Efficiently distills pretrained text-to-image models without real data, improving FID and CLIP scores.
problem Slow iterative refinement process of diffusion-based text-to-image models.
method Guided Score identity Distillation with Long and Short Classifier-Free Guidance.
result Achieves state-of-the-art FID performance with competitive CLIP score.
SiD distills pretrained diffusion models into a fast one-step generator.
problem Efficiently distilling pretrained diffusion models into a fast generator.
method Reformulates forward diffusion processes as semi-implicit distributions and uses three score-related identities to create a loss mechanism.
result Achieves high FID performance and significantly reduces generation time.
Few-step distillation improves T2I models without real images or CFG trade-offs.
problem Challenges in accelerating T2I models with high-resolution and CFG.
method Score identity distillation (SiD) for few-step generation, with adversarial loss and new guidance strategies.
result State-of-the-art performance on SDXL at 1024x1024 resolution, robust to real images absence.
FasterVoiceGrad speeds up VC by 6-7x with novel distillation.
problem Slow iterative sampling in diffusion-based VC models.
method Adversarial diffusion conversion distillation (ADCD) to create a faster one-step model.
result 6.6-6.9 and 1.8x faster on GPU and CPU, respectively.
Few-step protein backbone generators reduce sampling time by over 20x.
problem Computational bottleneck in diffusion-based protein generation models.
method Score distillation adapted for protein backbone generation, combined with inference time noise modulation.
result Significant reduction in sampling time (20+ fold) while maintaining comparable performance.
Improved sampling efficiency for inverse problems using variance-reduced diffusion methods.
problem Efficiently estimating noisy scores in inverse problems.
method Developed a nonparametric self-normalized importance sampling estimator and a state-dependent blending rule.
result Improved sample quality for fixed simulation budgets in synthetic targets and PDE-governed inverse problems.
This paper improves credit scoring models using a novel dataset distillation technique.
problem Limited scalability of pretrained models for tabular credit scoring datasets.
method Integrates class imbalance-aware dataset distillation with pretrained models.
result Improved AUC by 2.5% in financial datasets.
Anti-Distillation improves reproducibility of deep networks by making ensemble predictions more diverse.
problem Deep networks are prone to high prediction differences, making them less reproducible.
method Anti-Distillation uses ensembles to force predictions to be more different and diverse.
result Anti-Distillation reduces prediction differences by making ensemble predictions more diverse.
SMT trains generative models by estimating mixture scores, outperforming existing methods.
problem Training one-step generative models efficiently and effectively.
method Score-of-Mixture Training (SMT) estimates the score of mixture distributions between real and fake samples.
result SMT/SMD outperform existing methods on CIFAR-10 and ImageNet 64x64 datasets.
Improved diffusion models using energy distillation and sequential Monte Carlo.
problem Training instability and inferior performance in energy parameterized diffusion models.
method Introduced a novel training regime for energy functions through distillation of pre-trained diffusion models, and cast the sampling procedure as a Feynman Kac model.
result Demonstrated improved performance and new sampling techniques.
Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from teacher to student during knowledge distillation. We find that a large amount of robu…
Black-box risk scoring models permeate our lives, yet are typically proprietary or opaque. We propose Distill-and-Compare, a model distillation and comparison approach to audit such models. To gain insight into black-box models, we treat them as teachers, training transparent student models to mimic the risk scores ass…
Survey of knowledge distillation for resource-limited devices.
problem Deploying large deep learning models on resource-limited devices.
method Knowledge distillation using a smaller model trained with information from a larger model.
result A new metric (distillation metric) for comparing different knowledge distillation algorithms.
DreamPropeller accelerates text-to-3D generation by 4.7x with minimal loss in quality.
problem Long generation times in text-to-3D generation algorithms degrade user experience.
method DreamPropeller uses Picard iterations generalized for non-ODE paths to accelerate parallel sampling.
result Empirically achieves up to 4.7x speedup with negligible quality loss.
Develops a framework for distilling flow models from few steps.
problem Improving few-step sampling in diffusion models for better performance.
method Local approximation errors and dynamical amplification controlled through analytical tractability.
result Deep residual compositions efficiently approximate long-horizon transport with controlled global error.
Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another. In particular, when the architectures are identical, this is called self-distillation. The idea is to feed in predictions of the trained model as new target values for retraining (and itera…
Improved generalization with iterative self-distillation using weighted ground-truth targets.
problem Improving generalization accuracy in neural networks.
method Iterative kernel regression with weighted ground-truth targets and ℓ2 regularization. result Closed-form solution for optimal weighting parameter and efficient estimation.
Unified scoring model improves efficiency and performance across multiple tasks.
problem Efficient and resource-efficient automated scoring for diverse tasks.
method Knowledge-distilled multi-task Mixture-of-Experts (MoE) approach.
result Comparable performance to task-specific models with significantly less storage and training resources.
EM Distillation simplifies diffusion models to one-step generators.
problem Efficient sampling from complex diffusion models with minimal loss of quality.
method EM Distillation, a maximum likelihood approach based on Expectation-Maximization.
result EM Distillation outperforms existing one-step generative methods in FID scores.
FED distills ensemble predictions efficiently, improving accuracy and uncertainty.
problem Efficiently distilling ensemble predictions from limited data.
method Proposes Functional Ensemble Distillation (FED) using mixup augmentation.
result Significantly boosts performance in accuracy and uncertainty estimation.
A new algorithm improves federated learning by combining knowledge distillation and weighted combination loss.
problem Non-IID client data in federated learning leads to model drift and poor generalization.
method pFedKD-WCL integrates knowledge distillation with bi-level optimization to address non-IID challenges.
result pFedKD-WCL outperforms state-of-the-art algorithms in accuracy and convergence speed.
Optimal self-distillation improves generative models' velocity risk and mode recovery.
problem Improving generative models' velocity risk and mode recovery.
method Proved optimal self-distillation for rectified flow via linear probing, derived mixing coefficient, and provided validation tuning.
result Optimal self-distillation improves velocity risk and mode recovery.
Extends denoising and score estimation to energy models via Tweedie's formula.
problem Linking denoising and score estimation for a wider range of distributions.
method Derives a fundamental identity connecting energy score derivatives and scores.
result Establishes a new identity for energy scores analogous to Tweedie's formula.
Paper proposes ensemble distillation for well-calibrated structured prediction.
problem Well-calibrated predictions are hard to achieve in structured prediction.
method Ensemble distillation framework for structured prediction.
result Ensemble distillation produces well-calibrated models with similar performance and calibration benefits to ensembles.
PLD distills knowledge using choice-theoretic Plackett-Luce model.
problem Model compression and knowledge transfer between large and small networks.
method PLD uses a weighted list-wise ranking loss based on the Plackett-Luce model.
result PLD achieves consistent gains across diverse architectures and distillation methods.
Kernel-Gradient Drifting improves generative modeling for non-Euclidean data.
problem Challenges in generative modeling for non-Euclidean data.
method Replaces Euclidean displacement with kernel-induced directions, exposing score-based structure.
result Kernel-gradient drifting enables state-of-the-art one-step generation for non-Euclidean data.
DLM-One speeds up language generation by 500x with continuous models.
problem Efficiently generating text sequences in natural language processing.
method Score-distillation of continuous diffusion language models.
result Achieves up to 500x speedup in inference time with competitive performance.
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
Instance- and Label-dependent label Noise (ILN) widely exists in real-world datasets but has been rarely studied. In this paper, we focus on Bounded Instance- and Label-dependent label Noise (BILN), a particular case of ILN where the label noise rates -- the probabilities that the true labels of examples flip into the …
DLC enhances distillation-based continual learning with lightweight plugins.
problem Stability-plasticity dilemma in distillation-based continual learning.
method DLC deploys lightweight residual plugins into the classifier-proximal layer of a shared feature extractor.
result Significant 8% accuracy gain on large-scale benchmarks with minimal parameter increase.
ProSMIN improves representation quality through probabilistic self-supervised learning.
problem Improving representation quality in self-supervised learning.
method ProSMIN uses two neural networks, online and target, to learn diverse representations through knowledge distillation and a modified scoring rule loss function.
result ProSMIN achieves superior accuracy and calibration on various downstream tasks.
Improves score estimation for noised targets using known clean scores.
problem Poor score estimation at low noise levels in Denoising Score Matching.
method Introduces Target Score Identity and Target Score Matching loss.
result Score estimates are more accurate at low noise levels.
