Papers by Wang Zhonghua

2 papers
CtrlNews: LLM-based Multi-Agent Controllable News Writing via Knowledge Gravitational Field (2025.findings-emnlp)

Copied to clipboard

Challenge: Current approaches to news writing rely on superficially retrieved information and oversimplified knowledge enumeration resulting in shallow, repetitive, and unordered outputs.
Approach: They propose an LLM-based multi-agent controllable news writing framework called CtrlNews . they propose a fine-grained viewpoint control mechanism to regulate bias, emotion, and exaggeration attributes.
Outcome: The proposed framework simulates expert questioning through automated role assignment and question generation followed by a three-layer hierarchical gravitational graph iteratively refined via expansion-reflection cycles.
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for evicting KV pairs rely on the "persistence of importance" hypothesis . visual tokens display "deferred importance" but become pivotal during later decoding, authors say .
Approach: They propose an entropy-driven method that reformulates KV eviction from "discrete context truncation" to "continuous memory evolution" they propose to prune visual tokens with "deferred importance" visual token exhibiting low salience but becoming pivotal during later decoding .
Outcome: The proposed method achieves 5.0 KV cache compression and 1.5 decoding acceleration.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations