每天自动聚合 AI 领域最新动态
Deploying multimodal foundation models as closed-loop policies increasingly requires conditioning actions on observat...
Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. H...
AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ide...
Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering...
Video generative models ( VGMs) have become a new frontier that can be used not just for video generation but for a m...
World foundation models (WFMs) are powerful simulators, yet they predominantly operate in a single-view setting and l...
Learning to simulate human users in interactive settings could advance the training of agent assistants, evaluation o...
World models are transitioning from passive visual generators to foundational, operational infrastructure for Physica...
Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern pro...
Diffusion models have become a promising alternative to autoregressive models. Among these, uniform diffusion languag...
Graphical user interface (GUI) grounding requires vision-language models (VLMs) to identify small target elements in ...
Sparse Autoencoders (SAEs) decompose residual-stream activations into interpretable features. Recent latent-space def...