cs.CL（2026-09-24）

📊 共 22 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗⭐
1 SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data 提出SemMSA以解决多模态情感分析中的不完整数据问题 multimodal
2 From Policy Documents to Structured Survey Responses: Evaluating Large Language Models for Policy Monitoring 利用大型语言模型生成政策监测的结构化调查响应 large language model
3 Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code? 探讨大型语言模型在编程中的错误修复与重实现问题 large language model
4 TimeBraid: Unifying Time Series and Language for Understanding and Forecasting 提出TimeBraid以统一时间序列与语言理解与预测 foundation model instruction following
5 What, When, and How: Audio Description as Constrained Global Optimization 提出音频描述的约束全局优化方法以解决生成问题 large language model
6 CORDIAL: Calibrating Ordinal LLM Outputs from Few Labels 提出CORDIAL以校准少量标签下的有序LLM输出 large language model
7 R-DEIM Net: An Efficient Rationale-Augmented Dual-Expert Interaction Model for Paraphrase Detection 提出R-DEIM Net以解决同义句检测中的计算与透明性问题 large language model
8 Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs 提出超位置线性假设以揭示大语言模型的线性特性 large language model
9 ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts 提出ArGuard任务以解决阿拉伯语表情包和LLM提示中的有害内容检测问题 multimodal
10 Reasoning Instructions Can Break Answer Decoding in Vision--Language Models 提出CoT前缀评分以解决视觉语言模型评估失真问题 chain-of-thought
11 Tag-Aware Structured Text Translation: Towards a Systematic Understanding 提出标签感知结构化文本翻译以解决翻译流畅性与标签保真度的矛盾 large language model
12 Scoring Both Directions: LLMs realize the MRS they cannot reliably parse 评估大型语言模型在MRS解析与生成中的表现 large language model
13 MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression 提出MILO以解决多示例上下文学习中的KV缓存效率问题 large language model
14 CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding 提出CodeGraph以解决源代码知识提取问题 large language model
15 Grammatical "grandmother neurons" are rare in LLMs 提出无探针框架以解决LLMs语言结构可解释性问题 large language model
16 Polite but Misaligned: Evaluating LLM Politeness Judgments Against Human Pragmatic Norms 评估大型语言模型的礼貌判断与人类语用规范的对齐问题 large language model
17 ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts 提出ArGuard共享任务以解决阿拉伯语恶意内容检测问题 multimodal
18 All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation 提出因果感知框架以解决同时语音翻译中的数据稀缺问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
19 EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards 提出EAGER框架以解决生成事件提取中的奖励稀疏问题 reinforcement learning reward design large language model
20 Rufus-Air: An Open LLM Post-Training Recipe 提出Rufus-Air以优化GLM-4.5-Air的后训练过程 RLHF distillation reward design
21 Rufus-Air: An Open LLM Post-Training Recipe 提出Rufus-Air以优化大规模语言模型的后训练过程 RLHF distillation reward design

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
22 Asymmetric Classifier-Free Guidance for Target-Speaker ASR 提出非对称无分类器引导以解决目标说话人自动语音识别问题 classifier-free guidance

⬅️ 返回 cs.CL 首页 · 🏠 返回主页