Neoadjuvant chemoradiotherapy (nCRT) is the standard treatment for locally advanced rectal cancer (LARC). With the development of artificial intelligence, an increasing number of studies have begun to explore its appl...
详细信息
With the continuous progress of science and technology, the accuracy of satellite remote sensing, detection and reconnaissance technologies is getting higher and higher, and the amount of data generated by them is als...
详细信息
Drug-drug interaction (DDI) plays an increasingly crucial role in drug discovery. Predicting potential DDI is also essential for clinical research. Given the high cost and risk of wet-lab experiments, in-silico DDI pr...
详细信息
As robotic technologies advance, robotic arm manipulation tasks in complex environments become increasingly important. This paper presents a new collaborative pushing and grasping strategy to address two major challen...
详细信息
Multi-hop reasoning is an effective and explainable method for query answering to improve interpretability by finding reasoning paths over knowledge graphs (KGs). Recent studies apply reinforcement learning-based (RL-...
详细信息
Personalized news headline generation, aiming at generating user-specific headlines based on readers’ preferences, burgeons a recent flourishing research direction. Existing studies generally inject a user interest e...
Personalized news headline generation, aiming at generating user-specific headlines based on readers’ preferences, burgeons a recent flourishing research direction. Existing studies generally inject a user interest embedding into an encoder-decoder headline generator to make the output personalized, while the factual consistency of headlines is inadequate to be verified. In this paper, we propose a framework Fact-Preserved Personalized News Headline Generation (short for FPG), to prompt a tradeoff between personalization and consistency. In FPG, the similarity between the candidate news to be exposed and the historical clicked news is used to give different levels of attention to key facts in the candidate news, and the similarity scores help to learn a fact-aware global user embedding. Besides, an additional training procedure based on contrastive learning is devised to further enhance the factual consistency of generated headlines. Extensive experiments conducted on a real-world benchmark PENS 1 validate the superiority of FPG, especially on the tradeoff between personalization and factual consistency. 1 https://***/***
The advent of services such as big data and cloud computing has driven a continuous increase in the required transmission rate and capacity of optical fiber communication systems, which now support over 90% of global ...
详细信息
Diabetic retinopathy (DR), with its large patient population, has become a formidable threat to human visual health. In the clinical diagnosis of DR, multi-view fundus images are considered to be more suitable for DR ...
详细信息
We introduce a method that synergistically combines the distinct phase noise profiles of a dielectric resonator oscillator (DRO) and bichromatic Brillouin laser oscillator (BBLO), for high spectral purity microwave ge...
详细信息
Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high through...
详细信息
ISBN:
(纸本)9798331506476
Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high throughput to enhance user experience and cost-efficiency. However, implementing NVS on existing neural network accelerators and vector search accelerators is sub-optimal due to the separation between the embedding stage and vector search stage at both algorithm and architecture levels. Fortunately, we unveil that Product Quantization (PQ) opens up an opportunity to break separation. However, existing PQ algorithms and accelerators still focus on either the embedding stage or the vector search stage, rather than both simultaneously. Simply combining existing solutions still follows the beaten track of separation and suffers from insufficient parallelization, frequent data access conflicts, and the absence of scheduling, thus failing to reach optimal recall, latency, and throughput. To this end, we propose a unified and efficient NVS accelerator dubbed NeuVSA based on algorithm and architecture co-design philosophy. Specifically, on the algorithm level, we propose a learned PQ-based unified NVS algorithm that consolidates two separate stages into the same computing and memory access paradigm. It integrates an end-to-end joint training strategy to learn the optimal codebook and index for enhanced recall and reduced PQ complexity, thus achieving smoother acceleration. On the architecture level, we customize a homogeneous NVS accelerator based on the unified NVS algorithm. Each sub-accelerator is optimized to exploit all parallelism exposed by unified NVS, incorporating a structured index assignment strategy and an elastic on-chip buffer to alleviate buffer conflicts for reduced latency. All sub-accelerators are coordinated using a hardware-aware scheduling strategy for boosted throughput. Experimental results show that the joint training strategy improves recall
暂无评论