David Bau asks: Which new deep learning papers are essential reading?
davidbau · x · 2026-08-19
MIT researcher David Bau (known for GAN inversion and visualization) is updating his curated list "Famous Deep Learning Papers."
He is asking the community to suggest the most important new papers from the last few years that deserve a spot on the list. The current resource tracks key milestones from 1943 (McCulloch & Pitts) through the rise of modern deep learning.
This open call aims to help students and practitioners build a foundational understanding of the field.
More from Research
- NUS Releases V-RAE: Rethinking Video Latent Spaces — NationalUniversityofSingapore · 2026-08-19
- Studying AGI reachability through formal logic and computability theory — suayptalha · 2026-08-19
- Dynamic Short Convolutions Cut GPU Training Time by 21% — Cohere_Labs · 2026-08-19
- Portable, Versioned Knowledge Bases: Solving Real Problems or RAG with Extra Steps? — Rebootz · 2026-08-19
- Team hits 70% on ARC-AGI-2 Kaggle with 4 L4 GPUs and no internet — JFPuget · 2026-08-19
- Paper Proposes Set Theory-Based AGI Architecture with Human-Level Efficiency — MikePFrank · 2026-08-19