Abstract: In recent years, online social media has flourished, and a large amount of information has spread through social platforms, changing the way in which people access information. The ...
Abstract: In unmanned aerial vehicle (UAV) applications, the UAV's limited energy supply and storage have triggered the development of intelligent energy-conserving scheduling solutions. In this paper ...
In this work, we reveal that the full gradient component in SAM’s adversarial weight perturbation does not contribute to generalization and, in fact, has undesirable effects. We then propose an ...
accelerate launch train.py \ --model_name Qwen2.5-Math-7B \ --model_path /path/to/Qwen2.5-Math-7B \ --train_data dataset/1shot_rlvr/pi1_r1280.parquet \ --effective ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback