Input Optimization: Balancing Adversarial Discovery with Structured Sample Generation
What’s the best way to generate samples that meet structured criteria? In this post, we show the fine line between adversarial discovery and sample generation.
| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://nsortur.github.io/portfolio/
access-control-allow-origin: *
strict-transport-security: max-age=31556952
expires: Mon, 29 Dec 2025 21:47:09 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: 4748:3946E9:9481CD:A6BA58:6952F483
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 21:37:10 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210041-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767044230.802311,VS0,VE218
vary: Accept-Encoding
x-fastly-request-id: 87e7f07abf78b4aa232adae75c13ef588476a160
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 10 Dec 2025 05:34:45 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"69390675-2181"
expires: Mon, 29 Dec 2025 21:47:10 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 4C07:2F7ECD:95723F:A7A9FF:6952F485
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 21:37:10 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210041-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767044230.033883,VS0,VE232
vary: Accept-Encoding
x-fastly-request-id: 4816e27e80b1bfc831879877d5d912fd8ba401c0
content-length: 2798
Portfolio - Neel Sortur 
Neel Sortur
Master's student, GRFP Fellow at Northeastern University
- Boston, MA
- Github
- Google Scholar
Portfolio
xArm Handovers: Facilitating Human to Robot Handoffs
In this project, we trained an agent to dynamically hand over an object to a human. We used vision-based deep reinforcement learning and an xArm, pictured below. 