cs.LG（2026-08-14）

📊 共 19 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱四：生成式动作 (Generative Motion) (3) 支柱八：物理动画 (Physics-based Animation) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 CytoBERT: A Foundation Model for Cytometry Data 提出CytoBERT以解决细胞计数数据异质性问题 foundation model
2 Training Fair Tabular Foundation Models 提出FairTFM以解决表格模型公平性问题 foundation model
3 Forecast Collapse in Time-Series Foundation Models 提出CalibRank以解决时间序列预测中的预报崩溃问题 foundation model
4 MINT: A Universal Zero-Shot Predictor for Transaction Data 提出MINT以解决金融交易数据的零-shot预测问题 foundation model multimodal
5 Catching the Imposter: Self-Supervised Learning of Physical Coherence with Cross-Entity Feature Permutations 提出自监督学习方法以捕捉物理一致性问题 foundation model
6 Detecting Contaminated Code-Generation Prompt Batches via Influence Functions 提出CodeSIFT以检测受污染的代码生成提示批次 large language model
7 Model-agnostic Retrieval-Augmented Extended Forecasting for time series 提出RAEF以提高时间序列预测的效率与准确性 foundation model
8 QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction 提出QUASAR以降低量化感知训练的损失底线 large language model
9 Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification 提出几何过滤框架以提升LLM生成样本在少样本文本分类中的质量 large language model
10 Federated Prompt Learning: A Unified Framework, Empirical Analysis, and Future Directions 提出联邦提示学习框架以解决大语言模型隐私问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
11 Deep Reinforcement Learning solution for pickup and delivery routing problems with time window and capacity constraints 提出深度强化学习解决带时间窗和容量约束的货物配送问题 reinforcement learning deep reinforcement learning
12 Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View 提出统一路径空间视角的强化学习方法以优化扩散模型 reinforcement learning
13 CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing 提出一致性强制方法以提升dLLMs的并行解码性能 distillation large language model ✅
14 Learning to Run Power Networks: Effective AlphaZero-inspired Topological Control 提出基于AlphaZero的拓扑控制方法以应对电网稳定性问题 reinforcement learning PPO

🔬 支柱四：生成式动作 (Generative Motion) (3 篇)

#题目一句话要点标签🔗⭐
15 Adversarial Learning of Classifier-Free Guidance Schedules 提出动态引导调度学习以优化文本到图像生成 classifier-free guidance
16 ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning 提出ATLAS以解决LLM代理行为理解问题 penetration large language model
17 Probabilistic indirect models for undrained shear strength: addressing significant data missing and variability with advanced imputation and machine learning techniques 提出基于多头注意力机制的模型以解决无排水剪切强度预测问题 penetration

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
18 Non-Parametric Spatiotemporal Trajectory Prediction via State-Conditioned Transition Sampling 提出无参数时空轨迹预测方法以解决数据稀缺问题 spatiotemporal
19 Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction 提出结构引导的时空注意力图神经网络以解决交通流预测的透明性问题 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页