Learning Latent Graph Dynamics for Deformable Object Manipulation

DefOrmable Object Manipulation(G-DOOM) is a long-standing challenge in robotics . It aims to learn latent Graph dynamics for DefOratable Object Manipulations . We train the resulting graph dynamics model through contrastive learning in a high-fidelity simulator . We evaluate a set of challenging cloth and rope manipulation tasks and show that G-Doomperforms a state-of-the-art method .…

Prior free Strategic Multiagent Scheduling with focus on Social Distancing

The algorithm takes input from citizens and schedules the store’s time-slots based on their importance to visit the facility . We show that it reduces the socialcongestion significantly using users’ visit data from a store . The problem becomes NP-complete as soon as the multi-slot demands are indivisibleand provide a polynomial-time mechanism that is truthful, individuallyrational, and approximately optimal .…

Normal Driven Spherical Shape Analogies

This paper introduces a new method to stylize 3D geometry . The key observation is that the surface normal is an effective instrument to capturedifferent geometric styles . This formulation can deform a 3D shape intodifferent styles within a single framework .…

A Comprehensive Attempt to Research Statement Generation

Research statement generation (RSG) task aims to summarize one’s researchachievements and help prepare a formal research statement . For this task, we construct an RSG dataset with 62 research statements and the corresponding 1,203 publications . We propose a practical RSG method which identifies arearcher’s research directions by topic modeling and clustering techniques .…

Learning Passage Impacts for Inverted Indexes

DeepImpact is a new documentterm-weighting scheme suitable for efficient retrieval using a standardinverted index . Compared to existing methods, it improves impact-scoremodeling and tackles the vocabulary-mismatch problem . When deployed in a re-ranking scenario, it can reach the same effectiveness of state-of-the-art approaches with up to 5.1x speedup inefficiency .…

Random Spreading for Unsourced MAC with Power Diversity

We propose an improvement of the random spreading approach with polar codes for unsourced multiple access . Each user encodes its message by a polar code, and the coded bits are then spread using a random spreading sequence . The proposed approach outperforms the existing methods, especially when the number of active users is large, especially in large numbers of users .…

Improving the filtering of Branch And Bound MDD solver extended

This paper presents and evaluates two pruning techniques to reinforce theefficiency of constraint optimization solvers based on multi-valueddecision-diagrams (MDD) It adopts the branch-and-bound framework proposed by Bergman et al. in 2016 to solve dynamic programs to optimality . In particular, it shows that RUB delivers excellent results but requires some effort when defining the model .…

Ask Explore Grounded Question Answering for Curiosity Driven Exploration

In many real-world scenarios where extrinsic rewards to the agent are extremely sparse, curiosity has emerged as a useful concept . We show that natural language questions encourage the agent to uncoverspecific knowledge about their environment such as the physical properties of objects as well as their spatial relationships with other objects, which serve as valuable curiosity rewards to solve sparse-reward tasks more efficiently .…

On Logics and Homomorphism Closure

Predicate logic is the premier choice for specifying classes of relational structures . Homomorphisms are key to describing correspondences betweenrelational structures . Questions concerning the interdependencies between the sets are of fundamental interest . We investigate several problems regarding the homomorphism closure (homclosure) of the class of all (finite orarbitrary) models of logical sentences .…

Robust Connectivity of Graphs on Surfaces

Large robust connectivity was originally used to show flexible choosability in non-regular graphs . In this paper, we investigate some interesting properties of robustconnectivity for graphs embedded in surfaces . We prove a tight asymptotic bound of $Omega for the robust connectivity of $r$-connectedgraphs of Euler genus $gamma .…

Is research with qualitative data more prevalent and impactful now Interviews case studies focus groups and ethnographies

The prevalence of qualitativedata has increased, often substantially, since 1996 . All 27 broadfields (as classified by Scopus) now publish some qualitative research . This suggests thatqualitative methods teaching and should increase, and researchers, editors andpublishers should be increasingly open to the value that qualitative data can be used in their field to guide decision-making .…

