cs.LG（2025-01-20）

📊 共 16 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling T1：通过强化学习和推理扩展提升语言模型推理能力 reinforcement learning imitation learning large language model
2 DenoMAE: A Multimodal Autoencoder for Denoising Modulation Signals 提出DenoMAE，用于噪声环境下调制信号的去噪与分类 masked autoencoder MAE multimodal
3 Secure Resource Allocation via Constrained Deep Reinforcement Learning 提出SARMTO框架，通过约束深度强化学习实现安全高效的多云边缘资源分配 reinforcement learning deep reinforcement learning DRL
4 SeRpEnt: Selective Resampling for Expressive State Space Models 提出SeRpEnt：一种利用选择性重采样的表达型状态空间模型，用于序列建模。 Mamba SSM state space model
5 RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems? RedStar：通过扩展长链思维数据，解锁更优的慢思考系统 reinforcement learning multimodal chain-of-thought ✅
6 Momentum Contrastive Learning with Enhanced Negative Sampling and Hard Negative Filtering 提出双视角损失和选择性负样本的动量对比学习框架，提升表征质量。 representation learning contrastive learning
7 Collaborative Channel Access and Transmission for NR Sidelink and Wi-Fi Coexistence over Unlicensed Spectrum 提出协作信道接入机制和功率控制策略，解决NR侧链与Wi-Fi在非授权频谱上的共存问题。 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
8 Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial Simulations 评估大语言模型中的二元决策偏差，及其对公平的基于Agent金融模拟的影响 large language model
9 Multivariate Wireless Link Quality Prediction Based on Pre-trained Large Language Models 提出GAT-LLM模型，利用预训练大语言模型提升无线链路质量的多变量预测精度。 large language model
10 The OpenLAM Challenges OpenLAM挑战赛：构建开放原子模型基准，推动材料科学发展 large language model foundation model
11 A Survey on Diffusion Models for Anomaly Detection 扩散模型异常检测综述：探索复杂数据中异常识别的新范式 large language model multimodal ✅
12 Glinthawk: A Two-Tiered Architecture for Offline LLM Inference Glinthawk：一种用于离线LLM推理的两层架构，提升吞吐并降低成本。 large language model ✅
13 Can Bayesian Neural Networks Make Confident Predictions? 提出基于离散先验的贝叶斯神经网络，精确量化预测不确定性 multimodal
14 Trustformer: A Trusted Federated Transformer Trustformer：一种可信的联邦Transformer，降低通信开销并保护隐私 large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
15 Spatiotemporal Air Quality Mapping in Urban Areas Using Sparse Sensor Data, Satellite Imagery, Meteorological Factors, and Spatial Features 提出基于图神经网络的时空空气质量预测框架，融合多源数据提升城市空气质量监测精度。 sparse sensors spatiotemporal

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

#题目一句话要点标签🔗⭐
16 Mitigating Spatial Disparity in Urban Prediction Using Residual-Aware Spatiotemporal Graph Neural Networks: A Chicago Case Study 提出残差感知时空图神经网络，缓解城市预测中的空间差异性，以芝加哥为例。 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页