Yifan Yang

Cross-Modal Knowledge Distillation For Fine-Grained One-Shot Classification

2021

Few-shot learning can recognize a novel category based on only a few samples because it learns to learn from a lot of labeled samples during the training process. When data is insufficient, the performance is …

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game

2023 · arXiv (Cornell University)

Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However, continuously updating LLMs for …

Comparative analysis of strategies of knowledge distillation on BERT for text matching

2024 · Applied and Computational Engineering

Large language model is a highly effective and promising language model technology that can improve the performance and robustness of natural language processing tasks. As a representative work, Bidirectional Encoder Representations from Transformers (BERT) has …

Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions

2025 · arXiv (Cornell University)

Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing …