Picture for Zhanhui Kang

Zhanhui Kang

Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data

Add code
Jul 04, 2024
Viaarxiv icon

Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback

Add code
Jun 18, 2024
Viaarxiv icon

DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedback

Add code
May 24, 2024
Viaarxiv icon

ID-centric Pre-training for Recommendation

Add code
May 07, 2024
Figure 1 for ID-centric Pre-training for Recommendation
Figure 2 for ID-centric Pre-training for Recommendation
Figure 3 for ID-centric Pre-training for Recommendation
Figure 4 for ID-centric Pre-training for Recommendation
Viaarxiv icon

The Elephant in the Room: Rethinking the Usage of Pre-trained Language Model in Sequential Recommendation

Add code
Apr 12, 2024
Viaarxiv icon

PhD: A Prompted Visual Hallucination Evaluation Dataset

Add code
Mar 17, 2024
Figure 1 for PhD: A Prompted Visual Hallucination Evaluation Dataset
Figure 2 for PhD: A Prompted Visual Hallucination Evaluation Dataset
Figure 3 for PhD: A Prompted Visual Hallucination Evaluation Dataset
Figure 4 for PhD: A Prompted Visual Hallucination Evaluation Dataset
Viaarxiv icon

EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs

Add code
Mar 05, 2024
Figure 1 for EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
Figure 2 for EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
Figure 3 for EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
Figure 4 for EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
Viaarxiv icon

Plug-in Diffusion Model for Sequential Recommendation

Add code
Jan 05, 2024
Figure 1 for Plug-in Diffusion Model for Sequential Recommendation
Figure 2 for Plug-in Diffusion Model for Sequential Recommendation
Figure 3 for Plug-in Diffusion Model for Sequential Recommendation
Figure 4 for Plug-in Diffusion Model for Sequential Recommendation
Viaarxiv icon

Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning

Add code
Dec 29, 2023
Viaarxiv icon

E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity

Add code
Oct 24, 2023
Figure 1 for E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity
Figure 2 for E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity
Figure 3 for E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity
Figure 4 for E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity
Viaarxiv icon