64 citations · 152 across the 23 of their papers we have counts for
5 papers · 1 filter
PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
Jihwan Oh, Soowon Oh, Murad Aghazada +3
Persona prompting has been widely adopted to steer large language models (LLMs) behavior and improve their instruction performance by assigning specific characters. However, identi…
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Sangmin Bae, Yujin Kim, Reza Bayat +8
Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deployment expensive. Existing efficiency effo…
Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators
Jongwoo Ko, Sungnyun Kim, Sungwoo Cho +1
Human-generated reward signals are critical for aligning generative models with human preferences, guiding both training and inference-time evaluations. While large language models…
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
Jongwoo Ko, Tianyi Chen, Sungnyun Kim +4
Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies…
DistiLLM: Towards Streamlined Distillation for Large Language Models
Jongwoo Ko, Sungnyun Kim, Tianyi Chen +1
Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capab…