cs.LG（2024-02-28）

📊 共 20 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗2)

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

#题目一句话要点标签🔗⭐
1 Learning to Deliver: a Foundation Model for the Montreal Capacitated Vehicle Routing Problem 提出FM-MCVRP以解决蒙特利尔容量限制车辆路径问题 large language model foundation model
2 Priority Sampling of Large Language Models for Compilers 提出优先采样以解决大语言模型生成代码的多样性问题 large language model
3 NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models 提出NeuroPrune以解决大型语言模型训练效率问题 large language model
4 LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models 提出LoRA-SP以解决大语言模型微调的资源效率问题 large language model
5 Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models 提出基于多目标优化的特定令牌水印技术以提升可检测性和语义一致性 large language model ✅
6 FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization 提出FlattenQuant以解决大语言模型推理计算瓶颈问题 large language model
7 Pre-training Differentially Private Models with Limited Public Data 提出基于有限公共数据的差分隐私模型预训练方法 foundation model ✅
8 RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval 提出增强RNN上下文检索能力的方法以缩小与Transformer的差距 chain-of-thought
9 No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization 提出混合精度KV缓存以解决生成模型内存瓶颈问题 large language model
10 Merino: Entropy-driven Design for Generative Language Models on IoT Devices 提出信息熵驱动设计以优化物联网设备上的生成语言模型 large language model
11 Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars 提出增量解析器以解决代码生成中的语法正确性问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
12 Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards 提出方向偏好对齐框架以解决大语言模型的用户需求适应性问题 reinforcement learning RLHF DPO
13 Autoencoder-based General Purpose Representation Learning for Customer Embedding 提出DEEPCAE以解决多层收缩自编码器的嵌入问题 representation learning
14 Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation 提出风险敏感的分布式强化学习框架以应对不确定性决策问题 reinforcement learning
15 Diffusion-Based Neural Network Weights Generation 提出基于扩散的神经网络权重生成方法以优化迁移学习 representation learning large language model
16 Provably Efficient Partially Observable Risk-Sensitive Reinforcement Learning with Hindsight Observation 提出风险敏感的部分可观察强化学习算法以解决理论分析不足问题 reinforcement learning
17 Hierarchical Multi-Relational Graph Representation Learning for Large-Scale Prediction of Drug-Drug Interactions 提出层次化多关系图表示学习以解决药物间相互作用预测问题 representation learning
18 Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning 提出IIE方法以解决多智能体强化学习中的有效探索问题 reinforcement learning
19 Classes Are Not Equal: An Empirical Study on Image Recognition Fairness 提出图像识别公平性研究以解决类别不平衡问题 representation learning contrastive learning ✅
20 MMSR: Symbolic Regression is a Multi-Modal Information Fusion Task 提出MMSR以解决符号回归中的多模态信息融合问题 reinforcement learning contrastive learning ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页