• Publications
  • Influence
Path sharing and predicate evaluation for high-performance XML filtering
TLDR
The results show that the path sharing employed by YFilter can provide order-of-magnitude performance benefits, and two alternative techniques for extending YFilter's shared structure matching with support for value-based predicates are proposed, and the performance of these two techniques are compared. Expand
UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification
TLDR
This paper presents the claim verification pipeline approach, which, according to the preliminary results, scored third in the shared task, out of 23 competing systems, and introduces two extensions to the Enhanced LSTM (ESIM). Expand
GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server
TLDR
GeePS enables a state-of-the-art single-node GPU implementation to scale well, such as to 13 times the number of training images processed per second on 16 machines (relative to the original optimized single- node code), and achieves a higher training throughput with just four GPU machines than that a state of theart CPU-only system achieves with 108 machines. Expand
Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters
TLDR
Poseidon exploits the layered model structures in DL programs to overlap communication and computation, reducing bursty network communication and is applicable to different DL frameworks by plugging Poseidon into Caffe and TensorFlow. Expand
Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning
TLDR
This work presents a decentralized sensor-level collision avoidance policy for multi-robot systems, which directly maps raw sensor measurements to an agent's steering commands in terms of movement velocity and demonstrates that the learned policy can be well generalized to new scenarios that do not appear in the entire training period. Expand
The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding
TLDR
This PickPocket method is demonstrated to accurately predict MHC-peptide binding for a broad range of MHC alleles, including human and non-human species and was shown to be robust both when data is scarce and when the similarity to MHC molecules with characterized binding specificity is low. Expand
STAT3 regulates arginase-I in myeloid-derived suppressor cells from cancer patients.
TLDR
Results demonstrate that the suppressive function of arginase-I in both infiltrating and circulating MDSC is a downstream target of activated STAT3. Expand
Genome sequence of the Asian Tiger mosquito, Aedes albopictus, reveals insights into its biology, genetics, and evolution
TLDR
The Aedes albopictus Foshan strain has a large genome with significant population-based size variation, the largest mosquito genome sequenced to date, and its size results principally from an abundance of repetitive DNA classes. Expand
Turning from TF-IDF to TF-IGM for term weighting in text classification
TLDR
Experimental results show that TF-IGM outperforms the famous TF-IDF and the state-of-the-art supervised term weighting schemes and some new findings different from previous studies are obtained and analyzed in depth in the paper. Expand
Recurrent Topic-Transition GAN for Visual Paragraph Generation
TLDR
A semi-supervised paragraph generative framework that is able to synthesize diverse and semantically coherent paragraph descriptions by reasoning over local semantic regions and exploiting linguistic knowledge is investigated. Expand
...
1
2
3
4
5
...