collaborators

5 papers

cs.LG2026

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior

Zeyi Huang, Xuehai He, LiLiang Ren +8

We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as…

cs.CV2026

Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs

Zeyi Huang, Yuyang Ji, Xiaofang Wang +11

Long-form video understanding with Large Vision Language Models is challenged by the need to analyze temporally dispersed yet spatially concentrated key moments within limited cont…

cs.CV2025

IMPROVE: Iterative Model Pipeline Refinement and Optimization Leveraging LLM Experts

Eric Xue, Ke Chen, Zeyi Huang +2

Large language model (LLM) agents have emerged as a promising solution to automate the workflow of machine learning, but most existing methods share a common limitation: they attem…

cs.CV2025

VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection

Zeyi Huang, Yuyang Ji, Anirudh Sundara Rajan +5

We introduce VisTA, a new reinforcement learning framework that empowers visual agents to dynamically explore, select, and combine tools from a diverse library based on empirical p…

cs.CV2025

Do Vision Models Develop Human-Like Progressive Difficulty Understanding?

Zeyi Huang, Utkarsh Ojha, Yuyang Ji +2

When a human undertakes a test, their responses likely follow a pattern: if they answered an easy question incorrectly, they would likely answer a more difficult one…