Qi Chen

Source-Free Unsupervised Domain Adaptation with Hypothesis Consolidation of Prediction Rationale

2024 · arXiv (Cornell University)

Source-Free Unsupervised Domain Adaptation (SFUDA) is a challenging task where a model needs to be adapted to a new domain without access to target domain labels or source domain data. The primary difficulty in this …

Feature Selection for GPSR Based on Maximal Information Coefficient and Shapley Values

2024

Feature selection is a critical aspect of improving the interpretability of machine learning models. Genetic Programming (GP) has a built-in feature selection mechanism that explores the search space to include informative features in models. However, …

Integrative Decoding: Improve Factuality via Implicit Self-consistency

2024 · arXiv (Cornell University)

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models. Nonetheless, existing methods …

CIT: Rethinking Class-incremental Semantic Segmentation with a Class Independent Transformation

2024 · arXiv (Cornell University)

Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by distilling the current knowledge and incorporating the latest data. However, …

Research on Inference and Training Acceleration of Large Language Model

2024

Large language models have become an important research direction in the field of deep learning, and have received extensive attention from academia and industry. These models excel in natural language processing tasks, significantly improving the …

Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs

2025 · arXiv (Cornell University)

Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradicting source evidence, particularly due to inadequate localization reasoning. This work reveals a critical limitation in …