collaborators

5 papers

cs.LG2026

CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry

Huzama Ahmad, Cao Viet Hai Nam, Se-Young Yun

Deep Transformers are composed of uniformly stacked residual blocks, yet their deepest layers often add little value. We present two efficiency methods that exploit this asymmetry.…

cs.LG2026

SpotAttention: Plug-In Block-Sparse Routing for Pretrained Long-Context Transformers

Huzama Ahmad, Se-Young Yun

Long contexts have become standard in pretrained LLMs, yet they remain expensive to run: prefill compute grows quadratically with sequence length, and every decode step re-reads a…

cs.LG2026

Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting

Soowon Oh, Nam Cao, Yujin Kim +4

Block-diffusion drafters have recently emerged as a powerful alternative for speculative decoding by predicting multiple future-token distributions in a single parallel step. Howev…

cs.CV2025

Diffusion Models Through a Global Lens: Are They Culturally Inclusive?

Zahra Bayramli, Ayhan Suleymanzade, Na Min An +5

Text-to-image diffusion models have recently enabled the creation of visually compelling, detailed images from textual prompts. However, their ability to accurately represent vario…

cs.CL2025

When Tom Eats Kimchi: Evaluating Cultural Bias of Multimodal Large Language Models in Cultural Mixture Contexts

Jun Seong Kim, Kyaw Ye Thu, Javad Ismayilzada +6

In a highly globalized world, it is important for multi-modal large language models (MLLMs) to recognize and respond correctly to mixed-cultural inputs. For example, a model should…