Neurons++ is proposed, a visual-stream fMRI reconstruction framework for both static image and dynamic video reconstruction and achieves state-of-the-art video reconstruction and competitive image reconstruction across standard benchmarks.
Hao-Nan Wang, Yu-Chen Wang, Jing-Yu Lu et al.· 0 citations
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, but fine-tuning them with reinforcement learning (RL) remains constrained by the cost of real-world robot interaction. Model-based reinforcement learning (MBRL) reduces this cost by using a learned world model to generate...
Yi-Fei Sheng, Hao-Xiang Ren, Zhi-Long Zhang et al.· 0 citations
SyRe is presented, a promptable segmentation foundation model based on Synergistic vision-language Reinforcement that achieves accurate text-prompted segmentation across diverse clinical scenarios, with particularly strong performance on disease-related targets.
Haonan Wang, J. Mao, Le-Han Wang et al.· 2 citations
The predictive divergence mask is proposed, which asks whether the next policy-gradient step will increase or decrease the same divergence used by the trust region, and the resulting masks improve RL training across model scales and precision settings.
