A5055091245- Robot Manipulation and Learning
- Reinforcement Learning in Robotics
- Human-Automation Interaction and Safety
- Social Robot Interaction and HRI
- Fault Detection and Control Systems
- Genomics and Phylogenetic Studies
- Advanced Bandit Algorithms Research
- Prosthetics and Rehabilitation Robotics
- Genomics and Rare Diseases
- Cancer Genomics and Diagnostics
- Algorithms and Data Compression
- Gene expression and cancer classification
- Data Stream Mining Techniques
- Robotic Locomotion and Control
- SARS-CoV-2 and COVID-19 Research
- vaccines and immunoinformatics approaches
- Ethics in Clinical Research
- Advanced Control Systems Optimization
- Risk and Safety Analysis
- Cloud Computing and Resource Management
- Single-cell and spatial transcriptomics
- COVID-19 Clinical Research Studies
- Pancreatic and Hepatic Oncology Research
- Human Pose and Action Recognition
- Diabetic Foot Ulcer Assessment and Management
Microsoft (United States)
2011-2025
Carnegie Mellon University
2022-2024
Microsoft Research (United Kingdom)
2021
University of California, Berkeley
2018-2019
T cells are involved in the early identification and clearance of viral infections also support development antibodies by B cells. This central role for makes them a desirable target assessing immune response to SARS-CoV-2 infection. Here, we combined two high-throughput profiling methods create quantitative picture T-cell SARS-CoV-2. First, at individual level, deeply characterized 3 acutely infected 58 recovered COVID-19 subjects experimentally mapping their CD8 through antigen stimulation...
ABSTRACT Background Sugarcane cultivars are polyploid interspecific hybrids of giant genomes, typically with 10–13 sets chromosomes from 2 Saccharum species. The ploidy, hybridity, and size the genome, estimated to have >10 Gb, pose a challenge for sequencing. Results Here we present gene space assembly SP80-3280, including 373,869 putative genes their potential regulatory regions. alignment single-copy in diploid grasses indicates that could resolve 2–6 (up 15) homo(eo)logs 99.1%...
Cloud computing is a new paradigm, combining diverse client devices -- PCs, smartphones, sensors, single-function, and embedded with computation data storage in the cloud. As every advance computing, programming fundamental challenge, as cloud concurrent, distributed system running on unreliable hardware networks.
Translating the genetic and epigenetic heterogeneity underlying human cancers into therapeutic strategies is an ongoing challenge. Large-scale sequencing efforts have uncovered a spectrum of mutations in many hematologic malignancies, including acute myeloid leukemia (AML), suggesting that combinations agents will be required to treat these diseases effectively. Combinatorial approaches also critical for combating emergence genetically heterogeneous subclones, rescue signals...
Human biomedical datasets that are critical for research and clinical studies to benefit human health also often contain sensitive or potentially identifying information of individual participants. Thus, care must be taken when they processed made available comply with ethical regulatory frameworks informed consent data conditions. To enable streamline access these datasets, the Global Alliance Genomics Health (GA4GH) Data Use Researcher Identities (DURI) work stream developed approved...
Abstract Motivation Intra-tumor heterogeneity is one of the key confounding factors in deciphering tumor evolution. Malignant cells exhibit variations their gene expression, copy numbers and mutation even when originating from a single progenitor cell. Single cell sequencing has recently emerged as viable option for unmasking underlying heterogeneity. However, extracting features genomic data order to infer evolutionary trajectory remains computationally challenging due extremely noisy...
The Global Alliance for Genomics and Health (GA4GH) proposes a data access policy model-"registered access"-to increase improve to requiring an agreement basic terms conditions, such as the use of DNA sequence health in research. A registered would enable range categories users gain access, starting with researchers clinical care professionals. It also facilitate general reuse but within bounds consent restrictions other ethical obligations. In piloting Scientific Demonstration sharing...
T cells are involved in the early identification and clearance of viral infections also support development antibodies by B cells. This central role for makes them a desirable target assessing immune response to SARS-CoV-2 infection. Here, we combined two high-throughput profiling methods create quantitative picture T-cell SARS-CoV-2. First, at individual level, deeply characterized 3 acutely infected 58 recovered COVID-19 subjects experimentally mapping their CD8 through antigen stimulation...
Millirobots are a promising robotic platform for many applications due to their small size and low manufacturing costs. Legged millirobots, in particular, can provide increased mobility complex environments improved scaling of obstacles. However, controlling these small, highly dynamic, underactuated legged systems is difficult. Hand-engineered controllers sometimes control but they have difficulties with dynamic maneuvers terrains. We present an approach real-world millirobot that based on...
Our goal is for people to be physically comfortable when taking objects from robots. This puts a burden on the robot hand over object in such way that person can easily reach it, without needing strain or twist their arm - conducive ergonomic human grasping configurations. To achieve this, needs understand what makes configuration more less person, i.e. cost function. In this work, we formulate learning person's as an online estimation problem. The implicitly make queries by handing them...
Abstract The volume of genomics and health data is growing rapidly, driven by sequencing for both research clinical use. However, under current practices, the fragmented into many distinct datasets, researchers must go through a separate application process each dataset. This time-consuming stewards, it reduces velocity new discoveries that could improve human health. We propose to simplify this process, introducing standard Library Card identifies authenticates across all participating...
Abstract Much genomic data comes in the form of paired-end reads: two reads that represent genetic material with a small gap between. We present new algorithm for aligning both pair simultaneously by fuzzily intersecting sets candidate alignment locations each read. This is often much faster and produces alignments result variant calls having roughly same concordance as best competing aligners.
Many collaborative human-robot tasks require the robot to stay safe and work efficiently around humans. Since can only with respect its own model of human, we want learn a good human in order act both safely efficiently. This paper studies methods that enable explore space system improve robot's which will consequently allow access larger state better human. In particular, introduce active exploration under framework energy-function based control, investigate effect different strategies,...
People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at learning such tasks. Thus, there is an opportunity for AI agents to assist people these tasks more effectively. In this work, we use a multi-armed bandit as controlled setting explore direction. We pair with selection of and observe how well each human-agent team performs. find performance beat both human agent...
Robots can learn preferences from human demonstrations, but their success depends on how informative these demonstrations are. Being is unfortunately very challenging, because during teaching, people typically get no transparency into what the robot already knows or has learned so far. In contrast, students naturally provide a wealth of nonverbal feedback that reveals level understanding and engagement. this work, we study similarly minimally disruptive, yet gives teachers better mental...
Abstract Motivation Intra-tumor heterogeneity is one of the key confounding factors in deciphering tumor evolution. Malignant cells exhibit variations their gene expression, copy numbers, and mutation even when originating from a single progenitor cell. Single cell sequencing has recently emerged as viable option for unmasking underlying heterogeneity. However, extracting features genomic data order to infer evolutionary trajectory remains computationally challenging due extremely noisy...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Robots can influence people to accomplish their tasks more efficiently: autonomous cars inch forward at an intersection pass through, and tabletop manipulators go for object on the table first. However, a robot's ability also compromise safety of nearby if naively executed. In this work, we pose solve novel robust reach-avoid dynamic game which enables robots be maximally influential, but only when backup control exists. On human side, model human's behavior as goal-driven conditioned plan,...
As robots are deployed in human spaces, it's important that they able to coordinate their actions with the people around them. Part of such coordination involves ensuring have a good understanding how robot will act environment. This can be achieved through explanations robot's policy. Much prior work explainable AI and RL focuses on generating for single-agent policies, but little has been explored collaborative policies. In this work, we investigate generate multi-agent strategy...