LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
arXiv preprint arXiv:2303.07909 (2023) 3
12 Pith papers cite this work, alongside 76 external citations. Polarity classification is still indexing.
12
Pith papers citing it
76
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
PortraitGen integrates real-image exemplars into GRPO sampling and applies dual rewards (OmniReward and AI-Portrait) to improve photorealism, claiming better results than baselines on a new PortraitBench.
Super-Linear Advantage Shaping (SLAS) introduces a non-linear geometric policy update for RL post-training of text-to-image models that reshapes the local policy space via advantage-dependent Fisher-Rao weighting to reduce reward hacking and improve performance over GRPO baselines.
InfoTok uses mutual information constraints to regularize shared visual tokenization in unified MLLMs, improving both understanding and generation performance without extra training data.
EmoCtrl generates images faithful to content prompts while expressing target emotions via textual/visual enhancement modules and emotion-driven preference optimization.
MediSyn is a generalist latent diffusion model that synthesizes text-guided medical images across multiple specialties and modalities from public data and improves downstream classifiers in low-data settings.
A compact Chinese-native T2I U-Net (~0.387B) trained on Sugon K100, distilled to 4 steps, reports GenEval 0.69 and ~1.6–4.5s offline mobile generation.
A comprehensive public dataset of simulated Ariel exoplanet transmission spectra is released to benchmark detrending algorithms, with an ML baseline highlighting dataset shift risks.
Within-subjects study with 60 students found superior information retrieval and insight comprehension with GenAI-assisted data comics over conventional visualizations, independent of prior literacy, alongside engagement benefits and ethical concerns.
citing papers explorer
-
LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
-
Learning Interactive Real-World Simulators
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
-
PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation
PortraitGen integrates real-image exemplars into GRPO sampling and applies dual rewards (OmniReward and AI-Portrait) to improve photorealism, claiming better results than baselines on a new PortraitBench.
-
Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
Super-Linear Advantage Shaping (SLAS) introduces a non-linear geometric policy update for RL post-training of text-to-image models that reshapes the local policy space via advantage-dependent Fisher-Rao weighting to reduce reward hacking and improve performance over GRPO baselines.
-
InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs
InfoTok uses mutual information constraints to regularize shared visual tokenization in unified MLLMs, improving both understanding and generation performance without extra training data.
-
EmoCtrl: Controllable Emotional Image Content Generation
EmoCtrl generates images faithful to content prompts while expressing target emotions via textual/visual enhancement modules and emotion-driven preference optimization.
-
A Generalist Model for Diverse Text-Guided Medical Image Synthesis
MediSyn is a generalist latent diffusion model that synthesizes text-guided medical images across multiple specialties and modalities from public data and improves downstream classifiers in low-data settings.
-
JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators
A compact Chinese-native T2I U-Net (~0.387B) trained on Sugon K100, distilled to 4 steps, reports GenEval 0.69 and ~1.6–4.5s offline mobile generation.
-
A public dataset of Ariel simulated observations for developing exoplanetary atmosphere data reduction pipelines
A comprehensive public dataset of simulated Ariel exoplanet transmission spectra is released to benchmark detrending algorithms, with an ML baseline highlighting dataset shift risks.
-
Data Comics for Education: Evaluating Effectiveness, Benefits, and the Ethics of AI-Assisted Creation
Within-subjects study with 60 students found superior information retrieval and insight comprehension with GenAI-assisted data comics over conventional visualizations, independent of prior literacy, alongside engagement benefits and ethical concerns.
- Adversarial Concept Distillation for One-Step Diffusion Personalization
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation