cs.LG（2024-11-26）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱八：物理动画 (Physics-based Animation) (2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents APT：利用大型语言模型进行开放世界智能体的建筑规划与蓝图构建 large language model multimodal chain-of-thought
2 Pushing the Limits of Large Language Model Quantization via the Linearity Theorem 提出线性定理以优化大语言模型量化方法 large language model
3 TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations TabulaX：利用大型语言模型进行多类别表格转换，提升数据集成效率。 large language model
4 Synthetic Data Generation with LLM for Improved Depression Prediction 利用LLM生成合成数据，提升抑郁症预测模型性能 large language model chain-of-thought
5 COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection COAP：一种相关性感知梯度投影的内存高效训练方法 multimodal
6 Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens 揭示低比特量化偏好欠训练LLM：百兆token训练量化LLM的缩放法则 large language model ✅
7 Scalable iterative pruning of large language and vision models using block coordinate descent 提出基于块坐标下降的可扩展迭代剪枝算法iCBS，用于压缩大型语言和视觉模型。 large language model
8 Data-driven development of cycle prediction models for lithium metal batteries using multi modal mining 提出基于多模态数据挖掘的锂金属电池循环寿命预测模型 large language model
9 KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation KVPR：一种I/O感知的KV缓存部分重计算方法，用于高效LLM推理。 large language model ✅
10 Conformalised Conditional Normalising Flows for Joint Prediction Regions in time series 提出基于Conformal Prediction的条件Normalizing Flow，用于时间序列联合预测区域生成。 multimodal
11 Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning 提出ConDense-MoE，通过压缩而非剪枝MoE层，提升效率与性能 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
12 AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling AutoElicit：利用大语言模型为预测模型提取专家先验知识 predictive model large language model
13 Joint Combinatorial Node Selection and Resource Allocations in the Lightning Network using Attention-based Reinforcement Learning 提出基于注意力机制强化学习的LN节点选择与资源分配联合优化方法 reinforcement learning deep reinforcement learning DRL
14 CRASH: Challenging Reinforcement-Learning Based Adversarial Scenarios For Safety Hardening 提出CRASH框架，利用强化学习对抗场景提升自动驾驶安全性 reinforcement learning deep reinforcement learning
15 From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models 提出ETID框架，在满足GDPR“被遗忘权”的同时保持预测模型业务价值。 predictive model distillation
16 Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Environments with Delayed Rewards 提出混合策略PPO与TWTL奖励塑造，加速解决延迟奖励环境下的强化学习问题 reinforcement learning PPO reward shaping

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

#题目一句话要点标签🔗⭐
17 Multiscale spatiotemporal heterogeneity analysis of bike-sharing system's self-loop phenomenon: Evidence from Shanghai 针对共享单车自循环现象，提出多尺度时空异质性分析方法，助力优化单车分配。 spatiotemporal multimodal
18 A Graph Neural Network deep-dive into successful counterattacks 提出性别特定的图神经网络，用于预测足球反击成功率并分析关键因素。 spatiotemporal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
19 MetaGraphLoc: A Graph-based Meta-learning Scheme for Indoor Localization via Sensor Fusion MetaGraphLoc：基于图神经网络和元学习的室内定位传感器融合方案 spatial relationship

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
20 Contrastive CFG: Improving CFG in Diffusion Models by Contrasting Positive and Negative Concepts 提出对比CFG方法，通过对比正负概念提升扩散模型中CFG的性能。 classifier-free guidance

⬅️ 返回 cs.LG 首页 · 🏠 返回主页