Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
hub Mixed citations
Generative Adversarial Networks
Mixed citation behavior. Most common role is background (59%).
80
Pith papers citing it
4,572
external citations · Pith
Background
59% of classified citations
abstract
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.
hub tools
citation-role summary
background 18
method 4
citation-polarity summary
representative citing papers
NICE learns a composition of invertible neural-network layers that transform data into independent latent variables, enabling exact log-likelihood training and sampling for density estimation.
Introduces Forged Calamity benchmark and shows that fine-tuned and zero-shot synthetic image detectors lose substantial accuracy on unseen generators and disaster types.
OGAS uses a parallel diffusion model to bias PDE configuration sampling toward high surrogate difficulty, reducing 99th-percentile errors and error variance versus uniform sampling across tested 2D PDEs.
RANs generalize moment unfolding to full phase-space unbinned unfolding via detector-level Wasserstein critics without requiring support overlap or multiple iterations.
Nested-GPT is an autoregressive Transformer surrogate that generates variable-multiplicity parton showers while enforcing ordered Markovian branching and matches reference Monte Carlo results for leading-log non-global logarithm resummation in the large-Nc limit.
Creativity is defined as meta-learning where a frozen diffusion creator optimizes candidates for rapid improvement by an adapting appraiser such as an autoencoder or CLIP adapter.
High-resolution interferometric imaging of eight post-AGB circumbinary discs reveals diverse inner-rim substructures including azimuthal brightness enhancements and arc-like features not explained by inclination alone.
Transformer networks sample up to 180x180 2D Ising systems and 64x64 Edwards-Anderson systems by generating spin groups with probability approximations, yielding ~20x higher effective sample size than prior neural samplers at criticality.
VaFES constructs a latent space from reversible collective variables and variationally optimizes a tractable-density generative model to produce a continuous free energy surface from which rare events are directly sampled.
FlowGuard detects unsafe content during diffusion image generation via linear latent decoding and curriculum learning, outperforming prior methods by over 30% F1 while reducing GPU memory by 97% and projection time to 0.2 seconds.
A CNN-based discrete diffusion method refines sparse contours from segmentation masks using simplified denoising steps and minimal post-processing, outperforming baselines on small medical and environmental datasets while running 3.5 times faster.
The paper introduces the first comprehensive taxonomy and visualization of 11 categories of technologies facilitating AI-generated non-consensual intimate images, derived from synthesis of primary sources and demonstrated through case studies.
A LoRA-adapted conditional diffusion surrogate for electromagnetic calorimeter showers matches key observables within 2% RMSE and reproduces directional trends in design-utility gradients.
A U-Net GAN reconstructs CMB T and E maps from Planck-like simulations with foregrounds and systematics, achieving under 1% error outside the Galactic region and demonstrating first-time correction for non-circular beams and asymmetric scans.
PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
GlitchGAN generates class-conditioned time-domain glitches that pass Gravity Spy classification and show UMAP overlap with real samples while running at high speed.
Tac-DINO constructs a large tactile dataset and Vis-Tac Holographic Matching Benchmark, then proposes Vision-Tactile Patch Alignment (VTPA) methods that outperform non-aligned baselines on local-to-global feature matching.
A two-stage framework that decouples generation, selection, and refinement to improve budget use in diffusion-based dataset distillation.
CPGAN adds a lateral-acceleration collision loss and Voronoi motion features to a GAN to lower collision rates in bidirectional crowd flows while reproducing lane formation and N-t curves.
SGMD distills a 14B video diffusion model into a 4-step generator by matching fake and teacher scores with a stop-gradient Fisher objective plus dual NR/RC potentials, improving motion and cutting training cost about 3x.
A hybrid agentic architecture integrates knowledge-based physical verification tools into LLM-driven CAD design loops, producing more complex and functionally valid designs than prior agentic baselines.
citing papers explorer
-
Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
-
NICE: Non-linear Independent Components Estimation
NICE learns a composition of invertible neural-network layers that transform data into independent latent variables, enabling exact log-likelihood training and sampling for density estimation.
-
Forged Calamity: Benchmark for Cross-Domain Synthetic Disaster Detection in the Age of Diffusion
Introduces Forged Calamity benchmark and shows that fine-tuned and zero-shot synthetic image detectors lose substantial accuracy on unseen generators and disaster types.
-
Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training
OGAS uses a parallel diffusion model to bias PDE configuration sampling toward high surrogate difficulty, reducing 99th-percentile errors and error variance versus uniform sampling across tested 2D PDEs.
-
Reweighting Adversarial Networks for Unbinned Unfolding
RANs generalize moment unfolding to full phase-space unbinned unfolding via detector-level Wasserstein critics without requiring support overlap or multiple iterations.
