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
Advances in neural information processing systems , volume=
34 Pith papers cite this work. Polarity classification is still indexing.
34
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 1
citation-polarity summary
representative citing papers
Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
A multimodal diffusion model generates controllable alternative streetscapes from street-view imagery using visual metrics and text, shown on Chicago and Orlando data with gains in semantic consistency.
A multi-exposure video model predicts bracketed linear SDR sequences from single nonlinear SDR input, which a merging model combines into HDR video preserving shadow and highlight detail.
A hypernetwork maps style motion embeddings to LoRA updates that stylize text-driven motion diffusion models with improved generalization to unseen styles via contrastive structuring of the style space.
The choice of closeness measure in diffusion reward alignment determines the computational primitives and tractable reward classes, with linear exponential tilts sufficing for KL with convex rewards and proximal oracles for Wasserstein with concave or low-dimensional Lipschitz rewards.
RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
Adaptive guidance trajectories learned via PPO outperform fixed-scale CFG on controllability-quality balance in three controlled NLP generation tasks with discrete diffusion models.
MaMi-HOI counters geometric forgetting in diffusion models via a Geometry-Aware Proximity Adapter for precise contacts and a Kinematic Harmony Adapter for natural whole-body postures in human-object interactions.
PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
Timestep embeddings in diffusion models function as a separable side channel that can carry dedicated information for adversarial injection or detection.
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.
Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
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.
XDiffuser combines extrinsic graph planning with diffusion models to guide denoising and improve performance on long-horizon robotic tasks including multi-agent coordination and TSP-style problems.
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
Coupled initial noises in diffusion models, with designed dependence but unchanged marginal Gaussians, improve generated image diversity on Stable Diffusion variants while preserving quality and alignment.
ReSIDe generalizes logit-based confidence scores to intermediate layers of synthetic image detectors and uses preference optimization to aggregate them, cutting area under the risk-coverage curve by up to 69.55% under covariate shifts.
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
VIAR embeds an implicit equilibrium layer in next-scale AR image models, reporting FID 2.16 on ImageNet 256 with 38.4% of VAR’s parameters and a per-scale inference compute knob.
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.
PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.
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.
-
Diffeomorphic Optimization
Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
-
Designing streetscapes from street-view imagery using diffusion models
A multimodal diffusion model generates controllable alternative streetscapes from street-view imagery using visual metrics and text, shown on Chicago and Orlando data with gains in semantic consistency.
-
Generating HDR Video from SDR Video
A multi-exposure video model predicts bracketed linear SDR sequences from single nonlinear SDR input, which a merging model combines into HDR video preserving shadow and highlight detail.
-
Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
A hypernetwork maps style motion embeddings to LoRA updates that stylize text-driven motion diffusion models with improved generalization to unseen styles via contrastive structuring of the style space.
-
The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives
The choice of closeness measure in diffusion reward alignment determines the computational primitives and tractable reward classes, with linear exponential tilts sufficing for KL with convex rewards and proximal oracles for Wasserstein with concave or low-dimensional Lipschitz rewards.
-
Relative Score Policy Optimization for Diffusion Language Models
RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
-
Guidance Is Not a Hyperparameter: Learning Dynamic Control in Diffusion Language Models
Adaptive guidance trajectories learned via PPO outperform fixed-scale CFG on controllability-quality balance in three controlled NLP generation tasks with discrete diffusion models.
-
MaMi-HOI: Harmonizing Global Kinematics and Local Geometry for Human-Object Interaction Generation
MaMi-HOI counters geometric forgetting in diffusion models via a Geometry-Aware Proximity Adapter for precise contacts and a Kinematic Harmony Adapter for natural whole-body postures in human-object interactions.
-
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
-
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
Timestep embeddings in diffusion models function as a separable side channel that can carry dedicated information for adversarial injection or detection.
-
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.
-
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.
-
Unified Audio Intelligence Without Regressing on Text Intelligence
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
-
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.
-
Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning
XDiffuser combines extrinsic graph planning with diffusion models to guide denoising and improve performance on long-horizon robotic tasks including multi-agent coordination and TSP-style problems.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
-
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
-
Couple to Control: Joint Initial Noise Design in Diffusion Models
Coupled initial noises in diffusion models, with designed dependence but unchanged marginal Gaussians, improve generated image diversity on Stable Diffusion variants while preserving quality and alignment.
-
Post-hoc Selective Classification for Reliable Synthetic Image Detection
ReSIDe generalizes logit-based confidence scores to intermediate layers of synthetic image detectors and uses preference optimization to aggregate them, cutting area under the risk-coverage curve by up to 69.55% under covariate shifts.
-
Stylistic Attribute Control in Latent Diffusion Models
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
-
Visual Implicit Autoregressive Modeling
VIAR embeds an implicit equilibrium layer in next-scale AR image models, reporting FID 2.16 on ImageNet 256 with 38.4% of VAR’s parameters and a per-scale inference compute knob.
-
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.
-
PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.
-
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.
-
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
-
Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
Key vectors of concept text tokens in multimodal diffusion transformers encode an 'omission signal'; amplifying the omission-minus-presence direction during early denoising reduces object omission on FLUX.1-Dev and SD3.5-Medium.
-
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
-
Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
-
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.
-
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
F5-TTS generates natural speech from text via flow matching on DiT with simple text padding, ConvNeXt refinement, and sway sampling, trained on 100K hours multilingual data.
-
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