Tianyu(Vincent) Zhan

Issue about import pcdet.datasets.kitti.kitti_dataset

1

when trying to import kitti, it shows that RuntimeError: cannot statically infer the expected size of a list in this context: : Traceback (most recent call last): File "/home/tz2693/LCDNet/pcdet_test.py", line...

Clarification on Reward Usage in DPO Training

1

In the RLHF workflow paper, the Reward Model is used to annotate new data generated by the LLM during the iterative DPO process, resulting in scalar values. According to Algorithm...

Reward-KL Comparison

1

### Question about KL Divergence Evaluation in DPO Implementation I read the paper ["Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint"](link_to_paper) and noticed your...