collaborators

6 papers

cs.CV2025

Towards Long-window Anchoring in Vision-Language Model Distillation

Haoyi Zhou, Shuo Li, Tianyu Chen +3

While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited wind…

cs.LG2025

FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers

Tianyu Chen, Haoyi Zhou, Ying Li +5

Fourier Neural Operators (FNO) have emerged as promising solutions for efficiently solving partial differential equations (PDEs) by learning infinite-dimensional function mappings…

cs.CL2025

Instructing the Architecture Search for Spatial-temporal Sequence Forecasting with LLM

Xin Xue, Haoyi Zhou, Tianyu Chen +3

Spatial-temporal sequence forecasting (STSF) is a long-standing research problem with widespread real-world applications. Neural architecture search (NAS), which automates the neur…

cs.LG2025

Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding

Tianyu Chen, Xingcheng Fu, Yisen Gao +5

Modern vision-language models (VLMs) develop patch embedding and convolution backbone within vector space, especially Euclidean ones, at the very founding. When expanding VLMs to a…

cs.CE2025

PINNsAgent: Automated PDE Surrogation with Large Language Models

Qingpo Wuwu, Chonghan Gao, Tianyu Chen +6

Solving partial differential equations (PDEs) using neural methods has been a long-standing scientific and engineering research pursuit. Physics-Informed Neural Networks (PINNs) ha…

cs.CL2024

From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning

Pusen Dong, Tianchen Zhu, Yue Qiu +2

Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for p…