MusCaps Generating Captions for Music Audio

Current approaches to high-level music description typically make use of classification models, such as auto-tagging or genreand mood classification . We propose to address music descriptionvia audio captioning, defined as the task of generating a natural languaged description of music audio content in a human-like manner .…

Modeling Coverage for Non Autoregressive Neural Machine Translation

Non-Autoregressive Neural Machine Translation (NAT) has achieved significantinference speedup by generating all tokens simultaneously . Despite its highefficiency, NAT usually suffers from two kinds of translation errors: repeated tokens and under-translation . We propose anovel Coverage-NAT to model the coverage information directly by a token-levelcoverage iterative refinement mechanism and a sentence-level coverage agreement, which can remind the model if a source token has been translated ornot and improve the semantics consistency between the translation and the source, respectively .…

Language ID Prediction from Speech Using Self Attentive Pooling and 1D Convolutions

This memo describes NTR-TSU submission for SIGTYP 2021 Shared Task onpredicting language IDs from speech . Spoken Language Identification (LID) is an important step in a multilingualAutomated Speech Recognition (ASR) system pipeline . For many low-resource and endangered languages, only single-speaker recordings may be available, demanding a need for domain and speaker-invariant language ID systems .…

Elo Ratings for Large Tournaments of Software Agents in Asymmetric Games

The Elo rating system has been used world wide for individual sports and teamsports, as exemplified by the European Go Federation (EGF), International ChessFederation (FIDE), International Federation of Association Football (FIFA) and many others . To evaluate performance of artificial intelligence agents, it is natural to evaluate them on the same Elo scale as humans, such as the rating of 5185 attributed to AlphaGo Zero .…

Social Influence Prediction with Train and Test Time Augmentation for Graph Neural Networks

Data augmentation has been widely used in machine learning for naturallanguage processing and computer vision tasks to improve model performance . But little research has studied data augmentation on graph neuralnetworks, particularly using augmentation at both train- and test-time . We have designed amethod for social influence prediction using graph neural networks with train-and-test-time augmentation, which can effectively generate multiple augmentedgraphs for social networks by utilising a variational graph autoencoder in both scenarios .…

Additive Schwarz methods for serendipity elements

Serendipity elements allow us to obtain the same order of accuracy as rectangular tensor-product elements with many fewer degrees offreedom (DOFs) To realize the possible computational savings, we develop someadditive Schwarz methods (ASM) based on solving local patch problems . We prove that patchsmoothers give conditioning estimates independent of the polynomial degree for a model problem .…

Suboptimal coverings for continuous spaces of control tasks

We propose the suboptimal covering number to characterize multi-task control problems where the set of dynamical systems and/or cost functions is infinite . This notion may help quantify the function class expressiveness needed to represent a goodmulti-task policy, which is important for learning-based control methods that use parameterized function approximation .…

Membrane Fusion Based Transmitter Design for Static and Diffusive Mobile Molecular Communication Systems

This paper proposes a novel imperfect transmitter (TX) model that adopts MF between a vesicle and the TXmembrane to release molecules encapsulated within the vesicles . Incorporating molecular degradation and afully-absorbing receiver (RX), the channel impulse response (CIR) is derived for two scenarios: Both TX and RX are static, and both TX and TX arediffusion-based mobile .…

Towards Low burden Responses to Open Questions in VR

Subjective self-reports in VR user studies is a burdening and often tedioustask for the participants . To minimize the disruption with the ongoingexperience VR research has started to administer the surveying directly insidethe virtual environments . However, due to the tedious nature of text-entry inVR, most VR surveying tools focus on closed questions with predetermined answers, while open questions with free-text responses remain unexplored .…

MultiCruise Eco Lane Selection Strategy with Eco Cruise Control for Connected and Automated Vehicles

Connected and Automated Vehicles (CAVs) have real-time information from the surrounding environment by using local on-board sensors, V2X(Vehicle-to-Everything) communications, pre-loaded vehicle-specific lookuptables, and map database . Eco-Cruise and Eco-LaneSelection on highways and/or motorways have immense potential to save energy,because there are generally fewer traffic controllers and the vehicles keepmoving in general .…

