8 papers
From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
Yuchen Xian, Yunqiu Xu, Yang He +1
Multimodal image fusion aims to integrate complementary information from different modalities into a fused image that preserves rich local details while maintaining globally consis…
VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
Yuchen Xian, Yang He, Yunqiu Xu +1
Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-…
Soft Label Pruning and Quantization for Large-Scale Dataset Distillation
Xiao Lingao, Yang He
Large-scale dataset distillation requires storing auxiliary soft labels that can be 30-40x larger on ImageNet-1K and 200x larger on ImageNet-21K than the condensed images, undermin…
Dataset Color Quantization: A Training-Oriented Framework for Dataset-Level Compression
Chenyue Yu, Lingao Xiao, Jinhong Deng +2
Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing appr…
SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs
Jinhong Deng, Wen Li, Joey Tianyi Zhou +1
Multimodal Large Language Models (MLLMs) typically process a large number of visual tokens, leading to considerable computational overhead, even though many of these tokens are red…
Training-Free Dataset Pruning for Instance Segmentation
Yalun Dai, Lingao Xiao, Ivor W. Tsang +1
Existing dataset pruning techniques primarily focus on classification tasks, limiting their applicability to more complex and practical tasks like instance segmentation. Instance s…