Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks105 from public data
- Untangling Blockchain: A Data Processing View of Blockchain Systems1,186
This paper conducts a comprehensive evaluation of three major blockchain systems based on BLOCKBENCH, namely Ethereum, Parity, and Hyperledger Fabric, and discusses several research directions for bringing blockchain performance closer to the realm of databases.
- BLOCKBENCH: A Framework for Analyzing Private Blockchains933
BLOCKBENCH is described, the first evaluation framework for analyzing private blockchains and it serves as a fair means of comparison for different platforms and enables deeper understanding of different system design choices, and is released for public use.
- Social contextual recommendation317
This paper investigates social recommendation on the basis of psychology and sociology studies, which exhibit two important factors: individual preference and interpersonal influence, and proposes a novel probabilistic matrix factorization method to fuse them in latent spaces.
- FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting180
This work proposes FuseFormer, a Transformer model designed for video inpainting via fine-grained feature fusion based on novel Soft Split and Soft Composition operations, which surpasses state-of-the-art methods in both quantitative and qualitative evaluations.
- DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network95
This paper proposes a novel DivCo framework to properly constrain both "positive" and "negative" relations between the generated images specified in the latent space and introduces a novel latent-augmented contrastive loss, which encourages images generated from adjacent latent codes to be similar and those generated from distinct latent code to be dissimilar.
- HyperNews: Simultaneous News Recommendation and Active-Time Prediction via a Double-Task Deep Neural Network68
This paper proposes a novel approach dubbed HyperNews which explicitly models the effect of timeliness on news recommendation and introduces an auxiliary task of predicting the so-called "active-time" that users spend on each news article.
- Discrete Content-aware Matrix Factorization66
A Discrete Content-aware Matrix Factorization (DCMF) model is proposed to derive compact yet informative binary codes at the presence of user/item content information and an efficient discrete optimization algorithm for parameter learning is developed.
- 58
- Using Twitter to Predict When Vulnerabilities will be Exploited53
This paper proposes a novel framework to predict when a vulnerability will be exploited via Twitter discussion, without using CVSS score information, and introduces the unique concept of a family of CVE-Author-Tweet (CAT) graphs and builds a novel set of features based on such graphs.
- 52
- StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching50
The proposed end-to-end training framework introduces two novel losses, i.e., bidirectional multi-scale feature re-projection loss and correlation consistency loss, to help translate all synthetic stereo images into realistic ones as well as maintain epipolar constraints.
- Conditional Adversarial Generative Flow for Controllable Image Synthesis49
This paper proposes a novel flow-based generative model named conditional adversarial generative flow (CAGlow), which can synthesize images with conditional information like categories, attributes, and even some unknown properties and ensures the independence of different conditions and outperforms regular Glow to a significant extent.
- Discrete Factorization Machines for Fast Feature-based Recommendation47
A convergent updating rule is proposed that resolves the challenging discrete optimization of DFM and shows that DFM consistently outperforms state-of-the-art binarized recommendation models, and DFM shows very competitive performance compared to its real-valued version (FM), demonstrating the minimized quantization loss.
- 46
- 41
- Real-Time Anomaly Detection in Edge Streams37
Algorithms proposed have the following properties: they detects microcluster anomalies while providing theoretical guarantees about the false positive probability; they are online, thus processing each edge in constant time and constant memory, and also processes the data orders- of-magnitude faster than state-of-the-art approaches.
- Vulnerable GPU Memory Management: Towards Recovering Raw Data from GPU37
Evaluation results indicate that nearly all GPU-accelerated applications are vulnerable to such attacks, and adversaries can launch attacks without requiring any special privileges both on traditional multi-user operating systems, and emerging cloud computing scenarios.
- A hierarchical similarity based job recommendation service framework for university students35
This research proposes a student profiling based re-ranking framework that recommends a list of potential jobs based on those who have graduated and obtained job offers over the past few years, and shows this method’s potential.
- 35
- GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning34
The Guided Hybrid Policy Optimization (GHPO), a novel difficulty-aware reinforcement learning framework, is introduced, which significantly enhances both training stability and final reasoning performance, thus offering a scalable and efficient solution for developing powerful and robust reasoning models.
- 28
- Privacy-Preserving Cloud Auditing for Multiple Users Scheme With Authorization and Traceability21
This work uses certificateless signature technology to construct a privacy-preserving cloud auditing scheme for multiple users with authorization and traceability and introduces an identity authentication process between the third-party auditor (TPA) and the CSP to prevent the denial of service attack.
- 17
- Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native17
An AI-native computing paradigm that harnesses the power of both cloud-native technologies and advanced machine learning runtime is described, which aims to optimize costs-of-goods-sold (COGS) and improve resource accessibility.
- DAX17
DAX relies on multi-master replication and Dynamo-style flexible consistency, which enables it to run in multiple data centers and hence be disaster tolerant, and provides high availability and disaster tolerance for the DBMS storage tier.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.