01
IRI (CSIC–UPC)
Student Researcher
Developing path-conditioned diffusion policies for SOLO12 quadruped locomotion, using hindsight relabeling over pretrained walking and crouching policies, with DPPO fine-tuning in Isaac Lab.
Hi, I’m Sergi Flores.
Robot learning research, computer vision.
Final-year AI student at UPC, currently on exchange at NTUST in Taiwan. I’m mainly interested in robotics and computer vision, especially where learning, perception and control meet.
Girona, CataloniaBSc Artificial Intelligence · UPC · 2023–2027
$ pwd
/home/sergi/portfolio
$ ls
experience/ education/ projects/ awards/ skills/ about/ cv.pdf
Type help to see the available commands.
01 / experience.log
Experience
02
MANGO
Gen AI Research Intern
Worked on diffusion-based image generation and virtual try-on, fashion landmark detection, and end-to-end computer vision pipelines for fashion applications.
02 / education.md
Education
NTUST · Taiwan Tech
Exchange semester · Erasmus+
UPC · Facultat d’Informàtica de Barcelona
BSc in Artificial Intelligence
03 / projects.json
Projects
01Robotics / RL
SOLO12 diffusion policies
Research project on path-conditioned diffusion policies for SOLO12 quadruped locomotion, using hindsight relabeling over pretrained walking and crouching policies, with DPPO fine-tuning.
02Robotics / Award
Barrendeiros · SENER rover
The complete ROS 2 stack for an autonomous competition rover: RGB-D perception, localization, navigation and sample collection.
03Robotics / Multi-robot
Multi-robot CTF
A real-world multi-robot Capture the Flag system for TurtleBot3 Waffle Pi, combining collaborative SLAM, global and local path planning, computer vision, and autonomous coordination.
04Robotics / Planning
UR3 2×2 Rubik’s Cube solver
A task and motion planning system for solving a physical 2×2 Rubik’s Cube with a UR3 robot, PDDL and OMPL/Kautham planning.
05Robotics / RL
UR3 trajectory tracking with SAC
High-precision trajectory tracking for the Universal Robots UR3 using Soft Actor-Critic (SAC) reinforcement learning in MuJoCo, featuring curriculum learning and reward shaping strategies.
06Machine Learning
Diffusion for CMS collision data
DDPM-based generative model for CMS low-level collision data. Compares diffusion models against GANs and VAEs using statistical metrics (MMD, 1-NN, correlation gap), showing improved fidelity on sparse physics distributions.
07Research / Vision
Equivariant vision for astronomy
Set of experiments on equivariant vision models for image and sequential data using FITS astronomical inputs. Includes training, evaluation, and visualization pipelines for both general and sequential workflows.
083D Vision
Video to semantic 3D
A computer-vision pipeline that turns handheld video into a semantic 3D representation.
09Reinforcement Learning
Reinforcement learning methods
Reinforcement learning repository covering discrete model-free algorithms (Monte Carlo, SARSA, Q-learning) and continuous-control actor-critic methods (DDPG, TD3)
10Hackathon / Vision
NASA Space Apps · AI i Oli
Our team developed a computer vision–powered web application that enables users to explore high-resolution stellar images through natural language queries.
11Hackathon / ML
Medulloblastoma continuum scoring
Semi-supervised continuum scoring for medulloblastoma subtype classification, winner of the BSC challenge at BITS x La Marató 2025.
12Hackathon / Vision
Multi-camera 3D human pose
Real-time human detection, tracking and 3D pose reconstruction from multiple camera streams, awarded second prize at HackEPS 2025.
13Hackathon / ML
CARmen · CUPRA assistant
A multimodal RAG assistant, vehicle-part detector and 3D viewer built for the CUPRA challenge at HackUPC 2025.
14Hackathon / ML
Sempre Visibles
Street-level air-quality forecasting across Catalonia with spatial interpolation, traffic data, Random Forest and LightGBM.
15Hackathon / ML
DataMatch
End-to-end system for participant matching using feature engineering, PCA-based clustering, and cosine similarity. Groups users into balanced teams while considering prior connections and preferences, supported by a web interface and an AI chatbot for explainability and interaction.
Repository data is read from GitHub when the site builds.All repositories ↗
04 / awards.csv
Awards
01 / 07
SENER–CEA Bot Talent · Barrendeiros
Technology + Design
TechnologyDesign
After six months developing and integrating an autonomous ROS 2 rover, Team Barrendeiros represented UPC at the final in Madrid. The system received the competition’s Technology and Design awards.
view project ↗
BITS x La Marató · BSC Challenge
1st Prize
1st prize
We won the BSC challenge at Bits x La Marató, a charity hackathon supporting La Marató de TV3, with a semi-supervised continuum-scoring approach for medulloblastoma subtypes.
view project ↗
HackEPS · INGROUP Challenge
2nd Prize
2nd prize
We received second prize for a real-time 3D motion-capture system built from two IP cameras, stereo triangulation and YOLOv8-Pose.
view project ↗
NASA Space Apps Challenge
Global Nominee
Global nominee
AI i Oli was one of two global nominees at the Barcelona edition. It combines classical computer vision with natural-language-to-SQL queries for exploring stellar images.
view project ↗
HackUPC · CUPRA / SEAT Challenge
2nd Prize
2nd prize
CARmen received second prize for turning the CUPRA Tavascan manual into an interactive platform with a RAG chatbot, visual part search and a 3D interior viewer.
view project ↗
BITS x La Marató · BSC Challenge
1st Prize
1st prize
We won BSC’s Fem visible l’invisible challenge at Bits x La Marató, the charity hackathon supporting La Marató de TV3, using ML to downscale CALIOPE air-quality data across Catalonia.
view project ↗
Datathon FME · AED Challenge
1st Prize
1st prize
We won first prize among 300 participants. DataMatch used feature matching, PCA, cosine similarity and a chatbot to form compatible hackathon teams.
view project ↗05 / skills.yaml
Skills
01
Focus
- Robot learning
- Reinforcement learning
- Computer vision
- Diffusion models
- Deep learning
02
Core stack
- Python
- PyTorch
- TensorFlow
- OpenCV
- ROS 2
- Git
- R
- MATLAB
03
Robotics & RL
- Isaac Lab
- MuJoCo
- Gymnasium
- LiDAR
- C++
04
Data & web
- PostgreSQL
- TypeScript
- HTML
- CSS
- Astro
05
Languages
- Catalan · C1
- Spanish · C1
- English · B2
- French · B1
06 / about.txt
About
Alongside my studies, I have been exploring robotics and computer vision through research projects, internships and competitions. At IRI, I am developing diffusion policies for path-conditioned quadruped locomotion; before that, I worked on image generation and computer vision at MANGO, and on the perception stack of an autonomous rover for SENER–CEA Bot Talent. I am particularly interested in research around learning, perception and control, and would like to build on that in my Bachelor’s thesis.