cs.CL（2026-06-16）

📊 共 19 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) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings 提出多模态大语言模型以解决会议中的发言者预测问题 large language model multimodal
2 AIPatient Arena: EHR-grounded evaluation of large language models in end-to-end clinical consultation workflows 提出AIPatient Arena以解决医疗咨询中LLMs评估不足的问题 large language model
3 Unintended Effects of Geographic Conditioning in Large Language Models 揭示大语言模型中地理条件的意外影响 large language model
4 The Slop Paradox: How Synthetic Standardization Erodes Clinical Uncertainty and Cross-Modal Alignment in AI-Rewritten Radiology Reports 揭示合成标准化如何影响临床不确定性与跨模态对齐 large language model multimodal
5 Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond 分析用户向LLM询问安全与隐私问题的响应质量 large language model
6 Darshana Graph: A Parallel Commentary Corpus for Comparative Indian Philosophy, with Stylometric and Exploratory Graph Analyses 提出Darshana Graph以促进印度哲学的比较研究 large language model
7 ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions 提出ChLogic基准以评估中文表达中的逻辑推理鲁棒性 large language model
8 GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine? 提出GameCraft-Bench以解决游戏生成的评估问题 multimodal ✅
9 Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation 提出SwiftTrans以解决LLM代码翻译的效率问题 large language model
10 Prompt Perturbation for Reliable LLM Evaluation over Comparison Graphs 提出提示扰动框架以解决LLM评估中的不一致性问题 large language model

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

#题目一句话要点标签🔗⭐
11 NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama 提出NarrativeWorldBench以解决长篇音频剧创作中的模型局限性问题 world model world models Mamba
12 Reading between the Lines: Leveraging Large Language Models for Global Dementia and Depression Assessment from Clinical Interviews 利用大型语言模型评估老年痴呆与抑郁症的严重程度 MAE large language model
13 Learning task-specific subspaces via interventional post-training of speech foundation models 通过干预后训练学习任务特定子空间以优化语音模型 contrastive learning foundation model
14 Learning from the Self-future: On-policy Self-distillation for dLLMs 提出d-OPSD以解决扩散大语言模型的自蒸馏问题 distillation privileged information large language model ✅
15 From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning 提出LLM设计的训练环境以优化多智能体强化学习 reinforcement learning policy learning large language model
16 SuCo: Sufficiency-guided Continuous Adaptive Reasoning 提出SuCo以解决大规模推理模型效率低下问题 reinforcement learning chain-of-thought
17 Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models 提出动态回滚编辑以解决强化学习模型过度思考问题 reinforcement learning chain-of-thought
18 OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation 提出OPD-Evolver以解决自我进化智能体的经验管理问题 distillation
19 Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients 提出ZPPO以解决小学生模仿教师问题 reinforcement learning distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页