Kaixiong Zhou

8

Papers

8

Total Citations

Papers (8)

DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models

Flexible Group Count Enables Hassle-Free Structured Pruning

Knowledge Graphs Can be Learned with Just Intersection Features

Rethinking Independent Cross-Entropy Loss For Graph-Structured Data

TVE: Learning Meta-attribution for Transferable Vision Explainer

Soft Prompt Recovers Compressed LLMs, Transferably

GNNs Also Deserve Editing, and They Need It More Than Once

Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision