cs.CL（2026-06-15）

📊 共 39 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (27 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (8) 支柱一：机器人控制 (Robot Control) (3) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (27 篇)

#题目一句话要点标签🔗⭐
1 XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models 提出无训练的多模态大语言模型生成语音深伪检测的可解释性解释 large language model multimodal
2 Robust Dual-Signal Fusion: Hybrid Neuro-Symbolic Gating with Compressed Chain-of-Thought Refinement for Irony Detection in Social Media Texts 提出鲁棒双信号融合框架以解决社交媒体文本中的讽刺检测问题 large language model chain-of-thought
3 Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences 提出LOGOS模型以统一自然科学中的多任务生成语言 large language model foundation model
4 Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering 提出金位置协议以解决多模态问答中的首位偏差问题 multimodal
5 Creative Collision: Directorial Persona Steering and Competition in Large Language Models 提出创意碰撞方法以增强大语言模型的可控性 large language model
6 AuAu: A Benchmark for Auditing Authoritarian Alignment in Large Language Models 提出AuAu基准以审计大型语言模型的威权主义倾向 large language model ✅
7 The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models 提出MIXGUARD以解决隐私保护分割学习中的实用性与安全性问题 large language model
8 Progressive Knowledge-Guided Large Language Model Framework for Bearing Fault Diagnosis 提出渐进式知识引导的大语言模型框架以解决轴承故障诊断问题 large language model
9 FraudSMSWalker: Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection 提出FraudSMSWalker以解决SMS到网页的欺诈检测问题 large language model
10 Islamic Large Language Models: From Knowledge Acquisition to Trustworthy and Hallucination-Resistant AI 提出伊斯兰大型语言模型以解决知识获取与可信性问题 large language model
11 Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate 提出Tyler框架以优化语言模型的潜在推理过程 large language model chain-of-thought
12 Tying the Loop -- Tied Expert Layers in Mixture-of-Experts Language Models 提出专家参数共享以降低Mixture-of-Experts模型内存占用 large language model
13 P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portuguese Variety Bias in LLMs 提出P3B3基准以解决葡萄牙语变体偏见问题 large language model
14 A Mechanistic Understanding of Pronoun Fidelity in LLMs 提出机制性理解以提升大语言模型的代词忠诚度 large language model
15 Evaluating LLM Personalization via Semantic Constraint Verification 提出NLICV框架以解决LLM个性化评估的局限性 large language model
16 Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens 提出ASRD以解决扩散大语言模型中的解码速度与质量权衡问题 large language model
17 ACCORD: Action-Conditioned Contextual Grounding for Language Agents 提出ACCORD框架以解决语言代理中的上下文缺失问题 large language model
18 LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching 提出LectūraAgents框架以解决个性化学习与教学的挑战 multimodal
19 LESS Is More: Mutual-Stability Sampling for Diffusion Language Models 提出LESS以解决扩散语言模型采样效率问题 large language model
20 Revisiting the Systematicity in Negation in the Era of In-Context Learning 分析LLM在否定理解中的系统性以提升性能 large language model
21 LLM-based Visual Code Completion for Aerospace Geometric Design 提出基于LLM的视觉编程助手以解决航空几何设计问题 large language model
22 SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents 提出SING框架以解决大规模工具发现中的意图匹配问题 large language model
23 The BD-LSC Dataset: Facilitating the Benchmarking of Models for Lexical Semantic Change Detection in Slang and Standard Usage 提出BD-LSC数据集以解决词义变化检测中的双向挑战 large language model
24 Can LLM Coding Agents Reason About Time Series? 提出编码代理以提升时间序列分析能力 large language model
25 From Awareness to Adherence: Bridging the Context Gap in Spoken Dialogue Systems via Context-Aware Decoding 提出音频适应的上下文感知解码以解决对话系统的上下文遵循问题 multimodal
26 TMASC: Transmasculine Attitude and Speech Corpus 提出TMASC语料库以支持跨男性个体的声音健康研究 multimodal
27 Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization 提出ParetoPO以解决工具集成代理的多目标优化问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
28 Context-Aware RL for Agentic and Multimodal LLMs 提出ContextRL以解决长时推理和多模态性能不足问题 reinforcement learning large language model multimodal
29 Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning 提出代理自动机学习以评估LLM代理的环境推断能力 world model world models
30 Exploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code Interpreter 提出基于代码解释器的推理方法以提升大型语言模型能力 reinforcement learning large language model
31 Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Services 提出GhostPrint以解决LLM指纹伪造问题 distillation large language model
32 The Value Axis: Language Models Encode Whether They're on the Right Track 提出价值轴以评估语言模型的决策信心 reinforcement learning DPO direct preference optimization
33 DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents 提出DeepRubric以解决深度研究代理的奖励效率问题 reinforcement learning
34 Data-Driven Decoding of Russell's Circumplex Model of Affect 提出数据驱动框架以验证拉塞尔情感模型 representation learning multimodal
35 Long-Context Modeling via GSS-Transformer Hybrid Architecture with Learnable Mixing 提出并行混合架构以解决长范围依赖建模问题 SSM state space model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
36 How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation 提出SearchGEO框架以评估LLM搜索代理的推荐可靠性 manipulation large language model
37 IMPACTeen: Intentions, Manipulation, Persuasion, Annotations, and Consequences in Teen Communication Dataset 提出IMPACTeen数据集以解决青少年社交影响研究问题 manipulation
38 DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing 提出DoubtProbe以解决黑箱越狱防御问题 manipulation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
39 Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models 提出反射掩蔽以增强掩蔽扩散模型的推理能力 MDM chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页