-
Nested-GPT for variable-multiplicity parton showers: A case study in the resummation of non-global logarithms
Nested-GPT is an autoregressive Transformer surrogate that generates variable-multiplicity parton showers while enforcing ordered Markovian branching and matches reference Monte Carlo results for leading-log non-global logarithm resummation in the large-Nc limit.
-
Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
Creativity is defined as meta-learning where a frozen diffusion creator optimizes candidates for rapid improvement by an adapting appraiser such as an autoencoder or CLIP adapter.
-
VLTI/PIONIER imaging of post-AGB binaries. An INSPIRING hunt for inner rim substructures in circumbinary discs
High-resolution interferometric imaging of eight post-AGB circumbinary discs reveals diverse inner-rim substructures including azimuthal brightness enhancements and arc-like features not explained by inclination alone.
-
Sampling two-dimensional spin systems with transformers
Transformer networks sample up to 180x180 2D Ising systems and 64x64 Edwards-Anderson systems by generating spin groups with probability approximations, yielding ~20x higher effective sample size than prior neural samplers at criticality.
-
Differentiable free energy surface: a variational approach to directly observing rare events using generative deep-learning models
VaFES constructs a latent space from reversible collective variables and variationally optimizes a tractable-density generative model to produce a continuous free energy surface from which rare events are directly sampled.
-
FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding
FlowGuard detects unsafe content during diffusion image generation via linear latent decoding and curriculum learning, outperforming prior methods by over 30% F1 while reducing GPU memory by 97% and projection time to 0.2 seconds.
-
Contour Refinement using Discrete Diffusion in Low Data Regime
A CNN-based discrete diffusion method refines sparse contours from segmentation masks using simplified denoising steps and minimal post-processing, outperforming baselines on small medical and environmental datasets while running 3.5 times faster.
-
How to Stop Playing Whack-a-Mole: Mapping the Ecosystem of Technologies Facilitating AI-Generated Non-Consensual Intimate Images
The paper introduces the first comprehensive taxonomy and visualization of 11 categories of technologies facilitating AI-generated non-consensual intimate images, derived from synthesis of primary sources and demonstrated through case studies.
-
Differentiable Surrogate for Detector Simulation and Design with Diffusion Models
A LoRA-adapted conditional diffusion surrogate for electromagnetic calorimeter showers matches key observables within 2% RMSE and reproduces directional trends in design-utility gradients.
-
Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach
A U-Net GAN reconstructs CMB T and E maps from Planck-like simulations with foregrounds and systematics, achieving under 1% error outside the Galactic region and demonstrating first-time correction for non-circular beams and asymmetric scans.
-
PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models
PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.
-
Hierarchical Text-Conditional Image Generation with CLIP Latents
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
-
Realistic Time-Domain Synthesis of Gravitational-Wave Detector Glitches using Class-Conditional Derivative Generative Adversarial Networks
GlitchGAN generates class-conditioned time-domain glitches that pass Gravity Spy classification and show UMAP overlap with real samples while running at high speed.
-
Tac-DINO: Learning Vision-Tactile Features with Patch Alignment
Tac-DINO constructs a large tactile dataset and Vis-Tac Holographic Matching Benchmark, then proposes Vision-Tactile Patch Alignment (VTPA) methods that outperform non-aligned baselines on local-to-global feature matching.
-
Pool-Select-Refine for Allocation-Aware Generative Dataset Distillation
A two-stage framework that decouples generation, selection, and refinement to improve budget use in diffusion-based dataset distillation.
-
Simulation of collision avoidance behavior in crowd movement by data-driven approach
CPGAN adds a lateral-acceleration collision loss and Voronoi motion features to a GAN to lower collision rates in bidirectional crowd flows while reproducing lane formation and N-t curves.
-
SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
SGMD distills a 14B video diffusion model into a 4-step generator by matching fake and teacher scores with a stop-gradient Fisher objective plus dual NR/RC potentials, improving motion and cutting training cost about 3x.
-
Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
A hybrid agentic architecture integrates knowledge-based physical verification tools into LLM-driven CAD design loops, producing more complex and functionally valid designs than prior agentic baselines.
-
Study of jet-induced hydro response in high-energy heavy-ion collisions with a flow-matching generative model
A conditional flow-matching model trained on CoLBT-hydro reproduces marginal γ-jet medium-response hadron spectra in 0–10% Pb+Pb at 5.02 TeV with ~10⁶× speedup while preserving front and diffusion-wake statistics.
-
Dual-Diffusional Generative Fashion Recommendation
DualFashion introduces a dual-diffusion Transformer with image and text branches that generates both visual items and semantic descriptions for explainable personalized fashion recommendation.
-
Exceeding the Numerical and Performance Characteristics of IEEE-754 SGEMM with BFloat16 Tensor Cores on GPUs for Scientific Computing
BF16 tensor cores on GPUs emulate FP32 SGEMM with superior performance, power efficiency, and numerical accuracy compared to native FP32, including a library implementation that handles denormals.
