| 1 |
Foundation Models at Work: Fine-Tuning for Fairness in Algorithmic Hiring |
提出AutoRefine，通过强化学习微调基础模型，解决算法招聘中的公平性问题。 |
reinforcement learning large language model foundation model |
|
|
| 2 |
Improving DeFi Accessibility through Efficient Liquidity Provisioning with Deep Reinforcement Learning |
提出基于深度强化学习的流动性提供策略，优化Uniswap v3的DeFi可访问性。 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 3 |
Performance Optimization of Ratings-Based Reinforcement Learning |
探索超参数优化方法，提升基于人类评价的强化学习性能 |
reinforcement learning policy learning |
|
|
| 4 |
Subject Representation Learning from EEG using Graph Convolutional Variational Autoencoders |
提出基于图卷积变分自编码器的GC-VASE模型，用于脑电信号的个体表征学习。 |
representation learning contrastive learning |
|
|
| 5 |
Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data |
提出GILD，通过元学习离线数据目标函数，提升在线强化学习在稀疏奖励环境下的性能。 |
reinforcement learning imitation learning |
|
|
| 6 |
Dataset Distillation as Pushforward Optimal Quantization |
将数据集蒸馏重构为推前最优量化问题，提升ImageNet性能。 |
distillation |
|
|
| 7 |
Human-Inspired Multi-Level Reinforcement Learning |
提出一种受人类启发的多层次强化学习方法，提升决策优化能力 |
reinforcement learning |
|
|
| 8 |
TIMRL: A Novel Meta-Reinforcement Learning Framework for Non-Stationary and Multi-Task Environments |
提出基于高斯混合模型和Transformer的元强化学习框架，解决非平稳多任务环境下的样本效率问题。 |
reinforcement learning |
|
|
| 9 |
Combining LLM decision and RL action selection to improve RL policy for adaptive interventions |
结合LLM决策与RL动作选择，提升自适应干预的RL策略 |
reinforcement learning large language model |
|
|
| 10 |
ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression |
提出角度补偿对比正则化方法ACCon，提升深度回归任务的性能。 |
representation learning contrastive learning |
|
|