papers

Publications (6)

cs.CV2026

Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning

Xin Zou, Haolin Deng, Yibo Yan +6

Inductive biases steer learning toward generalizable solutions by encoding task structure. In this work, we identify a crucial missing bias in MLLMs: cross-view consistency, \texti…

cs.CL2024

WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations

Haolin Deng, Chang Wang, Xin Li +6

Enhancing the attribution in large language models (LLMs) is a crucial task. One feasible approach is to enable LLMs to cite external sources that support their generations. Howeve…

cs.CV2026

Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation

Xin Zou, Haolin Deng, Yibo Yan +5

Multimodal Large Language Models (MLLMs) are prone to hallucination as their generation preferences are insufficiently calibrated to visual evidence, causing them to fall back on l…

cs.CV2026

Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization

Haolin Deng, Xin Zou, Zhiwei Jin +3

Multimodal hallucination remains a persistent challenge for Vision-Language Models (VLMs). Standard textual Direct Preference Optimization (DPO) often fails to mitigate it due to a…

cs.CV2025

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

Zhiwei Jin, Xiaohui Song, Nan Wang +36

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hu…

cs.CL2022

Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset

Haolin Deng, Yanan Zhang, Yangfan Zhang +9

Event extraction (EE) is crucial to downstream tasks such as new aggregation and event knowledge graph construction. Most existing EE datasets manually define fixed event types and…