cs.CL（2025-09-07）

📊 共 13 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) (13 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge	提出基于图文描述辅助的多模态推理框架，解决科学问题理解难题。	multimodal	✅
2	Uncovering the Vulnerability of Large Language Models in the Financial Domain via Risk Concealment	提出风险隐藏攻击RCA，揭示金融领域大语言模型在监管风险上的脆弱性	large language model
3	Benchmarking Gender and Political Bias in Large Language Models	提出 EuroParlVote 基准测试，用于评估大型语言模型在性别和政治偏见上的表现。	large language model
4	Generating Individual Travel Diaries Using Large Language Models Informed by Census and Land-Use Data	提出基于大型语言模型（LLM）的个体出行日记生成方法，利用人口普查和土地利用数据提升生成质量。	large language model
5	Assisting Research Proposal Writing with Large Language Models: Evaluation and Refinement	提出基于内容质量和引用有效性的评估指标，并结合迭代提示优化LLM的研究计划书写作能力	large language model
6	Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal	利用稀疏自编码器剖析大语言模型拒绝行为，实现可控的越狱攻击	large language model
7	Orthogonal Low-rank Adaptation in Lie Groups for Continual Learning of Large Language Models	OLieRA：基于李群的正交低秩自适应方法，用于大语言模型的持续学习	large language model
8	Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis	提出MFCIG-CSS以解决对话语音合成中的细粒度上下文交互建模问题	multimodal	✅
9	KatotohananQA: Evaluating Truthfulness of Large Language Models in Filipino	KatotohananQA：构建菲律宾语TruthfulQA基准，评估大语言模型真实性	large language model
10	Accelerating Large Language Model Inference via Early-Exiting Algorithms	通过早退算法加速大型语言模型推理，解决动态推理的系统瓶颈问题。	large language model
11	Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes	研究LLM对齐方法如何影响多智能体协作决策	large language model
12	MSLEF: Multi-Segment LLM Ensemble Finetuning in Recruitment	MSLEF：多段LLM集成微调框架，提升招聘自动化中简历解析精度	large language model
13	Augmented Fine-Tuned LLMs for Enhanced Recruitment Automation	提出增强型微调LLM，提升招聘自动化流程的精度与效率	large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页