-Instruct
Text Generation • Updated • 98.6k • 293 -
Dream-org/Dream-v0-Base-7B
Feature Extraction • Updated • 13.3k • 36 -
Dream-org/Dream-v0-Instruct-7B
Feature Extraction • Updated • 54.9k • 103 -
GSAI-ML/LLaDA-8B-Base
Text Generation • Updated • 173k • 64 -
kuleshov-group/bd3lm-owt-block_size16
Text Generation • Updated • 1.63k • 15 -
kuleshov-group/bd3lm-owt-block_size4
Text Generation • Updated • 745 • 2 -
kuleshov-group/bd3lm-owt-block_size8
Text Generation • Updated • 305 • 1 -
JingyangOu/radd-lambda-dce
Updated • 227 • 2 -
JingyangOu/radd-t-dce
Updated • 21 • 2 -
louaaron/sedd-small
Updated • 610 • 8 -
louaaron/sedd-medium
Updated • 444 • 5 -
diffusionfamily/diffullama
Text Generation • Updated • 2.17k • 9 -
amyxlu/plaid
Updated • 3 -
nieshen/SMDM
Updated • 7 -
kuleshov-group/mdlm-owt
Fill-Mask • Updated • 7.05k • 17 -
jacklishufan/lavida-dream-v1.0-instruct
Updated • 51 • 1 -
jacklishufan/lavida-llada-v1.0-instruct
Updated • 4.92k • 4 -
Gen-Verse/MMaDA-8B-Base
Any-to-Any • Updated • 18.2k • 68 -
rp-yu/Dimple-7B
Image-Text-to-Text • Updated • 1.17k • 6 -
GSAI-ML/LLaDA-1.5
Text Generation • Updated • 1.93k • 9 -
GSAI-ML/LLaDA-V
Image-Text-to-Text • Updated • 1.42k • 11 -
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Paper • 1503.03585 • Published • 4 -
Structured Denoising Diffusion Models in Discrete State-Spaces
Paper • 2107.03006 • Published -
PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion
Paper • 2412.17780 • Published • 5 -
A Reparameterized Discrete Diffusion Model for Text Generation
Paper • 2302.05737 • Published -
Simple and Effective Masked Diffusion Language Models
Paper • 2406.07524 • Published • 11 -
Simplified and Generalized Masked Diffusion for Discrete Data
Paper • 2406.04329 • Published • 7 -
DPLM-2: A Multimodal Diffusion Protein Language Model
Paper • 2410.13782 • Published • 22 -
GenMol: A Drug Discovery Generalist with Discrete Diffusion
Paper • 2501.06158 • Published -
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
Paper • 2406.03736 • Published -
AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion
Paper • 2503.07418 • Published -
d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
Paper • 2504.12216 • Published • 2 -
Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
Paper • 2402.07754 • Published -
DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
Paper • 2211.15029 • Published -
A Cheaper and Better Diffusion Language Model with Soft-Masked Noise
Paper • 2304.04746 • Published -
TESS: Text-to-Text Self-Conditioned Simplex Diffusion
Paper • 2305.08379 • Published • 3 -
Likelihood-Based Diffusion Language Models
Paper • 2305.18619 • Published • 1 -
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
Paper • 2310.16834 • Published • 4 -
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
Paper • 2505.15045 • Published • 54 -
TESS 2: A Large-Scale Generalist Diffusion Language Model
Paper • 2502.13917 • Published • 6 -
Large Language Diffusion Models
Paper • 2502.09992 • Published • 120 -
LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
Paper • 2505.19223 • Published • 8 -
CtrlDiff: Boosting Large Diffusion Language Models with Dynamic Block Prediction and Controllable Generation
Paper • 2505.14455 • Published -
Scaling up Masked Diffusion Models on Text
Paper • 2410.18514 • Published -
dKV-Cache: The Cache for Diffusion Language Models
Paper • 2505.15781 • Published • 16 -
LaViDa: A Large Diffusion Language Model for Multimodal Understanding
Paper • 2505.16839 • Published • 12 -
Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding
Paper • 2505.16990 • Published • 21 -
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
Paper • 2505.16933 • Published • 32 -
MMaDA: Multimodal Large Diffusion Language Models
Paper • 2505.15809 • Published • 89 -
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
Paper • 2505.20147 • Published -
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
Paper • 2505.23606 • Published • 14 -
Discrete Flow Matching
Paper • 2407.15595 • Published • 13 -
Remasking Discrete Diffusion Models with Inference-Time Scaling
Paper • 2503.00307 • Published • 10 -
MaskGIT: Masked Generative Image Transformer
Paper • 2202.04200 • Published -
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Paper • 2410.17891 • Published • 16 -
Unified Multimodal Discrete Diffusion
Paper • 2503.20853 • Published • 9