IJCAI Best Papers CollectingInternational Joint Conferences on Artificial Intelligence is a non-profit corporation founded in California, in 1969 for scientific and educational purposes, including dissemination of information on Artificial Intelligence at conferences in which cutting-edge scientific results are presented and through dissemination of materials presented at these meetings in form of Proceedings, books, video recordings, and other educational materials.
IJCAI, pp.4623-4629, (2018)
We present a commonsense knowledge aware conversational model to demonstrate how commonsense knowledge can facilitate language understanding and generation in open-domain conversational systems
Cited by100BibtexViews374Links
1
0
IJCAI, pp.4446-4452, (2018)
We propose SentiGAN, which can generate a variety of high-quality texts of different sentiment labels
Cited by55BibtexViews187Links
1
0
IJCAI, pp.2595-2601, (2018)
We defined a general framework for improving the performance of graph comparison algorithms
Cited by28BibtexViews173Links
0
0
Chun Kai Ling,Fei Fang,J. Zico Kolter
IJCAI, (2018): 396-402
We demonstrate the effectiveness of our approach on several domains: a toy normal-form game where payoffs depend on external context; a one-card poker game; and a security resource allocation game, which is an extensive-form generalization of defender-attacker game in security do...
Cited by28BibtexViews147Links
0
0
IJCAI, pp.49-55, (2018)
In the paper we addressed a number of questions related to whether consensus can be achieved in settings where opinions of the agents are affected by social influence phenomena
Cited by17BibtexViews162Links
0
0
IJCAI, pp.1810-1816, (2018)
An important step into this direction has been made by Kikot and Zolin who identify a large class of conjunctive queries that are rewritable into instance queries: a conjunctive queries is rewritable into an ALCI-instance queries if it is connected and every cycle passes through ...
Cited by3BibtexViews165Links
0
0
Li Xue
IJCAI, pp.2411-2417, (2018)
In practice, the circumstance that training and test data are clean is not always satisfied. The performance of existing methods in the learning using privileged information (LUPI) paradigm may be seriously challenged, due to the lack of clear strategies to address potential nois...
Cited by1BibtexViews123Links
0
0
IJCAI, (2017): 1123-1130
While certain forms of aggregation can be simulated by iterating over the object domain, as in our examples in Section 3, such a solution may be too cumbersome for practical use, and it relies on the existence of a linear order over the object domain, which is a strong theoretica...
Cited by8BibtexViews164Links
0
0
IJCAI, pp.3235-3241, (2016)
We have showed that hierarchical Finite State Controllers can be generated in an incremental fashion to address more challenging generalized planning problems
Cited by10BibtexViews109Links
0
0
J. Artif. Intell. Res., (2015): 127-168
The famous archetypical NP-complete problem of Boolean satisfiability (SAT) and its PSPACE-complete generalization of quantified Boolean satisfiability (QSAT) have become central declarative progra...
Cited by60BibtexViews99Links
0
0
IJCAI'15 Proceedings of the 24th International Conference on Artificial Intelligence, (2015)
This paper proposed a new approach to solving hard nonconvex optimization problems based on recursive decomposition
Cited by33BibtexViews132Links
0
0
IJCAI'15 Proceedings of the 24th International Conference on Artificial Intelligence, pp.3605-3611, (2015)
We proposed a framework for query efficient posterior estimation for expensive blackbox likelihood evaluations
Cited by21BibtexViews161Links
0
0
Artif. Intell., no. C (2014): 78-122
Dropout is a recently introduced algorithm for training neural network by randomly dropping units during training to prevent their co-adaptation. A mathematical analysis of some of the static and dynamic properties of dropout is provided using Bernoulli gating variables, general ...
Cited by138BibtexViews64Links
0
0
IJCAI, pp.1778-1784, (2013)
This paper has shown that it is possible to use random embeddings in Bayesian optimization to optimize functions of high extrinsic dimensionality D, provided that they have low intrinsic dimensionality de
Cited by161BibtexViews175Links
0
0
IJCAI, pp.2422-2428, (2013)
The advantage of the flexibility metric we propose is twofold: First of all, this metric takes into account the correlations between time events unlike previous methods that have been proposed in the literature
Cited by7BibtexViews108Links
0
0
IJCAI, pp.649-654, (2011)
We have presented Nested Rollout Policy Adaptation, an Monte Carlo tree search algorithm that uses gradient ascent on its rollout policy to navigate search
Cited by92BibtexViews152Links
0
0
IJCAI, pp.55-60, (2011)
We showed NP-hardness for BORDA MANIPULATION even for very restricted settings such as having constant numbers of input votes and manipulators
Cited by89BibtexViews123Links
0
0
international joint conference on artificial intelligence, (2011): 957-962
The moral is the same: the topological spaces of most interest for Qualitative Spatial Reasoning exhibit special characteristics which any topological constraint language able to express connectedness must take into account
Cited by14BibtexViews112Links
0
0
international joint conference on artificial intelligence, pp.2040-2045, (2009)
Ontology languages based on Description Logics, such as OWL,1 are becoming increasingly popular among ontology developers thanks to the availability of ontology reasoners, which provide automated support for visualization, debugging, and querying of ontologies
Cited by224BibtexViews123Links
0
0