cs.LG（2024-02-23）

📊 共 28 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (11 🔗1) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱八：物理动画 (Physics-based Animation) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Multimodal Transformer With a Low-Computational-Cost Guarantee 提出低计算成本的多模态Transformer以解决计算复杂性问题 multimodal
2 On Trojan Signatures in Large Language Models of Code 探讨代码大语言模型中的特洛伊签名问题 large language model
3 MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs 提出MegaScale以解决大规模语言模型训练效率与稳定性问题 large language model
4 GraphEdit: Large Language Models for Graph Structure Learning 提出GraphEdit以解决图结构学习中的显式信息依赖问题 large language model ✅
5 Towards Efficient Active Learning in NLP via Pretrained Representations 提出通过预训练表示加速NLP中的主动学习 large language model
6 How Do Nonlinear Transformers Learn and Generalize in In-Context Learning? 提出非线性Transformer的训练动态分析以提升上下文学习能力 large language model
7 Explorations of Self-Repair in Language Models 探讨语言模型中的自我修复机制 large language model
8 GPTVQ: The Blessing of Dimensionality for LLM Quantization 提出GPTVQ以提升大语言模型量化的准确性与效率 large language model
9 ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition 提出ChunkAttention以解决长序列自注意力延迟问题 large language model
10 Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition 提出统一框架以理解Grokking、双重下降与新兴能力 large language model
11 Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer 提出HiZOO优化器以解决大语言模型微调中的内存问题 large language model
12 Studying LLM Performance on Closed- and Open-source Data 研究大型语言模型在闭源与开源数据上的表现差异 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
13 Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization 提出结合深度强化学习与Black-Litterman模型的组合以优化投资组合 reinforcement learning deep reinforcement learning DRL
14 Genie: Generative Interactive Environments 提出Genie以生成无标签视频的交互式虚拟环境 world model world models spatiotemporal
15 Efficient State Space Model via Fast Tensor Convolution and Block Diagonalization 提出高效状态空间模型以解决长序列建模效率问题 Mamba SSM state space model ✅
16 Smooth and Sparse Latent Dynamics in Operator Learning with Jerk Regularization 提出连续算子学习框架以解决时空建模中的动态平滑性问题 latent dynamics spatiotemporal
17 Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding 提出轨迹导向的迭代强化学习框架以解决自动竞价问题 reinforcement learning offline RL
18 United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once 提出自监督对比预训练方法以解决时间序列表示学习问题 representation learning
19 Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation 提出在线分布鲁棒强化学习以解决动态不确定性问题 reinforcement learning
20 Shapley Value Based Multi-Agent Reinforcement Learning: Theory, Method and Its Application to Energy Network 基于Shapley值的多智能体强化学习解决信用分配问题 reinforcement learning
21 When in Doubt, Think Slow: Iterative Reasoning with Latent Imagination 提出迭代推理与潜在想象以提升强化学习代理性能 reinforcement learning world model world models
22 Smoothed Graph Contrastive Learning via Seamless Proximity Integration 提出平滑图对比学习以解决负样本处理不均问题 contrastive learning
23 Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms 提出离线逆强化学习新解法以应对数据限制问题 reinforcement learning inverse reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
24 Foundation Policies with Hilbert Representations 提出无监督框架以解决强化学习中的通用策略预训练问题 locomotion manipulation reinforcement learning
25 Data/moment-driven approaches for fast predictive control of collective dynamics 提出数据驱动方法以加速集体动态的预测控制 MPC model predictive control
26 Fair Resource Allocation in Multi-Task Learning 提出FairGrad以解决多任务学习中的公平资源分配问题 manipulation reinforcement learning ✅

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

#题目一句话要点标签🔗⭐
27 Spatiotemporal Observer Design for Predictive Learning of High-Dimensional Data 提出时空观察者以解决高维数据预测问题 spatiotemporal
28 Real-Time FPGA Demonstrator of ANN-Based Equalization for Optical Communications 提出基于ANN的均衡器以解决光通信系统中的信号失真问题 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页