每天自动聚合 AI 领域最新动态
Training Latent Diffusion Models (LDMs) within Federated Learning (FL) has attracted increasing attention due to its ...
Dense retrieval embedding models are a fundamental component of modern retrieval-based AI systems. Most dense retriev...
We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publica...
The problem of optimal sizing and power scheduling in microgrids subject to uncertainties is well known to the contro...
Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from d...
Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world inte...
AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, mana...
Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric represen...
Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of i...
Memory remains a critical bottleneck for long-horizon robotic manipulation, as standard Vision-Language-Action (VLA) ...
Attention-based Multiple Instance Learning aggregators in medical imaging are prone to attention concentration, produ...
Self-attention is central to Transformer performance and is often the most expensive part of the Transformer at long ...