cs.CL（2026-07-05）

📊 共 34 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (26) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 EduArt: An educational-level benchmark for evaluating art history knowledge in large language models 提出EduArt基准以评估大语言模型的艺术历史知识 large language model multimodal
2 PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation 提出PairCoder以解决代码驱动生成的验证问题 large language model multimodal
3 Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning 提出SpeechCombine以解决语音语言模型的指令调优问题 large language model instruction following
4 MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering 提出MultAttnAttrib以解决多模态文档问答中的归因问题 multimodal
5 TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models 提出TokenScope以解决大语言模型代码生成的可解释性问题 large language model
6 CreativityPrism: A Cross-Domain Evaluation Framework for Large Language Model Creativity 提出CreativityPrism以解决LLM创意评估的跨域问题 large language model
7 RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned Evaluation 提出RusFinChain以解决俄语金融领域推理基准不足问题 chain-of-thought
8 NAVER LABS Europe Submission to the Instruction-following 2026 Short Track 提出基于SpeechMapper的多语言指令跟随系统以提升语音处理性能 instruction following
9 Large language models reshape the language of science 分析大型语言模型对科学语言的影响及其应用 large language model
10 StatEval: A Comprehensive Benchmark for Large Language Models in Statistics 提出StatEval以解决LLM在统计推理中的不足问题 large language model
11 YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models 提出YuFeng-XGuard以解决大型语言模型的安全评估问题 large language model
12 Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting 提出Grounded Optimization框架以减少LLM在简历优化中的幻觉问题 large language model instruction following
13 Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas 提出DramaSR-LRM以解决长视频剧集中的说话人识别问题 multimodal
14 Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization 提出Object Aligner以解决JSON相似性评分问题 large language model
15 Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens 提出资源高效的领域自适应预训练方法以提升网络安全LLM专业化 large language model
16 Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms 提出分布级无监督特征发现方法以审计语言模型机制 large language model
17 Kara: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression 提出Kara以解决推理语言模型KV缓存压缩问题 chain-of-thought
18 IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs 提出ISOSCI基准以评估LLMs的推理与知识检索能力 chain-of-thought
19 DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents 提出DiPS框架以解决高风险劝说场景中的对话策略选择问题 large language model
20 SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses 提出SPLIT基准以评估跨语言情感支持能力 large language model
21 RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules 提出RuleChef框架以生成可执行的NLP任务规则 large language model
22 Beyond Skepticism: Evaluating LLMs Pedagogical Intent Reasoning with the Adaptive Pedagogical Vigilance Framework 提出自适应教学警觉框架以优化LLMs的教学意图推理 large language model
23 The Future of NLP may not be at NLP Conferences: Scholarly Migration Patterns in Natural Language Processing 探讨NLP研究发表场所的迁移趋势 large language model
24 Will Scaling Improve Social Simulation with LLMs? 探讨规模扩展对社会模拟的影响与改进 large language model
25 Polite on the Surface, Broken in Practice: A Curated Dataset for Fixing Generation and Register Failures in Low-Resource Bangla Text Generation 提出BLADE数据集以解决低资源孟加拉文本生成中的生成与注册失败问题 large language model
26 Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues 提出Cue Visibility Gap以解决大语言模型的道德安全问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
27 LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models 提出LearNAT以解决NL2SQL中的任务分解问题 reinforcement learning preference learning DPO
28 Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning 提出VRRL框架以解决视觉语言模型自我反思不足问题 reinforcement learning multimodal visual grounding
29 From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages 评估Mamba模型在南非语言的自动语音识别中的应用 Mamba state space model
30 Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning 提出ReRanking Preference Optimization以解决RAG重排序问题 reinforcement learning
31 Multi-Objective Exploration and Preference Optimization via Mutual Information 提出MI-EPO框架以解决多目标偏好优化问题 direct preference optimization large language model
32 Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning 提出主动路由范式以提高视觉推理效率 DRL multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
33 Scaling Latent Reasoning via Looped Language Models 提出Ouro模型以增强语言模型的推理能力 manipulation chain-of-thought

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

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

⬅️ 返回 cs.CL 首页 · 🏠 返回主页