Yanfeng Wang

Exploring Effective Mask Sampling Modeling for Neural Image Compression

2023 · arXiv (Cornell University)

Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy, but rarely address the channel redundancy. …

Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning

2023 · arXiv (Cornell University)

Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). To address the most challenging issue in this goal, i.e., catastrophic …

Federated Domain Generalization with Generalization Adjustment

2023

Federated Domain Generalization (FedDG) attempts to learn a global model in a privacy-preserving manner that generalizes well to new clients possibly with domain shift. Recent exploration mainly focuses on designing an unbiased training strategy within …

Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have demonstrated remarkable proficiency in human interactions, yet their application within the medical field remains insufficiently explored. Previous works mainly focus on the performance of medical knowledge with examinations, which is …

Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning

2024 · arXiv (Cornell University)

Noisy correspondence that refers to mismatches in cross-modal data pairs, is prevalent on human-annotated or web-crawled datasets. Prior approaches to leverage such data mainly consider the application of uni-modal noisy label learning without amending the …

Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models

2024 · arXiv (Cornell University)

Federated learning (FL) enables multiple parties to collaboratively fine-tune an large language model (LLM) without the need of direct data sharing. Ideally, by training on decentralized data that is aligned with human preferences and safety …

CS3-Bench: Evaluating and Enhancing Speech-to-Speech LLMS for Mandarin-English Code-Switching

2026

The advancement of multimodal large language models has accelerated the development of speech-to-speech interaction systems. While natural monolingual interaction has been achieved, we find existing models exhibit deficiencies in language alignment. In our proposed Code-Switching …