Pinned Loading

1. Reinforcement-Calibration-SimCSE Reinforcement-Calibration-SimCSE Public

   Reinforcement Calibration SimCSE, combining contrastive learning, artificial potential fields, perceptual loss, and RLHF to achieve improved Semantic Textual Similarity (STS) embeddings. PyTorch-ba…

   Python 10

2. event-timeline-generation-olympics event-timeline-generation-olympics Public

   A toy system for generating event timelines from social media data, specifically focusing on the Olympic Game medalist events.

   Jupyter Notebook 6

3. byte_pair_encoding_BPE_subword_tokenization_implementation_python byte_pair_encoding_BPE_subword_tokenization_implementation_python Public

   Byte-Pair Encoding (BPE) (subword-based tokenization) algorithm implementaions from scratch with python

   Python 13

4. Logic-RL-Lite Logic-RL-Lite Public

   Lightweight replication study of DeepSeek-R1-Zero. Explores pure RL without SFT for post-training for reasoning capability. No "Aha moment" and "Longer CoT ≠ Accuracy".

   Python 1