5 papers
SQLord: A Robust Enterprise Text-to-SQL Solution via Reverse Data Generation and Workflow Decomposition
Song Cheng, Qiannan Cheng, Linbo Jin +2
Transforming natural language into SQL queries (NL2SQL) is crucial for data-driven business applications. Existing frameworks, trained on open-source datasets, struggle with comple…
ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning
Yeyuan Wang, Dehong Gao, Rujiao Long +4
Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements…
Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
Bin Li, Dehong Gao, Yeyuan Wang +4
Despite the significant success of Large Vision-Language models(LVLMs), these models still suffer hallucinations when describing images, generating answers that include non-existen…
Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples
Yeyuan Wang, Dehong Gao, Lei Yi +4
Existing Vision-Language Pretraining (VLP) methods have achieved remarkable improvements across a variety of vision-language tasks, confirming their effectiveness in capturing coar…
MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning
Yufei Ma, Zihan Liang, Huangyu Dai +9
The growing demand for larger-scale models in the development of \textbf{L}arge \textbf{L}anguage \textbf{M}odels (LLMs) poses challenges for efficient training within limited comp…