| 16 |
Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction Following |
提出CC-OPD以解决多约束指令跟随问题 |
distillation instruction following |
|
|
| 17 |
PhyMo: A Physical-Field Modality for Multimodal AI4Physics |
提出PhyMo以解决多模态物理系统预测问题 |
representation learning spatiotemporal multimodal |
|
|
| 18 |
RL Starts before RL: On Policy Distillation for Better Reinforcement Learning |
提出基于策略蒸馏的预训练方法以提升强化学习性能 |
reinforcement learning distillation |
|
|
| 19 |
Curriculum Learning with GNN-based Reinforcement Learning for Job Shop Scheduling |
提出基于图神经网络的课程学习以解决作业车间调度问题 |
reinforcement learning curriculum learning |
|
|
| 20 |
When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment |
提出统一熵校准信用分配方法以解决教师信任问题 |
reinforcement learning PPO distillation |
|
|
| 21 |
DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment |
提出DCRL框架以解决强化学习中的奖励系统不稳定问题 |
reinforcement learning large language model |
|
|
| 22 |
Quantum Reinforcement Learning for Cost and Delay Tradeoffs in Quantum Cloud Orchestration |
提出QRLQ框架以解决量子云调度中的成本与延迟权衡问题 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 23 |
FairTest: Search-Based Fairness Testing for Multi-Agent Reinforcement Learning Systems |
提出FairTest以解决多智能体强化学习系统的公平性测试问题 |
reinforcement learning deep reinforcement learning |
|
|
| 24 |
Context-Continuous Preference Learning for Exoskeleton Personalization |
提出上下文连续偏好学习以解决外骨骼个性化问题 |
preference learning |
|
|
| 25 |
Improving Ensemble Filters with Flow Matching |
提出FlowEF以改进经典集合滤波器在数据同化中的表现 |
flow matching |
|
|
| 26 |
Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency Regularization |
提出RACER框架以解决强化学习中的鲁棒性问题 |
reinforcement learning |
|
|
| 27 |
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning |
提出ProCredit以解决长时间代理任务的奖励信号不足问题 |
reinforcement learning |
|
|