cs.CL（2026-07-01）

📊 共 15 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) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Towards Developing a Multimodal Chat Assistant for University Stakeholders: RAG-based Approach 提出多模态大学聊天助手以解决信息获取难题 large language model multimodal
2 Understanding Large Language Models 探讨大型语言模型的机制与人类认知的关系 large language model
3 DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning 提出DiscoLoop以解决多步推理中的表示瓶颈问题 large language model chain-of-thought
4 Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads 提出Logit-Contribution评分以识别非字面检索头 large language model
5 From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives 提出MAGNET框架以解决长篇叙事生成中的一致性问题 large language model
6 CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models 提出信心自适应思维以解决大型推理模型的效率问题 chain-of-thought
7 BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal 提出BaseRT以提升Apple Silicon上LLM推理性能 large language model ✅
8 Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates 提出可解释的代理LLM集体作为人工生命研究基础 large language model
9 YOMI-Bench: A Benchmark for Evaluating Kanji Reading and Phonological Understanding of LLMs for Japanese 提出YOMI-Bench以评估日语汉字阅读与语音理解能力 large language model
10 Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors 提出潜在关键任务模型以解决语言模型幻觉问题 large language model
11 Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training 提出行为评估框架以验证大语言模型的记忆能力 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🔗⭐
12 Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation 提出D2D方法以检测语言模型中的隐性偏见 distillation
13 Efficient Multilingual Reasoning Transfer via Progressive Code-Switching 提出PCS框架以高效转移多语言推理能力 reinforcement learning distillation

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

#题目一句话要点标签🔗⭐
14 AGC-Bench: Measuring Artificial General Creativity 提出AGC-Bench以衡量人工通用创造力 HuMoR

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 "Don't Say It!": Constraints, Compliance, and Communication when Language Models Play Taboo 探讨语言模型在Taboo游戏中的约束与沟通策略 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页