generative-models

Tag

Cards List
#generative-models

LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction

arXiv cs.LG · 2d ago Cached

This paper introduces LC-GRPO, a flow-based GRPO framework with Langevin correction that bridges the train-inference gap by aligning stochastic training rollouts with deterministic ODE sampling, improving reward optimization on models like SD3.5, FLUX.1-Dev, and HunyuanVideo.

0 favorites 0 likes
#generative-models

Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models

arXiv cs.LG · 2d ago Cached

This paper shows that matching a marginal Gaussian prior in factorized generative models does not prevent conditional style leakage, where style latents carry class information. Multiple remedies are explored, but the authors conclude that marginal statistics alone cannot certify class-invariance.

0 favorites 0 likes
#generative-models

DiffImaginE: Imagine to Verify Entity Types with Diffusio

arXiv cs.AI · 4d ago Cached

DiffImaginE is a research paper proposing a diffusion-based verifier for multimodal named entity recognition, replacing deterministic imagination with conditional latent diffusion inference for more robust entity type verification.

0 favorites 0 likes
#generative-models

One-Sided Quantile Coupling for Flow Matching

arXiv cs.LG · 5d ago Cached

Proposes Quantile Coupling Flow Matching (QC-FM), a lightweight one-sided coupling that constructs source samples from data ranks along random directions without needing pairwise cost matrices or assignment. Achieves up to 12.9% FID improvement over baseline on CIFAR-10, CelebA, FFHQ, and ImageNet-64.

0 favorites 0 likes
#generative-models

StraightDP: Geometry-Aware Differential Privacy for Rectified-Flow Transformers

arXiv cs.LG · 6d ago Cached

This paper introduces StraightDP, a geometry-aware differential privacy framework for text-conditioned rectified-flow transformers. It partitions the privacy budget to release class-conditional moments and use DP-SGD, improving accuracy and FID over uniform DP training at strong privacy levels.

0 favorites 0 likes
#generative-models

Representations from Pretrained Machine-Learning Interatomic Potentials as Coarse Coordinates for Material Generation and Evaluation

arXiv cs.LG · 6d ago Cached

This paper proposes using atom-averaged features from pretrained MLIPs like MACE as coarse coordinates for evaluating and guiding inorganic crystal structure generation, introducing the Coarse-Fine Transport Distance (CFTD) metric that captures both quality and novelty in a distribution-based framework.

0 favorites 0 likes
#generative-models

PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective

arXiv cs.LG · 2026-07-31 Cached

This paper introduces PlatformBid, the first comprehensive auto-bidding benchmark designed from a unified advertising platform perspective, along with BidFlow, a novel flow-matching-based auto-bidding method. Experiments show BidFlow improves target cost by +0.68% in online tests on Kuaishou.

0 favorites 0 likes
#generative-models

Flow Map Learning via Nongradient Vector Flow

arXiv cs.LG · 2026-07-30 Cached

This paper introduces SGFlow, a method for learning flow maps for diffusion models that avoids invertibility constraints and backpropagation through model iterations, achieving competitive FID scores on CIFAR with a proven stationary-point guarantee.

0 favorites 0 likes
#generative-models

Concept-based Visual Counterfactual Explanations with Diffusion Models

arXiv cs.AI · 2026-07-28 Cached

Introduces C-VCE, a diffusion framework that builds an interpretable concept bottleneck layer into the generative model, enabling human-guided visual counterfactual explanations without relying on external noise-robust classifiers.

0 favorites 0 likes
#generative-models

From Score Approximation to Distribution Approximation in Score-Based Diffusion Models

arXiv cs.LG · 2026-07-27 Cached

This paper establishes a rigorous quantitative connection between neural network score function approximation and the resulting distribution approximation in score-based diffusion models, proving that accurate score approximation leads to close distribution approximation in KL divergence, with an explicit bound.

