Search Results for author:
Found 9 papers, 2 papers with code
MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More
Our MC-MoE integrates static quantization and dynamic pruning to collaboratively achieve extreme compression for MoE-LLMs with less accuracy loss, ensuring an optimal trade-off between performance and efficiency.
Differentiable Proximal Graph Matching
The whole algorithm can be considered as a differentiable map from the graph affinity matrix to the prediction of node correspondence.
Ensemble Quadratic Assignment Network for Graph Matching
In this paper, we propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods.
Debiasing Text-to-Image Diffusion Models
Despite its simplicity, we show that IDA shows efficiency and fast convergence in resolving the social bias in TTI diffusion models.
SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training
We discover that the lack of consideration for sample-wise affinity consistency across modalities in existing training objectives is the central cause.
Semantic Diffusion Network for Semantic Segmentation
We then propose a novel learnable approach called semantic diffusion network (SDN) to approximate the diffusion process, which contains a parameterized semantic difference convolution operator followed by a feature fusion module.
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference
Experiments show that the proposed vertical-layered representation and developed once QAT scheme are effective in embodying multiple quantized networks into a single one and allow one-time training, and it delivers comparable performance as that of quantized models tailored to any specific bit-width.
Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention
To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to improve its efficiency.
Proxy Graph Matching with Proximal Matching Networks
It consists of three parts: a graph neural network to generate a high-level local feature, an attention-based module to normalize the rotational transform, and a global feature matching module based on proximal optimization.
