J. Chen

GranCATs: Cross-Lingual Enhancement through Granularity-Specific Contrastive Adapters

2023

Multilingual language models (MLLMs) have demonstrated remarkable success in various cross-lingual downstream tasks, facilitating the transfer of knowledge across numerous languages, whereas this transfer is not universally effective. Our study reveals that while existing MLLMs …

Improved algorithm for a two-dimensional Darwin particle-in-cell code

2024 · arXiv (Cornell University)

A two-dimensional particle-in-cell code for simulation of low-frequency electromagnetic processes in laboratory plasmas has been developed. The code uses the Darwin method omitting the electromagnetic wave propagation. The Darwin method separates the electric field into …

ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models

2024 · arXiv (Cornell University)

Despite the recent breakthroughs achieved by Large Vision Language Models (LVLMs) in understanding and responding to complex visual-textual contexts, their inherent hallucination tendencies limit their practical application in real-world scenarios that demand high levels of …

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute

2025 · arXiv (Cornell University)

Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource-intensive models introduces significant deployment challenges in private environments, prompting a critical question: \textit{How can …