Papers by Zihang Liu

6 papers
HTMuon: Improving Muon via Heavy-Tailed Spectral Correction (2026.findings-acl)

Copied to clipboard

Challenge: Muon’s orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and over-emphasizes the training along noise-dominated directions.
Approach: They propose to preserve Muon's ability to capture parameter interdependencies while producing heavier-tailed updates and inducing heavier-tail weight spectra.
Outcome: The proposed algorithm suppresses the emergence of heavy-tailed weight spectra and over-emphasizes training along noise-dominated directions.
RFS-Guard: Detecting Reasoning Hallucinations via Cross-Phase Routing Focus in Large Reasoning Models (2026.acl-long)

Copied to clipboard

Challenge: Large reasoning models (LRMs) generate intermediate reasoning traces before the final answer, yet they remain vulnerable to reasoning hallucinations such as subtle arithmetic errors.
Approach: They propose a Routing Focus Score (RFS) that measures how strongly cross-step attention routing aligns with semantic proximity derived from hidden-state cosine similarity.
Outcome: The proposed framework detects and localizes hallucinations without external tools or repeated sampling.
Model Balancing Helps Low-data Training and Fine-tuning (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in foundation models have emphasized the need to align pre-trained models with specialized domains using small, curated datasets.
Approach: They propose a layer-wise learning rate scheduler that balances training quality across layers . they adapt it to a curated dataset to achieve alignment with specialized domains .
Outcome: The proposed model shows that it can be used to balance training quality across layers and improve low-data training and fine-tuning for both NLP and SciML tasks.
Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in multimodal reasoning overlook the audio modality.
Approach: They propose a large-scale audio language model for deep reasoning that leverages a multitask audio dataset.
Outcome: The proposed model performs well across key benchmarks including MMAU-mini, AIR-Bench chat/foundation, and MELD.
Long-form Hallucination Detection with Self-elicitation (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for hallucination detection tend to decompose text into isolated statements, unable to understand contextual semantics.
Approach: They propose a framework to leverage self-generated thoughts derived from prior statements as catalysts to elicit the expression of intrinsic knowledge and understand contextual semantics.
Outcome: The proposed framework enables self-elicitation to elicit expressions of knowledge and understand semantics.
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly permeating daily lives and require real-time interactions that mirror human conversations.
Approach: They propose to use time-division-multiplexing to process queries and responses pseudo-simultaneously.
Outcome: The proposed model can listen to users while generating output and adjust to provide instant feedback.

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