每天自动聚合 AI 领域最新动态
Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packag...
The world evolves following its dynamics, i.e., its laws of motion. However, leading video diffusion models largely f...
Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primar...
ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inhere...
Large language models often fail when answer options require combining atomic judgments under explicit logical operat...
Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-...
Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits (VI...
Modernizing legacy Fortran is a problem of volume: the transformations are individually routine, but the codebases ca...
Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simu...
Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration. F...
LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction...
Background: Accurate segmentation of the Left Anterior Descending (LAD) artery in 3D free-breathing, non-contrast CT ...