Publications
We not only work independently but also collaborate closely with individuals from academia to advance our research.
*Participant name in bold works at KRAFTON
Filter
How to Correctly Report LLM-as-a-Judge Evaluations
How to Correctly Report LLM-as-a-Judge Evaluations
ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
Coverage Improvement and Fast Convergence of On-policy Preference Learning
Coverage Improvement and Fast Convergence of On-policy Preference Learning
Zeroth-Order Optimization at the Edge of Stability
Zeroth-Order Optimization at the Edge of Stability
Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
Secure Inference for Diffusion Models via Unconditional Scores
