Emilien Dupont

@emidup

phd student in machine learning @oxcsml @UniofOxford 🐳 previously research intern @Apple, computational maths @Stanford, theoretical physics @imperialcollege

California, USA

emiliendupont.github.io

Replies Reposts Media

Emilien Dupont
@emidup
May 14, 2025
We introduce 🌸✨ AlphaEvolve ✨🌸, an evolutionary coding agent using LLMs coupled with automatic evaluators, to tackle open scientific problems 🧑‍🔬 and optimize critical pieces of compute infra ⚙️ deepmind.google/discover/blog/…
GIF
Emilien Dupont
@emidup
Mar 13, 2024
We build neural codecs from a *single* image or video, achieving compression performance close to SOTA models trained on large datasets, while requiring ~100x fewer FLOPs for decoding ⚡ #CVPR2024 c3-neural-compression.github.io
4
Emilien Dupont
@emidup
Dec 14, 2023
We present #FunSearch in @Nature today - a system combining LLMs with evolutionary search to generate new discoveries in math and computer science! 👩‍🔬🔬✨
Google DeepMind
@GoogleDeepMind
Dec 14, 2023
Introducing FunSearch in @Nature: a method using large language models to search for new solutions in mathematics & computer science. 🔍 It pairs the creativity of an LLM with an automated evaluator to guard against hallucinations and incorrect ideas. 🧵 dpmd.ai/x-funsearch
GIF
3
Emilien Dupont
@emidup
Feb 2, 2023
One more day to submit to our ICLR'23 workshop on Neural Fields! Submissions on all topics related to Neural Fields are welcome 😌 sites.google.com/view/neural-fi…
Emilien Dupont
@emidup
Jun 7, 2022
By treating functions parameterized by neural nets as data points, called functa, we introduce a framework for tackling several deep learning tasks, including diffusion models on NeRF and 3D shape inference! 💫
Hyunjik Kim
@hyunjik11
Jun 7, 2022
Ever wondered why deep learning is always done on array data?🤔 Happy to announce our work: From data to functa: Your data point is a function and you can treat it like one 📝arxiv.org/abs/2201.12204 w/ @emidup @arkitus @DaniloJRezende @danrsm, to appear in ICML22
GIF