每天自动聚合 AI 领域最新动态
Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a c...
Prior work has shown that in-context demonstrations can jailbreak language models, but it remains unclear how models ...
Securing AI agents that operate in complex digital environments has become a critical need, and runtime monitoring ap...
LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on cod...
Flow-matching text-to-speech systems achieve remarkable zero-shot quality but remain static after deployment: pronunc...
Autonomous agents are increasingly connected to cloud, deployment, and data-control workflows, but production mutatio...
Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for s...
Neurosymbolic systems such as DeepProbLog combine neural perception with probabilistic logic, but standard inference ...
Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling ...
Style-captioned text-to-speech systems use natural language to control voice characteristics, but how individual word...
Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important f...
Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming...