cs.CL（2026-10-29）

📊 共 20 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Raincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference 提出Raincheck框架以解决多轮对话中的信息利用效率问题 large language model multimodal
2 Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records 提出CEDAR模型以提高儿童糖尿病预后预测精度 large language model multimodal
3 Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin 评估低资源非洲语言中的大型语言模型安全性 large language model
4 What Makes Medical Examination Items Difficult? Using Large Language Models to Explore Patterns Associated With Empirical Item Difficulty 利用大语言模型探索医学考试项目难度的模式 large language model
5 Towards Full-Text Scholarly Argument Mining using Entity-Anchored Claim Extraction 提出基于实体锚定的主张提取方法以解决学术论文论证挖掘问题 large language model zero-shot transfer
6 How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates 提出模板增强方法以解决多语言安全对齐问题 large language model
7 Upcycling Language Models for Multiple Specialized Domains 提出领域专用的模型扩展方法以解决多领域适应问题 large language model
8 A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening 提出低秩空间方法以捕捉LLM与人类神经活动的线性对齐 large language model ✅
9 Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation 提出CORAL以解决长时间任务中的认知过载问题 large language model
10 ScienceJudge: Pattern Perturbation Augmentation for Sentence-Level Scientific Claim Verification 提出Pattern Perturbation Augmentation以解决科学声明验证问题 multimodal
11 AI Cosmos: An Agentic Infra for Situated Learning 提出AI Cosmos以解决学习者独立应用知识的能力不足问题 large language model
12 AgentHeal: Evaluating Goal-Preserving Resource Recovery of Web Agents under Access Barriers 提出AgentHeal以解决网络代理在访问障碍下的资源恢复问题 large language model
13 Qistas: A Pre-Registered, Portable Protocol for Fairness Evaluation of Large Language Models 提出Qistas协议以解决大型语言模型公平性评估问题 large language model
14 Fewer Heads, Fewer Memories: Pruning Redundant Attention Heads Suppresses Verbatim Memorisation 通过剪枝冗余注意力头抑制逐字记忆以提升语言模型性能 large language model
15 Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses 提出Mage-VL-Cowork以解决计算机使用代理的多模态交互问题 multimodal

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

#题目一句话要点标签🔗⭐
16 Incentivizing Self-Learning in Large Language Models via Reinforcement Learning 通过强化学习激励大型语言模型的自学习能力 reinforcement learning large language model
17 Grounding Multimodal Reasoning with Evidence-Ablated Negatives 提出EVAN框架以解决多模态推理中的信用分配模糊问题 reinforcement learning multimodal ✅
18 Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation 提出多教师自适应在线自蒸馏方法以提升语言模型性能 distillation large language model ✅
19 ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender 提出ShallowDefend以解决多轮对话中的安全对齐问题 reinforcement learning large language model
20 Li$^{2}$SAO: Lifting Light Singl-Rollout Asynchronous RL Optimization via Group-Relative Actor-Critic Bootstrapping 提出Li$^{2}$SAO以解决异步强化学习中的稳定性问题 reinforcement learning large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页