2 citations · 8 across the 13 of their papers we have counts for
13 papers
Heavy-Tailed Flow Matching via Random Clocks
Zhouhao Yang, Yezhen Wang, Kenji Kawaguchi +2
Heavy-tailed data arise in many domains where rare events carry disproportionate importance, such as imbalanced image datasets, financial returns, and weather extremes. Standard di…
DeRaDiff: Denoising Time Realignment of Diffusion Models
Ratnavibusena Don Shahain Manujith, Teoh Tze Tzun, Kenji Kawaguchi +1
Recent advances align diffusion models with human preferences to increase aesthetic appeal and mitigate artifacts and biases. Such methods aim to maximize a conditional output dist…
Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized
Er Jin, Yang Zhang, Yongli Mou +4
Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resembl…
Minimalist Concept Erasure in Generative Models
Yang Zhang, Er Jin, Yanfei Dong +5
Recent advances in generative models have demonstrated remarkable capabilities in producing high-quality images, but their reliance on large-scale unlabeled data has raised signifi…
Learnable Sparsity for Vision Generative Models
Yang Zhang, Er Jin, Wenzhong Liang +5
Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity a…
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
Haonan Wang, Qian Liu, Chao Du +4
Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de f…
Investigating Layer Importance in Large Language Models
Yang Zhang, Yanfei Dong, Kenji Kawaguchi
Large language models (LLMs) have gained increasing attention due to their prominent ability to understand and process texts. Nevertheless, LLMs largely remain opaque. The lack of…
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Qianli Shen, Yezhen Wang, Zhouhao Yang +6
Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems. As deep learning models continue to grow in size,…
FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
Yang Zhang, Yawei Li, Xinpeng Wang +5
Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compu…
Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models
Yang Zhang, Teoh Tze Tzun, Lim Wei Hern +2
Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle…
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
Haonan Wang, Qianli Shen, Yao Tong +2
The commercialization of text-to-image diffusion models (DMs) brings forth potential copyright concerns. Despite numerous attempts to protect DMs from copyright issues, the vulnera…
On Copyright Risks of Text-to-Image Diffusion Models
Yang Zhang, Teoh Tze Tzun, Lim Wei Hern +2
Diffusion models excel in many generative modeling tasks, notably in creating images from text prompts, a task referred to as text-to-image (T2I) generation. Despite the ability to…
AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Yang Zhang, Yawei Li, Hannah Brown +5
Feature attribution explains neural network outputs by identifying relevant input features. The attribution has to be faithful, meaning that the attributed features must mirror the…