13 papers
Detached Skip-Links and -Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR
Ziye Yuan, Ruchang Yao, Chengxin Zheng +3
Multimodal large language models (MLLMs) excel at high-level reasoning yet fail on OCR tasks where fine-grained visual details are compromised or misaligned. We identify an overloo…
Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers
Yusheng Zhao, Hourun Li, Bohan Wu +5
The attention mechanism has been the core component in modern transformer architectures. However, the computation of standard full attention scales quadratically with the sequence…
DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise
Yusheng Zhao, Jiaye Xie, Qixin Zhang +5
Graph neural networks (GNNs) have been widely used in various graph machine learning scenarios. Existing literature primarily assumes well-annotated training graphs, while the reli…
Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs
Yusheng Zhao, Qixin Zhang, Xiao Luo +5
Large language models (LLMs) have been used in many zero-shot learning problems, with their strong generalization ability. Recently, adopting LLMs in text-attributed graphs (TAGs)…
Embracing Large Language Models in Traffic Flow Forecasting
Yusheng Zhao, Xiao Luo, Haomin Wen +3
Traffic flow forecasting aims to predict future traffic flows based on the historical traffic conditions and the road network. It is an important problem in intelligent transportat…
Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
Yangning Li, Weizhi Zhang, Yuyao Yang +17
Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inf…