We propose TraceRL, a trajectory-aware reinforcement learning method for diffusion language models, which demonstrates the best performance among RL approaches for DLMs. We also introduce a ...
Figure 1. FIPO vs. baselines on AIME 2024. FIPO shows that pure RL training alone can outperform reproduced pure-RL baselines such as DAPO and DeepSeek-R1-Zero-32B, surpass o1-mini, and produce ...
Abstract: The energy storage self-scheduling (ESSS) problem is typically formulated as a mixed-integer linear programming (MILP) or quadratically constrained programming (QCP) model, reflecting the ...
Abstract: Power peaks occur when multiple electric trains draw high power simultaneously, e.g., during acceleration. This stresses the power grid and may lead to blackouts, posing a major concern for ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results