-
Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in cooperative MARL.
-
Separate Universe Super-Resolution Emulator
A generative adversarial network emulator upscales low-resolution N-body simulations with non-zero curvature to high resolution, recovering most large-scale power but with up to 10% small-scale suppression and altered halo profiles.
-
Energy-based models for diagnostic reconstruction and analysis in a laboratory plasma device
A single energy-based model trained on LAPD plasma data enables diagnostic reconstruction, inverse inference of probe position, conditional trend sampling, and unconditional mode reproduction for potential anomaly detection.
-
CASCADE: Context-Aware Relaxation for Speculative Image Decoding
CASCADE formalizes semantic interchangeability and convergence in target model representations to enable context-aware acceptance relaxation in tree-based speculative decoding, delivering up to 3.6x speedup on text-to-image models without quality loss.
-
HyperEvoGen: Exploring deep phylogeny using non-Euclidean variational inference
HyperEvoGen uses hyperbolic variational inference to learn phylogenetic representations from protein alignments that preserve hierarchy and scale with evolutionary divergence, outperforming baselines in ancestral reconstruction on simulated data.
-
Diffusion-based Galaxy Simulations for the Roman High Latitude Survey
A denoising diffusion model trained on transformed JWST observations generates multi-band galaxy images that match key statistical properties of real galaxies for Roman weak lensing simulations.
-
COMPASS: A Unified Decision-Intelligence System for Navigating Performance Trade-off in HPC
COMPASS formalizes HPC configuration questions as ML tasks on traces, quantifies recommendation trustworthiness, and delivers 65.93% lower average job turnaround time plus 80.93% lower node usage versus prior methods in simulator tests.
-
AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning
AnomalyAgent uses tool-augmented reinforcement learning with self-reflection to generate realistic industrial anomalies, achieving better metrics than zero-shot methods on MVTec-AD.
-
Dartmouth Stellar Evolution Emulator (DSEE) 1: Generative Stellar Evolution Model Database
DSEE is a flow-based emulator that generates stellar evolution tracks and isochrones as probabilistic outputs from a single model trained on millions of simulations, enabling fast interpolation and uncertainty-aware analyses.
-
Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models
MI-VAE generates physics-constrained synthetic trajectories from scarce real data to improve offline RL policy performance on planetary lander tasks over standard VAEs.
-
Perspective-Equivariant Fine-tuning for Multispectral Demosaicing without Ground Truth
PEFD recovers fine spectral details without ground truth by exploiting projective geometry and adapting foundation models, nearing supervised performance on surgical and automotive data.
-
HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal
A black-box audio watermark removal attack trained on limited samples that generalizes across datasets and watermark schemes with high attack success rates.
-
Recovering Sub-threshold S-wave Arrivals in Deep Learning Phase Pickers via Shape-Aware Loss
A shape-aware loss strategy recovers sub-threshold S-wave arrivals in deep learning seismic phase pickers by treating labels as coherent shapes, achieving a 64% increase in effective detections.
-
Fast, close, non-singular and property-preserving approximations of entropic measures
FEA introduces rational approximations to Shannon entropy and symmetrized KL that are non-singular, require few operations, achieve low error, and yield faster better ML feature selection than LASSO.
-
Planning Under Observation Mismatch for Traffic Signal Control via Adaptive Modular World Models
AMM separates domain-specific observation adapters from a meta-learned shared dynamics model to enable transferable planning under observation mismatch in traffic signal control.
-
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
-
Shap-E: Generating Conditional 3D Implicit Functions
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
-
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.
-
Demystifying MMD GANs
MMD GANs have unbiased critic gradients but biased generator gradients from sample-based learning, and the Kernel Inception Distance provides a practical new measure for GAN convergence and dynamic learning rate adaptation.
-
Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization
SteinDiff applies Stein-derived residual corrections at each step to stabilize large-step inference in diffusion probability flow ODEs without retraining or reference samples.
-
DiffUNet^2: Bidirectional Prediction, Probabilistic Generation and Collaborative Visual Discovery for Scientific Data
DiffUNet^2 is a bidirectional conditional diffusion model integrated with visual tools for probabilistic exploration of scientific time series across five evaluated datasets.
-
Three-dimensional Conditional Diffusion Models for Cosmological 21 cm Lightcone Emulation
Yeo-Johnson preprocessing combined with moderate amplitude compression provides the best trade-off for conditional diffusion models emulating 3D 21 cm lightcones, supported by MAE_std on the global signal, though biases remain in power spectra and higher-order statistics.
-
Machine Learning for neutron source distributions
Generative models including VAEs, normalizing flows, GANs, and diffusion models can learn neutron source distributions from Monte Carlo lists for fast, memory-free sampling after training.