cs.AI（2024-07-12）

📊 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) (14 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 A Neural Matrix Decomposition Recommender System Model based on the Multimodal Large Language Model 提出BoNMF模型，结合多模态大语言模型和神经矩阵分解，提升推荐系统精度。 large language model multimodal
2 Refusing Safe Prompts for Multi-modal Large Language Models MLLM-Refusal：通过对抗扰动使多模态大模型拒绝安全提示 large language model multimodal ✅
3 Inference Optimization of Foundation Models on AI Accelerators 针对AI加速器，提出基础模型推理优化方法，降低成本和延迟。 large language model foundation model
4 TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models 提出TelecomGPT框架，构建电信领域专用大语言模型 large language model
5 Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay ChildPlay：通过游戏评估大语言模型在文本理解之外的泛化能力 large language model ✅
6 Predicting and Understanding Human Action Decisions: Insights from Large Language Models and Cognitive Instance-Based Learning 利用大型语言模型和认知实例学习预测和理解人类行为决策 large language model
7 SpreadsheetLLM: Encoding Spreadsheets for Large Language Models SpreadsheetLLM：提出一种高效的表格编码方法，提升LLM在表格理解和推理任务上的能力。 large language model
8 Enhancing Few-Shot Stock Trend Prediction with Large Language Models 提出基于LLM的“去噪-投票”方法，提升小样本股票趋势预测精度 large language model
9 Human-inspired Episodic Memory for Infinite Context LLMs 提出EM-LLM以解决长序列上下文处理问题 large language model
10 MUSCLE: A Model Update Strategy for Compatible LLM Evolution MUSCLE：一种兼容LLM演进的模型更新策略，减少模型更新带来的性能退化。 large language model
11 GAVEL: Generating Games Via Evolution and Language Models GAVEL：利用进化算法和语言模型生成新颖棋盘游戏 large language model
12 ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs 提出ShadowCode以解决代码LLM的外部提示注入攻击问题 large language model ✅
13 The Two Sides of the Coin: Hallucination Generation and Detection with LLMs as Evaluators for LLMs 利用大型语言模型评估器进行幻觉生成与检测，探索LLM能力边界。 large language model
14 TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing TensorTEE：统一异构TEE粒度，实现高效安全协同张量计算 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🔗⭐
15 Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments 提出结合LLM与强化学习的层级框架，解决虚拟环境中复杂指令跟随问题 reinforcement learning large language model instruction following
16 A Benchmark Environment for Offline Reinforcement Learning in Racing Games 提出OfflineMania：用于赛车游戏中离线强化学习的基准环境 reinforcement learning offline reinforcement learning
17 Deep Attention Driven Reinforcement Learning (DAD-RL) for Autonomous Decision-Making in Dynamic Environment 提出基于深度注意力驱动强化学习的DAD-RL框架，用于动态环境中自动驾驶车辆的决策。 reinforcement learning SAC spatiotemporal
18 Constrained Intrinsic Motivation for Reinforcement Learning 提出约束内在动机(CIM)以提升强化学习在无奖励预训练和探索任务中的性能。 reinforcement learning ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
19 Graph Neural Networks with Model-based Reinforcement Learning for Multi-agent Systems 提出基于图神经网络与模型预测控制的多智能体强化学习方法 model predictive control reinforcement learning
20 MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants 提出MaPP攻击，评估对抗性提示对LLM编程助手的影响 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页