cs.CL（2026-09-25）

📊 共 19 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) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting 提出基于度量的损失加权方法以提升多模态机器翻译的视觉敏感性 large language model multimodal visual grounding
2 ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs 提出ViSTA以解决临床时间序列理解中的视觉对齐问题 large language model multimodal
3 Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models 提出EoupCT框架以解决大语言模型的持续微调遗忘问题 large language model
4 RupeeBias: Auditing Demographic Bias in Indian Economic Guidance from Large Language Models 提出RupeeBias以审计印度经济指导中的人口统计偏见 large language model
5 Evaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries 评估中文大型语言模型在事实问题上的谄媚性 large language model
6 LocUS: Head Selection and Subspace Projection for Targeted Activation Steering 提出LocUS以解决激活引导中的目标干扰问题 large language model
7 Evaluating Cultural Awareness of LLMs for Haitian Creole 评估大型语言模型在海地克里奥尔语中的文化意识 large language model
8 Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding 提出Highlight-Then-Summarize以解决长文本理解中的证据稀疏问题 large language model
9 G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation 提出G$^2$PTQ以解决LLM后训练量化中的梯度滞后问题 large language model ✅
10 Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference 利用LLMs和知识图谱推理建模学生的意义构建 large language model
11 FAVoR: Measuring and Mitigating Author-Style Homogenization in Federated Personalized Generation 提出FAVoR以解决联邦个性化生成中的作者风格同质化问题 large language model
12 Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance 提出随机化中间指导以提升双向语音模型的自然对话行为 large language model
13 Prompt Injection Detection for Email Agents Through Attack Chain Modeling 提出基于攻击链建模的电子邮件代理提示注入检测方法 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
14 ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning 提出ToolSearcher以解决大规模工具选择问题 reinforcement learning large language model
15 Persistent Negatives for Adversarial Black-Box On-Policy Distillation 提出持久负样本以解决对抗性黑箱在线蒸馏问题 distillation
16 ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker 提出ZooWork-ShopRanker以解决电商重排中的用户偏好问题 distillation large language model
17 Understanding the Role of Prompt Template in Knowledge Distillation for Safety Alignment 探讨提示模板在知识蒸馏中的作用以提升安全对齐 distillation ✅
18 Recursive Self-Improvement via On-Policy Distillation for Reasoning 提出递归自我改进方法以提升推理能力 distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 Where a Model Sends Its Own Repeated Token 提出模型自我重复标记的识别方法以探究失败模式 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页