Jongwoo Ko

WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference

Revisiting Multi-Agent Debate as Test-Time Scaling: When Does Multi-Agent Help?

Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge

SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins

Understanding Bias Reinforcement in LLM Agents Debate

HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning