RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusabilityby Vishwesh Sangarya, Jung-Eun…
Stylish and Functional: Guided Interpolation Subject to Physical Constraintsby Yan-Ying Chen, Nikos Arechiga, Chenyang Yuan,…
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learningby Yangkun Chen, Kai Yang, Jian…
PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Timeby Alireza Pourali, Arian Boukani,…
Generalized Back-Stepping Experience Replay in Sparse-Reward Environmentsby Guwen Lyu, Masahiro SatoFirst submitted to arxiv on:…
SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branchby Shengyu Feng, Yiming YangFirst submitted to arxiv…
FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHFby Flint Xiaofeng Fan, Cheston Tan,…
Maximize Your Data’s Potential: Enhancing LLM Accuracy with Two-Phase Pretrainingby Steven Feng, Shrimai Prabhumoye, Kezhi…
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Modelsby Yinlam Chow, Guy Tennenholtz, Izzeddin Gur,…
Deep reinforcement learning with time-scale invariant memoryby Md Rysul Kabir, James Mochizuki-Freeman, Zoran TiganjFirst submitted…