每天自动聚合 AI 领域最新动态
Scientific poster construction compresses a long multimodal paper into a readable, editable canvas. Existing systems ...
Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it...
Video world models predict future observations conditioned on historical observations and control signals, enabling l...
We introduce a new problem domain for human action recognition: the fine-grained analysis of children's gait behavior...
Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and w...
Pixel-space diffusion models aim to learn an end-to-end generator directly over raw pixels. This is challenging becau...
Geospatial foundation models aim to learn representations that transfer across regions and sensors, yet evaluating th...
Scientific figure comprehension and reasoning using multimodal AI requires integrating visual perception with domain-...
Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries an...
Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors...
Multimodal clinical models are usually judged on accuracy with every modality present, but deployment removes modalit...
LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to opera...