cs.CL（2026-09-18）

📊 共 12 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) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

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

#	题目	一句话要点	标签	🔗	⭐
1	Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction	提出Omni Demand Understanding以解决多模态交互中的用户需求推断问题	multimodal
2	Evaluating In-Context Learning and Retrieval Strategies for Devanagari Post-OCR Correction	提出CharBM25策略以提升德瓦纳加里后OCR校正效果	large language model	✅
3	When Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap	提出潜在到语言过渡差距以解决语言模型控制问题	chain-of-thought
4	Chinese Competitive Debating Dataset and Benchmark	提出中文辩论数据集与基准以评估语言模型理解能力	large language model
5	Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30	通过道德基础引导大型语言模型的响应	large language model
6	From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers	提出情境-内在状态-行为角色框架以提升社交媒体影响者的角色扮演能力	large language model
7	An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency	提出可解释的记忆决策控制器以解决大语言模型的信任问题	large language model
8	CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation	提出系统化防御组合以应对大型语言模型的越狱攻击	large language model
9	Conformal Privacy Auditing: Calibrated Re-identification Attacks with Statistical Guarantees	提出共形隐私审计以解决身份重识别风险问题	large language model
10	I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance	提出主动音频辅助以解决传统音频模型反应不足问题	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
11	MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance	提出MIRAGE框架以提升大语言模型的推理能力	reinforcement learning large language model chain-of-thought
12	ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RL	提出ArenaFlow以解决开放式智能体强化学习中的奖励稀缺问题	reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页