cs.CL（2026-08-21）

📊 共 13 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) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning	提出记忆增强压缩以解决链式思维推理效率问题	large language model chain-of-thought
2	PromptResponse: Optimizing Prompts for LLM Coding Tasks	提出PromptResponse以优化LLM编码任务的提示	large language model
3	Target-Aware Calibration Data Selection for Preserving Uncertainty in Quantized Language Models	提出目标感知的校准数据选择以保持量化语言模型的不确定性	large language model
4	Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy	提出心理治疗移动分类法以改善LLM的治疗效果	large language model
5	Benchmarking Patent Drafting from Inventor-Style Disclosures	提出Dis2Pat数据集与Patent-MAF框架以解决专利撰写挑战	large language model
6	Affective Context Amplifies Sycophancy in LLM Responses	研究情感背景对大型语言模型谄媚行为的影响	large language model
7	When the Feature Pool Goes Algorithmic: Extending Mufwene's Ecology of Language Evolution to LLM-Mediated Exposure	提出算法重加权机制以解决语言演化中的选择问题	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	🔗	⭐
8	STAR-OPD: Structured Aspect-Cascade-Aware On-Policy Reward Distillation for ABSA Quadruple Extraction	提出STAR-OPD以解决ABSA四元组提取中的蒸馏问题	distillation chain-of-thought
9	Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs	提出量化感知修复以恢复压缩的4位LLM性能	distillation large language model
10	SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields	提出SAC-Copula以解决扩散语言模型水印质量下降问题	SAC
11	ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction	提出ForeDreamer以解决开放网络未来事件预测问题	dreamer	✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation	提出MentorPulse以解决长文本生成中的静态指导问题	PULSE instruction following

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Jokes Aside: Measuring the Semantic Distance of Double Meanings	提出基于语义距离的新指标以改进幽默生成模型	HuMoR large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页