30 papers
Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation
Chaofan Gan, Zicheng Zhao, Yuanpeng Tu +6
Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently und…
Reliability-Prioritized Fine-Grained Generation in Multimodal Large
Xiaomeng Fan, Wei Wu, Yuwei Wu +9
Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptions of visual content. However, we observe and theoretically show that generati…
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…
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…
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
Jie Hong, Shi Qiu, Weihao Li +4
Point cloud learning is receiving increasing attention. However, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown object…
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…