System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such servi…
为什么值得关注：属于技术进展，可能扩散到其他领域
We propose a method for choosing the shared memory parameter $β_1=β_2=β$ in Adam from a short pilot training.The selecte…
为什么值得关注：属于技术进展，可能扩散到其他领域
Diffusion models generate data through a continuum of denoising problems, and are widely observed to reveal coarse struc…
为什么值得关注：属于技术进展，可能扩散到其他领域
Long-horizon world-model planning typically relies on autoregressive rollouts, where predicted states are repeatedly fed…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Contact with contaminated objects can spread hazards through a household robot's grippers, tools, and shared surfaces, w…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency.In principle, paral…
为什么值得关注：内容与关注主题相关
Software-engineering agents can enable people without formal software training to build systems they could not otherwise…
为什么值得关注：为行业报告，可提供结构化数据
Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language mo…
为什么值得关注：提供了新的研究结果
As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warrante…
为什么值得关注：属于技术进展，可能扩散到其他领域
Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance withou…
为什么值得关注：属于技术进展，可能扩散到其他领域
On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment…
为什么值得关注：提供了新的研究结果
Language models increasingly act as agents.An agent that says an action is wrong and then takes it anyway is a different…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by…
为什么值得关注：属于技术进展，可能扩散到其他领域
Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each ot…
为什么值得关注：属于企业动态，反映产业投入方向
Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent pro…
为什么值得关注：属于技术进展，可能扩散到其他领域
Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped.In September 2026 Meta's Muse show…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging…
为什么值得关注：属于技术进展，可能扩散到其他领域
Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doi…
为什么值得关注：属于科研论文，可作为研究依据
Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap…
Sequential recommenders typically use a fixed slate size even though the number of useful alternatives changes within a…