collaborators

26 papers

cs.LG2026

Efficient Test-Time Scaling for LLM-based Time Series Forecasting

Xuan-May Le, Minh-Tuan Tran, Ling Luo +3

Long-term time series forecasting benefits from preserving global structure such as trends and seasonality. Recent LLM-based forecasters often improve accuracy through test-time sc…

cs.CV2026

Hi-DREAM: Brain-Inspired Hierarchical Diffusion for fMRI-to-Image Reconstruction via ROI Encoder and VisuAl Mapping

Guowei Zhang, Yun Zhao, Kai Sun +4

Reconstructing natural images from fMRI requires bridging neural activity with both the structural and semantic representations used by modern generative models. Existing diffusion…

cs.CV2026

Adaptive Subspace Projection for Generative Personalization

Van-Anh Nguyen, Anh Tuan Bui, Tamas Abraham +5

Generative personalization often suffers from the semantic collapsing problem (SCP), where a learned personalized concept overpowers the rest of the text prompt, causing the model…

cs.LG2026

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

Quyen Tran, Hai Nguyen, Hoang Phan +6

In online incremental learning, data continuously arrives with substantial distributional shifts, creating a significant challenge because previous samples have limited replay valu…

cs.LG2026

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…

cs.CV2026

Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling

Minh-Tuan Tran, Xuan-May Le, Quan Hung Tran +3

Existing generative models, such as diffusion and auto-regressive networks, are inherently static, relying on a fixed set of pretrained parameters to handle all inputs. In contrast…