DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
Paper
•
2410.09344
•
Published
•
1
wenlong deng
dwenlong
·
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned
Models
authored
a paper
5 days ago
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via
Knowledge Graphs
authored
a paper
5 days ago
Token Hidden Reward: Steering Exploration-Exploitation in Group Relative
Deep Reinforcement Learning
Organizations
authored
4
papers
5 days ago
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Paper
•
2504.00993
•
Published
•
3
Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
Paper
•
2510.03669
•
Published
•
2
When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
Paper
•
2602.00344
•
Published
•
3
authored
a
paper
27 days ago