每天自动聚合 AI 领域最新动态
The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects...
A key challenge in Arabic NLP is the scarcity of dialectal data relative to Modern Standard Arabic (MSA), causing LLM...
The inherent complexity of video understanding makes it difficult to determine whether Video-LLM benchmark performanc...
The rapid development of large language models and multimodal large language models has accelerated the emergence of ...
Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of p...
Semantic audio applications increasingly require controllable generation on commodity and embedded hardware rather th...
In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-...
Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures...
Current computational approaches for drug design typically focus on generating molecules conditioned on specific targ...
Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length ...
Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules...
Long-horizon failure in world models is conventionally attributed to compounding error, a generic framing that does n...