脉冲语言模型新突破：无Softmax注意力与对齐蒸馏打造超低能耗大模型。
arXiv:2605.13859v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) offer promising energy-efficient alternatives to large language model…
用频谱分析揭示假新闻传播结构，为检测提供全新理论框架。
arXiv:2605.13861v1 Announce Type: cross Abstract: The propagation structure of fake news has been shown to be an important cue for detecting it; yet, …
从遗憾视角统一在线多重检验的评估，揭示假阳性与假阴性非对称成本的优化新框架。
arXiv:2605.13916v1 Announce Type: cross Abstract: Online Multiple Testing (OMT), a fundamental pillar of sequential statistical inference, traditional…
揭示WarmPrior用动作历史替代高斯噪声，大幅提升机器人操作成功率，简单有效。
arXiv:2605.13959v1 Announce Type: cross Abstract: Generative policies based on diffusion and flow matching have become a dominant paradigm for visuomo…
探讨地缘政治场景下大语言模型安全评估的创新方法，助力国家安全与公共安全防护。
arXiv:2605.14152v1 Announce Type: cross Abstract: Safety evaluations for large language models (LLMs) increasingly target high-stakes National Securit…
从图视角剖析RAG失败根源，揭示模型内部机制，精准定位错误成因。
arXiv:2605.14192v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving la…
新微调方法PreFT仅优化预填充阶段，解决大模型个性化服务时PEFT导致的吞吐量瓶颈，理论与实证兼备。
arXiv:2605.14217v1 Announce Type: cross Abstract: Large language models can now be personalised efficiently at scale using parameter efficient finetun…
新方法AudioMosaic融合对比学习与掩码表示，攻克音频自监督的对比方法难题。
arXiv:2605.14231v1 Announce Type: cross Abstract: Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale …
提出General Dijkstra Search与动态潜路由后训练方法，实现MDP子策略最优时序组合，为语言模型强化学习提供新范式。
arXiv:2605.14323v1 Announce Type: cross Abstract: We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with ti…
新方法通过正交分解问答表征，实现高效幻觉检测，兼顾准确率与分布迁移鲁棒性。
arXiv:2605.14449v1 Announce Type: cross Abstract: Hallucination detection in large language models (LLMs) requires balancing accu racy, efficiency, an…
提出维度级意图保真度评估框架，通过结构化提示消融实验揭示LLM的意图还原与形式复制差异。
arXiv:2605.14517v1 Announce Type: cross Abstract: Holistic evaluation scores capture overall output quality but do not distinguish whether a model rep…
逆向强化学习新突破：MLE与Min-Max-IRL等价性及快速统计率证明，线性奖励MDP下理论简洁有力。
arXiv:2605.14599v1 Announce Type: cross Abstract: We establish novel structural and statistical results for entropy-regularized min-max inverse reinfo…
创新性双网络生成框架，用学习标量势在线评分桥接样本，突破传统均匀回归权重局限
arXiv:2605.14631v1 Announce Type: cross Abstract: We introduce Action-Inspired Generative Models (AGMs), a dual-network generative framework motivated…
arXiv新论文教你评估和优化类激活映射，破解CNN解释性难题。
arXiv:2605.14641v1 Announce Type: cross Abstract: Class attribution maps (CAMs) provide local explanations for the decisions of convolutional neural n…
基于视觉的水位和流速估计新框架，融合前沿计算机视觉技术，提升环境监测精度与鲁棒性。
arXiv:2605.14645v1 Announce Type: cross Abstract: With the rapid evolution of computer vision, vision-based methodologies for water level and river su…
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…
利用引文演化图作为监督信号，突破静态检索局限，让大模型生成更具创新性的研究想法。
arXiv:2605.14790v1 Announce Type: cross Abstract: Research idea generation is the innovation-driving step of automated scientific research. Recently, …
用随机少样本指导提升RLVR在困难问题上的样本效率，大模型训练新思路。
arXiv:2605.15012v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has achieved great success in developing Large…
离策略评估的精度取决于日志策略设计，这篇论文系统研究如何优化它
arXiv:2605.15108v1 Announce Type: cross Abstract: Off-policy evaluation (OPE) estimates the value of a target treatment policy (e.g., a recommender sy…
看AI如何像人类一样通过观察和交互学习物理与因果，1000+异构游戏基准测试揭秘突破！
arXiv:2511.15407v3 Announce Type: replace Abstract: Humans learn by observing, interacting with environments, and internalizing physics and causality.…