Picture for Bang An

Bang An

Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence

Add code
Jun 16, 2025
Viaarxiv icon

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles

Add code
May 28, 2025
Viaarxiv icon

AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security

Add code
Apr 29, 2025
Viaarxiv icon

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Add code
Apr 25, 2025
Viaarxiv icon

PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models

Add code
Mar 10, 2025
Viaarxiv icon

LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data

Add code
Dec 19, 2024
Viaarxiv icon

GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models through Statistically-Guided Geo-Prototyping

Add code
Dec 19, 2024
Viaarxiv icon

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion

Add code
Dec 16, 2024
Figure 1 for Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion
Figure 2 for Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion
Figure 3 for Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion
Figure 4 for Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion
Viaarxiv icon

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

Add code
Dec 04, 2024
Viaarxiv icon

Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine

Add code
Nov 20, 2024
Figure 1 for Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
Figure 2 for Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
Figure 3 for Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
Figure 4 for Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
Viaarxiv icon