| 1 |
Disentangling the Causes of Plasticity Loss in Neural Networks |
提出多机制干预以解决神经网络塑性丧失问题 |
reinforcement learning deep reinforcement learning |
|
|
| 2 |
Curiosity-driven Red-teaming for Large Language Models |
提出好奇驱动的红队方法以提升语言模型测试覆盖率 |
reinforcement learning large language model |
✅ |
|
| 3 |
Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming |
提出Dr. Strategy以提升模型基础强化学习中的梦境策略 |
reinforcement learning generalist agent |
|
|
| 4 |
Deep Reinforcement Learning: A Convex Optimization Approach |
提出基于凸优化的深度强化学习算法以解决非线性系统问题 |
reinforcement learning deep reinforcement learning |
|
|
| 5 |
Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs |
提出直接对齐草稿模型以加速LLM推理 |
reinforcement learning distillation large language model |
|
|
| 6 |
Theoretical Foundations of Deep Selective State-Space Models |
提出深度选择性状态空间模型的理论基础以提升序列数据建模 |
Mamba SSM foundation model |
|
|
| 7 |
A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations |
提出基于模型的方法以提高强化学习效率 |
reinforcement learning deep reinforcement learning |
|
|
| 8 |
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL |
提出ArCHer框架以解决多轮RL在语言模型中的应用问题 |
reinforcement learning large language model |
|
|
| 9 |
DIGIC: Domain Generalizable Imitation Learning by Causal Discovery |
提出DIGIC以解决领域泛化模仿学习问题 |
imitation learning |
|
|
| 10 |
Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features |
提出监督对比表示学习以分析神经崩溃现象 |
representation learning |
|
|
| 11 |
Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks |
提出损失感知课程学习以提升异构图神经网络性能 |
curriculum learning |
✅ |
|