Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
Xingyu Lu, Jinpeng Wang, YiFan Zhang +12
We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks. Specifically, to enhance Identifiability, we provide the reward model wit…
cs.LG2025
Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
Wei Chen, Xin Yan, Bin Wen +4
Although multimodal large language models (MLLMs) exhibit remarkable reasoning capabilities on complex multimodal understanding tasks, they still suffer from the notorious hallucin…