Parikh s theorem for infinite alphabets

We investigate commutative images of languages recognised by registerautomata and grammars . Semi-linear and rational sets can be naturally extended to this setting by allowing for orbit-finite unions instead of only finite ones . We conjecture analogous results for automata with more than many registers .…

Adaptive Sampling Algorithmic vs Human Waypoint Selection

A paper compares the performance of humans versus adaptiveinformative sampling algorithms for selecting informative waypoints . The results show that the robot can on average perform better than the average human, and approximately as good as the best human, when the model assumptions don’t correspond to the characteristics of the field .…

Wireless Federated Learning WFL for 6G Networks Part II The Compute then Transmit NOMA Paradigm

The Compute-then-Transmit NOMA(CT-NOMA) protocol is introduced, where users terminate concurrently the localmodel training and then simultaneously transmit the trained parameters to the central server . The simulation resultsverify the effectiveness of CT-NomA in terms of delay reduction, compared to the considered benchmark that is based on time-division multiple access .…

Task Offloading Optimization in NOMA Enabled Multi hop Mobile Edge Computing System Using Conflict Graph

Resource allocation is investigated for offloading computational-intensive tasks in multi-hop mobile edge computing (MEC) system . The envisioned system has both the cooperative access points (AP) with the computing capability and the MEC servers . A user-device (UD) uploads a computing task to the nearest AP, and the AP can either locally process the received task oroffload to MEC server .…

Explainable Artificial Intelligence Reveals Novel Insight into Tumor Microenvironment Conditions Linked with Better Prognosis in Patients with Breast Cancer

We investigated the relationship between features in the tumormicroenvironment (TME) and the overall and 5-year survival in triple-negativebreast cancer (TNBC) and non-TNBC (NTNBC) patients by using ExplainableArtificial Intelligence (XAI) models . Novel insights derived from our XAI model showed that CD4+ T cells and B cells are more critical than other TME features for enhanced prognosis for both TNBC and NTNBC patients .…

Privacy as a Planned Behavior Effects of Situational Factors on Privacy Perceptions and Plans

To account for privacy perceptions and preferences in user models and developpersonalized privacy systems, we need to understand how users make privacy decisions in various contexts . We conducted a survey onMechanical Turk (N=401) based on the theory of planned behavior (TPB) to measure the way users’ perceptions of privacy factors and intent to disclose are affected by three situational factors embodied by hypothetical scenarios: information type, recipients’ role, and trust source .…

EXplainable Neural Symbolic Learning X NeSyL methodology to fuse deep learning representations with expert knowledge graphs the MonuMAI cultural heritage use case

Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms . However, DL models are black-box methods hard to debug, interpret, and certify . In contrast, symbolic AI systems that convert concepts into rules or symbols are easier to explain .…

Exploring Multi dimensional Data via Subset Embedding

Multi-dimensional data exploration is a classic research topic invisualization . Most existing approaches are designed for identifying recordpatterns in dimensional space or subspace . In this paper, we propose a visualanalytics approach to exploring subset patterns . The core of the approach is asubset embedding network (SEN) that represents a group of subsets asuniformly-formatted embeddings .…

SnapCheck Automated Testing for Snap Programs

Programming environments such as Snap, Scratch, and Processing engage students by allowing them to create programming artifacts such as apps and games, with visual and interactive output . Learning programming with such amedia-focused context has shown to increase retention and success rate .…

COMTEST Project A Complete Modular Test Stand for Human and Humanoid Posture Control and Balance

This work presents a system to benchmark humanoid posture control and balanceperformances under perturbed conditions . System includes a motion platform used toprovide the perturbation, an innovative body-tracking system suitable for robots, humans and exoskeletons . The design of the system is modularity: all its components can be replaced or extended according to experimental needs .…

Constantine Automatic Side Channel Resistance Using Efficient Control and Data Flow Linearization

In the era of microarchitectural side channels, vendors scramble to deploymitigations for transient execution attacks . But traditional side-channel attacks against sensitive software (e.g., crypto programs) must be fixed by means of constant-time programming . Constantine pursues a radical design point where secret-dependent control and data flows are completely linearized (i.e.,…