1 citations · 1 across the 2 of their papers we have counts for
5 papers
Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM
SooHwan Eom, Jay Shim, Gwanhyeong Koo +4
The Transformer's quadratic complexity with input length imposes an unsustainable computational load on large language models (LLMs). In contrast, the Selective Scan Structured Sta…
Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning
Thanh Nguyen, Tung Luu, Tri Ton +2
Offline reinforcement learning (RL) has garnered significant interest due to its safe and easily scalable paradigm. However, training under this paradigm presents its own challenge…
ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson +2
We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's…
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
Eunseop Yoon, Hee Suk Yoon, SooHwan Eom +7
Reinforcement Learning from Human Feedback (RLHF) leverages human preference data to train language models to align more closely with human essence. These human preference data, ho…
Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization
Tung M. Luu, Thanh Nguyen, Tee Joshua Tian Jin +2
Recent studies reveal that well-performing reinforcement learning (RL) agents in training often lack resilience against adversarial perturbations during deployment. This highlights…