cs.CL（2026-08-12）

📊 共 21 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) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗⭐
1 Locating and Controlling Implicit Personalization in Large Language Models 提出隐式个性化控制方法以提升大语言模型的输出一致性 large language model
2 Large Language Model-Driven Small-Capitalization Trading: Integrating Financial News Sentiment, Macroeconomic Indicators, and Technical Signals 提出基于大语言模型的小市值股票交易策略以提升投资决策 large language model
3 LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training 提出LazyTrain以解决有限资源下的大语言模型训练问题 large language model ✅
4 LabelFusion-TS: Fusing Large Language Models, Transformer Encoders, and Financial Time Series for Monetary-Policy Stance Classification 提出LabelFusion-TS以融合金融时间序列和语言模型进行货币政策态度分类 large language model
5 Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models 提出Ripple-Pivot Search以加速扩散大语言模型解码 large language model
6 Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models 提出Semantic Lenia框架以实现语言模型的动态推理 large language model
7 AWARe: Mitigating Catastrophic Forgetting via Activation-Weighted Adaptive REtention 提出AWARe以解决多模态大语言模型的灾难性遗忘问题 large language model multimodal ✅
8 Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge 提出信息丰富悖论以解决长上下文训练的知识编码问题 large language model
9 Accuracy and Order Sensitivity Diverge Under Label-Free Strategies 提出无标签策略以解决多选题模型评估中的偏差问题 large language model
10 ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents 提出ToolHazard以解决LLM代理的安全评估与对齐问题 large language model
11 Who Would You Vote For? Auditing Political Alignment in LLMs: An Italian Case-Study 提出审计框架以评估大型语言模型的政治倾向 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
12 Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus 提出对混合线性注意力大语言模型中大激活的系统研究 linear attention large language model ✅
13 RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation 提出RT-SEMamba以解决实时语音增强问题 Mamba distillation
14 Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs 提出Self-Fix Step-DPO以解决大型语言模型自我纠错问题 reinforcement learning DPO large language model
15 One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL 提出多模拟器训练方法以解决多智能体RL中的模拟器崩溃问题 reinforcement learning large language model
16 Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing 提出混合策略自编辑以解决非结构化知识编辑问题 distillation large language model
17 Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed 评估小型语言模型的可信度：预训练与压缩的比较 distillation large language model
18 When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use 提出后训练策略以解决多语言API调用中的语言不一致问题 reinforcement learning large language model
19 Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs 提出对抗性说服框架以增强LLM的抗干扰能力 reinforcement learning large language model
20 Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations 提出偏好树优化框架以提升目标导向对话系统的性能 DPO direct preference optimization

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
21 Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages 探讨AI基础设施对弱势语言使用者的影响与解决方案 penetration

⬅️ 返回 cs.CL 首页 · 🏠 返回主页