63 citations · 235 across the 69 of their papers we have counts for
17 papers · 1 filter
Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers
Chaofan Gan, Zicheng Zhao, Yuanpeng Tu +5
Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for visual generation. Recent observations reveal \emph{Massive Activations} (MAs) in their internal feat…
Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
Wei Wu, Xiaomeng Fan, Yuwei Wu +4
Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features fro…
Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
Haocheng Luo, Mehrtash Harandi, Dinh Phung +1
Sharpness-aware minimization (SAM) has emerged as a highly effective technique to improve model generalization, but its underlying principles are not fully understood. We investiga…
Curvature Learning for Generalization of Hyperbolic Neural Networks
Xiaomeng Fan, Yuwei Wu, Zhi Gao +2
Hyperbolic neural networks (HNNs) have demonstrated notable efficacy in representing real-world data with hierarchical structures via exploiting the geometric properties of hyperbo…
Advancements and Challenges in Continual Reinforcement Learning: A Comprehensive Review
Amara Zuffer, Michael Burke, Mehrtash Harandi
The diversity of tasks and dynamic nature of reinforcement learning (RL) require RL agents to be able to learn sequentially and continuously, a learning paradigm known as continuou…
Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces
Pengxiang Li, Yuwei Wu, Zhi Gao +5
Learning in hyperbolic spaces has attracted increasing attention due to its superior ability to model hierarchical structures of data. Most existing hyperbolic learning methods use…
A Set-to-Set Distance Measure in Hyperbolic Space
Pengxiang Li, Wei Wu, Zhi Gao +6
We propose a hyperbolic set-to-set distance measure for computing dissimilarity between sets in hyperbolic space. While point-to-point distances in hyperbolic space effectively cap…
Flashbacks to Harmonize Stability and Plasticity in Continual Learning
Leila Mahmoodi, Peyman Moghadam, Munawar Hayat +2
We introduce Flashback Learning (FL), a novel method designed to harmonize the stability and plasticity of models in Continual Learning (CL). Unlike prior approaches that primarily…
Exemplar-Free Continual Learning for State Space Models
Isaac Ning Lee, Leila Mahmoodi, Trung Le +1
State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. However, their evolving internal sta…
Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
Chaofan Gan, Yuanpeng Tu, Xi Chen +4
Pre-trained stable diffusion models (SD) have shown great advances in visual correspondence. In this paper, we investigate the capabilities of Diffusion Transformers (DiTs) for acc…
MoKD: Multi-Task Optimization for Knowledge Distillation
Zeeshan Hayder, Ali Cheraghian, Lars Petersson +1
Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges…
Optimizing Specific and Shared Parameters for Efficient Parameter Tuning
Van-Anh Nguyen, Thanh-Toan Do, Mehrtash Harandi +2
Foundation models, with a vast number of parameters and pretraining on massive datasets, achieve state-of-the-art performance across various applications. However, efficiently adap…
PCGS: Progressive Compression of 3D Gaussian Splatting
Yihang Chen, Mengyao Li, Qianyi Wu +3
3D Gaussian Splatting (3DGS) achieves impressive rendering fidelity and speed for novel view synthesis. However, its substantial data size poses a significant challenge for practic…
Learning from Noisy Labels with Contrastive Co-Transformer
Yan Han, Soumava Kumar Roy, Mehrtash Harandi +1
Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the prese…
Why Domain Generalization Fail? A View of Necessity and Sufficiency
Long-Tung Vuong, Vy Vo, Hien Dang +5
Despite a strong theoretical foundation, empirical experiments reveal that existing domain generalization (DG) algorithms often fail to consistently outperform the ERM baseline. We…
HAC++: Towards 100X Compression of 3D Gaussian Splatting
Yihang Chen, Qianyi Wu, Weiyao Lin +2
3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians an…
Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
Haocheng Luo, Tuan Truong, Tung Pham +3
Sharpness-Aware Minimization (SAM) has attracted significant attention for its effectiveness in improving generalization across various tasks. However, its underlying principles re…