Lucas Dionisopoulos
Bit about me:
- Grew up in Nebraska
- Spent my first two years post-grad in investment banking
- Knew I wanted a career change... so I took a gap year where I mostly studied (but also had a bit of fun)
- Worked on research in grad school (UCSD). Primarily focused on RL for LLMs - gave a talk at NeurIPS (FoRLM Workshop) and published a paper at ICML
- Currently at Hadrian
If you're in LA / just want to chat - you should reach out!
Blogs
Some Writing
- The Update The update on the pivot 2.5 years later.
- Why Pivot? My motivation for leaving finance, taking a gap year to study ML, and starting grad school.
- My Hours as an Investment Banking Analyst. I tracked hours during my 2 years in banking and made some neat charts.
Research
Some Research
Primarily worked on RL + LLMs in PEARLS Lab. Previously worked with UCSD ProgSys. My thesis ties these two together.
How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess
NeurIPS 2025 FoRLM Workshop (Oral)
ICML 2026
Outperformed state-of-the-art open-source reasoning models in chess through SFT and RL on a 7B-parameter language model. The key focus of this work was to study how fine-tuning influenced post-RL reasoning using custom theoretically-inspired datasets.
Philosophize That
Neat project I whipped up to train a philosophy classifier using paragraph-level text embeddings (I then classified my own writing).
Projects
Some Technical Projects
RL Benchmarking Gym
Built a clean, hackable RL gym engine from scratch to implement and ablate algorithms from baseline to SoTA.
Dungeon Coder
Full-stack webapp combining image generation and image-to-3D asset models to create custom assets you can place in interactive dungeons or 3D print. Includes a dungeon generator that turns a prompt into a 3D dungeon using classical algorithms plus LLM agents. Built with React, Three.js, and self-hosted CV models.
SLAM-Based Autonomy for 4-Wheel Rover
Developed an autonomy stack for an uncalibrated 4-wheel differential-drive rover, implementing vision, EKF-SLAM from scratch, and path planning algorithms. Built with ROS2, OpenCV, and Python.
Reinforcement Learning Driver
Created and optimized a racing game in Pygame and taught an RL agent to drive it using Double Q-learning.
Machine Learning Anomaly Detection
Developed a real-time, interpretable anomaly detection system over noisy time-series data using kernel ridge regression for a San Diego healthtech company.
Recreating Word2Vec
Recreated Word2Vec vector arithmetic entirely from scratch, from building a tokenizer to cleaning English Wikipedia and training an embedding model.
Personal
Sabbatical
When I finished banking, I wanted to lock in and study ML.
I considered my options: study at home in Wisconsin or study abroad at long-term Airbnbs and pet sits.
One of these paths seemed more fun.
Note: I also did a lot of work.
Feel free to reach out!
firstlast[at]gmail[dot]com