cs.CL（2026-06-09）

📊 共 27 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (20 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use 提出PhysTool-Bench以评估多模态大语言模型在物理工具使用中的能力 embodied AI large language model multimodal
2 Large Language Models as Modal Models in Linguistics 提出将大型语言模型视为语言学中的模态模型以促进理论研究 large language model
3 OpenRTLSet: A Fully Open-Source Dataset for Large Language Model-based Verilog Module Design 提出OpenRTLSet以推动开源硬件设计数据集的发展 large language model
4 Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models 提出多重人格建模方法以解决复杂行为控制问题 large language model multimodal
5 Generative Archetype-Grounded Item Representations for Sequential Recommendation 提出GenAIR以解决序列推荐中的项目表示不足问题 large language model ✅
6 The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring 通过顺序微调LLaMA提升自动化作文评分的连贯性 large language model
7 T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains 提出T1-Bench以解决多场景智能体评估问题 large language model
8 Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings 提出注意力扩展机制以解决长文档关键短语提取问题 large language model
9 Benchmarking Knowledge Editing using Logical Rules 提出新的基准以评估知识编辑中的逻辑规则处理能力 large language model
10 LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization 提出LC-QAT以解决低比特量化训练效率问题 large language model
11 Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models 提出TRACE以解决Mixture-of-Experts模型中的机器遗忘问题 large language model
12 Who Brought Easter Eggs to Eid? Auditing Cultural Translation of Math Word Problems Across Diverse Languages and Regions 分析语言模型在数学问题文化翻译中的一致性与多样性问题 large language model
13 It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO 提出一种单例GRPO方法以揭示语言模型的偏见脆弱性 large language model
14 Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs 提出预测门控银行稀疏训练方法以优化大语言模型 large language model
15 REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs 提出REAL框架以解决LLMs的长期记忆管理问题 large language model
16 Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval 提出ParaEval以解决MCQA评估中的表述敏感性问题 large language model
17 Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning 提出SDBN框架以解决PEFT在小数据环境下的鲁棒性问题 foundation model
18 Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models 提出Prefilling-dLLM以解决长上下文推理中的计算复杂性问题 large language model ✅
19 UniSVQ: 2-bit Unified Scalar-Vector Quantization 提出UniSVQ以解决2-bit量化性能下降问题 large language model
20 Where You Inject Diversity Matters: A Unified Framework for Diverse Generation 提出统一框架以提升开放式生成任务的多样性 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🔗⭐
21 PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning 提出PADD框架以优化MoE学生的知识蒸馏 distillation large language model
22 Dynamic Linear Attention 提出动态线性注意力机制以解决长上下文表示能力不足的问题 linear attention large language model
23 Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization 提出重力加权直接偏好优化以解决多层指令层次问题 DPO direct preference optimization
24 Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It 提出QK-Restore以解决混合LLM中的长范围记忆衰退问题 linear attention chain-of-thought
25 Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation 提出知识增强工具执行框架以解决LLM工具调用问题 reinforcement learning large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
26 The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models 提出跨语言分布偏差审计方法以解决大型语言模型的偏见问题 manipulation RLHF large language model
27 TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning 提出TabClaw以解决电子表格分析中的透明性与适应性问题 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页