5 papers
From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inference
Liu hung ming
We present SemantiClean, a modular framework for extracting structured semantic signals from e-commerce session data and driving pluggable inference targets including purchase inte…
Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation
Hung Ming Liu
Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context window receives substantially les…
Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking
Liu Hung Ming
In decentralized Multi-Agent Reinforcement Learning (MARL), steganographic collusion -- where agents develop private protocols to evade monitoring -- presents a critical AI safety…
Interpretable by AI Mother Tongue: Native Symbolic Reasoning in Neural Models
Hung Ming Liu
We present a framework where neural models develop an AI Mother Tongue, a native symbolic language that simultaneously supports intuitive reasoning, compositional symbol chains, an…
AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems
Hung Ming Liu
In Decentralized Multi-Agent Reinforcement Learning (MARL), the development of Emergent Communication has long been constrained by the ``Joint Exploration Dilemma'', leading agents…