cs.CL（2024-10-27）

📊 共 10 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation	提出基于Llama的TTS-Llama和MoLE-Llama，用于文本到语音生成及多模态问答。	large language model multimodal
2	Self-correction is Not An Innate Capability in Large Language Models	研究表明大语言模型道德自纠正能力并非天生	large language model chain-of-thought
3	Fine-Tuning and Evaluating Open-Source Large Language Models for the Army Domain	微调开源大语言模型TRACLM，并构建MilBench评估框架，提升其在陆军领域的应用能力。	large language model
4	MedGo: A Chinese Medical Large Language Model	MedGo：一个用于提升中文医疗服务质量的医学大型语言模型	large language model
5	Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chains	提出基于吸收马尔可夫链的解码策略，缓解大语言模型中的幻觉问题	large language model
6	MatViX: Multimodal Information Extraction from Visually Rich Articles	提出MatViX基准，用于评估视觉丰富型科研文章的多模态信息抽取能力。	multimodal
7	What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration	深入探索多模态上下文学习的关键影响因素，为优化策略提供指导	large language model
8	TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration	TrajAgent：通过大小模型协作的LLM-Agent轨迹建模框架	large language model	✅
9	FIRP: Faster LLM inference via future intermediate representation prediction	FIRP：通过预测未来中间表示加速LLM推理	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data	提出Stackelberg响应优化(SRO)，利用非平行数据提升LLM文本解毒能力	DPO direct preference optimization large language model	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页