Changyou Chen

Associate Professor@State University of New York at Buffalo·美国·OpenReview

研究方向

Multi-Modal Learning · Vision and Language · Foundation Models · Meta Learning · Deep Reinforcement Learning · Deep Generative Models · Large-scalable Bayesian Learning · Deep Learning · Bayesian Nonparametrics

Changyou Chen

Social Agents: Collective Intelligence Improves LLM Predictions

Bayesian Data Reweighting Improves Retrieval in Knowledge-Based VQA

MusiXQA: Advancing Visual Music Understanding in Multimodal LLMs

SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction

KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs

GUI‑AIMA: Aligning Intrinsic Multi-Modal Attention with a Context Anchor for GUI Grounding

A LLM-Refined Dynamic Topic Clustering Framework for Business Forecasts with Large Corpora

SPRO: Improving Image Generation via Self-Play

Teaching Human Behavior Improves Content Understanding Abilities Of VLMs

Measuring And Improving Engagement of Text-to-Image Generation Models

SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

LLaVA-Read: Enhancing Reading Ability of Multimodal Large Language Models

KidSpeak: A General Multi-Purpose LLM for Kids' Speech Recognition and Screening

Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements

Heterogeneous Federated Learning: A Dual Matching Dataset Distillation Approach