A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
hub
Denoising diffusion probabilistic models
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Derives a conditional-marginal entropy-rate objective for bridge-aware discretization that yields U-shaped schedules and improves low-NFE sample quality on 2D, CIFAR-10, and protein tasks.
Defines Conditional Distribution Matching (CDM) as finding inputs whose induced conditional distributions match a target distribution and proposes the MLGD-F inference-time algorithm using pretrained diffusion models to solve it without retraining.
Diffusion models can extract reusable density-mode concepts from their time-indexed scores to enable compositional generation at test time on held-out benchmarks from ColorMNIST and CelebA.
Many reward-based fine-tuning methods for diffusion and flow models are special cases of a common score-matching objective whose differences reduce to value-guidance estimator design, temporal weighting, and trust-region realization.
Langevin sampling on the modern Hopfield energy produces training-free stochastic attention that transitions from exact retrieval to generation as temperature rises, with an entropy inflection condition marking the shift.
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
Diff-ANO uses conditional consistency models and adjoint neural operator surrogates to enable fast, high-quality USCT reconstructions under sparse and partial views by replacing slow PDE solvers and enabling few-step sampling.
DrawVideo is a sketch-guided framework that decomposes long videos into controllable shots using keyframe sketches, appearance prompts, and motion prompts, supported by a new SketchLongVideo dataset.
GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.
ACSAC adaptively selects action chunk sizes via a causal Transformer Q-network in actor-critic RL, proves the Bellman operator is a contraction, and reports state-of-the-art results on long-horizon manipulation tasks.
Probability-Flow Distillation exactly matches the Wasserstein gradient flow of the target distribution when distilling 2D diffusion priors into 3D models, yielding higher-fidelity results than SDS or SDI.
Conservative flows generate by running probability-preserving stochastic dynamics initialized at data points rather than noise, using corrected Langevin or predictor-corrector mechanisms on top of any pretrained flow model and showing gains on Swiss-roll, ImageNet-256 and Oxford Flowers-102.
PRISM iteratively transforms semantic priors into behavior-conditioned posteriors via cross-modal refinement to improve representation learning on dynamic text-attributed graphs.
SSTS extracts causal topological orders from score functions via Schur complements of the Score-Jacobian Information Matrix, bypassing acyclicity optimization.
3D-GeoFlow reformulates discrete categorical 3D geological generation as simulation-free continuous vector field regression with 3D attention gates, claiming to outperform heuristics and diffusion models on a 2,200-case synthetic dataset.
Matrix-Game 2.0 introduces a scalable data pipeline, action-injection module, and few-step distillation to enable real-time streaming video generation at 25 FPS from game-engine interactions, with open-sourced weights and code.
citing papers explorer
-
Vision as Unified Multimodal Generation
A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
-
Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\"odinger Samplers
Derives a conditional-marginal entropy-rate objective for bridge-aware discretization that yields U-shaped schedules and improves low-NFE sample quality on 2D, CIFAR-10, and protein tasks.
-
Inverse Design for Conditional Distribution Matching
Defines Conditional Distribution Matching (CDM) as finding inputs whose induced conditional distributions match a target distribution and proposes the MLGD-F inference-time algorithm using pretrained diffusion models to solve it without retraining.
-
Test-Time Compositional Generalization in Diffusion Models via Concept Discovery
Diffusion models can extract reusable density-mode concepts from their time-indexed scores to enable compositional generation at test time on held-out benchmarks from ColorMNIST and CelebA.
-
Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
Many reward-based fine-tuning methods for diffusion and flow models are special cases of a common score-matching objective whose differences reduce to value-guidance estimator design, temporal weighting, and trust-region realization.
-
Stochastic Attention via Langevin Dynamics on the Modern Hopfield Energy
Langevin sampling on the modern Hopfield energy produces training-free stochastic attention that transitions from exact retrieval to generation as temperature rises, with an entropy inflection condition marking the shift.
-
Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
-
Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators
Diff-ANO uses conditional consistency models and adjoint neural operator surrogates to enable fast, high-quality USCT reconstructions under sparse and partial views by replacing slow PDE solvers and enabling few-step sampling.
-
DrawVideo: Generating Long Video from Storyboard Keyframe Sketches
DrawVideo is a sketch-guided framework that decomposes long videos into controllable shots using keyframe sketches, appearance prompts, and motion prompts, supported by a new SketchLongVideo dataset.
-
GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization
GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.
-
ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network
ACSAC adaptively selects action chunk sizes via a causal Transformer Q-network in actor-critic RL, proves the Bellman operator is a contraction, and reports state-of-the-art results on long-horizon manipulation tasks.
-
Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation
Probability-Flow Distillation exactly matches the Wasserstein gradient flow of the target distribution when distilling 2D diffusion priors into 3D models, yielding higher-fidelity results than SDS or SDI.
-
Conservative Flows: A New Paradigm of Generative Models
Conservative flows generate by running probability-preserving stochastic dynamics initialized at data points rather than noise, using corrected Langevin or predictor-corrector mechanisms on top of any pretrained flow model and showing gains on Swiss-roll, ImageNet-256 and Oxford Flowers-102.
-
PRISM: Iterative Cross-Modal Posterior Refinement for Dynamic Text-Attributed Graphs
PRISM iteratively transforms semantic priors into behavior-conditioned posteriors via cross-modal refinement to improve representation learning on dynamic text-attributed graphs.
-
Optimization-Free Topological Sort for Causal Discovery via the Schur Complement of Score Jacobians
SSTS extracts causal topological orders from score functions via Schur complements of the Score-Jacobian Information Matrix, bypassing acyclicity optimization.
-
Attention-Guided Flow-Matching for Sparse 3D Geological Generation
3D-GeoFlow reformulates discrete categorical 3D geological generation as simulation-free continuous vector field regression with 3D attention gates, claiming to outperform heuristics and diffusion models on a 2,200-case synthetic dataset.
-
Matrix-game 2.0: An open-source real-time and streaming interactive world model
Matrix-Game 2.0 introduces a scalable data pipeline, action-injection module, and few-step distillation to enable real-time streaming video generation at 25 FPS from game-engine interactions, with open-sourced weights and code.