Set diffusion factorizes likelihood over arbitrary token sets and uses a set-causal diffusion architecture to support KV caching and any-order decoding, yielding improved speed-quality tradeoffs versus prior diffusion LMs.
hub
International conference on machine learning , pages=
29 Pith papers cite this work. Polarity classification is still indexing.
29
Pith papers citing it
hub tools
representative citing papers
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
Using adjoint equations, the paper derives S-independent IPM convergence bounds for masked and uniform discrete diffusion, controlled by score-matching losses.
VMU-Diff improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.
DirectTryOn achieves state-of-the-art one-step virtual try-on performance by applying pure conditional transport, garment preservation loss, and self-consistency loss to straighten trajectories in pretrained generative models.
DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
OGPP is a particle flow-matching method using orbit-space canonicalization and geometric paths that achieves lower error and fewer steps than prior approaches on 3D benchmarks.
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
NI Sampling accelerates discrete diffusion language models up to 14.3 times by training a neural indicator to select which tokens to sample at each step using a trajectory-preserving objective.
PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models while generalizing better to prompts over 500 tokens.
Absorbing discrete diffusion models the conditional distributions of clean data; reparameterizing yields a time-independent RADD that unifies with AO-ARMs and reaches SOTA perplexity among diffusion models on zero-shot language benchmarks.
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
A threshold-guided alignment method lets visual generative models be optimized directly from scalar human ratings instead of requiring paired preference data.
A training-free technique manipulates low-frequency noise in diffusion models to control image color and structure using low-frequency priors.
LASER couples a latent world model with a GRPO-trained RL policy to adaptively reposition sensors for sparse continuum field reconstruction, outperforming fixed and offline-optimized placement strategies across PDE and real-world benchmarks.
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
DAG-STL decomposes long-horizon STL planning into decomposition, timed waypoint allocation, and diffusion-based trajectory generation to enable zero-shot planning under unknown dynamics.
VisionReward learns multi-dimensional human preferences for image and video generation via hierarchical assessment and linear weighting, outperforming VideoScore by 17.2% in prediction accuracy and yielding 31.6% higher win rates in text-to-video models.
Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
ProSAC-CT is a progressive diffusion model for LDCT denoising that combines anatomical conditioning, residual frequency decoupling, and staged decoding to improve fidelity and preserve anatomical details over prior methods.
GPC learns a motion vocabulary via Finite Scalar Quantization and end-to-end RL, then trains an autoregressive transformer for next-token control generation, achieving 99.98% motion reproduction success with emergent robustness.
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.
Near-reversible Runge-Kutta ODE solvers combined with vector-field smoothing deliver more stable and higher-fidelity text-guided edits in diffusion models than exactly reversible schemes.
citing papers explorer
-
Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding
Set diffusion factorizes likelihood over arbitrary token sets and uses a set-causal diffusion architecture to support KV caching and any-order decoding, yielding improved speed-quality tradeoffs versus prior diffusion LMs.
-
Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
-
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
Using adjoint equations, the paper derives S-independent IPM convergence bounds for masked and uniform discrete diffusion, controlled by score-matching losses.
-
VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting
VMU-Diff improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.
-
DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport
DirectTryOn achieves state-of-the-art one-step virtual try-on performance by applying pure conditional transport, garment preservation loss, and self-consistency loss to straighten trajectories in pretrained generative models.
-
Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
-
Generative Modeling with Orbit-Space Particle Flow Matching
OGPP is a particle flow-matching method using orbit-space canonicalization and geometric paths that achieves lower error and fewer steps than prior approaches on 3D benchmarks.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
NI Sampling accelerates discrete diffusion language models up to 14.3 times by training a neural indicator to select which tokens to sample at each step using a trajectory-preserving objective.
-
Long-Text-to-Image Generation via Compositional Prompt Decomposition
PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models while generalizing better to prompts over 500 tokens.
-
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
Absorbing discrete diffusion models the conditional distributions of clean data; reparameterizing yields a time-independent RADD that unifies with AO-ARMs and reaches SOTA perplexity among diffusion models on zero-shot language benchmarks.
-
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
-
Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
-
Threshold-Guided Optimization for Visual Generative Models
A threshold-guided alignment method lets visual generative models be optimized directly from scalar human ratings instead of requiring paired preference data.
-
Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation
A training-free technique manipulates low-frequency noise in diffusion models to control image color and structure using low-frequency priors.
-
LASER: Learning Active Sensing for Continuum Field Reconstruction
LASER couples a latent world model with a GRPO-trained RL policy to adaptively reposition sensors for sparse continuum field reconstruction, outperforming fixed and offline-optimized placement strategies across PDE and real-world benchmarks.
-
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
-
DAG-STL: A Hierarchical Framework for Zero-Shot Trajectory Planning under Signal Temporal Logic Specifications
DAG-STL decomposes long-horizon STL planning into decomposition, timed waypoint allocation, and diffusion-based trajectory generation to enable zero-shot planning under unknown dynamics.
-
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
VisionReward learns multi-dimensional human preferences for image and video generation via hierarchical assessment and linear weighting, outperforming VideoScore by 17.2% in prediction accuracy and yielding 31.6% higher win rates in text-to-video models.
-
Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
-
ProSAC-CT: Progressive Spectral-Anatomical Co-Guided Multi-Stage Diffusion Model for Low-Dose CT Denoising
ProSAC-CT is a progressive diffusion model for LDCT denoising that combines anatomical conditioning, residual frequency decoupling, and staged decoding to improve fidelity and preserve anatomical details over prior methods.
-
GPC: Large-Scale Generative Pretraining for Transferable Motor Control
GPC learns a motion vocabulary via Finite Scalar Quantization and end-to-end RL, then trains an autoregressive transformer for next-token control generation, achieving 99.98% motion reproduction success with emergent robustness.
-
Lossless Anti-Distillation Sampling
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.
-
Stable and Near-Reversible Diffusion ODE Solvers for Image Editing
Near-reversible Runge-Kutta ODE solvers combined with vector-field smoothing deliver more stable and higher-fidelity text-guided edits in diffusion models than exactly reversible schemes.
-
Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
A structured diffusion bridge method achieves near fully-paired modality translation quality using alignment constraints even in unpaired or semi-paired regimes.
-
Consistent Diffusion Language Models
CDLM introduces MPDC training for discrete diffusion models, recovering prior methods as limits and claiming new SOTA text generation performance especially at low sampling budgets.
-
Statistical Properties of Training & Generalization
Review of neural scaling laws and their relation to constraints and inductive biases when applying machine learning to physics problems.
- Functionalization via Structure Completion and Motion Rectification
- Unifying Deep Stochastic Processes for Image Enhancement