Yuchen Liu

Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting

2023 · arXiv (Cornell University)

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust AGgregation …

Gentopia: A Collaborative Platform for Tool-Augmented LLMs

2023 · arXiv (Cornell University)

Augmented Language Models (ALMs) empower large language models with the ability to use tools, transforming them into intelligent agents for real-world interactions. However, most existing frameworks for ALMs, to varying degrees, are deficient in the …

Cross-Prompt Adversarial Attack on Segment Anything Model

2024

Segment Anything Model (SAM) proposes promptable image segmentation based on various types of prompts like points and boxes. Although SAM presents impressive performance on segmentation and provides unparalleled versatility, it still suffers from the threat …

Consistency Adversarial Training for Robust Decision Boundaries

2024

Adversarial attacks pose a significant threat to the security of deep learning systems. While Adversarial Training (AT) has emerged as a prominent defense strategy, traditional AT methods focus primarily on training with loss-maximizing adversarial samples, …

SWE-GPT: A Process-Centric Language Model for Automated Software Improvement

2025 · Proceedings of the ACM on software engineering.

Large language models (LLMs) have demonstrated remarkable performance in code generation, significantly enhancing the coding efficiency of developers. Recent advancements in LLM-based agents have led to significant progress in end-to-end automatic software engineering (ASE), particularly …

End-to-End Speech Translation with Knowledge Distillation

2019

End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years.Compared to conventional pipepine systems, end-to-end ST models have advantages of lower latency, smaller …