cs.CL（2026-08-13）

📊 共 18 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) (16 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model 提出CASA以解决自动口语评估中的内容与音频信息分离问题 large language model multimodal
2 Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models 测量自指诱导在大语言模型中的反应不稳定性 large language model
3 DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data 提出Mimir v1以解决开放数据集限制问题 large language model foundation model ✅
4 Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization 提出SNIPER框架以优化大语言模型的结构化剪枝 large language model
5 GEM: A Generative Embedding Model Bridging Reasoning and Retrieval 提出GEM模型以解决检索与推理之间的鸿沟问题 instruction following
6 LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation 提出LigBench以解决LLM研究创意生成评估标准缺乏的问题 large language model
7 Falsehood and Impossibility Are Different Directions in an AI's Representation of Language 探讨AI语言表示中的虚假与不可能性差异 multimodal
8 From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options 提出结构化组合推理框架以解决复合答案选项问题 large language model
9 ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval 提出ERSkill以解决长时记忆检索的静态性问题 large language model
10 SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization 提出SAEVerbalizer以解决稀疏自编码器特征解释问题 large language model
11 Which LLM Is Your Ideal Companion? Evaluating Emotional Companion Capabilities of LLMs Based on Adult Attachment Theory 引入成人依恋理论评估LLM的情感陪伴能力 large language model
12 Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research 提出信任分层图书管理员与多智能体写作系统以解决研究报告漂移问题 large language model
13 Prompts in the Wild: A Large Analyzed Collection of Transactional Prompts in Code 提出结构化本体以分析代码中的事务性提示 large language model ✅
14 BavGround: A Benchmark for Regional Cultural Grounding and Dialect Competence in Bavarian 提出BavGround基准以评估巴伐利亚地区文化与方言能力 large language model
15 The Embedder's Dilemma: LLMs Are Better, but at What Cost? 提出大语言模型与嵌入模型的成本效益比较以优化文本处理 large language model ✅
16 GEM: A Generative Embedding Model Bridging Reasoning and Retrieval 提出GEM模型以解决检索与推理之间的鸿沟问题 instruction following

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
17 CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation 提出CROP以解决选择性在线蒸馏中的任务相关性问题 teacher-student distillation
18 GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis 提出GALA以解决文本条件时间序列生成中的对齐问题 flow matching foundation model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页