Papers by Haiwen Li

3 papers
EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular Dynamics (2026.findings-acl)

Copied to clipboard

Challenge: Existing models operate on static molecular representations or rely on external tools for reasoning.
Approach: They propose a framework that reformulates species-level molecular dynamics as a symbolic temporal language modeling problem.
Outcome: The proposed model outperforms neural networks and language-based baselines on multiple temporal prediction tasks and generates plausible interpretations of reaction dynamics.
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Challenge: Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon .
Approach: They propose a routing-guided intervention method that enhances domain expert activation.
Outcome: The proposed method achieves consistent improvements on visual reasoning tasks.
Can Large Language Models Tackle Graph Partitioning? (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have remarkable capabilities in understanding complex tasks, but they can only handle graph partitioning tasks that require global perception abilities.
Approach: They propose a pipeline for coarsening, reasoning, and refining to enable LLMs to perform graph partitioning on small-scale graphs.
Outcome: The proposed pipeline can handle graph partitioning tasks on small graphs with coarsening, reasoning, and refining.

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