Task-fine-tuned large language model (LLM) classifiers acquire task-specific decision knowledge, but this knowledge remains implicit in distributed internal computations, making their decision logic difficult to interpret. We introduce the Executable Decision Compression (EDC) framework and propose J-Miner, which mines...
Yun-Fan Gao, Xinyi Huang, Tao Sheng et al.· 0 citations
C3Flow (Concurrent Claude Code Workflow), a framework that transforms Claude Code from an interactive assistant into a SIMD-style SIMD-style concurrent compute engine, is introduced, demonstrating its effectiveness for production-scale deep research pipelines.
Yunfan Gao, Xin-Yi Huang, Yijie Zhong et al.· Annual International ACM SIG...· 0 citations
J-Miner is introduced, which mines text-level named concepts by aggregating vocabulary-aligned internal signals across layers and token positions, and uses the classifier's own predictions to learn executable decision rules over them, and shows that task-specific decision knowledge can be faithfully represented in an e...
Yunfan Gao, Xinyi Huang, Tao Sheng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.