Yuhan Ma

M.S. student in Computer Science at New York University

I am a graduate student in Computer Science at New York University. My interests are centered on recommender systems, language model reasoning, and machine learning systems that are rigorous, reproducible, and useful beyond a single benchmark.

Recently, I have been building end-to-end retrieval-ranking pipelines, transformer training code from scratch, and reinforcement learning workflows for reasoning models. I am especially interested in how system design choices affect stability, evaluation quality, and downstream behavior.

Prior to NYU, I received my B.E. in Computer Science and Technology from Anhui University, where I graduated as an Outstanding Undergraduate Graduate of the Class of 2025. I also joined an exchange program at Deakin University.

I am happy to discuss research, engineering, internships, and collaboration in general. You can reach me by email, browse my GitHub, or open my CV.

I am currently interested in:

  • Recommender Systems: retrieval, ranking, re-ranking, sequence modeling, and evaluation design.
  • LLM Reasoning and Post-Training: supervised fine-tuning, reward design, GRPO-style optimization, and test-time behavior.
  • ML Systems: reproducible data pipelines, checkpointing, experiment tracking, and low-friction deployment.

updates

Apr 14, 2026 Launched this academic-style personal website and uploaded my latest CV.
Mar 2026 Completed a reinforcement learning pipeline for LLM reasoning using SFT and GRPO on Qwen2.5-Math-1.5B.
Mar 2026 Finished a four-stage recommendation system for short-video feed ranking on KuaiRand-Pure.
Feb 2026 Built a GPT-style transformer language model from scratch with a streaming tokenizer and memmap training pipeline.
Mar 2024 Completed a machine learning engineering internship at National Quantum, working on image segmentation and deployment.

selected projects

  1. RecSys

    Four-Stage Recommendation System for Short-Video Feed

    Jan 2026 - Mar 2026

    Built a full recommendation system on KuaiRand-Pure with multi-channel retrieval, coarse ranking, fine ranking, and rule-based re-ranking. The pipeline used time-based splitting and materialized intermediate candidates to keep experiments reproducible.

    Highlights: Recall@100 of 0.2476 / 0.2343 on validation and test, val AUC of 0.8149 for coarse ranking, and improved top-100 recall after candidate reduction.

    ItemCF Two-Tower Graph Embedding LightGBM DIN
  2. Benchmark

    Retrieval-Ranking Benchmark for Recommender Systems

    Sep 2025 - Nov 2025

    Built a unified recommendation benchmark on MovieLens-32M with negative sampling, Recall, and NDCG evaluation, and compared BPR-MF, GRU4Rec, SASRec, BERT4Rec, and dual-tower retrieval.

    Highlights: BERT4Rec achieved Recall@10 = 0.97 and NDCG@10 = 0.80.

    BPR-MF GRU4Rec SASRec BERT4Rec Dual-Tower
  3. LLM

    GPT-Style Transformer Language Model from Scratch

    Jan 2026 - Feb 2026

    Implemented a byte-level BPE tokenizer and core transformer modules including causal self-attention, RoPE, RMSNorm, and SwiGLU, then paired them with a streaming tokenization and uint16 memmap pipeline.

    Highlights: processed 541M training tokens and 5.46M validation tokens, with a full-dev loss of 1.475.

    Transformer RoPE RMSNorm SwiGLU TinyStories
  4. RL

    Reinforcement Learning for LLM Reasoning

    Feb 2026 - Mar 2026

    Built a training and evaluation pipeline for reasoning models based on Qwen2.5-Math-1.5B, covering zero-shot baselines, SFT, GRPO, reward design, automatic grading, and rollout-based updates.

    Highlights: improved Countdown validation accuracy to 32.4%.

    SFT REINFORCE GRPO Reward Design

experience

National Quantum

Machine Learning Engineer Intern · Jan 2024 - Mar 2024

Worked on magnetic-particle image segmentation under limited-data conditions. I designed data processing and annotation workflows, used SAM for bootstrapped labeling, trained UNet variants in PyTorch, and improved validation performance with augmentation, Optuna, Focal Loss, and Dice Loss.

I also completed model export and production-side inference with ONNX Runtime, which gave me end-to-end exposure from training to deployment.

Education

New York University · Aug 2025 - May 2027

M.S. in Computer Science, Concentration in Artificial Intelligence · GPA 3.9 / 4.0

Anhui University · Sep 2021 - Jun 2025

B.E. in Computer Science and Technology · GPA 3.73 / 4.0 · Outstanding Undergraduate Graduate of the Class of 2025 · Exchange Program at Deakin University, Australia