HKUST-KnowComp
- 276 followers
- HKUST, Hong Kong
- https://github.com/organizations/HKUST-KnowComp
- @HKUSTKnowComp
Pinned Loading
Repositories
- skillrevise Public Forked from xuansenpa1/skillrevise
Official release for SkillRevise: trace-conditioned revision of LLM-authored agent skills
- rethinkskill Public
Provenance-first research code for controlled agent-skill evolution experiments.
- HypoAgent Public
- DeepRefine Public
A reinforcement learning framework for agentic knowledge refinement that evolves KBs with multi-turn interaction history.
- PACE Public
Official code for PACE: Factor-Guided Coarse-to-Fine Reasoning for Long Videos (EMNLP 2026)
- GSPR Public
EMNLP 2026 Accpeted Paper: GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners
- Legal-Rule-Induction Public
Dataset for paper: Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents
- NOVA Public
The official codebase for our paper "NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems"
- KGPFN Public
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…