| 1 |
MKGR: Multimodal Knowledge-Graph Representation Learning for Cold-Start Protein-Protein Interaction Prediction |
提出MKGR以解决冷启动蛋白质-蛋白质相互作用预测问题 |
representation learning multimodal |
|
|
| 2 |
Generalization in offline RL: The structure is more important than the amount of pessimism |
提出对称性价值函数以优化离线强化学习中的泛化能力 |
reinforcement learning offline RL offline reinforcement learning |
|
|
| 3 |
Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training |
提出自蒸馏策略优化以解决持续后训练中的遗忘问题 |
reinforcement learning policy learning distillation |
✅ |
|
| 4 |
DemoPSD: Disagreement-Modulated Policy Self-Distillation |
提出DemoPSD以解决信息泄露与探索能力不足问题 |
distillation privileged information large language model |
|
|
| 5 |
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation |
提出Neuron-OPSD以解决无标注LLM自蒸馏问题 |
offline RL distillation large language model |
|
|
| 6 |
DecompRL: Solving Harder Problems by Learning Modular Code Generation |
提出DecompRL以解决复杂问题的模块化代码生成 |
reinforcement learning world model world models |
|
|
| 7 |
Evolutionary Feature Engineering for Structured Data |
提出进化特征工程框架以优化结构化数据处理 |
MAE large language model foundation model |
|
|
| 8 |
Learning the Supports for Categorical Critic in Reinforcement Learning |
提出动态学习支持区间以改进强化学习中的价值函数估计 |
reinforcement learning deep reinforcement learning |
|
|
| 9 |
Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling |
提出液态潜在状态动态模型以解决涡扇发动机健康监测问题 |
world model world models latent dynamics |
|
|
| 10 |
WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs |
提出WattGPU以解决LLM推理能耗与延迟预测问题 |
predictive model large language model |
✅ |
|
| 11 |
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective |
提出近端波函数优化以改进神经量子态训练 |
reinforcement learning |
|
|
| 12 |
Rank-Then-Act: Reward-Free Control from Frame-Order Progress |
提出Rank-Then-Act框架以解决无奖励控制问题 |
reinforcement learning policy learning reward design |
|
|
| 13 |
Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling |
提出多角色评分生成方法以解决单一评估维度盲点问题 |
reinforcement learning large language model |
|
|
| 14 |
Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning |
提出角色感知神经凸散度头以解决非对称表示学习问题 |
representation learning |
|
|
| 15 |
WARP: Weight-Space Analysis for Recovering Training Data Portfolios |
提出WARP框架以恢复训练数据组合，解决模型透明性问题 |
MAE foundation model |
|
|