Recent advances in pre-training huge models on large amounts of text through self supervision have obtained state-of-the-art results in various natural language processing tasks. However, these huge and expensive models are difficult to use in practise for downstream tasks. Some recent efforts use knowledge distillatio…
Recent state-of-the-art natural language understanding models, such as BERT and XLNet, score a pair of sentences (A and B) using multiple cross-attention operations - a process in which each word in sentence A attends to all words in sentence B and vice versa. As a result, computing the similarity between a query sente…
LSD distills high-quality samplers for DDMs with fewer steps.
problem Inefficient sampling in DDMs leads to low quality and high computational cost.
method LSD employs a distillation approach to train fast samplers with learnable coefficients and time schedules.
result LSD+ achieves higher sampling quality with fewer steps compared to existing samplers.
Generative framework improves causal estimation from observational data.
problem Estimating individualized treatment effects from non-randomized data.
method Importance-Weighted Diffusion Distillation (IWDD) combining diffusion models and IPW.
result IWDD achieves state-of-the-art prediction performance and significantly improves causal estimation.
It is often stated in papers tackling the task of inferring Bayesian network structures from data that there are these two distinct approaches: (i) Apply conditional independence tests when testing for the presence or otherwise of edges; (ii) Search the model space using a scoring metric. Here I argue that for complete…
Identity-link IRT improves TVD-MI scores without curvature violations.
problem Preserving additivity in TVD-MI scores for efficient LLM evaluation.
method Derives clipped-linear model from Gini entropy maximization, using identity link.
result Identity-link yields lower curvature violations (median curl 0.080-0.150) compared to probit/logit.
Framework detects brain tumors robustly from MRI images.
problem Low clinical incidence of brain tumor cases makes diagnosis challenging.
method YOLOv8n for detection, DeiT for classification, PTP metric for evaluation.
result F1-score of 0.92 achieved with reduced computational resources.
Algorithm optimizes biological sequences using bootstrapped training with a score-conditioned generator.
problem Optimizing biological sequences for a black-box score function.
method Bootstrapped training of score-conditioned generator (BootGen) algorithm.
result Our method outperforms competitive baselines on biological sequential design tasks.
A new filter reduces density fitting to a linear solve, improving performance on nonlinear systems.
problem Nonlinear Bayesian filtering challenges in representing belief distributions.
method Combines score matching with Stein's identity to avoid partition function evaluation.
result The Score Kalman Filter (SKF) outperforms existing methods on nonlinear systems.
Recent variants improve knowledge distillation performance.
problem Improving the performance of knowledge distillation.
method Introducing additional components or changing the learning process.
result These variants have shown promising results.
Despite their accuracy, neural network-based classifiers are still prone to manipulation through adversarial perturbations. Those perturbations are designed to be misclassified by the neural network, while being perceptually identical to some valid input. The vast majority of attack methods rely on white-box conditions…
Knowledge Distillation (KD) consists of transferring âknowledgeâ from one machine learning model (the teacher) to another (the student). Commonly, the teacher is a high-capacity model with formidable performance, while the student is more compact. By transferring knowledge, one hopes to benefit from the studentâs…
FedAUX improves Federated Learning by better using unlabeled data.
problem Improving Federated Learning performance with unlabeled data.
method FedAUX modifies FD training by unsupervised pre-training and private certainty scoring.
result FedAUX outperforms state-of-the-art Federated Learning methods.
ED-NeRF efficiently edits 3D scenes using latent space NeRF and improved loss functions.
problem Slow training speeds and inadequate editing loss functions in existing NeRF editing techniques.
method Embedding real-world scenes into latent space of LDM, using a unique refinement layer and an improved loss function.
result ED-NeRF achieves faster editing speed and improved output quality compared to state-of-the-art models.
User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predicting the label of identity pairs or selecting the most relevant identity pair based …
This study improves knowledge distillation for RNN-T models with noisy labels.
problem Challenges in distilling knowledge from RNN-T models with variable quality teachers.
method Full-sum distillation and sequence-level knowledge distillation.
result Full-sum distillation outperforms other methods for RNN-T models, especially for bad teachers.