cs.CL（2026-07-14）

📊 共 11 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) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Epistemic Stance Flexibility Probing: Measuring Prompt-Conditioned Register Shift in Large Language Models	提出ESFP基准以评估语言模型的认知立场灵活性	large language model instruction following
2	Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations	提出ThReadMed-QA以评估多轮医疗对话中的误解问题	large language model
3	Segregate, Refine, Integrate: Decomposing Multimodal Fusion for Sentiment Analysis	提出SeRIn以解决多模态融合中的信号精炼与交互建模问题	multimodal
4	Language Identification with Succinct Machine-Independent Traces	提出小字母表的计算追踪以解决语言识别问题	large language model chain-of-thought
5	PalmClaw: A Native On-Device Agent Framework for Mobile Phones	提出PalmClaw框架以提升移动设备上的智能代理性能	large language model	✅
6	Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?	探讨情感诱导对大语言模型决策行为的影响	large language model
7	The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context	揭示任务无关上下文对语言模型预测的影响	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	🔗	⭐
8	From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation	提出CARE-PPO框架以解决语言预测中的信心估计问题	reinforcement learning PPO instruction following
9	Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning	提出Ring-Zero以解决大规模零强化学习的推理能力问题	reinforcement learning chain-of-thought

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill	提出KnowAct-GUIClaw以解决OpenClaw的GUI交互与自我进化问题	manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction	提出系统性元评估以优化LLM生成的评估标准	affordance

⬅️ 返回 cs.CL 首页 · 🏠 返回主页