0 favorites 0 likes
#generative-models

Diffusion Models in Medical Image Inpainting: Challenges, Solution Taxonomy, and Future Directions

arXiv cs.CL · 2026-07-27 Cached

A systematic review of diffusion-based methods for medical image inpainting, covering architectures, applications, datasets, and evaluation strategies, with a proposed taxonomy and identification of challenges such as lack of standardized benchmarks.

0 favorites 0 likes
#generative-models

Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling

Hugging Face Daily Papers · 2026-07-26 Cached

Chamaileon introduces a framework for multi-target and multi-state protein binder design using contextualized sequence-structure co-modeling and mixed sampling, achieving adaptability across diverse conformational landscapes and multi-target requirements.

0 favorites 0 likes
#generative-models

On the Failure of Boundary-Seeking Distillation in Bottlenecked Generative Architectures

arXiv cs.LG · 2026-07-20 Cached

This paper investigates the failure of boundary-seeking knowledge distillation (CAKE) when applied to bottlenecked generative autoencoders, showing that the shared latent manifold creates gradient conflicts that prevent effective synthesis of contrastive samples. A simple noise forward pass baseline is proposed instead.

0 favorites 0 likes
#generative-models

Do Generative Models Keep Time? A Time-Aware Evaluation of Synthetic Sequential Tabular Data

arXiv cs.LG · 2026-07-20 Cached

This paper presents a taxonomy-guided evaluation protocol for assessing temporal fidelity in synthetic sequential tabular data, revealing that conventional evaluation overlooks temporal failures and that rankings differ substantially when time is considered.

0 favorites 0 likes
#generative-models

Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling

arXiv cs.LG · 2026-07-20 Cached

This position paper argues that probabilistic scaling of generative models is insufficient for quantum circuit generation due to strict mathematical constraints, and proposes verification-aware architectures that integrate formal methods.

0 favorites 0 likes
#generative-models

@aimalysheva: latent actions are having a moment, especially in robotics: instead of predicting a robot's actual joint commands or ga…

X AI KOLs Following · 2026-07-18 Cached

Latent actions are gaining traction in robotics as a way to learn from unlabeled video without action labels. Recent papers from DeepMind and FAIR demonstrate progress from controlled game environments to in-the-wild internet video, promising scalable training for imitation learning.

0 favorites 0 likes
#generative-models

HEDGEHOG: Hierarchical Evaluation of Drug Generators Through Rigorous Filtration

arXiv cs.LG · 2026-07-16 Cached

Introduces HEDGEHOG, a hierarchical benchmark for evaluating molecular generative models in drug discovery, revealing that only 0.65% of generated molecules pass all medicinal chemistry and docking filters.

0 favorites 0 likes
#generative-models

Conservation Laws for Diffusion Models

arXiv cs.LG · 2026-07-14 Cached

This paper develops conservation laws for diffusion models using generalized extrinsic information transfer (GEXIT) functions, showing that the cross-entropy can be characterized as an integral of local information-theoretic derivatives along the noise path, unifying likelihood characterization for discrete and continuous diffusion.

0 favorites 0 likes
#generative-models

Quantum Circuits in Diffusion Models: A Fair-Comparison Study and a Mechanistic Analysis of Angle-Embedding Failures

arXiv cs.LG · 2026-07-13 Cached

This paper presents a fair-comparison study of variational quantum circuits in diffusion models, introducing a squeeze-and-excitation scaffold to isolate quantum contributions. It finds functional parity with classical controls and identifies angle-embedding failures in score-based settings, offering a rigorous methodology and mechanistic analysis.

0 favorites 0 likes
#generative-models

Latent-Identity Tuning in Text-to-Image Personalization Models

Hugging Face Daily Papers · 2026-07-13 Cached

This paper presents a method for fine-grained identity tuning in text-to-image personalization models. It explores the latent space of a frozen encoder to enable localized, semantically coherent facial edits without additional training.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback