cs.CL（2026-06-03）

📊 共 35 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) (21 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (13) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026 提出基于指令的多语言长文本语音理解方法以应对新任务挑战 large language model instruction following
2 Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention 提出Entity-Aware Chain-of-Thought以解决语音LLM推理中的实体绑定失败问题 large language model chain-of-thought
3 Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases 提出MedSP1000以解决临床决策动态评估问题 large language model
4 Large Language Models in K-12 Education: Alignment with State Curriculum Standards and Student Personas 提出基于LLM的管道以评估美国历史课程标准的对齐性 large language model
5 Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models 提出动态填充锚点以解决格式约束生成问题 large language model
6 A Systematic Evaluation of Positional Bias in Multi-Video Summarization with MLLMs 研究多视频摘要中的位置偏差问题以提升MLLM性能 large language model multimodal
7 Automatic Generation of Titles for Research Papers Using Language Models 提出一种基于语言模型的自动生成研究论文标题的方法 large language model
8 Fast & Faithful Function Vectors 提出快速且可靠的函数向量以优化大语言模型的学习效果 large language model
9 SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding 提出SAID框架以加速扩散语言模型的推理过程 large language model ✅
10 Can Crowdsourcing Survive the LLM Era? A Community Survey on Human Data Collection 调查LLM时代众包数据收集的挑战与应对策略 large language model
11 Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in Lean 提出行动路由代理以优化Lean中的成本-质量权衡 large language model
12 Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents 提出Agent Planning Benchmark以解决LLM代理规划能力评估问题 multimodal
13 SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction 提出SMADE-IE以解决零-shot信息提取中的多代理冲突问题 large language model
14 Cartridges at Scale: Training Modular KV Caches over Large Document Collections 提出CAS框架以解决大规模文档集合的KV缓存问题 large language model
15 Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization 提出TAP-PER以解决大规模LLM个性化问题 large language model
16 GENEB: Why Genomic Models Are Hard to Compare 提出GENEB以解决基因组模型比较困难的问题 foundation model
17 SANE Schema-aware Natural-language Evaluation of Biological Data 提出SANE以解决生物数据访问中的SQL专业知识需求问题 large language model
18 Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation 提出SGR框架以解决LLMs多步推理中的一致性问题 large language model
19 Listening to the Workforce: Measuring Construction Worker Safety Attitudes from Social Media Discourse Using LLMs 提出建筑安全态度框架以测量工人安全态度 large language model
20 Disentangling Answer Engine Optimization from Platform Growth: A Log-Based Natural Experiment on ChatGPT Referral Traffic 提出基于日志的实验方法以优化答案引擎流量分析 large language model
21 LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding 提出LazyAttention以解决长上下文生成中的KV缓存问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (13 篇)

#题目一句话要点标签🔗⭐
22 Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM 提出基于查询的跨模态投影器以提升Mamba多模态LLM效率 Mamba large language model multimodal
23 VCIFBench: Evaluating Complex Instruction Following for Video Understanding 提出VCIFBench以评估视频理解中的复杂指令跟随能力 DPO large language model multimodal
24 Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair 提出Teleological Reasoning Infilling以解决LLMs推理链错误问题 DPO large language model chain-of-thought
25 Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models 提出CAPR算法以优化扩散语言模型的强化学习 reinforcement learning PPO large language model
26 GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards 提出GRAIL以解决强化学习中奖励分配不均问题 reinforcement learning large language model
27 LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling 提出LDARNet以解决基因组建模中的固定标记化问题 Mamba large language model foundation model
28 Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data 提出自我评估引导方法以提升大语言模型的输出质量预测 reinforcement learning distillation large language model
29 GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation 提出GARL框架以解决多智能体战略优先级问题 reinforcement learning reward design
30 DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer 提出DuDi框架以提升东南亚语言的小型语言模型性能 teacher-student distillation
31 Self-Evolving Deep Research via Joint Generation and Evaluation 提出自演化共同进化框架以解决深度研究生成与评估问题 reinforcement learning reward design large language model
32 Arithmetic Pedagogy for Language Models 提出基于人类数学教学法的语言模型算术推理训练方法 reinforcement learning chain-of-thought
33 Rethinking Continual Experience Internalization for Self-Evolving LLM Agents 提出经验内化新方法以解决LLM的能力崩溃问题 distillation large language model
34 When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling 提出基于认知行为疗法的抵抗感知框架以解决心理咨询评估不匹配问题 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🔗⭐
35 Hybrid Adversarial Defence for Natural Language Understanding Tasks 提出混合对抗防御框架以提升自然语言理解任务的鲁棒性 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页