每天自动聚合 AI 领域最新动态
Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers s...
Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio...
Multimodal representation learning is a cornerstone of modern AI. By encoding multimodal queries and targets into vec...
Aerial image-goal navigation requires an unmanned aerial vehicle (UAV) to reach a target location specified by a goal...
World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action pred...
Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher...
Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-tim...
Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it a...
LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. ...
Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable ...
Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and rol...
Creative capabilities of MLLMs matter in design, communication, education, and human--AI collaboration, yet remain di...