cs.CL（2026-10-15）

📊 共 48 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) (9) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#题目一句话要点标签🔗⭐
1 Multimodal AI Detection for Math-Heavy Scientific Text 提出多模态AI检测方法以解决数学密集科学文本的识别问题 large language model multimodal
2 Beyond Invariance: Factor-wise Selective Treatment of Shifts for Multimodal Learning 提出FaShift框架以解决多模态学习中的分布偏移问题 multimodal
3 Multi-SFT: Permissively-Licensed Multilingual Instruction-Following 提出Multi-SFT以解决多语言指令跟随数据集不足问题 instruction following
4 Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling 提出Intern-Decision以提升多模态决策效率 multimodal
5 Name-Bias in Large Language Models 评估大型语言模型中的姓名偏见问题 large language model
6 TEM: Temporal State Tracking Memory for Large Language Model Agents 提出TEM以解决大语言模型代理的记忆更新问题 large language model
7 Data Strategies for Large Language Models: A Unified Perspective on the Training Lifecycle 提出统一的数据策略以优化大语言模型训练过程 large language model ✅
8 VALCON: Benchmarking and Enhancing Value Consistency in Large Language Models via Dual-Role Variation 提出VALCON框架以解决大语言模型价值一致性问题 large language model ✅
9 Making every stage of medical device document assessment with large language models deterministic 提出确定性评估框架以解决医疗设备文档评估不一致问题 large language model
10 KBS: A Korean Benchmark Suite for Foundation Model Evaluation 提出KBS基准套件以评估基础模型在韩语环境下的表现 foundation model
11 From Long Context to Selective Memory:A Survey of Memory-Centric Compression for Large Language Models 提出记忆中心压缩方法以解决长上下文处理问题 large language model
12 Reliable Knowledge Acquisition for Continual Learning Agents 提出RIKA以解决持续学习中知识可靠性问题 foundation model
13 DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents 提出DialFork以评估对话体中的程序性幻觉问题 large language model ✅
14 Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents 提出SpecAgent以优化工具使用代理的任务执行效率 large language model
15 System1-Arena: Which Decisions Can Be Left to System 1? 提出System1-Arena基准以评估决策模型的能力 large language model
16 Change the Number, Change the Answer: Assessing Rating Scale Sensitivity in LLM-Based Text Scoring 提出量表敏感性评估方法以提高LLM文本评分可靠性 large language model
17 Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization 提出混合专家模型以解决大语言模型个性化问题 large language model
18 Rethinking the Role of Tool Graph Memory in Multi-Turn Tool Use 重新思考工具图记忆在多轮工具使用中的作用 large language model
19 PremiseSQL: Evaluating Premise Critique and Abstention in Text-to-SQL Systems 提出PremiseSQL以解决NL2SQL系统中的前提缺陷问题 large language model ✅
20 Behavioral Forgetting Is Not Privacy in Machine Unlearning 提出跨语言查询评估以改进机器遗忘隐私性 large language model
21 Translation Circuit Discovery and Targeted Optimization for Low-Resource Multilingual Translation 提出TITAN框架以优化低资源多语言翻译 large language model
22 RenoLayout: Unified Floorplan Renovation and Furniture Layout for Constraint-Aware Residential Design 提出RenoLayout以解决住宅设计中的空间依赖问题 instruction following
23 Emotion Is Not External Knowledge: Internal Attention Signals for Affective State Reasoning 提出自目标内部注意力增强方法以提升情感状态推理 large language model
24 VoteGEO-Bench: Measuring the Impact of Generative Engine Optimization on Electoral Visibility 提出VoteGEO-Bench以评估生成引擎优化对选举信息可见性的影响 large language model
25 FGSS-BO: Feedback-Guided Hypothesis Management for LLM-Based Bayesian Optimization 提出FGSS-BO以改进LLM引导的贝叶斯优化 large language model
26 ReviewPilot: A Multi-Agent System for Screening and Data Extraction in Systematic Reviews 提出ReviewPilot以自动化系统评价中的文献筛选与数据提取 large language model ✅
27 A Plausible Explanation Is Enough to Mislead Multimodal Judges 提出JUPE基准以揭示多模态模型的判断偏差 large language model multimodal chain-of-thought
28 CoLU: Confidence-Weighted Layerwise Unlearning for Large Language Models 提出CoLU以解决大语言模型的选择性遗忘问题 large language model
29 Measuring Mechanistic Uncertainty in Large Language Models via Causal Robustness 提出机械不确定性概念以解决大语言模型的可靠性问题 large language model
30 AuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems 提出AuditKIT以统一评估大型语言模型和智能系统 large language model
31 Multimodal Filesystem Memory For Long-Horizon Embodied Agents 提出多模态文件系统记忆以解决长时间交互中的经验重用问题 multimodal
32 alkhder at ImageEval 2026 Shared Tasks: Constrained Selection and Rotation-Averaged Logit Scoring for Multimodal Hallucination Detection 提出基于旋转平均逻辑评分的多模态幻觉检测方法 multimodal
33 Explore Separately, Adopt Selectively: Execution-Guided Tool Use over Large Tool Libraries 提出BRIA以解决大工具库中的工具选择问题 large language model
34 Risk and Refusal: Mechanisms of LLM Responses to Suicidal Ideation 提出针对自杀意念的LLM响应机制以提高安全性 large language model
35 Cultural (In)Competence: Investigating Culture-Specific Stereotype Detection Capabilities of LLMs 探讨LLMs在文化特定刻板印象检测中的能力 large language model
36 Literal Lock-In: How Test Language Shifts Literal Attraction in Typed Decision Models on Bengali Idioms 提出语言测试对决策模型的影响分析以解决语义理解问题 chain-of-thought ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
37 OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling 提出OmniVerifier-C1以解决多模态生成世界建模中的验证问题 reinforcement learning world model world models
38 Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence 提出PACE以解决多模态RLVR中的奖励信号不均衡问题 reinforcement learning multimodal
39 Learning Speech Attribute Representations via Multi-Teacher Distillation 提出多教师蒸馏框架以同时学习多种语音属性 distillation motion representation
40 Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing 提出Hy-Memory-30B-A3B以解决长时记忆写入问题 reinforcement learning distillation large language model
41 Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods 通过对抗训练和蒸馏方法缓解音频增强大语言模型中的偏见 distillation large language model
42 OPRD: On-Policy Reminder Distillation for Long-Horizon Coding Agents 提出OPRD以解决长时间编码代理的反馈响应问题 distillation instruction following
43 LLM-Based Weak Annotation for Cybersecurity Tweet Classification: A Teacher-Student Framework 提出教师-学生框架以解决网络安全推文分类中的标注瓶颈问题 teacher-student large language model
44 Mosaic: Multi-Session Agentic Reinforcement Learning 提出Mosaic以解决多会话强化学习中的轨迹不匹配问题 reinforcement learning
45 Training Reasoning Models to Generate Diverse Scientific Ideas 提出基于强化学习的多样化科学创意生成模型 reinforcement learning large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
46 Identifying Effective Strategies in Prompt Evolution for Stress and Emotion Prediction 提出有效的提示演变策略以改善压力与情绪预测 motion prediction large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
47 A misinformation playbook sharpens judgement without breeding cynicism 提出一种新防御策略以应对虚假信息的影响 manipulation

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
48 ProPerAgent: Toward Memory-Driven Proactive Assistance 提出ProPerAgent以解决记忆驱动的主动辅助问题 egocentric

⬅️ 返回 cs.CL 首页 · 🏠 返回主页