cs.CL（2026-07-06）

📊 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) (8 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱二：RL算法与架构 (RL & Architecture) (2)

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

#题目一句话要点标签🔗⭐
1 LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure 提出LP-SFT以解决语言模型微调中的能力退化问题 multimodal
2 RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain 提出RABBiT模型以解决语言引发脑反应预测问题 foundation model ✅
3 Multi-Large Language Model Orchestrated Severity Assessment of Clinical Records (MOSAIC) 提出MOSAIC框架以评估临床记录中的疾病严重性 large language model
4 Evaluating Large Language Models for Antisemitic Incident Classification 提出大语言模型用于反犹太事件分类以应对仇恨事件监测 large language model
5 How Much is Left? LLMs Linearly Encode Their Remaining Output Length 提出线性探测器以估计大语言模型的剩余输出长度 large language model
6 Curated retrieval versus open web search in public AI information services: a coverage-trust trade-off 探讨公共AI信息服务中的信息来源可信度与覆盖率的权衡 large language model
7 When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games 提出一种新方法以评估自主代理的承诺可靠性 large language model
8 Semantic Homogenization in Italian Popular Music: A Diachronic Analysis 提出一种灵活高效的方法以分析意大利流行音乐歌词的语义变化 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
9 Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations 提出RetroCoT以解决语言模型安全对齐问题 manipulation large language model chain-of-thought
10 Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs 提出知识与表述分离的方法以解决数学可解性问题 manipulation

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

#题目一句话要点标签🔗⭐
11 CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning 提出CARD模型以解决音频字幕生成中的编码器瓶颈问题 distillation large language model
12 Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment 提出选择性重要性采样以解决LLM的离策略训练问题 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页