cs.CL（2025-08-30）

📊 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) (15 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition 提出离散提示调优以解决个性化视觉情感识别问题 large language model multimodal
2 GIER: Gap-Driven Self-Refinement for Large Language Models 提出GIER框架以提升大型语言模型输出质量 large language model chain-of-thought
3 The Resurgence of GCG Adversarial Attacks on Large Language Models 提出GCG对大语言模型的对抗攻击评估方法 large language model
4 Wage Sentiment Indices Derived from Survey Comments via Large Language Models 提出工资情感指数以预测日本工资动态 large language model
5 No Clustering, No Routing: How Transformers Actually Process Rare Tokens 揭示Transformer如何处理稀有词汇以提升预测能力 large language model
6 Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting 提出角色提示优化方法以解决对话代理过度发言问题 large language model ✅
7 TECP: Token-Entropy Conformal Prediction for LLMs 提出TECP以解决大语言模型的不确定性量化问题 large language model
8 ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute 提出ParaThinker以解决大语言模型推理效率瓶颈问题 large language model
9 Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling 提出基准测试以提升LLM推理效率 large language model
10 Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems? 提出多轮自我精炼单代理语言模型以解决复杂编程问题 chain-of-thought ✅
11 Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness 提出Probe-Rewrite-Evaluate方法以解决评估意识问题 large language model
12 When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment 提出机制性洞察以解决推理引发的失调问题 large language model
13 Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM Summarization 提出基于角色条件的LLM摘要评估框架以应对法律动机推理问题 large language model
14 GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction 提出GraphKV以解决KV缓存管理中的动态选择问题 large language model
15 KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation 提出KG-RAG框架以提升GUI代理的决策能力 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🔗⭐
16 Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models 提出平衡演员初始化以解决蒸馏模型的RLHF训练不稳定问题 reinforcement learning RLHF distillation
17 ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking 提出ERank以解决文本重排序中的效率与效果问题 reinforcement learning large language model
18 Open Data Synthesis For Deep Research 提出InfoSeek框架以解决复杂深度研究任务的合成问题 reward design large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页