Jiangang Chen

KongMen: Real-Time Dialogue Purification via Training-Free Entity-Redundancy Gating

Long-context LLMs (128K–1M tokens) reduce truncation loss, but full-length inputs incur proportional latency, cost, and memory overhead. We propose KongMen, a training-free, LLM-free real-time dialogue purifier for multi-turn conversations. KongMen removes conversation-internal r...

KongMen: Real-Time Dialogue Purification via Training-Free Entity-Redundancy Gating

Long-context LLMs (128K–1M tokens) reduce truncation loss, but full-length inputs incur proportional latency, cost, and memory overhead. We propose KongMen, a training-free, LLM-free real-time dialogue purifier for multi-turn conversations. KongMen removes conversation-internal r...

Pull: Lazy Materialization of Working Memory for Stateful LLM Conversations

As LLM conversations grow to hundreds of turns, full-context injection incurs O(N²) cumulative token costs, while lossy summarization or hard truncation irreversibly discards historical state. We propose Pull, a session router that maintains an addressable metadata directory via...

Pull: Lazy Materialization of Working Memory for Stateful LLM Conversations

As LLM conversations grow to hundreds of turns, full-context injection incurs O(N²) cumulative token costs, while lossy summarization or hard truncation irreversibly discards historical state. We propose Pull, a session router that maintains an addressable metadata directory via...