Papers by Beichen Huang

2 papers
Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to speed up parallel scaling have relied on similarity-based or confidence-based pruning, but these signals do not reliably indicate trace quality.
Approach: They propose a pruning framework that evaluates reasoning steps using hidden states and dynamically prunes unpromising traces during generation.
Outcome: The proposed framework reduces end-to-end inference latency by 45%–70% on average compared to self-consistency while improving reasoning accuracy.
Think Beyond Words: Exploring Context-Relevant Visual Commonsense for Diverse Dialogue Generation (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to generate intelligent open-domain dialogue agents only consider auxiliary commonsense stored in pure text, ignoring grounding information from the external visual world.
Approach: They propose a VIsual Commonsense enhanced dialogue generaTOR that exploits auxiliary commonsense from images related to context to generate coherent and informative responses.
Outcome: The proposed method outperforms the latest competitive methods in terms of coherence and diversity on two public datasets.

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