collaborators

7 papers

cs.CV2026

Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models

Tao Xia, Jiawei Liu, Yukun Zhang +3

Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image edit…

cs.AI2026

How Vision Becomes Language: A Layer-wise Information-Theoretic Analysis of Multimodal Reasoning

Hongxuan Wu, Yukun Zhang, Xueqing Zhou

When a multimodal Transformer answers a visual question, is the prediction driven by visual evidence, linguistic reasoning, or genuinely fused cross-modal computation -- and how do…

cs.LG2026

Where to Add PDE Diffusion in Transformers

Yukun Zhang, Xueqing Zhou

Transformers enable powerful content-based global routing via self-attention, but they lack an explicit local geometric prior along the sequence axis. As a result, the placement of…

cs.CL2025

Integrating Domain Knowledge for Financial QA: A Multi-Retriever RAG Approach with LLMs

Yukun Zhang, Stefan Elbl Droguett, Samyak Jain

This research project addresses the errors of financial numerical reasoning Question Answering (QA) tasks due to the lack of domain knowledge in finance. Despite recent advances in…

cs.LG2025

Understanding Transformer Architecture through Continuous Dynamics: A Partial Differential Equation Perspective

Yukun Zhang, Xueqing Zhou

The Transformer architecture has revolutionized artificial intelligence, yet a principled theoretical understanding of its internal mechanisms remains elusive. This paper introduce…

cs.LG2025

Continuous-Time Attention: PDE-Guided Mechanisms for Long-Sequence Transformers

Yukun Zhang, Xueqing Zhou

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of…