Search Results for author:
Found 29 papers, 8 papers with code
Rethinking Diverse Human Preference Learning through Principal Component Analysis
Understanding human preferences is crucial for improving foundation models and building personalized AI systems.
Latent Radiance Fields with 3D-aware 2D Representations
The framework consists of three stages: (1) a correspondence-aware autoencoding method that enhances the 3D consistency of 2D latent representations, (2) a latent radiance field (LRF) that lifts these 3D-aware 2D representations into 3D space, and (3) a VAE-Radiance Field (VAE-RF) alignment strategy that improves image decoding from the rendered 2D representations.
UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
In this paper, we propose UIBDiffusion, the universal imperceptible backdoor attack for diffusion models, which allows us to achieve superior attack and generation performance while evading state-of-the-art defenses.
Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error.
Robust Decision Transformer: Tackling Data Corruption in Offline RL via Sequence Modeling
These results highlight the potential of robust sequence modeling for learning from noisy or corrupted offline datasets, thereby promoting the reliable application of offline RL in real-world tasks.
V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation
In our work on portrait video generation, we identified audio signals as particularly weak, often overshadowed by stronger signals such as facial pose and reference image.
Unified Directly Denoising for Both Variance Preserving and Variance Exploding Diffusion Models
Here, we propose a unified DDDM (uDDDM) framework that generates images in one-step/multiple steps for both Variance Preserving (VP) and Variance Exploding (VE) cases.
Directly Denoising Diffusion Models
In this paper, we present the Directly Denoising Diffusion Model (DDDM): a simple and generic approach for generating realistic images with few-step sampling, while multistep sampling is still preserved for better performance.
Unsupervised Microscopy Video Denoising
In this paper, we introduce a novel unsupervised network to denoise microscopy videos featured by image sequences captured by a fixed location microscopy camera.
Effectively Prompting Small-sized Language Models for Cross-lingual Tasks via Winning Tickets
Then, we prepend soft prompts to the original pre-trained language model and only update the selected parameters together with prompt-related parameters when adapting to the downstream tasks.
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems.
Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective
To address this, we define a fair pruning task where a sparse model is derived subject to fairness requirements.
Is GPT Powerful Enough to Analyze the Emotions of Memes?
Large Language Models (LLMs), representing a significant achievement in artificial intelligence (AI) research, have demonstrated their ability in a multitude of tasks.
Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach
To alleviate the huge computational cost required by pixel-based diffusion SR, latent-based methods utilize a feature encoder to transform the image and then implement the SR image generation in a compact latent space.
LIVABLE: Exploring Long-Tailed Classification of Software Vulnerability Types
(2) adaptive re-weighting module, which adjusts the learning weights for different types according to the training epochs and numbers of associated samples by a novel training loss.
Contrastive Representation Disentanglement for Clustering
We conduct a theoretical analysis of the proposed loss and highlight how it assigns different weights to negative samples during the process of disentangling the feature representation.
Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model
In this paper, we propose Multi-level Multilingual Knowledge Distillation (MMKD), a novel method for improving multilingual language models.
Understanding and Measuring Robustness of Multimodal Learning
We then introduce a new type of multimodal adversarial attacks called decoupling attack in MUROAN that aims to compromise multimodal models by decoupling their fused modalities.
Sk-Unet Model with Fourier Domain for Mitosis Detection
Mitotic count is the most important morphological feature of breast cancer grading.
MHER: Model-based Hindsight Experience Replay
Replacing original goals with virtual goals generated from interaction with a trained dynamics model leads to a novel relabeling method, model-based relabeling (MBR).
A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation
Experiments also show that our proposed method achieves competitive performance compared to existing boundary-based methods with a lightweight design and a simple pipeline.
Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning
Two main challenges in multi-goal reinforcement learning are sparse rewards and sample inefficiency.
Multi-level Knowledge Distillation via Knowledge Alignment and Correlation
While it is important to transfer the full knowledge from teacher to student, we introduce the Multi-level Knowledge Distillation (MLKD) by effectively considering both knowledge alignment and correlation.
Second-order Neural Network Training Using Complex-step Directional Derivative
We believe our method will inspire a wide-range of new algorithms for deep learning and numerical optimization.
An STPA-based Approach for Systematic Security Analysis of In-vehicle Diagnostic and Software Update Systems
In this paper, a system-oriented approach is proposed on the basis of the System-Theoretic Process Analysis (STPA).
Cryptography and Security Software Engineering Systems and Control Systems and Control
Double cycle-consistent generative adversarial network for unsupervised conditional generation
We enforce the encoder and the generator of GAN to form an encoder-generator pair in addition to the generator-encoder pair, which enables us to avoid the low-diversity generation and the triviality of latent features.
Community Detection on Networks with Ricci Flow
Many complex networks in the real world have community structures -- groups of well-connected nodes with important functional roles.
Social and Information Networks Physics and Society
CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior
The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks.
Variational Principles for Minkowski Type Problems, Discrete Optimal Transport, and Discrete Monge-Ampere Equations
In this paper, we develop several related finite dimensional variational principles for discrete optimal transport (DOT), Minkowski type problems for convex polytopes and discrete Monge-Ampere equation (DMAE).
Geometric Topology Differential Geometry Metric Geometry 52-XX I.3.5
