ICLR 2025论文揭示如何通过神经元干预为LLM注入特定人格特质，打开模型个性化新维度。
arXiv:2410.12327v2 Announce Type: replace Abstract: Large language models (LLMs) have become increasingly proficient at simulating various personality…
最新基准测试CIAware-Bench，评估前沿大模型对控制干预的感知能力，揭示AI安全新挑战。
arXiv:2606.11063v1 Announce Type: new Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially un…
从界面设计入手，探讨如何通过UI干预引导用户更可持续地使用LLM聊天机器人，跳出传统模型优化思路。
arXiv:2606.10861v1 Announce Type: cross Abstract: LLM-powered chatbots are increasingly embedded in everyday workflows, raising sustainability concern…
LLM智能体悄然失败？新研究用干预法精准定位错误根源，让沉默不再失控。
arXiv:2606.09071v1 Announce Type: new Abstract: Large language model (LLM) agents now solve complex tasks through long plan-and-execution traces, yet …
一种基于证据诊断的干预训练方法，让大模型评分时严格遵循给定规则，提升可靠性与可解释性
arXiv:2606.06350v1 Announce Type: new Abstract: Reliable rubric grading requires more than accurate score prediction. Each judgement must be grounded …
日本或抛售美债干预汇市，还有俞浩表态专注实业、天津AI传感器产业园开园等财经科技快讯一网打尽。
大公司： 首关15亿元，英诺科创三期基金持续聚焦早期科技投资 36氪获悉，6月5日，英诺基金宣布旗下英诺科创三期基金完成首轮关账，规模15亿元。该基金聚焦早期科技投资，重点布局前沿科技及人工智能领域。 比特币“金库”公司市值蒸发620亿美元 比特币本周下跌约14%，至四个月低点附近。随着加密货6月5…
用稀疏恢复技术从子集扰动中精确归因训练数据，破解大模型因果干预的计算难题
arXiv:2606.05165v1 Announce Type: cross Abstract: Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The …
语音大模型推理中实体绑定出错了怎么办？这篇论文系统诊断问题并提出思维链干预方案。
arXiv:2606.04474v1 Announce Type: new Abstract: Speech Large Language Models (SLLMs) underperform their text counterparts on complex reasoning. We rev…
自主AI代理执行长任务时，何时干预？本研究用18维情感动力学引擎揭示时机陷阱，LLM裁判也靠不住。
arXiv:2606.04296v1 Announce Type: new Abstract: As autonomous AI agents move from conversational systems to long-horizon software execution, runtime s…
概念异质性感知的表示引导，突破单一方向局限，精准控制大模型行为
arXiv:2603.02237v2 Announce Type: replace Abstract: Representation steering offers a lightweight mechanism for controlling the behavior of large langu…
从ADHD患者角度出发，探索神经包容性情绪调节的AI干预与用户体验研究。
arXiv:2605.31131v1 Announce Type: cross Abstract: Attention-deficit/hyperactivity disorder (ADHD) is a psychiatric disorder which presents itself in i…
IT之家 5 月 31 日消息，特斯拉车主在北美成功完成了一项曾被视作自动驾驶测试领域终极目标的挑战。一群热衷电动汽车的爱好者，完成了全球首趟全程无人工干预、横穿加拿大的不间断自动驾驶之旅，车辆在纵贯整个加拿大的行驶过程中，所有操作全部由 FSD 完成，全程无需人为修正操作。 参与者戴维・莫斯（账号…
无需训练，推理时直接干预logit实现语言模型可控生成，SWAI方法简洁高效。
arXiv:2601.10960v2 Announce Type: replace-cross Abstract: Controllable generation requires language models to realize output characteristics such as r…
社交媒体如何成为家暴受害者隐秘的求救信号？这项研究揭示了自我披露与支持寻求的动态机制。
arXiv:2509.12288v2 Announce Type: replace-cross Abstract: Domestic Violence (DV) is a pervasive public health problem characterized by patterns of coe…
用因果干预方法优化LLM代理长期记忆选择，告别语义相似度检索的局限性
arXiv:2605.17641v1 Announce Type: cross Abstract: Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet exist…
AI正突破特教行业“不可能三角”，用精准个性化干预让偏远地区孩子也能享受优质康复资源。
从可信商业干预视角重新审视生成式AI广告，为这个争议领域提供理论框架。
arXiv:2605.18673v1 Announce Type: cross Abstract: Major deployed generative AI advertising systems preserve a visible boundary between commercial cont…
探讨预测与干预博弈中不变集的数学结构，为理解智能体交互提供理论框架。
arXiv:2605.16828v1 Announce Type: cross Abstract: We consider the following two-player game: using observational data, the leader chooses a prediction…
突破线性干预局限，提出大模型非线性特征干预新方法，为理解LLM内部表征开辟新路径
arXiv:2605.14749v1 Announce Type: cross Abstract: Intervention is one of the most representative and widely used methods for understanding the interna…
MBRL新突破：主动潜在干预打破历史束缚，让想象力从潜在流形自由生成
arXiv:2605.16030v1 Announce Type: new Abstract: Model-Based Reinforcement Learning (MBRL) leverages latent imagination for sample efficiency, yet rema…