AI.info

Jaehyung Kim

Explore Jaehyung Kim on AI.info.

• LookBack: Where and How to Score LVLM Responses via Visual Reference Usage
• Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
• Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
• SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation
• Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting
• Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
• Revisiting the UID Hypothesis in LLM Reasoning Traces
• Revisiting the Uniform Information Density Hypothesis in LLM Reasoning