Blink of an eye: a simple theory for feature localization in generative models
Fuente:
arXiv
Guardado en:
| Autores principales: | Li, Marvin, Karan, Aayush, Chen, Sitan |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
Critical windows: non-asymptotic theory for feature emergence in diffusion models
por: Li, Marvin, et al.
Publicado: (2024)
por: Li, Marvin, et al.
Publicado: (2024)
ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems
por: Karan, Aayush, et al.
Publicado: (2025)
por: Karan, Aayush, et al.
Publicado: (2025)
Unrolled denoising networks provably learn optimal Bayesian inference
por: Karan, Aayush, et al.
Publicado: (2024)
por: Karan, Aayush, et al.
Publicado: (2024)
Reasoning with Sampling: Your Base Model is Smarter Than You Think
por: Karan, Aayush, et al.
Publicado: (2025)
por: Karan, Aayush, et al.
Publicado: (2025)
Provably learning a multi-head attention layer
por: Chen, Sitan, et al.
Publicado: (2024)
por: Chen, Sitan, et al.
Publicado: (2024)
What does guidance do? A fine-grained analysis in a simple setting
por: Chidambaram, Muthu, et al.
Publicado: (2024)
por: Chidambaram, Muthu, et al.
Publicado: (2024)
Optimal Inference Schedules for Masked Diffusion Models
por: Chen, Sitan, et al.
Publicado: (2025)
por: Chen, Sitan, et al.
Publicado: (2025)
A simple mean field model of feature learning
por: Göring, Niclas, et al.
Publicado: (2025)
por: Göring, Niclas, et al.
Publicado: (2025)
When does a predictor know its own loss?
por: Gollakota, Aravind, et al.
Publicado: (2025)
por: Gollakota, Aravind, et al.
Publicado: (2025)
Gradient dynamics for low-rank fine-tuning beyond kernels
por: Dayi, Arif Kerem, et al.
Publicado: (2024)
por: Dayi, Arif Kerem, et al.
Publicado: (2024)
High-accuracy and dimension-free sampling with diffusions
por: Gatmiry, Khashayar, et al.
Publicado: (2026)
por: Gatmiry, Khashayar, et al.
Publicado: (2026)
There is more to graphs than meets the eye: Learning universal features with self-supervision
por: Das, Laya, et al.
Publicado: (2023)
por: Das, Laya, et al.
Publicado: (2023)
Learning general Gaussian mixtures with efficient score matching
por: Chen, Sitan, et al.
Publicado: (2024)
por: Chen, Sitan, et al.
Publicado: (2024)
Efficient Pauli channel estimation with logarithmic quantum memory
por: Chen, Sitan, et al.
Publicado: (2023)
por: Chen, Sitan, et al.
Publicado: (2023)
A Hands-free Spatial Selection and Interaction Technique using Gaze and Blink Input with Blink Prediction for Extended Reality
por: Rolff, Tim, et al.
Publicado: (2025)
por: Rolff, Tim, et al.
Publicado: (2025)
Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Data
por: Mishra, Aayush, et al.
Publicado: (2025)
por: Mishra, Aayush, et al.
Publicado: (2025)
An optimal tradeoff between entanglement and copy complexity for state tomography
por: Chen, Sitan, et al.
Publicado: (2024)
por: Chen, Sitan, et al.
Publicado: (2024)
Optimal high-precision shadow estimation
por: Chen, Sitan, et al.
Publicado: (2024)
por: Chen, Sitan, et al.
Publicado: (2024)
Detecting Blinks in Healthy and Parkinson's EEG: A Deep Learning Perspective
por: Lensky, Artem, et al.
Publicado: (2025)
por: Lensky, Artem, et al.
Publicado: (2025)
Adaptivity can help exponentially for shadow tomography
por: Chen, Sitan, et al.
Publicado: (2024)
por: Chen, Sitan, et al.
Publicado: (2024)
Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
por: Gupta, Shivam, et al.
Publicado: (2024)
por: Gupta, Shivam, et al.
