结合局部与全局熵的新方法，提升大模型不确定性量化精度，值得关注。
arXiv:2606.09875v1 Announce Type: cross Abstract: Large language models hallucinate confidently, making uncertainty quantification (UQ) essential for …
从信息熵视角揭示多智能体协作的成败关键，为LLM系统设计提供理论依据
arXiv:2602.04234v6 Announce Type: cross Abstract: Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models …
从熵动力学新视角解析LLM多智能体系统的协调者识别机制，揭示系统涌现行为。
arXiv:2606.01351v1 Announce Type: new Abstract: The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving …
Soft-NBCE提出熵加权块融合方法，有效提升模型对长文本的处理能力，为长上下文建模提供新思路。
arXiv:2606.01101v1 Announce Type: new Abstract: The quadratic complexity of self-attention remains a bottleneck for Large Language Models (LLMs) proce…
提出功能熵方法，通过不确定性量化预测LLM生成代码的功能正确性，为代码可靠性评估提供全新视角
arXiv:2605.28500v1 Announce Type: cross Abstract: Large language models have shown impressive capabilities in code generation, yet they often produce …
提出保证生成质量的同时最大化输出多样性的策略优化方法，破解LLM内容同质化难题。
arXiv:2602.15894v2 Announce Type: replace-cross Abstract: In many large language model (LLM) alignment applications, users expect not only high-qualit…
用α-Rényi集成提升LLM后训练的不确定性建模，学术前沿。
arXiv:2605.27747v1 Announce Type: cross Abstract: Existing training approaches for large language models learn a single set of parameters, based on la…
用几何熵混合优化LLM数据筛选，新方法已提交ICML 2026
arXiv:2605.26121v1 Announce Type: cross Abstract: LLM pre-training efficacy increasingly depends on data composition rather than sheer volume. Yet, op…
自适应共形语义熵方法，精准量化LLM不确定性，攻克幻觉难题，赋能安全关键部署
arXiv:2605.04295v2 Announce Type: replace-cross Abstract: LLMs' overconfidence, particularly when hallucinating, poses a significant challenge for the…
从动力系统与熵相变视角揭示LLM推理的触发条件，为理解大模型认知机制提供新洞见。
arXiv:2605.22873v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet…
提出数字熵损失函数，专门提升大语言模型对数字的处理能力，让AI更懂数值。
arXiv:2605.20369v1 Announce Type: cross Abstract: Number prediction stands as a fundamental capability of large language models (LLMs) in mathematical…
用通俗语言解释密码熵，让你真正理解“强密码”到底有多强
Every password generator tells you the password is "strong." Very few tell you how strong, or what that actually means in practice. The answer is entr…
非线性贝叶斯滤波新突破：用分数匹配完成预测-更新循环，解决密度表示难题
arXiv:2605.16644v1 Announce Type: cross Abstract: A central obstacle in nonlinear Bayesian filtering is representing the belief distribution. Moment-b…
平均场朗之万动力学的镜像变体，为无穷宽神经网络训练提供新理论视角
arXiv:2505.02621v2 Announce Type: replace Abstract: The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex function…
提出熵自编码器框架，通过隐式自由能最小化解决VAE后验崩溃，理论创新显著。
arXiv:2605.16164v1 Announce Type: new Abstract: Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a f…
扩散语言模型遇上强化学习，熵引导步骤选择与逐步优势破局后训练难题。
arXiv:2603.12554v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has been effective for post-training autoregressive (AR) languag…
利用熵最优传输实现几何约束的冠状动脉狭窄编辑，为医学影像数据增强提供新思路，有望突破数据稀缺瓶颈，提升自动检测的泛化能力。
arXiv:2605.08851v2 Announce Type: replace-cross Abstract: The scarcity of high-quality imaging data for coronary angiography (CAG) stenosis limits the…