A transformer-based diffusion model learns the joint distribution of convergence maps and cosmology from log-normal weak lensing simulations and generates calibrated posterior samples matching MCMC results.
hub
Forty-first international conference on machine learning , year=
21 Pith papers cite this work. Polarity classification is still indexing.
21
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
years
2026 21roles
background 2polarities
background 2representative 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.
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
The paper proves negative weight drift at initialization under MSE or cross-entropy with asymmetric activations, links it to up to 90% sparsity in GPT-nano, maps the sparsity-accuracy cliff across 79 configurations, and shows clipped ReLU² and GELU² improve validation loss.
PermFlow applies conditional flow matching on the affine subspace of doubly stochastic matrices with a closed-form tangent projector and nearest-target coupling to capture multimodal permutation distributions.
RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
MPFM models flow matching velocity as a Gaussian mixture prior per normal class plus a mutual information regularizer to improve open-set anomaly detection over unimodal prototypes.
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.
Fine-tuning CogVideoX with autoregressive context management and bidirectional alignment enables a single model to perform event-based video reconstruction, prediction, and zero-shot interpolation with superior temporal stability.
An autoregressive diffusion driving model predicts each action before its corresponding future frame, using cross-modal denoising to beat prior planners on NAVSIM.
A post-hoc detection framework exploits generation-induced patterns in autoregressive image outputs to enable provenance tracing across multiple IAR models without altering the generation process.
Frontier LLMs exhibit bias from stigmatizing language in clinical vignettes across four conditions, skewing decisions toward less aggressive management, with limited mitigation from Chain-of-Thought or self-debiasing prompts.
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
SCOPE maintains semantic commitments via structured specifications and conditional skill orchestration, achieving 0.60 EGIP on the new Gen-Arena benchmark while outperforming baselines on WISE-V and MindBench.
RealCam is a causal autoregressive model for real-time camera-controlled video-to-video generation, using cross-frame in-context teacher distillation and loop-closed data augmentation to achieve high fidelity and consistency.
Latent diffusion models exhibit geometric decoupling where curvature in out-of-distribution generation is misallocated to unstable semantic boundaries instead of image details, identifying geometric hotspots as the structural cause of editing instability.
Introduces dual pose-image representation, cross-modal alignment, and iterative construction to improve prompt alignment and diversity in multi-person text-to-image generation.
AdaptiveLoad cuts computational imbalance in video DiT training from 39% to 18.9% and raises throughput 27.2% via memory-compute constraints and a custom LayerNorm-Modulate kernel.
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.
DirectEdit eliminates reconstruction error in flow-based image editing by aligning forward paths and applying attention feature injection with mask-guided noise blending.
citing papers explorer
-
Joint inference of weak lensing convergence map and cosmology with diffusion models
A transformer-based diffusion model learns the joint distribution of convergence maps and cosmology from log-normal weak lensing simulations and generates calibrated posterior samples matching MCMC results.
-
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.
-
Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
-
Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes
The paper proves negative weight drift at initialization under MSE or cross-entropy with asymmetric activations, links it to up to 90% sparsity in GPT-nano, maps the sparsity-accuracy cliff across 79 configurations, and shows clipped ReLU² and GELU² improve validation loss.
-
Learning Unbiased Permutations via Flow Matching
PermFlow applies conditional flow matching on the affine subspace of doubly stochastic matrices with a closed-form tangent projector and nearest-target coupling to capture multimodal permutation distributions.
-
RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
-
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
-
Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection
MPFM models flow matching velocity as a Gaussian mixture prior per normal class plus a mutual information regularizer to improve open-set anomaly detection over unimodal prototypes.
-
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.
-
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
Fine-tuning CogVideoX with autoregressive context management and bidirectional alignment enables a single model to perform event-based video reconstruction, prediction, and zero-shot interpolation with superior temporal stability.
-
ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving
An autoregressive diffusion driving model predicts each action before its corresponding future frame, using cross-modal denoising to beat prior planners on NAVSIM.
-
Data Provenance for Image Auto-Regressive Generation
A post-hoc detection framework exploits generation-induced patterns in autoregressive image outputs to enable provenance tracing across multiple IAR models without altering the generation process.
-
Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making
Frontier LLMs exhibit bias from stigmatizing language in clinical vignettes across four conditions, skewing decisions toward less aggressive management, with limited mitigation from Chain-of-Thought or self-debiasing prompts.
-
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
-
SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
SCOPE maintains semantic commitments via structured specifications and conditional skill orchestration, achieving 0.60 EGIP on the new Gen-Arena benchmark while outperforming baselines on WISE-V and MindBench.
-
RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control
RealCam is a causal autoregressive model for real-time camera-controlled video-to-video generation, using cross-frame in-context teacher distillation and loop-closed data augmentation to achieve high fidelity and consistency.
-
Geometric Decoupling: Diagnosing the Structural Instability of Latent
Latent diffusion models exhibit geometric decoupling where curvature in out-of-distribution generation is misallocated to unstable semantic boundaries instead of image details, identifying geometric hotspots as the structural cause of editing instability.
-
Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes
Introduces dual pose-image representation, cross-modal alignment, and iterative construction to improve prompt alignment and diversity in multi-person text-to-image generation.
-
AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training
AdaptiveLoad cuts computational imbalance in video DiT training from 39% to 18.9% and raises throughput 27.2% via memory-compute constraints and a custom LayerNorm-Modulate kernel.
-
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.
-
DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing
DirectEdit eliminates reconstruction error in flow-based image editing by aligning forward paths and applying attention feature injection with mask-guided noise blending.