cs.LG（2025-12-24）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Assessing the Software Security Comprehension of Large Language Models 系统评估大型语言模型在软件安全理解方面的能力，揭示其知识边界与常见误解。 large language model
2 Interpretable Perturbation Modeling Through Biomedical Knowledge Graphs 提出基于生物医学知识图谱的可解释扰动建模框架，用于预测药物对基因表达的影响。 foundation model multimodal
3 Fuzzwise: Intelligent Initial Corpus Generation for Fuzzing FuzzWise：利用LLM智能生成模糊测试初始语料库，提升测试效率 large language model
4 Learning to Reconfigure: Using Device Status to Select the Right Constrained Coding Scheme 针对TDMR存储，提出基于设备状态学习的自适应约束编码方案选择方法 TAMP
5 LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphs LLMTM：基准测试并优化LLM在动态图时间motif分析中的应用 large language model
6 LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics 提出基于瑞士轮动态竞争的LLM综合评估框架，解决静态评估的局限性。 large language model
7 Deadline-Aware Online Scheduling for LLM Fine-Tuning with Spot Market Predictions 提出基于预测的在线调度方法以优化LLM微调成本 foundation model
8 Can Agentic AI Match the Performance of Human Data Scientists? Agentic AI在数据科学中难匹人类专家：领域知识缺失是瓶颈 large language model
9 RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks RevFFN：利用可逆块实现MoE LLM全参数高效微调 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
10 ReACT-Drug: Reaction-Template Guided Reinforcement Learning for de novo Drug Design ReACT-Drug：基于反应模板引导的强化学习用于全新药物设计 reinforcement learning PPO representation learning ✅
11 dUltra: Ultra-Fast Diffusion Language Models via Reinforcement Learning 提出dUltra，通过强化学习加速扩散语言模型并行解码，提升推理效率。 reinforcement learning distillation
12 A Survey of Freshness-Aware Wireless Networking with Reinforcement Learning 综述：基于强化学习的面向信息新鲜度的无线网络研究 reinforcement learning
13 Model Merging via Multi-Teacher Knowledge Distillation 提出SAMerging，通过多教师知识蒸馏实现模型合并，提升泛化性能。 distillation ✅
14 MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models 提出MiST：通过中阶段科学训练提升化学推理模型性能 reinforcement learning large language model
15 Shared Representation Learning for High-Dimensional Multi-Task Forecasting under Resource Contention in Cloud-Native Backends 提出用于云原生后端高维多任务预测的共享表示学习框架，解决资源竞争下的预测难题。 representation learning

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
16 Temporal Visual Semantics-Induced Human Motion Understanding with Large Language Models 提出基于大语言模型的时间视觉语义引导的人体运动分割方法 human motion large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页