Publicado: (2024)
Assessing the Impact of Upselling in Online Fantasy Sports
por: Chaudhary, Aayush
Publicado: (2024)
por: Chaudhary, Aayush
Publicado: (2024)
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
por: Kim, Jaeyeon, et al.
Publicado: (2025)
por: Kim, Jaeyeon, et al.
Publicado: (2025)
S4S: Solving for a Diffusion Model Solver
por: Frankel, Eric, et al.
Publicado: (2025)
por: Frankel, Eric, et al.
Publicado: (2025)
Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
por: Kim, Jaeyeon, et al.
Publicado: (2026)
por: Kim, Jaeyeon, et al.
Publicado: (2026)
ODD: Overlap-aware Estimation of Model Performance under Distribution Shift
por: Mishra, Aayush, et al.
Publicado: (2025)
por: Mishra, Aayush, et al.
Publicado: (2025)
Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models
por: Tulinski, Thomas, et al.
Publicado: (2026)
por: Tulinski, Thomas, et al.
Publicado: (2026)
Selective Underfitting in Diffusion Models
por: Song, Kiwhan, et al.
Publicado: (2025)
por: Song, Kiwhan, et al.
Publicado: (2025)
Energy Efficient Protein Language Models: Leveraging Small Language Models with LoRA for Controllable Protein Generation
por: Shah, Aayush, et al.
Publicado: (2024)
por: Shah, Aayush, et al.
Publicado: (2024)
Modeling stochastic eye tracking data: A comparison of quantum generative adversarial networks and Markov models
por: Bhandari, Shailendra, et al.
Publicado: (2024)
por: Bhandari, Shailendra, et al.
Publicado: (2024)
Information-Computation Gaps in Quantum Learning via Low-Degree Likelihood
por: Chen, Sitan, et al.
Publicado: (2025)
por: Chen, Sitan, et al.
Publicado: (2025)
Stabilizer bootstrapping: A recipe for efficient agnostic tomography and magic estimation
por: Chen, Sitan, et al.
Publicado: (2024)
por: Chen, Sitan, et al.
Publicado: (2024)
Decorrelated feature importance from local sample weighting
por: Fröhlich, Benedikt, et al.
Publicado: (2025)
por: Fröhlich, Benedikt, et al.
Publicado: (2025)
Global Plane Waves From Local Gaussians: Periodic Charge Densities in a Blink
por: Elsborg, Jonas, et al.
Publicado: (2026)
por: Elsborg, Jonas, et al.
Publicado: (2026)
Don't trust your eyes: on the (un)reliability of feature visualizations
por: Geirhos, Robert, et al.
Publicado: (2023)
por: Geirhos, Robert, et al.
Publicado: (2023)
Sample-Optimal Agnostic Boosting with Unlabeled Data
por: Ghai, Udaya, et al.
Publicado: (2025)
por: Ghai, Udaya, et al.
Publicado: (2025)
Learning local discrete features in explainable-by-design convolutional neural networks
por: Kaplanoglou, Pantelis I., et al.
Publicado: (2024)
por: Kaplanoglou, Pantelis I., et al.
Publicado: (2024)
A solvable model of learning generative diffusion: theory and insights
por: Cui, Hugo, et al.
Publicado: (2025)
por: Cui, Hugo, et al.
Publicado: (2025)
Sublinear iterations can suffice even for DDPMs
por: Zhang, Matthew S., et al.
Publicado: (2025)
por: Zhang, Matthew S., et al.
Publicado: (2025)
LLM-based feature generation from text for interpretable machine learning
por: Balek, Vojtěch, et al.
Publicado: (2024)
por: Balek, Vojtěch, et al.
Publicado: (2024)
Ejemplares similares
-
Critical windows: non-asymptotic theory for feature emergence in diffusion models
por: Li, Marvin, et al.
Publicado: (2024) -
ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems
por: Karan, Aayush, et al.
Publicado: (2025) -
Unrolled denoising networks provably learn optimal Bayesian inference
por: Karan, Aayush, et al.
Publicado: (2024) -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
por: Karan, Aayush, et al.
Publicado: (2025) -
Provably learning a multi-head attention layer
por: Chen, Sitan, et al.
Publicado: (2024)