cs.CL（2026-07-08）

📊 共 12 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) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning	提出SciReasoner以解决结构-属性关系理解问题	large language model foundation model multimodal
2	TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models	提出TF-Engram以解决大语言模型知识扩展问题	large language model
3	Comprehensive Evaluation of Large Language Model Responses: A Multi-Factor Scoring System	提出多因素评分系统以全面评估大语言模型响应质量	large language model
4	Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale	提出激活分散度以区分实体熟悉度与事实可靠性	large language model
5	MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning	提出MILES框架以优化LLM推理中的记忆选择问题	large language model
6	SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation	提出SynthAVE以解决电商属性提取标注成本高的问题	large language model
7	From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization	提出STRACE框架以解决长时间代理优化中的噪声问题	large language model	✅
8	Understanding Interpretation Difficulty in Harmful Online Communication: Insights from Cybercrime Communities	提出对网络犯罪社区有害通信的理解方法以解决解读困难问题	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Future Confidence Distillation in Large Language Models	提出未来信心蒸馏以提升大语言模型的置信度估计	distillation large language model
10	Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation	提出行为杠杆不平衡以优化多教师在线蒸馏训练	distillation
11	DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation	提出DiaLLM以解决英语方言生成的鲁棒性问题	reward design large language model
12	Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?	提出层次化搜索代理以优化模型容量分配问题	distillation large language model	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页