437 citations · 814 across the 15 of their papers we have counts for
9 papers · 1 filter
Panda: Test-Time Adaptation with Negative Data Augmentation
Ruxi Deng, Wenxuan Bao, Tianxin Wei +1
Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-t…
Graph4MM: Weaving Multimodal Learning with Structural Information
Xuying Ning, Dongqi Fu, Tianxin Wei +2
Real-world multimodal data usually exhibit complex structural relationships beyond traditional one-to-one mappings like image-caption pairs. Entities across modalities interact in…
NIRVANA: Structured Pruning Reimagined for Large Language Model Compression
Mengting Ai, Tianxin Wei, Sirui Chen +1
While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance…
LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation
Xinrui He, Yikun Ban, Jiaru Zou +3
Missing data imputation is a critical challenge in various domains, such as healthcare and finance, where data completeness is vital for accurate analysis. Large language models (L…
Meta Clustering of Neural Bandits
Yikun Ban, Yunzhe Qi, Tianxin Wei +2
The contextual bandit has been identified as a powerful framework to formulate the recommendation process as a sequential decision-making process, where each item is regarded as an…
Adaptive Test-Time Personalization for Federated Learning
Wenxuan Bao, Tianxin Wei, Haohan Wang +1
Personalized federated learning algorithms have shown promising results in adapting models to various distribution shifts. However, most of these methods require labeled data on te…
MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models
Mengting Ai, Tianxin Wei, Yifan Chen +2
Fine-tuning a pre-trained language model (PLM) emerges as the predominant strategy in many natural language processing applications. However, this process is known to be expensive,…
Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
Tianxin Wei, Yuning You, Tianlong Chen +3
This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (w…
Neural Collaborative Filtering Bandits via Meta Learning
Yikun Ban, Yunzhe Qi, Tianxin Wei +1
Contextual multi-armed bandits provide powerful tools to solve the exploitation-exploration dilemma in decision making, with direct applications in the personalized recommendation.…