generative-models

Tag

Cards List
#generative-models

Sparse Priors for Efficient Distribution Learning

arXiv cs.LG · 2d ago Cached

This paper introduces sparse priors to improve theoretical guarantees on distribution learning, showing that under a sparse prior, the sample complexity scales as Ω(√(k/n)) instead of O(n^{-1/Θ(d)}), thereby mitigating the curse of dimensionality.

0 favorites 0 likes
#generative-models

Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization

arXiv cs.LG · 5d ago Cached

The paper proposes a fast Bayesian optimization method for de novo discovery by leveraging linear models in latent spaces, achieving over 100x speedup over existing methods while maintaining performance.

0 favorites 0 likes
#generative-models

FlowATC: Aircraft Trajectory Prediction via Flow Matching

arXiv cs.LG · 2026-09-16 Cached

The paper introduces a flow-matching model for predicting aircraft trajectories using ADS-B data, achieving superior performance over traditional methods in probabilistic trajectory prediction.

0 favorites 0 likes
#generative-models

Generative models for simulation based filtering: Formulations and Empirical Comparisons

arXiv cs.LG · 2026-09-16 Cached

The paper presents a unified formulation and empirical comparison of generative-model approaches to nonlinear filtering, deriving new filters based on stochastic interpolants, flow-matching, and Schrödinger bridges, and comparing them against existing methods.

0 favorites 0 likes
#generative-models

New method enables AI for safety-critical situations

MIT News — Artificial Intelligence · 2026-09-14 Cached

MIT researchers have developed a new method called HardFlow that helps generative AI models satisfy strict safety and task-specific constraints in high-stakes applications by enforcing requirements only on the final output, improving performance in domains like robotics and control systems.

0 favorites 0 likes
#generative-models

DF26: We Cannot Tell Fake From Real Anymore

Hugging Face Daily Papers · 2026-09-07 Cached

The paper introduces DF26, a benchmark for detecting AI-generated public-speaking videos, showing that both humans and current detectors perform near chance, underscoring the need for improved robustness to generative model distribution shifts.

0 favorites 0 likes
#generative-models

Agentic Visual Generation: From Generative Models to Agentic Control

Hugging Face Daily Papers · 2026-09-06 Cached

This paper proposes a four-level framework classifying agentic visual generation systems based on the controller's direct decision scope over generation operations, from fixed support to experience-adaptive control.

0 favorites 0 likes
#generative-models

LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL

arXiv cs.LG · 2026-09-04 Cached

LeanGRPO eliminates redundant recomputation in diffusion RL methods by introducing recompute-free training schedules, achieving up to 1.83x speedup while preserving optimization objectives.

0 favorites 0 likes
#generative-models

Spectral characteristics of autoencoder parameters as a vector representation of data

arXiv cs.LG · 2026-09-04 Cached

This paper investigates the link between autoencoder parameters and data statistics, proposing that parameters can function as a vector representation of data, supported by theoretical analysis and experiments on CIFAR-10 and FashionMNIST.

0 favorites 0 likes
#generative-models

Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling

arXiv cs.LG · 2026-09-04 Cached

This paper introduces Quantile AlignTree Flow Matching (QAT-FM), a structured coupling method for flow matching that constructs hierarchical couplings using quantile-aligned trees to achieve non-crossing paths and efficient training for high-dimensional generative tasks.

0 favorites 0 likes
#generative-models

Portable Causal Fairness Across Synthetic Data Generator Families

arXiv cs.LG · 2026-09-04 Cached

This paper demonstrates that causal fairness mechanisms, specifically edge cuts on causal graphs, are portable across various synthetic data generator families including GANs and diffusion models, with minimal impact on data fidelity and utility.

0 favorites 0 likes
#generative-models

Do Large Language Models Capture the Diversity in their Training Data?

arXiv cs.CL · 2026-09-03 Cached

The paper investigates the conditional diversity gap in large language models by comparing the entropy of generated outputs with training data and proposes an information-theoretic framework to measure and mitigate this gap.

0 favorites 0 likes
#generative-models

Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization

arXiv cs.LG · 2026-09-02 Cached

The paper introduces Elite-Weighted Supervised Fine-tuning (EW-SFT), a method for goal-directed molecular optimization that uses reward to guide elite selection and updates via the model's native loss, applicable across various generative architectures and tasks.

0 favorites 0 likes
#generative-models

Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation

arXiv cs.CL · 2026-09-01 Cached

This paper investigates the effects of inference-time interventions and weight consolidation on open-ended AI generation, finding that training on value-filtered candidates improves mean quality but does not exceed classic heuristic performance.

0 favorites 0 likes
#generative-models

@goyalshaliniuk: Every AI System Is Built on Machine Learning Models From predicting trends to generating art, these 20 ML models are th…

X AI KOLs Timeline · 2026-08-28 Cached

This article provides an overview of 20 key machine learning models that underpin modern AI systems, explaining their roles in tasks from prediction to generative art.

0 favorites 0 likes
#generative-models

Gromov-Monge Flow Matching for Equivariant Graph Generation

arXiv cs.LG · 2026-08-28 Cached

This paper introduces Gromov-Monge flow matching for equivariant graph generation, improving sample quality with structure-aware couplings compatible with standard architectures.

0 favorites 0 likes
#generative-models

Self-Augmented Diffusion Guidance for Physics-Informed Generation

arXiv cs.LG · 2026-08-28 Cached

The paper proposes a self-augmented diffusion guidance method to incorporate physical laws into diffusion models, reducing deviations from true dynamics and enabling faster generation.

0 favorites 0 likes
#generative-models

GRAS: Guided Reduced-Variance Proposals and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion

arXiv cs.LG · 2026-08-28 Cached

GRAS is a training-free method for reward alignment in discrete diffusion models that reduces variance in guided proposals and adaptively selects particles, achieving state-of-the-art results on DNA and protein design tasks.

0 favorites 0 likes
#generative-models

Magpie: Real-Time World Renderer for Interactive Games

Hugging Face Daily Papers · 2026-08-27 Cached

Magpie is a real-time generative rendering system for interactive games that separates gameplay logic from visual generation to reduce asset production costs and preserve interactive designability.

0 favorites 0 likes
#generative-models

@r_de_santi: Generative models can’t discover what they can’t reach. We’re excited to introduce ActFlow: a continued pre-training sc…

X AI KOLs Timeline · 2026-08-26 Cached

The article introduces ActFlow, a continued pre-training scheme that expands the valid design space for flow and diffusion models, enabling out-of-distribution generative modeling and evolvable search spaces in scientific discovery.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback