cs.LG（2025-01-16）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

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

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

#	题目	一句话要点	标签	🔗	⭐
1	Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment	提出因果奖励建模方法，提升大型语言模型对齐的可靠性和公平性	reinforcement learning RLHF large language model
2	Enhancing Generalization in Chain of Thought Reasoning for Smaller Models	提出PRADA框架，提升小模型在思维链推理中的泛化能力	distillation chain-of-thought
3	Optimization Strategies for Enhancing Resource Efficiency in Transformers & Large Language Models	针对Transformer与LLM，提出优化策略以提升资源效率	distillation large language model
4	From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model Explanation	提出基于Shapley值的模型解释方法，提升强化学习策略的可解释性。	reinforcement learning deep reinforcement learning
5	Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation	提出SCLIFD框架，解决少样本下类别增量故障诊断中的灾难性遗忘和类别不平衡问题	representation learning distillation	✅
6	Clone-Robust AI Alignment	提出加权MLE算法，增强RLHF在非均匀数据集下的克隆鲁棒性	reinforcement learning RLHF large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
7	U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection	提出基于不确定性的多模态多任务学习框架U-Fair，用于更公平的抑郁症检测。	multimodal
8	Large Language Model is Secretly a Protein Sequence Optimizer	利用大语言模型进行蛋白质序列优化，实现定向进化	large language model
9	An LLM-Guided Tutoring System for Social Skills Training	提出一种LLM引导的辅导系统，用于动态生成社交技能训练场景。	large language model
10	Cueless EEG imagined speech for subject identification: dataset and benchmarks	提出无提示脑电想象语音范式，用于安全可靠的个体身份识别	foundation model
11	Rational Tuning of LLM Cascades via Probabilistic Modeling	提出概率模型以优化LLM级联的置信度阈值	large language model
12	Confidence Estimation for Error Detection in Text-to-SQL Systems	针对Text-to-SQL系统，提出基于熵的置信度估计方法以进行错误检测。	large language model

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

#	题目	一句话要点	标签	🔗	⭐
13	Predicting Air Temperature from Volumetric Urban Morphology with Machine Learning	提出一种基于体素化城市形态和机器学习的城市气温预测方法，辅助城市规划。	spatial relationship

⬅️ 返回 cs.LG 首页 · 🏠 返回主页