cs.LG（2024-10-06）

📊 共 11 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) (6) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective	全面分析硬件平台对大语言模型推理加速的影响与优化方法	large language model multimodal
2	Large Language Models for Knowledge-Free Network Management: Feasibility Study and Opportunities	利用大型语言模型实现知识无关的网络管理	large language model foundation model
3	EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles	EnsemW2S：利用大语言模型集成提升弱到强泛化能力	large language model
4	Hammer: Robust Function-Calling for On-Device Language Models via Function Masking	Hammer：通过函数掩码实现设备端语言模型稳健的函数调用	large language model foundation model
5	On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective	提出贝叶斯视角评估框架，揭示LLM作为函数逼近器的能力局限与优势	large language model
6	Continuous Approximations for Improving Quantization Aware Training of LLMs	提出连续近似方法，提升LLM量化感知训练的性能	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	🔗	⭐
7	Latent Feature Mining for Predictive Model Enhancement with Large Language Models	提出FLAME框架，利用大语言模型挖掘潜在特征，提升预测模型在弱相关数据场景下的性能。	predictive model large language model
8	Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF	提出REFUEL，解决LLM多轮对话中因协变量偏移导致的策略优化难题。	reinforcement learning RLHF DPO	✅
9	Robustness Reprogramming for Representation Learning	提出鲁棒性重编程方法，无需修改模型参数即可提升模型抗扰动能力	representation learning
10	AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning	AdaMemento：面向稀疏奖励强化学习的自适应记忆增强策略优化	reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Bisimulation metric for Model Predictive Control	提出基于Bisimulation Metric的MPC方法，提升模型预测控制的稳定性和鲁棒性。	MPC model predictive control reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页