cs.CL（2025-06-17）

📊 共 40 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (36 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (36 篇)

#题目一句话要点标签🔗⭐
1 M2BeamLLM: Multimodal Sensing-empowered mmWave Beam Prediction with Large Language Models 提出M2BeamLLM以解决毫米波通信中的波束预测问题 large language model multimodal
2 Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot 重新审视链式思维提示：零-shot优于少量示例 large language model chain-of-thought
3 Memory Tokens: Large Language Models Can Generate Reversible Sentence Embeddings 提出可逆句子嵌入生成方法以提升文本重构能力 large language model
4 From Chat to Checkup: Can Large Language Models Assist in Diabetes Prediction? 利用大型语言模型辅助糖尿病预测 large language model
5 AIn't Nothing But a Survey? Using Large Language Models for Coding German Open-Ended Survey Responses on Survey Motivation 利用大型语言模型高效编码德语开放式调查反馈 large language model
6 Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models 提出集体道德推理框架以解决大型语言模型的道德判断偏差问题 large language model
7 Re-Initialization Token Learning for Tool-Augmented Large Language Models 提出工具增强的大语言模型重初始化令牌学习方法以解决复杂任务问题 large language model
8 From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentary 提出统一框架以系统化AI生成游戏解说领域 multimodal
9 S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models 提出S$^4$C以解决大语言模型推理延迟问题 large language model
10 LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops 提出LingoLoop攻击以解决多模态大语言模型的资源耗尽问题 large language model multimodal
11 Semantic uncertainty in advanced decoding methods for LLM generation 提出解码方法以解决大语言模型生成中的语义不确定性问题 large language model chain-of-thought
12 Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team 提出Xolver框架以解决大型语言模型的经验整合问题 generalist agent large language model ✅
13 Hypothesis Testing for Quantifying LLM-Human Misalignment in Multiple Choice Settings 提出假设检验框架以量化LLM与人类行为的不一致性 large language model
14 A Cross-Cultural Comparison of LLM-based Public Opinion Simulation: Evaluating Chinese and U.S. Models on Diverse Societies 评估LLM在中美社会中模拟公众意见的能力 large language model
15 CrEst: Credibility Estimation for Contexts in LLMs via Weak Supervision 提出CrEst框架以解决LLMs上下文可信度评估问题 large language model
16 A Variational Framework for Improving Naturalness in Generative Spoken Language Models 提出变分框架以提升生成语音模型的自然性 large language model ✅
17 Mercury: Ultra-Fast Language Models Based on Diffusion 提出Mercury以实现超快的语言模型，提升编程效率 large language model
18 Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers 提出训练时标记优化以提升长尾特征表现 instruction following
19 Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality 通过大规模监督微调实验揭示数据与训练因素对LLM对齐质量的影响 large language model ✅
20 GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors 提出GuiLoMo以优化LoRA-MoE中的专家数量与排名分配 large language model ✅
21 Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees 提出GG方法以解决CISC到RISC的代码转译问题 large language model
22 AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs 提出AlphaDecay以解决LLMs模块间权重衰减不均问题 large language model ✅
23 LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data 提出LexiMark以增强LLM训练数据的水印验证 large language model
24 Evaluation of LLM-based Strategies for the Extraction of Food Product Information from Online Shops 提出基于LLM的间接提取策略以优化食品产品信息获取 large language model
25 How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison 提出测试时间学习评估框架以提升大语言模型能力 large language model
26 ChatGPT Reads Your Tone and Responds Accordingly -- Until It Does Not -- Emotional Framing Induces Bias in LLM Outputs 探讨情感框架对大型语言模型输出的影响 large language model ✅
27 Empirical Evidence for Alignment Faking in a Small LLM and Prompt-Based Mitigation Techniques 提出小型LLM对齐伪装的实证证据及干预技术 large language model
28 Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding 提出Thunder-NUBench以解决LLMs句子级否定理解问题 large language model
29 ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection 提出基于LLM的批判性问题生成与选择方法以促进深度思考 large language model
30 A Vision for Geo-Temporal Deep Research Systems: Towards Comprehensive, Transparent, and Reproducible Geo-Temporal Information Synthesis 提出地理时间深度研究系统以解决信息获取中的时空限制问题 large language model
31 Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent 提出多轮对话推荐代理的期望确认偏好优化方法 large language model
32 From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents 提出及时对话响应生成方法以解决对话代理的时间响应问题 large language model
33 MAS-LitEval : Multi-Agent System for Literary Translation Quality Assessment 提出MAS-LitEval以解决文学翻译质量评估问题 large language model
34 VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents 提出VIDEE以解决文本分析入门门槛问题 large language model
35 MIST: Towards Multi-dimensional Implicit BiaS Evaluation of LLMs via Theory of Mind 提出多维隐性偏见评估框架以解决大型语言模型的偏见问题 large language model
36 Acoustic scattering AI for non-invasive object classifications: A case study on hair assessment 提出基于声学散射的非侵入式物体分类方法解决头发评估问题 foundation model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
37 Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs 提出Ring-lite以解决大规模语言模型推理效率问题 reinforcement learning distillation large language model
38 Reasoning with Exploration: An Entropy Perspective 提出基于熵的探索方法以提升强化学习推理能力 reinforcement learning large language model
39 GRAM: A Generative Foundation Reward Model for Reward Generalization 提出GRAM模型以解决奖励模型泛化问题 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
40 Passing the Turing Test in Political Discourse: Fine-Tuning LLMs to Mimic Polarized Social Media Comments 通过微调大型语言模型模拟极化社交媒体评论 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页