Search Results for author:
Found 16 papers, 5 papers with code
Pegasus-v1 Technical Report
This technical report introduces Pegasus-1, a multimodal language model specialized in video content understanding and interaction through natural language.
Denoising Task Difficulty-based Curriculum for Training Diffusion Models
By organizing timesteps or noise levels into clusters and training models with descending orders of difficulty, we facilitate an order-aware training regime, progressing from easier to harder denoising tasks, thereby deviating from the conventional approach of training diffusion models simultaneously across all timesteps.
Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts
To achieve this, we employ a sparse mixture-of-experts within each transformer block to utilize semantic information and facilitate handling conflicts in tasks through parameter isolation.
HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D
This work introduces HarmonyView, a simple yet effective diffusion sampling technique adept at decomposing two intricate aspects in single-image 3D generation: consistency and diversity.
Denoising Task Routing for Diffusion Models
Diffusion models generate highly realistic images by learning a multi-step denoising process, naturally embodying the principles of multi-task learning (MTL).
Multi-Architecture Multi-Expert Diffusion Models
In this paper, we address the performance degradation of efficient diffusion models by introducing Multi-architecturE Multi-Expert diffusion models (MEME).
ScoreCL: Augmentation-Adaptive Contrastive Learning via Score-Matching Function
Self-supervised contrastive learning (CL) has achieved state-of-the-art performance in representation learning by minimizing the distance between positive pairs while maximizing that of negative ones.
Addressing Negative Transfer in Diffusion Models
Through this, our approach addresses the issue of negative transfer in diffusion models by allowing for efficient computation of MTL methods.
Cross Encoding as Augmentation: Towards Effective Educational Text Classification
To mitigate these issues, here we propose a novel retrieval approach CEAA that provides effective learning in educational text classification.
Evaluation of Question Generation Needs More References
To this end, we propose to paraphrase the reference question for a more robust QG evaluation.
Towards Practical Plug-and-Play Diffusion Models
For that, the existing practice is to fine-tune the guidance models with labeled data corrupted with noises.
Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling
In addition, through Fourier analysis of feature maps, the model's response patterns according to signal frequency changes, we observe which inductive bias is advantageous for each data scale.
Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis
Although recent methods generate high-quality novel views, synthesizing with only one explicit or implicit 3D geometry has a trade-off between two objectives that we call the "seesaw" problem: 1) preserving reprojected contents and 2) completing realistic out-of-view regions.
Geometrically Adaptive Dictionary Attack on Face Recognition
We apply the GADA strategy to two existing attack methods and show overwhelming performance improvement in the experiments on the LFW and CPLFW datasets.
Residual-Guided Learning Representation for Self-Supervised Monocular Depth Estimation
In this paper, we propose residual guidance loss that enables the depth estimation network to embed the discriminative feature by transferring the discriminability of auto-encoded features.
On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attacks
In this paper, we pay attention to an implicit assumption of query-based black-box adversarial attacks that the target model's output exactly corresponds to the query input.
