9 accepted papers
Hash center-based deep hashing methods improve upon pairwise or triplet-based approaches by assigning fixed hash centers to each class as learning targets, thereby avoiding the inefficiency of local similarity optimization. However, random center initialization often disregards inter-class semantic
The progressive scaling of large language models (LLMs) has consistently enhanced multimodal understanding and advanced reasoning capabilities, but has substantially increased computational and hardware execution overhead. In this paper, we present S-Quant, a novel post-method that compresses only m…
Channel permutation is a powerful technique for enhancing the accuracy of N:M sparse models by reordering the channels of weight matrices to prioritize the retention of important weights. However, traditional channel permutation methods rely on handcrafted quality metrics, which often fail to accur…
Nowadays, Large Language Models (LLMs) mostly possess billions of parameters, bringing significant challenges to hardware platforms. Although quantization is an efficient approach to reduce computation and memory overhead for inference optimization, we stress the challenge that mainstream low-bit qu…
The tool-use Large Language Models (LLMs) that integrate with external Python interpreters have significantly enhanced mathematical reasoning capabilities for open-source LLMs, while tool-free methods chose another track: augmenting math reasoning data. However, a great method to integrate the above…
Recently, the tool-use Large Language Models (LLMs) that integrate with external Python interpreters have significantly enhanced mathematical reasoning capabilities for open-source LLMs. However, these models fall short in demonstrating the calculation process, which compromises user-friendliness an…
Aspect-based sentiment analysis (ABSA) is aimed at predicting the sentiment polarities of the aspects included in a sentence instead of the whole sentence itself, and is a fine-grained learning task compared to the conventional text classification. In recent years, on account of the ability to model…
The training and inference efficiency of ever-larger deep neural networks highly rely on the performance of tensor operators on specific hardware platforms. Therefore, a compilation-based optimization flow with automatic tensor generation and parameter tuning is necessary for efficient model deploym…
Since Transformers can alleviate some critical and fundamental problems of graph neural networks (GNNs), such as over-smoothing, over-squashing and limited expressiveness, they have been successfully applied to graph representation learning and achieved impressive results. However, although there ar…