每天自动聚合 AI 领域最新动态
We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliv...
Many scalable latent 3D generators operate on structured tensors, whereas pre-optimized 3D Gaussian Splatting (3DGS) ...
Large-scale image generation has benefited from advances in data scale, quality, rebalancing, and recaptioning, yet c...
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and...
Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance o...
Although Large Vision-Language Models (VLMs) have significantly advanced embodied navigation, their direct deployment...
Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastruct...
AI co-scientists that generate hypotheses, retrieve related work, design experiments, execute code, and draft full pa...
Graph neural networks are commonly described through family-specific equations whose notation obscures shared computa...
Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent sta...
Modern agents operate inside agent harnesses that manage tools, context, and control flow, making the harness a criti...
Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable ...