1
Local Constrained Bayesian Optimization
瞄准局部约束下的黑箱优化难题，提出新方法并在ICML 2026发表，值得关注。
arXiv:2603.07965v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) for high-dimensional constrained problems remains a significant c…
2
Constrained Flow Matching via Lagrangian Dual Flows
拉格朗日对偶流为约束流匹配开辟新路径，交叉优化与生成建模，值得技术党细读。
arXiv:2607.04513v1 Announce Type: cross Abstract: Flow matching is a powerful tool for generative modeling, but emerging applications in robotics, pla…
3
Constrained Variable Projection for Structured Problems
面向结构化优化问题的约束变量投影新方法，为复杂约束场景提供可证收敛的求解思路，值得优化领域研究者关注。
arXiv:2606.23939v1 Announce Type: cross Abstract: Variable projection is a classical technique for separable nonlinear least-squares problems, in whic…
4
Online LLM Selection via Constrained Bandits with Time-Varying Demand
挑战在线LLM选择中的时变需求？这篇论文提出约束赌博机框架，动态平衡性能与成本。
arXiv:2606.17489v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in edge-cloud inference systems to handle div…
5
Utility-Constrained Policy Optimization
强化学习策略优化引入“效用约束”，平衡性能与安全边界，理论创新亮眼。
arXiv:2606.14029v1 Announce Type: new Abstract: Constrained MDPs (CMDPs) are a widely adopted framework for incorporating safety into RL agents; howev…
6
Neural Slack Variables for Shape Constraints
提出神经松弛变量方法，为神经网络施加形状约束（如单调性、凸性），突破传统硬约束限制。
arXiv:2606.13803v1 Announce Type: new Abstract: Enforcing functional inequality constraints such as monotonicity and convexity in neural networks is a…
7
Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models
用冻结视觉语言模型实现前瞻性安全强化学习，让机器人在碰撞前就能预判危险
arXiv:2606.11266v1 Announce Type: new Abstract: The cost signal that constrained-RL algorithms optimize against is almost always reactive: the simulat…
8
Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment
语义基础+固定惩罚约束优化，让大模型对齐过程获得可认证的安全保障
arXiv:2510.03520v2 Announce Type: replace-cross Abstract: Ensuring safety is a foundational requirement for large language models (LLMs). Achieving an…
9
Optimal Transport under Group Fairness Constraints
群组公平约束下最优传输新框架，ICML 2026 Spotlight论文，理论深度与实践价值兼备。
arXiv:2601.07144v3 Announce Type: replace-cross Abstract: Ensuring fairness in matching algorithms is a key challenge in allocating scarce resources a…
10
Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
无需微调，推理阶段通过约束优化实现黑盒大模型安全对齐，兼顾性能与安全性。
arXiv:2510.09330v3 Announce Type: replace Abstract: Ensuring that large language models (LLMs) comply with safety requirements is a central challenge …
11
Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement
用扩散模型破解非凸优化难题，加权自举精炼框架提升求解质量，ICML 2026录用论文。
arXiv:2502.10330v4 Announce Type: replace Abstract: Recent advances in diffusion models show promising potential to accelerate nonconvex problem solvi…
12
LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks
从根源解决LLM代理的奖励黑客隐患，提出约束优化新方法，让自主智能更安全可靠
arXiv:2605.27375v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly acting as autonomous agents, but their continuous intera…
13
Constrained Auto-Bidding via Generative Response Modeling
用生成式响应建模突破传统方法，为在线广告中的约束自动竞价提供更优解法
arXiv:2605.27811v1 Announce Type: new Abstract: Auto-bidding systems aim to maximize advertiser value over long horizons under budget constraints and …
14
Constrained Bayesian Experimental Design via Online Planning
ICML 2026 提出用在线规划解决约束贝叶斯实验设计，理论结合实践，方法新颖。
arXiv:2605.26990v1 Announce Type: cross Abstract: Bayesian experimental design (BED) is a principled framework for data-efficient design of sequential…
15
Stochastic Penalty-Barrier Methods for Constrained Machine Learning
提出随机惩罚-障碍方法，解决约束机器学习优化难题，理论创新与算法实践兼备。
arXiv:2605.18618v1 Announce Type: new Abstract: Constrained machine learning enables fairness-aware training, physics-informed neural networks, and in…
16
RanSOM: Second-Order Momentum with Randomized Scaling for Constrained and Unconstrained Optimization
提出RanSOM方法，用随机缩放解决动量方法在随机优化中的曲率偏差，无需昂贵辅助采样，实现高效收敛。
arXiv:2602.06824v2 Announce Type: replace-cross Abstract: Momentum methods, such as Polyak's Heavy Ball, are the standard for training deep networks b…