Wei Lin

Tag2Vec: Learning Tag Representations in Tag Networks

2019 · arXiv (Cornell University)

Network embedding is a method to learn low-dimensional representation vectors for nodes in complex networks. In real networks, nodes may have multiple tags but existing methods ignore the abundant semantic and hierarchical information of tags. …

ActMAD: Activation Matching to Align Distributions for Test-Time-Training

2023

Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. We propose to perform this adaptation via Activation Matching (ActMAD): We analyze activations …

Llumnix: Dynamic Scheduling for Large Language Model Serving

2024 · arXiv (Cornell University)

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and unpredictable in terms …

Aligning Explanations for Recommendation with Rating and Feature via Maximizing Mutual Information

2024 · arXiv (Cornell University)

Providing natural language-based explanations to justify recommendations helps to improve users' satisfaction and gain users' trust. However, as current explanation generation methods are commonly trained with an objective to mimic existing user reviews, the generated …

Evaluation system for the effectiveness of college English curriculum teaching reform based on DPSIR model

2025 · International Journal of Continuing Engineering Education and Life-Long Learning

Inderscience is a global company, a dynamic leading independent journal publisher disseminates the latest research across the broad fields of science, engineering and technology; management, public and business administration; environment, ecological economics and sustainable development; …