Skip to content

Author

Zonghan Wu

We have 9 of 16 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

Entropogram-guided Visual Realignment Decoding: Capturing the Rhythm of Multimodal Reasoning

This work revisit hallucination in MLLMs from the perspective of reasoning generation dynamics and proposes an entropy-aware self-introspective framework for MLLM reasoning, arguing that entropy is not merely a static measure of uncertainty but a structured signal that reflects how modality information is integrated th...

Jia-Qi Deng, Zhe Fu, Ya-Kun Chen et al. · 0 citations
Preprint Oct 2026

Post-SQLFix: Property-Guided Repair of LLM-Generated SQL with Runtime Verification

Large Language Models (LLMs) for Text-to-SQL frequently generate queries with syntax errors, invalid identifier references, or violations of SQL scoping and typing rules. Repairing these errors is a program correctness problem, yet existing approaches rely on Execution Feedback (EF), whose symptom-level, dialect-specif...

Zhi-Hao Guo, Zong-Han Wu, Yi Shao et al. · 0 citations
Sep 2026

Is AI Widening the Wage Gap? A Hybrid Agentic Simulation for Labor Equity

Artificial intelligence (AI) is reshaping labor markets, yet its effects on wage distribution and the underlying mechanisms remain insufficiently understood. Conventional analytical approaches are limited in their ability to directly examine the dynamic evolution of worker behavior and income distribution under sustain...

Zong-Bo Hu, Zong-Han Wu, Georgina Curto et al. · 0 citations
Preprint Aug 2026

HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit

The proposed method HalluTracer, which averages layer-wise probe logits to predict truthfulness before decoding, achieves the highest area under the receiver operating characteristic curve (AUROC) in 23 of 24 model--benchmark pairs among the compared methods.

Zhi-Hao Guo, Zong-Han Wu, Huan Huo et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration

SPMC, a training framework that identifies grounding-responsive heads and selectively regularizes their text-to-image attention, demonstrates that targeted guidance of sparse and implicit visual evidence pathways can directly improve multimodal reasoning.

Jia-Qi Deng, Zong-Han Wu, Zhan Heng et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers

Looped Transformers offer a parameter-efficient route to test-time scaling by reusing shared layers for iterative latent reasoning. However, additional iterations can reduce support for a reference answer, leaving unclear whether an update's direction is locally unhelpful or its full displacement moves too far. We stud...

Zhi-Hao Guo, Zong-Han Wu, Hai-Zhou Du et al. · 1 citation
Aug 2026

UniDrug-LLM: A Reliability-Aware Multimodal LLM-based Framework for Drug Discovery.

This work establishes a principled paradigm shift toward reliability-aware multi-modal learning for drug discovery by performing integrated representation learning across multiple modalities, and proposes Cross-Modal Subspace Alignment (CMSA), which treats incomplete knowledge graphs as recoverable signals, synthesizin...

Xiaodong Zhu, Longjun Song, Shi-Ying Zeng et al. · 0 citations
Preprint Aug 2026

Mint-Agent: Introducing Finance-Native Agentic Foundation Models

Mint-Agent, a family of finance-native agentic models designed around these two scales of financial intelligence, is presented, establishing a path toward trustworthy financial intelligence in which domain expertise, long-horizon execution, and auditable evidence are jointly engineered as a unified foundation for front...

Mint-Agent Team, Kun Wang, Gavin Zhang et al. · 0 citations
#natural language process... Preprint Aug 2026

HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals

HalluTracer is introduced, a detection framework that reads and aggregates truthfulness evidence across every layer of the forward pass before the model emits any answer token, recasts hallucination detection from a layer-selection problem into a depth-aggregation problem governed by the geometric sparsity of the truth...

Zhi-Hao Guo, Zong-Han Wu, Huan Huo et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.