Richard Fan

University of Waterloo

richard.jpeg

I am a Researcher at Pika Labs working with Chenlin Meng.

Previously, I interned at

  • NVIDIA (GPU Kernel)
  • Google (LLM Fine-Tuning & Distillation)
  • TuSimple (Perception for Autonomous Trucks)

I’ve had the previledge of working with

  • Prof. Pascal Poupart (LLM Alignment)
  • Prof. Wenhu Chen (LLM Benchmarking & Video Generation)
  • Prof. Yaoliang Yu (Data Poisoning & Privacy Protection)
  • Prof. Alexander Wong (Copyright Infringement Detection)
  • Prof. Jimmy Lin (Embedding Extraction)
  • Prof. Yash Pant (F1tenth Autonomous Racing)

My research interest lies in

  • Controllable Deep Generative Models (text to image/video)
  • Post-Training for Large Multi-Modal Models

Fun fact: I am a 5 Dan Go player.

news

May 01, 2025 Towards Cost-Effective Reward Guided Text Generation got accepted to ICML 2025!
Sep 26, 2024 GenAI Arena got accepted to NeurIPS 2024!
Sep 26, 2024 MMLU-Pro got accepted to NeurIPS 2024!
Sep 20, 2024 VideoScore got accepted to EMNLP 2024!
Sep 09, 2024 Started interning at NVIDIA! See you in Santa Clara!

latest posts

selected publications

  1. ICML 2025
    mmlu_pro.png
    Towards Cost-Effective Reward Guided Text Generation
    2025
  2. NeurIPS 2024
    mmlu_pro.png
    Mmlu-pro: A more robust and challenging multi-task language understanding benchmark
    Yubo Wang , Xueguang Ma , Ge Zhang , and 14 more authors
    2024
  3. NeurIPS 2024
    genai_arena.png
    GenAI Arena: An Open Evaluation Platform for Generative Models
    Dongfu Jiang , Max Ku , Tianle Li , and 4 more authors
    2024