Using adjoint equations, the paper derives S-independent IPM convergence bounds for masked and uniform discrete diffusion, controlled by score-matching losses.
hub
High-resolution image synthesis with latent diffusion models
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
representative citing papers
AudioMoG is a mixture-of-guidance sampling technique that combines CFG and AG signals to outperform single-guidance baselines in text-to-audio generation at equivalent speed.
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
MetaSymbO proposes a three-agent framework with symbolic latent evolution that improves structural validity and language alignment for metamaterial design from free-form text intents.
EG-GRPO improves autoregressive text-to-image models by reallocating RL updates according to token entropy, excluding low-entropy tokens from reward signals while adding entropy bonuses to high-entropy ones, yielding state-of-the-art results on standard benchmarks.
SeMoBridge projects images into the text modality via a semantic bridge to reduce CLIP's intra-modal misalignment and improve few-shot performance.
Causal-Adapter adapts frozen diffusion backbones via structural causal modeling, prompt-aligned injection, and conditioned token contrastive loss to achieve faithful counterfactual generation with strong attribute control and identity preservation.
CogVideoX generates coherent 10-second text-to-video outputs at high resolution using a 3D VAE, expert adaptive LayerNorm transformer, progressive training, and a custom data pipeline, claiming state-of-the-art results.
CameraCtrl enables accurate camera pose control in video diffusion models through a trained plug-and-play module and dataset choices emphasizing diverse camera trajectories with matching appearance.
ConjNorm reframes OOD detection score design as optimizing norm p in an exponential family density model via a Bregman divergence theorem, with a tractable Monte Carlo estimator, claiming SOTA gains on CIFAR-100 and ImageNet-1K.
TAPE applies temporal-aware token pruning with smoothing, reselection, and timestep scheduling to speed up video diffusion models while preserving visual fidelity and coherence.
citing papers explorer
-
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.
-
AudioMoG: Guiding Audio Generation with Mixture-of-Guidance
AudioMoG is a mixture-of-guidance sampling technique that combines CFG and AG signals to outperform single-guidance baselines in text-to-audio generation at equivalent speed.
-
Diffusion Models Are Real-Time Game Engines
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
-
METASYMBO: Multi-Agent Language-Guided Metamaterial Discovery via Symbolic Latent Evolution
MetaSymbO proposes a three-agent framework with symbolic latent evolution that improves structural validity and language alignment for metamaterial design from free-form text intents.
-
From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
EG-GRPO improves autoregressive text-to-image models by reallocating RL updates according to token entropy, excluding low-entropy tokens from reward signals while adding entropy bonuses to high-entropy ones, yielding state-of-the-art results on standard benchmarks.
-
SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
SeMoBridge projects images into the text modality via a semantic bridge to reduce CLIP's intra-modal misalignment and improve few-shot performance.
-
Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
Causal-Adapter adapts frozen diffusion backbones via structural causal modeling, prompt-aligned injection, and conditioned token contrastive loss to achieve faithful counterfactual generation with strong attribute control and identity preservation.
-
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
CogVideoX generates coherent 10-second text-to-video outputs at high resolution using a 3D VAE, expert adaptive LayerNorm transformer, progressive training, and a custom data pipeline, claiming state-of-the-art results.
-
CameraCtrl: Enabling Camera Control for Text-to-Video Generation
CameraCtrl enables accurate camera pose control in video diffusion models through a trained plug-and-play module and dataset choices emphasizing diverse camera trajectories with matching appearance.
-
ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
ConjNorm reframes OOD detection score design as optimizing norm p in an exponential family density model via a Bregman divergence theorem, with a tractable Monte Carlo estimator, claiming SOTA gains on CIFAR-100 and ImageNet-1K.
-
Temporal Aware Pruning for Efficient Diffusion-based Video Generation
TAPE applies temporal-aware token pruning with smoothing, reselection, and timestep scheduling to speed up video diffusion models while preserving visual fidelity and coherence.
- Score-based Membership Inference on Diffusion Models