Kang Liu

13

Papers

163

Total Citations

Papers (13)

Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons

Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models

Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation

Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks

CITI: Enhancing Tool Utilizing Ability in Large Language Models Without Sacrificing General Performance

Capability Localization: Capabilities Can be Localized rather than Individual Knowledge

MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?

DFD: Distilling the Feature Disparity Differently for Detectors

Local Dense Logit Relations for Enhanced Knowledge Distillation

Adaptive Dual Guidance Knowledge Distillation

Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models

Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks