每天自动聚合 AI 领域最新动态
Addressing critical global challenges, from food security and disaster risk to disease outbreaks and socio-economic v...
We present a first application of sparse-autoencoder-based mechanistic interpretability to particle physics. Studying...
Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, o...
In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed...
Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and vi...
Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through g...
Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning st...
Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single u...
Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized...
Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art model...
Multi-arm collaboration is becoming a core capability in embodied manipulation. Recent vision-language-action (VLA) m...
Massively parallel simulation changes the data regime in which off-policy reinforcement learning (RL) is trained, cha...