1 citations · 2 across the 5 of their papers we have counts for
7 papers
Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking
Taehyeon Kim, Hyunsoo Lee, Youngsoo Jang +1
Large reasoning models (LRMs) achieve strong performance by externalizing explicit reasoning traces before producing the answer, yet suffer from overthinking challenge that allocat…
Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution
Ahin Lee, Jinwoo Seo, Youngsoo Jang +1
Visual disruptions can arise while a robot is executing a task, leaving a vision-language-action (VLA) policy to respond without knowing the disruption type or timing. We introduce…
A Regret Minimization Framework on Preference Learning in Large Language Models
Suhwan Kim, Taehyun Cho, Geon-Hyeong Kim +4
Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness sig…
SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning
Taewook Nam, Junmo Cho, Youngsoo Jang +1
Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to collect demonstrations through human opera…
SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety
Geon-Hyeong Kim, Yu Jin Kim, Byoungjip Kim +4
As Large Language Models (LLMs) are increasingly deployed in real-world applications, balancing helpfulness and safety has become a central challenge. A natural approach is to inco…
Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments
Sangwoo Shin, Seunghyun Kim, Youngsoo Jang +2
In embodied instruction-following (EIF), the integration of pretrained language models (LMs) as task planners emerges as a significant branch, where tasks are planned at the skill…
Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection
Kyungjae Lee, Dasol Hwang, Sunghyun Park +2
Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance o…