Charles Fleming

6

Papers

10

Total Citations

Papers (6)

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

Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model

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

Targeted Forgetting of Image Subgroups in CLIP Models

Probing Hidden Knowledge Holes in Unlearned LLMs

Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities