5 papers
Instruction-tuned Self-Questioning Framework for Multimodal Reasoning
You-Won Jang, Yu-Jung Heo, Jaeseok Kim +3
The field of vision-language understanding has been actively researched in recent years, thanks to the development of Large Language Models~(LLMs). However, it still needs help wit…
Confidence-guided Refinement Reasoning for Zero-shot Question Answering
Youwon Jang, Woo Suk Choi, Minjoon Jung +2
We propose Confidence-guided Refinement Reasoning (C2R), a novel training-free framework applicable to question-answering (QA) tasks across text, image, and video domains. C2R stra…
From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning
Junseok Park, Hyeonseo Yang, Min Whoo Lee +3
Reinforcement learning (RL) agents often face challenges in balancing exploration and exploitation, particularly in environments where sparse or dense rewards bias learning. Biolog…
Communicating Unexpectedness for Out-of-Distribution Multi-Agent Reinforcement Learning
Min Whoo Lee, Kibeom Kim, Soo Wung Shin +2
Applying multi-agent reinforcement learning methods to realistic settings is challenging as it may require the agents to quickly adapt to unexpected situations that are rarely or n…
Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning
Junseok Park, Yoonsung Kim, Hee Bin Yoo +5
Toddlers evolve from free exploration with sparse feedback to exploiting prior experiences for goal-directed learning with denser rewards. Drawing inspiration from this Toddler-Ins…