H
Data Science Intern
HiLabs,
@beingamanfr
Aman Behera
@beingamanfr
I’m Aman Behera, a systems-focused C++ developer and open-source contributor from IIT Roorkee (’26). I work on performance-critical numerical software, memory-efficient algorithms, and low-level infra
I’m Aman Behera, a systems-focused C++ developer and open-source contributor from IIT Roorkee (’26). I work on performance-critical numerical software, memory-efficient algorithms, and low-level infra
Data Science Intern, HiLabs
Roorkee, India
5
projects
5
0
prizes
0
6
hackathons
6
0
Hackathons org.
0
762
contributions in the last year
Sep
S
M
T
W
T
F
S
Aug
188
stars earned
77
repositories
54
followers
Not So Smart OCR | Document extraction you can inspect, Extract text and structure from PDFs and images.
Python
0Stars
0Forks
[NeurIPS'2026] Position Bias in Mamba and Hybrid Language Models | Evidence Position Bias Across Sequence Mixers in Long-Context Question Answering
Python
3Stars
0Forks
Developed a sophisticated machine learning model capable of generating diverse interview questions aligned with specific topics, ensuring depth of conversation. Integrated advanced Natural Language Processing (NLP) algorithms to analyse spoken responses, identifying grammatical errors & offering accurate corrections after the interview.
Jupyter Notebook
46Stars
13Forks
Rubric Decoupled Advantage Normalisation GRPO is a Rubric-based Reinforcement Learning (RL) repository for aligning Large Lan- guage Models (LLMs) with complex, open-domain instruction following tasks
Python
0Stars
0Forks
H
H
I
X
H
HiLabs,
I
Info Edge,
X
XLRI Jamshedpur,
The game consists of a stricker located at the bottom end of the screen, a ball & many bricks above the striker. The basic theme of this game is to break the blocks with the ball using the stricker.
Usage of Monte Carlo Simulation to predict future stock prices and help to optimize a portfolio, helping an investor ensure maximum returns vesting an investment amount into various stock assets.
Usage of modules like qiskit to optimize portfolios and see how well quantum approaches compare to classical approaches.
Experimental study on the orientation of elongated fluidized bed particles with the help of OpenCV and Hough Transform
medium.com
Developed a sophisticated machine learning model capable of generating diverse interview questions aligned with specific topics, ensuring depth of conversation. Integrated advanced Natural Language Processing (NLP) algorithms to analyze spoken responses, identifying grammatical errors & offering accurate corrections after the interview. Chat-bot Interviewer The Chat-bot Interviewer is a conversational AI system designed to engage in natural language interactions with users, simulating the experience of a...
medium.com
Hey guys, lately I have been working on structuring the layout of a project I wish to work on. Let’s get some insights into it, and stick along as I bring it to life! Introduction: A model for hit song prediction that can be used to identify emerging trends and potential artists or songs before they are marketed to the public. While most previous work formulates hit song prediction as a regression or classification problem, here a convolutional neural network (CNN) model is presented that treats it as a ...
medium.com
AI-Generated Text Detection using BERT 🌟 AI-generated text detectionusing BERT( Bi-directional Encoder Representation Transformer) is from the family of LLMs, which has been used for the classification of human-authored texts and AI-Generated Texts. It uses various feature selection techniques in the core for categorizing the texts generated by the two groups. It detects the two based on semantic differences, usage of vocabulary, statistical distributions, and sentiment analysis measures. This detectio...