Papers by Shudong Yang

2 papers
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding (2026.acl-long)

Copied to clipboard

Challenge: Existing models struggle to maintain stable understanding performance and low GPU memory overhead.
Approach: They propose a training-free architecture for real-time and accurate understanding of video streams . HERMES reuses a compact KV cache, enabling efficient streaming understanding .
Outcome: The proposed architecture achieves 10 faster TTFT compared to prior SOTA.
DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction (2023.findings-emnlp)

Copied to clipboard

Challenge: Current Event Extraction methods focus on high-resource scenarios, which requires large amount of annotated data.
Approach: They propose a demonstration-based learning paradigm for EE to fully use annotated data . they propose EE as a natural language generation task guided by schema-based prompts .
Outcome: The proposed model outperforms current methods in low-resource scenarios.

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