Pinned Loading

1. BMN-Boundary-Matching-Network BMN-Boundary-Matching-Network Public

   Forked from lalopark/BMN-Boundary-Matching-Network

   Pytorch implementation of the paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", along with three new modules to address overfitting issues found in the baseline model…

   Python

2. ecommerce-env-data ecommerce-env-data Public

   synthetic data generation pipeline for ecommerce env

   Python

3. adv-reward-bench adv-reward-bench Public

   Terminal-Bench-style tasks that hand agents a flawed success signal: a validator or test suite that a naive solution passes while breaking the real instructions. It measures whether agents notice t…

   HTML

4. code-native-labeler-ui code-native-labeler-ui Public

   code-native labeler UI for systematic coding data collection

   TypeScript

5. cua-review cua-review Public

   Review CUA env tasks with multi-class rubric judges (Jev) and an ACCEPT / REWORK verdict

   HTML

6. talking-machines talking-machines Public

   podcast creation pipeline that transforms academic AI papers into engaging, conversational podcast episodes — from PDF to audio.

   Python