cs.LG(2026-08-17)

📊 共 19 篇论文

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (10) 支柱九:具身大模型 (Embodied Foundation Models) (7) 支柱一:机器人控制 (Robot Control) (1) 支柱八:物理动画 (Physics-based Animation) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗
1 Q-based Variational Inverse Reinforcement Learning 提出Q基变分逆强化学习以解决人类偏好学习问题 reinforcement learning inverse reinforcement learning
2 CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated? 提出CaliBench以解决视频世界模型的物理校准问题 world model world models
3 SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry 提出SCALE以提升JEPA规划中的状态校准潜在嵌入 world model worldmodel world models
4 Le Critique: Privileged Value Functions for LLM Reinforcement Learning 提出特权价值函数以解决LLM强化学习中的方差问题 reinforcement learning large language model
5 PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data 提出PertMind以解决生物推理训练成本高的问题 reinforcement learning large language model
6 TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH 提出TRACE-CASH以解决时间序列CASH中的自适应配置探索问题 reinforcement learning
7 POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment 提出LLM-MGCL以解决POI推荐中的冷启动问题 contrastive learning multimodal
8 The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning 提出统一框架以解决潜变量依赖与结构之间的权衡问题 representation learning
9 An Analytical-Prior Framework for Data-Efficient Prediction of Sound-Reduction Frequencies in Rectangular Side-Branch Helmholtz Resonators 提出分析先验框架以提高赫尔姆霍兹共鸣器的声减频率预测效率 MAE distillation
10 Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics 通过受控引导和调节价值动态提出深度Q学习稳定性解决方案 reinforcement learning representation learning

🔬 支柱九:具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗
11 Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis 提出MGSI框架以解决多模态情感分析中的信号融合问题 large language model multimodal
12 Beyond Binary Priorities: Multi-Tier SLA Scheduling for Large Language Model Serving 扩展多层次SLA调度以优化大型语言模型服务 large language model
13 Evolving Executable Pipeline Programs for AutoML with Language Models 提出LACE框架以解决AutoML中管道生成的局限性 large language model foundation model
14 Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments 提出CHIVE以评估LLM行为解释的有效性 chain-of-thought
15 LLMs for Zero-Shot Threat Detection via Structured Risk Indicators 提出双阶段LLM框架以实现零-shot威胁检测 large language model
16 Pallas: A Proactive KV Cache Migration Framework for LLM Inference in AI-RAN 提出Pallas框架以解决AI-RAN中的KV缓存迁移问题 large language model
17 SAUL: Sharpness-Aware Augmented-Lagrangian Unlearning 提出SAUL以解决大语言模型中的机器遗忘问题 large language model

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
18 The Ethical Decision Head: Operationalizing Normative Ethics in Autonomous Vehicles via Reinforcement Learning from Human Feedback 提出伦理决策头以解决自主车辆道德决策问题 locomotion reinforcement learning PPO

🔬 支柱八:物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗
19 Self-Supervised Noise2Noise-Enhanced Denoising for Continuous-Scan Air-Plasma THz Spectroscopy 提出自监督Noise2Noise增强去噪方法以解决THz光谱噪声问题 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页