cs.AI（2023-12-14）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Personalized Autonomous Driving with Large Language Models: Field Experiments	提出Talk2Drive框架，利用大语言模型实现个性化自动驾驶，并通过实地实验验证。	large language model
2	Design, construction and evaluation of emotional multimodal pathological speech database	构建情感多模态病理语音数据库，用于研究构音障碍患者的情感表达	multimodal
3	Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent	提出PRER框架以增强LLM在复杂数学推理中的表现	large language model
4	Multi-modal Latent Space Learning for Chain-of-Thought Reasoning in Language Models	提出基于扩散过程的多模态隐空间学习方法，提升语言模型的CoT推理能力	chain-of-thought
5	Inter-Layer Scheduling Space Exploration for Multi-model Inference on Heterogeneous Chiplets	针对异构Chiplet多模型推理，提出层间调度空间探索框架	large language model
6	Rational Sensibility: LLM Enhanced Empathetic Response Generation Guided by Self-presentation Theory	提出基于自呈现理论和LLM增强的共情回复生成模型，提升回复的理性和感性。	large language model
7	ChatSOS: LLM-based knowledge Q&A system for safety engineering	ChatSOS：基于LLM的知识问答系统，用于提升安全工程领域的应用能力	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	🔗	⭐
8	Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft	Auto MC-Reward：利用大语言模型自动设计Minecraft密集奖励函数，提升强化学习效率。	reinforcement learning reward design large language model
9	Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations	提出Math-Shepherd，无需人工标注即可验证并强化LLM的数学解题过程。	reinforcement learning PPO large language model
10	On the Difficulty of Defending Contrastive Learning against Backdoor Attacks	揭示对比学习后门攻击的脆弱性，并分析其与监督学习的差异	contrastive learning
11	Efficient speech detection in environmental audio using acoustic recognition and knowledge distillation	利用声学识别和知识蒸馏，高效检测环境音频中的人类语音	distillation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Speeding up Photoacoustic Imaging using Diffusion Models	提出DiffPam算法，利用扩散模型加速光声成像重建，无需大量训练数据。	penetration PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页