QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
arXiv preprint arXiv:1412.69801412(6) (2014) 25
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Morpheus learns morphable category-level shape priors to produce implicit 3D correspondences in camera space without explicit supervision and releases the HouseCorr3D benchmark with amodal and symmetry annotations.
Split-MoPE integrates split learning with predefined-expert routing to maximize usable data in vertical federated learning under sample misalignment, delivering state-of-the-art accuracy in one communication round plus built-in robustness and per-sample contribution scores.
URF-GS creates a single radiation field from visual and wireless observations via 3D Gaussian splatting to predict radio signals at any location and configuration with higher accuracy and fewer samples than prior NeRF approaches.
LEAP is a transformer-based surrogate for multi-fluid MHD that predicts Europa plasma-induced magnetic perturbations with 2.6 nT test error and matches the parent model on Galileo E4/E14 flybys at 40,000x speedup.
DEFAR rectifies exposure bias in Flow Matching by treating bias signals as adaptive feedback for directional correction and low-frequency compensation, outperforming baselines on CIFAR-10, CelebA-64, and ImageNet.
A deep learning method with an enhanced physical degradation model incorporating anisotropic light spread and hidden skyglow, trained via generative models and synthetic-real coupling, removes light pollution from night cityscape images more effectively than prior restoration techniques.
citing papers explorer
-
QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers
QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
-
Category-Level 3D Correspondence in Camera Space via Morphable Object Priors
Morpheus learns morphable category-level shape priors to produce implicit 3D correspondences in camera space without explicit supervision and releases the HouseCorr3D benchmark with amodal and symmetry annotations.
-
Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning
Split-MoPE integrates split learning with predefined-expert routing to maximize usable data in vertical federated learning under sample misalignment, delivering state-of-the-art accuracy in one communication round plus built-in robustness and per-sample contribution scores.
-
Bridging Visual and Wireless Sensing via a Unified Radiation Field for 3D Radio Map Construction
URF-GS creates a single radiation field from visual and wireless observations via 3D Gaussian splatting to predict radio signals at any location and configuration with higher accuracy and fewer samples than prior NeRF approaches.
-
LEAP: A Rapid Neural Surrogate of Multi-Fluid MHD at Europa
LEAP is a transformer-based surrogate for multi-fluid MHD that predicts Europa plasma-induced magnetic perturbations with 2.6 nT test error and matches the parent model on Galileo E4/E14 flybys at 40,000x speedup.
-
Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
DEFAR rectifies exposure bias in Flow Matching by treating bias signals as adaptive feedback for directional correction and low-frequency compensation, outperforming baselines on CIFAR-10, CelebA-64, and ImageNet.
-
Deep Light Pollution Removal in Night Cityscape Photographs
A deep learning method with an enhanced physical degradation model incorporating anisotropic light spread and hidden skyglow, trained via generative models and synthetic-real coupling, removes light pollution from night cityscape images more effectively than prior restoration techniques.