| 1 |
$\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models |
提出M²LLM以解决分子属性预测的多视角问题 |
representation learning large language model |
|
|
| 2 |
Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem Solving |
提出GF-Reasoner以解决几何问题求解中的推理不足 |
reinforcement learning chain-of-thought |
|
|
| 3 |
Scaling Up Active Testing to Large Language Models |
提出高效的主动测试方法以评估大型语言模型 |
predictive model large language model |
|
|
| 4 |
Generative Modeling for Robust Deep Reinforcement Learning on the Traveling Salesman Problem |
提出COGS以解决旅行商问题的分布鲁棒性挑战 |
reinforcement learning deep reinforcement learning |
|
|
| 5 |
Distilling Reinforcement Learning into Single-Batch Datasets |
提出强化学习蒸馏方法以生成单批次数据集 |
reinforcement learning distillation |
|
|
| 6 |
Interpretable Reward Model via Sparse Autoencoder |
提出稀疏自编码器增强的奖励模型以解决传统模型可解释性不足问题 |
reinforcement learning RLHF large language model |
✅ |
|
| 7 |
Multi-level Collaborative Distillation Meets Global Workspace Model: A Unified Framework for OCIL |
提出多层协作蒸馏以解决在线增量学习中的稳定性与适应性问题 |
distillation |
|
|
| 8 |
A Personalized Exercise Assistant using Reinforcement Learning (PEARL): Results from a four-arm Randomized-controlled Trial |
提出个性化运动助手PEARL以解决身体活动不足问题 |
reinforcement learning |
|
|
| 9 |
Pattern-based Knowledge Component Extraction from Student Code Using Representation Learning |
提出基于模式的知识组件提取框架以解决编程教育中的自动化问题 |
representation learning |
|
|
| 10 |
Constrained Black-Box Attacks Against Multi-Agent Reinforcement Learning |
提出约束黑箱攻击方法以解决多智能体强化学习的脆弱性问题 |
reinforcement learning |
|
|
| 11 |
PersRM-R1: Enhance Personalized Reward Modeling with Reinforcement Learning |
提出PersRM-R1以解决个性化奖励建模中的数据稀缺问题 |
reinforcement learning |
|
|
| 12 |
GRAVITY: A Controversial Graph Representation Learning for Vertex Classification |
提出GRAVITY以解决图节点分类中的动态聚合问题 |
representation learning |
|
|
| 13 |
MCLPD:Multi-view Contrastive Learning for EEG-based PD Detection Across Datasets |
提出MCLPD以解决跨数据集的帕金森病检测问题 |
contrastive learning |
|
|