4 papers
TableVista: Benchmarking Multimodal Table Reasoning under Visual and Structural Complexity
Zheyuan Yang, Liqiang Shang, Junjie Chen +6
We introduce TableVista, a comprehensive benchmark for evaluating foundation models in multimodal table reasoning under visual and structural complexity. TableVista consists of 3,0…
VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading
Cheng Xu, Xiaofeng Hou, Jiacheng Liu +1
Large-scale vision-language mixture-of-experts (VL-MoE) models provide strong multimodal capability, but efficient deployment on memory-constrained platforms remains difficult. Exi…
FlowWalker: A Memory-efficient and High-performance GPU-based Dynamic Graph Random Walk Framework
Junyi Mei, Shixuan Sun, Chao Li +9
Dynamic graph random walk (DGRW) emerges as a practical tool for capturing structural relations within a graph. Effectively executing DGRW on GPU presents certain challenges. First…
MMBench: Benchmarking End-to-End Multi-modal DNNs and Understanding Their Hardware-Software Implications
Cheng Xu, Xiaofeng Hou, Jiacheng Liu +9
The explosive growth of various types of big data and advances in AI technologies have catalyzed a new type of workloads called multi-modal DNNs. Multi-modal DNNs are capable of in…