每天自动聚合 AI 领域最新动态
Scarcity of labeled data limits development of deep learning biomarkers in oncology. We develop a two-stage AI model ...
Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation wit...
Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from set...
We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dy...
This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS sh...
Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, colla...
Recurrent neural networks (RNNs) compress the historical context into a memory state of fixed size, thus allowing for...
Looped Transformers introduce recurrent depth as a new scaling axis for LLMs: by repeatedly applying shared Transform...
Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines the...
Legal language models require reward signals that capture not only answer correctness but also the multidimensional q...
Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and str...
Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tas...