Pinned Loading

1. Corpus2Skill Corpus2Skill Public

   Official Findings of EMNLP 2026 implementation of Corpus2Skill: compile a document corpus into a navigable skill hierarchy that LLM agents explore at query time, with document lookup instead of a s…

   Python 85 7

2. CQG-MBQA CQG-MBQA Public

   Official ICLR 2025 implementation of CQG-MBQA: interpretable semantic text embeddings where every dimension is the answer to an automatically generated discriminative question.

   Jupyter Notebook 10 1

3. ZipRerank ZipRerank Public

   Official ICML 2026 implementation. A framework for training highly efficient list-wise multimodal rerankers for long documents.

   Python 9 1

4. Implicit-Embeddings Implicit-Embeddings Public

   Code for the ICML 2026 position paper arguing that text embeddings should capture implicit semantics, not just surface meaning.

   Python 6 1

5. GGSS GGSS Public

   Official EMNLP 2026 implementation of GGSS: inference-time demographic debiasing for generative VLMs/MLLMs via norm-preserving, token-level geodesic activation steering. No retraining.

   Python 1

6. ACL-PRISM ACL-PRISM Public

   Official ACL 2025 implementation of PRISM: interpretable political bias embeddings produced by a political-aware cross-encoder.

   Python 2