cs.LG（2025-01-18）

📊 共 12 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Fake Advertisements Detection Using Automated Multimodal Learning: A Case Study for Vietnamese Real Estate Data	提出FADAML以解决越南房地产虚假广告检测问题	multimodal
2	Jailbreaking Large Language Models in Infinitely Many Ways	提出“无限释义攻击”（IMP）方法，有效绕过大型语言模型的安全防护机制。	large language model
3	Unveiling the Mystery of Weight in Large Foundation Models: Gaussian Distribution Never Fades	揭示大模型权重奥秘：高斯分布特性永存，助力模型适应与编辑	foundation model
4	Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback	Step-KTO：通过逐步二元反馈优化LLM的数学推理能力	large language model chain-of-thought
5	Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments	Learn-by-interact：一种数据为中心的框架，用于在真实环境中自适应LLM Agent	large language model
6	CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention	提出CEReBrO，一种基于高效交替注意力机制的紧凑型脑电信号表征编码器。	foundation model
7	FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models	FSMoE：一种灵活可扩展的稀疏混合专家模型训练系统	large language model

#	题目	一句话要点	标签
8	Stability Enhancement in Reinforcement Learning via Adaptive Control Lyapunov Function	提出SAC-CLF框架，通过自适应控制Lyapunov函数增强强化学习的稳定性和安全性	reinforcement learning SAC reward shaping
9	Diffusion-Based Imitation Learning for Social Pose Generation	提出基于扩散模型的模仿学习方法，用于社交场景中人物姿态生成。	imitation learning behavior cloning
10	PEARL: Preconditioner Enhancement through Actor-critic Reinforcement Learning	提出 PEARL，通过 Actor-Critic 强化学习增强矩阵预处理器的性能。	reinforcement learning
11	Self-supervised Graph Transformer with Contrastive Learning for Brain Connectivity Analysis towards Improving Autism Detection	提出基于对比学习的自监督图Transformer，用于脑连接分析以提升自闭症检测。	contrastive learning
12	Hybrid-Quantum Neural Architecture Search for The Proximal Policy Optimization Algorithm	提出基于正则化演化的混合量子神经网络架构搜索PPO算法	reinforcement learning PPO