cs.CL（2026-07-09）

📊 共 14 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition	提出JAM框架以解决个性识别中的理论依赖问题	large language model
2	Structured Pruning of Large Language Models via Power Transformation and Sign-Preserving Score Aggregation with Adaptive Feature Retention	提出改进的结构化剪枝方法以解决大语言模型的适应性特征保留问题	large language model
3	Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models	提出隐式解码方法以解决大语言模型计算扩展问题	large language model
4	What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness	通过内部表示探测提升语言模型的校准与可信度	large language model chain-of-thought
5	UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks	提出UniClawBench以解决现有主动智能体评估不足问题	large language model multimodal	✅
6	MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction	提出MASTE以解决零-shot方面情感三元组提取问题	large language model chain-of-thought	✅
7	Prompt Compression via Activation Aggregation	通过激活聚合实现提示压缩以提升语言模型效率	large language model
8	UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing	提出UltraX以解决大规模预训练数据编辑效率和质量问题	large language model
9	ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents	提出LLM辅助的OCR后校正方法以解决历史文献中的OCR错误问题	large language model
10	PLURAL: A Global Dataset for Value Alignment	提出PLURAL数据集以解决语言模型价值对齐问题	large language model	✅
11	Token-Flow Firewall: Semantic Runtime Auditing for Persistent AI Agents	提出Token-Flow Firewall以解决持久AI代理的安全问题	large language model
12	Grounded Event Extraction from SEC 8-K Filings with a Fine-Grained Taxonomy	提出基于细粒度分类法的SEC 8-K文件事件提取方法	large language model
13	From Execution to Education: A Bloom-Aligned Framework for Measuring Educational Control in LLMs	提出Bloom对齐框架以测量LLMs的教育控制能力	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
14	SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation	提出SQuaD-SQL以提升小型语言模型在Text-to-SQL任务中的效率	distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页