cs.CL(2026-08-07)

📊 共 13 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) (10 🔗2) 支柱二:RL算法与架构 (RL & Architecture) (2) 支柱一:机器人控制 (Robot Control) (1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗
1 Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding 提出概念探测基准以提升大语言模型的概念理解能力 large language model
2 Gaze Behavior in Visual World Experiments Can be Modeled With Off-the-shelf Language-Vision Encoders 提出多模态双编码器模型以预测视觉世界实验中的注视行为 multimodal
3 Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models? 提出基于熵的候选过滤器以提升视觉检索增强生成的准确性 multimodal
4 An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation 提出混合知识图谱生成方法以解决HR平台技能匹配问题 large language model
5 GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base 提出GPTKB 2.0以解决知识库歧义性问题 large language model
6 FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding 提出FutureBridge以解决小型语言模型推理支持不足问题 large language model
7 Progressive Content Refinement with Decaying Reward Joint LinUCB 提出一种衰减奖励联合LinUCB算法以解决过度利用问题 large language model
8 Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models 提出递归式训练策略以解决语言模型的两跳推理问题 large language model
9 LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers 提出LLMRouter以解决大语言模型路由问题 large language model
10 TA-RAG: Tone Awareness as a Design Imperative for Retrieval-Augmented Generation 提出TA-RAG以解决RAG系统的语调感知问题 large language model

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

#题目一句话要点标签🔗
11 Simple-OPD: Demystifying Warm-up for On-policy Distillation 提出Simple-OPD以优化在政策蒸馏中的热身阶段 distillation chain-of-thought
12 CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity 提出CreativeInstruct以解决LLMs创意与多样性不足问题 reinforcement learning large language model

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
13 Confirming Our Biases? Evaluating the Capabilities, Risks, and Societal Impact of Large Language Models 评估大型语言模型在偏见确认中的能力与风险 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页