Charles Fleming

Command-V: Training-Free Representation Finetuning Transfer

Membership Inference Attacks Against Fine-tuned Diffusion Language Models

NetBurst: Event-Centric Forecasting of Bursty, Intermittent Time Series

CAR-LoRA: Training Compression-Aware and Robust LoRA Adapters for Evolving LLMs

The Adaptive Interrogator: Detecting Trojan LLMs in Multi-Agent Systems via Evolved Conversational Strategies

Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization

Beyond Invariance: A Feature-Strength Framework for OOD Generalization

Probing Hidden Knowledge Holes in Unlearned LLMs

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains

Robust Quantum Neural Networks Against Dynamic Noise Landscape in the NISQ Era