DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models Paper • 2406.11633 • Published Jun 17 • 1
Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy Paper • 2410.09873 • Published Oct 13
Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression Paper • 2403.15835 • Published Mar 23
Performance-aware Approximation of Global Channel Pruning for Multitask CNNs Paper • 2303.11923 • Published Mar 21, 2023
CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation Paper • 2410.18311 • Published Oct 23
ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning Paper • 2402.12185 • Published Feb 19