Search Results for author:
Found 35 papers, 24 papers with code
InfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive Regularizers
This contrastive regularizer is inspired by a natural notion of disentanglement: latent traversal.
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
As the first work to demonstrate the possibility of one-step generation for image AR models, DD challenges the prevailing notion that AR models are inherently slow, and opens up new opportunities for efficient AR generation.
GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
To avoid hallucination of a single MLLM agent, we decompose this stage to four sequentially-executed MLLM-based agents: verification agent, suggestion agent, correction agent, and output structuring agent.
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
To provide comprehensive and practical evaluations on the safety of code agents, we propose RedCode, a benchmark for risky code execution and generation: (1) RedCode-Exec provides challenging prompts that could lead to risky code execution, aiming to evaluate code agents' ability to recognize and handle unsafe code.
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
For example, we demonstrate that pruning up to 75% of experts in Mixtral $8\times7$B-Instruct results in a substantial reduction in parameters with minimal performance loss.
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
We reveal some findings: (1) Teaching materials that make it easier for students to learn have clearer and more accurate logic when using in-context learning as the student's "learning" method; (2) Weak-to-strong generalization: LbT might help improve strong models by teaching weak models; (3) Diversity in students might help: teaching multiple students could be better than teaching one student or the teacher itself.
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Diffusion transformers (DiTs) have exhibited remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions.
Improving the Training of Rectified Flows
In this work, we propose improved techniques for training rectified flows, allowing them to compete with \emph{knowledge distillation} methods even in the low NFE setting.
Ranked #21 on
Image Generation
on ImageNet 64x64
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Finally, we develop an integer-programming-based method to conduct bit-width allocation.
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
For example, LCSC achieves better performance using 1 number of function evaluation (NFE) than the base model with 2 NFE on consistency distillation, and decreases the NFE of DM from 15 to 9 while maintaining the generation quality on CIFAR-10.
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
In recent years, there has been significant progress in the development of text-to-image generative models.
Efficiently Computing Similarities to Private Datasets
We abstract out this common subroutine and study the following fundamental algorithmic problem: Given a similarity function $f$ and a large high-dimensional private dataset $X \subset \mathbb{R}^d$, output a differentially private (DP) data structure which approximates $\sum_{x \in X} f(x, y)$ for any query $y$.
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Lin et al. (2024) recently introduced the Private Evolution (PE) algorithm to generate DP synthetic images with only API access to diffusion models.
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
By using MoLE existing linear-centric models can achieve SOTA LTSF results in 68% of the experiments that PatchTST reports and we compare to, whereas existing single-head linear-centric models achieve SOTA results in only 25% of cases.
Ranked #1 on
Time Series Forecasting
on Electricity (720)
Enhanced Index-Based Feedback Overhead Reduction for WLANs
Compressed beamforming algorithm is used in the current Wi-Fi standard to reduce the beamforming feedback overhead (BFO).
An Unsupervised Machine Learning Scheme for Index-Based CSI Feedback in Wi-Fi
We explore several methods that consider different representations of the data in the candidate set.
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Our results demonstrate that our algorithm can achieve competitive performance with strong privacy levels.
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
This work aims at decreasing the end-to-end generation latency of large language models (LLMs).
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Yet, while the literature on the trustworthiness of GPT models remains limited, practitioners have proposed employing capable GPT models for sensitive applications such as healthcare and finance -- where mistakes can be costly.
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Diffusion probabilistic models (DPMs) are a new class of generative models that have achieved state-of-the-art generation quality in various domains.
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
We further demonstrate the promise of applying PE on large foundation models such as Stable Diffusion to tackle challenging private datasets with a small number of high-resolution images.
Selective Pre-training for Private Fine-tuning
In this work, we show that a careful pre-training on a \emph{subset} of the public dataset that is guided by the private dataset is crucial to train small language models with differential privacy.
Bounding System-Induced Biases in Recommender Systems with A Randomized Dataset
To bridge this gap, we study the debiasing problem from a new perspective and propose to directly minimize the upper bound of an ideal objective function, which facilitates a better potential solution to the system-induced biases.
Summary Statistic Privacy in Data Sharing
We study a setting where a data holder wishes to share data with a receiver, without revealing certain summary statistics of the data distribution (e. g., mean, standard deviation).
On the Privacy Properties of GAN-generated Samples
By drawing connections to the generalization properties of GANs, we prove that under some assumptions, GAN-generated samples inherently satisfy some (weak) privacy guarantees.
RareGAN: Generating Samples for Rare Classes
We study the problem of learning generative adversarial networks (GANs) for a rare class of an unlabeled dataset subject to a labeling budget.
Intelligent Feedback Overhead Reduction (iFOR) in Wi-Fi 7 and Beyond
The IEEE 802. 11 standard based wireless local area networks (WLANs) or Wi-Fi networks are critical to provide internet access in today's world.
Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions
A Pareto GAN leverages extreme value theory and the functional properties of neural networks to learn a distribution that matches the asymptotic behavior of the marginal distributions of the features.
MLGO: a Machine Learning Guided Compiler Optimizations Framework
Leveraging machine-learning (ML) techniques for compiler optimizations has been widely studied and explored in academia.
Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
Spectral normalization (SN) is a widely-used technique for improving the stability and sample quality of Generative Adversarial Networks (GANs).
Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
By shedding light on the promise and challenges, we hope our work can rekindle the conversation on workflows for data sharing.
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution.
Robustness of Conditional GANs to Noisy Labels
When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN).
RNN-SM: Fast Steganalysis of VoIP Streams Using Recurrent Neural Network
Experiments show that on full embedding rate samples, RNN-SM is of high detection accuracy, which remains over 90% even when the sample is as short as 0. 1 s, and is significantly higher than other state-of-the-art methods.
PacGAN: The power of two samples in generative adversarial networks
Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples.
