Deep generative models often produce structured outputs composed of interacting components.Modelling these outputs with…
为什么值得关注：属于技术进展，可能扩散到其他领域
Long conversational agents have become essential in our daily lives.They must remember what was said long back in order…
为什么值得关注：提供了新的研究结果
While unlearning seeks to negate undesired capabilities acquired through learning, little research has examined how the…
为什么值得关注：属于技术进展，可能扩散到其他领域
Skin cancer is a major global health concern, and early detection and accurate lesion delineation are important for effe…
为什么值得关注：属于企业动态，反映产业投入方向
Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content.We…
为什么值得关注：提供了新的研究结果
Sequence-level power sampling has recently emerged as a training-free approach to reasoning by sampling from a sharpened…
为什么值得关注：属于技术进展，可能扩散到其他领域
Activation steering has gained popularity as a lightweight inference-time debiasing technique for large language models.…
为什么值得关注：为行业报告，可提供结构化数据
While HCI increasingly examines AI-safety for youth, the literature lacks a comprehensive view of what risks have been i…
为什么值得关注：内容与关注主题相关
Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretab…
为什么值得关注：涉及教育实践，可对照自己的研究场景
Sequential test-time training adapts a memory network through successive updates, each computing an inner-loop gradient…
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
Probes are the workhorse of interpretability.If a model's hidden states predict a variable, the model is said to represe…
为什么值得关注：属于技术进展，可能扩散到其他领域
In this paper, we investigate the synthesis of Micro Neural Policies (MNP) to enable safe and robust real-time robotic c…
为什么值得关注：属于技术进展，可能扩散到其他领域
Whether alignment gets easier or harder as models grow is often argued from isolated findings, as if alignment were one…
为什么值得关注：属于技术进展，可能扩散到其他领域
Probabilistic load forecasting has been widely studied for power-system operation and planning, but customer- and transf…
为什么值得关注：属于技术进展，可能扩散到其他领域
In the field of Explainable AI (XAI), counterfactual (CF) explanations interpret a model's decision by suggesting the ch…
为什么值得关注：提供了新的研究结果
Clinical diagnosis is inherently a structured reasoning process, yet existing deep learning models often bypass this str…
为什么值得关注：属于技术进展，可能扩散到其他领域
Execution feedback lets coding agents revise programs and learn from their own corrections.A correction's learning weigh…
为什么值得关注：提供了新的研究结果
LLMs are increasingly deployed as autonomous agents in social environments, making it critical to study their ability to…
为什么值得关注：提供了新的研究结果
Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the…
为什么值得关注：提供了新的研究结果
Proactive power management systems reduce processor dynamic power through runtime power prediction and power-aware sched…
为什么值得关注：属于技术进展，可能扩散到其他领域