cs.CL(2024-04-17)

📊 共 21 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (18 🔗2) 支柱二:RL算法与架构 (RL & Architecture) (2) 支柱一:机器人控制 (Robot Control) (1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗
1 Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent 提出Octopus v3以解决边缘设备上的多模态AI代理问题 large language model multimodal
2 Missed Connections: Lateral Thinking Puzzles for Large Language Models 探讨大语言模型在抽象推理中的应用与挑战 large language model chain-of-thought
3 ViLLM-Eval: A Comprehensive Evaluation Suite for Vietnamese Large Language Models 提出ViLLM-Eval以评估越南大型语言模型的能力 large language model foundation model
4 REQUAL-LM: Reliability and Equity through Aggregation in Large Language Models 提出REQUAL-LM以解决大型语言模型的可靠性与公平性问题 large language model
5 AI-Enhanced Cognitive Behavioral Therapy: Deep Learning and Large Language Models for Extracting Cognitive Pathways from Social Media Texts 提出基于深度学习的社交媒体认知路径提取方法以支持心理治疗 large language model
6 Offset Unlearning for Large Language Models 提出δ-Unlearning框架以解决黑箱LLM的敏感信息遗忘问题 large language model
7 Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models 提出粗到细的推理效率评估方法以优化大型语言模型 large language model
8 Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models 提出自一致性方法以提升大语言模型的数学推理能力 large language model
9 Open-Ended Wargames with Large Language Models 提出基于大型语言模型的开放式战争游戏系统以解决传统游戏局限 large language model
10 A Preference-driven Paradigm for Enhanced Translation with Large Language Models 提出基于偏好的方法以提升大语言模型翻译性能 large language model
11 Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages 提出Language Ranker以解决低资源语言LLM性能评估问题 large language model
12 Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions 提出社会智能AI代理的技术挑战与开放问题 multimodal
13 In-Context Learning State Vector with Inner and Momentum Optimization 提出状态向量优化方法以提升大语言模型的上下文学习能力 large language model
14 Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues 提出归纳-演绎策略重用以解决多轮指令对话问题 large language model
15 How often are errors in natural language reasoning due to paraphrastic variability? 提出一种新指标评估自然语言推理中的释义一致性 large language model
16 MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory 提出MemLLM以解决大语言模型记忆更新不足问题 large language model
17 Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization 提出PackLLM以解决多模型融合在测试阶段的挑战 large language model
18 Sampling-based Pseudo-Likelihood for Membership Inference Attacks 提出基于采样的伪似然方法以解决成员推断攻击问题 large language model

🔬 支柱二:RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗
19 Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning 提出TREACLE以解决预算约束下的语言模型选择问题 reinforcement learning policy learning large language model
20 A Novel ICD Coding Method Based on Associated and Hierarchical Code Description Distillation 提出基于关联与层次代码描述蒸馏的新型ICD编码方法以解决编码不当问题 representation learning distillation

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
21 Position Engineering: Boosting Large Language Models through Positional Information Manipulation 提出位置工程以提升大型语言模型的性能 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页