Papers by Haiteng Zhao

4 papers
MUR: Momentum Uncertainty guided Reasoning for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for optimizing reasoning quality are limited by overthinking.
Approach: They propose a method that allocates thinking budgets to critical reasoning steps by tracking and aggregating step-wise uncertainty over time.
Outcome: The proposed method reduces computation by over 45% on average while improving accuracy by 0.33โ€“3.46%.
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for enhancing LLM reasoning rely on supervisory signals . current methods rely heavily on outcome supervision and auxiliary reward models .
Approach: They propose a gen-eralizable and purely unsupervised self-training framework to enhance LLM reasoning without supervision.
Outcome: The proposed framework improves LLM reasoning without supervision without external supervision.
Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach: They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome: The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.
๐œ™-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation (2025.acl-long)

Copied to clipboard

Challenge: Existing inference-time optimization strategies address the shortsightedness of auto-regressive generation, but the vast search space leads to excessive exploration and insufficient exploitation.
Approach: They propose a decoding strategy that approximates two distributions via foresight and clustering to provide an efficient estimation of step value.
Outcome: The proposed decoding strategy outperforms strong baselines in performance and efficiency.

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