6 papers
REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment
Kai Ye, Xianwei Mao, Sheng Zhou +6
Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval. However, exis…
MaS-VQA: A Mask-and-Select Framework for Knowledge-Based Visual Question Answering
Xianwei Mao, Kai Ye, Sheng Zhou +4
Knowledge-based Visual Question Answering (KB-VQA) requires models to answer questions by integrating visual information with external knowledge. However, retrieved knowledge is of…
Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation
Yuansheng Gao, Peng Gao, Han Bao +4
Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online interactions. Detecting such behavior is…
MedFact-R1: Towards Factual Medical Reasoning via Pseudo-Label Augmentation
Gengliang Li, Rongyu Chen, Bin Li +2
Ensuring factual consistency and reliable reasoning remains a critical challenge for medical vision-language models. We introduce MEDFACT-R1, a two-stage framework that integrates…
LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
Yining Huang, Bin Li, Keke Tang +1
Large-scale generative models like DeepSeek-R1 and OpenAI-O1 benefit substantially from chain-of-thought (CoT) reasoning, yet pushing their performance typically requires vast data…
Learning to Unify Audio, Visual and Text for Audio-Enhanced Multilingual Visual Answer Localization
Zhibin Wen, Bin Li
The goal of Multilingual Visual Answer Localization (MVAL) is to locate a video segment that answers a given multilingual question. Existing methods either focus solely on visual m…