Dongjun Kim
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces SEC-bench Pro, a rigorous benchmark for evaluating LLM-based bug hunting on complex software, finding that even advanced agents struggle with long-horizon security tasks.
The paper introduces FoLoRA, a novel optimization framework that uses a generalized Rayleigh quotient to achieve a superior balance between adapting foundation models to specific tasks and preserving their general, pretraining-acquired capabilities.
The paper introduces FoLoRA, a novel optimization framework that uses a generalized Rayleigh quotient to achieve a superior balance between adapting foundation models to specific tasks and preserving their general, pretraining-acquired capabilities.
The paper proposes JOVE, an online framework that jointly assigns executor LLMs and selects intermediate outputs for paid verification to reduce latency and improve accuracy in complex reasoning queries.
Papers
JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs
Haoran Zhang, Dongjun Kim, Seohyeon Cha, Kevin S Chan +3 more
The paper proposes JOVE, an online framework that jointly assigns executor LLMs and selects intermediate outputs for paid verification to reduce latency and improve accuracy in complex reasoning queri…