method · first seen 6 Oct 2026
implicit maximum likelihood estimation
Also: iMLE, conditional IMLE
Approximate gradient method for backpropagating through non-differentiable combinatorial optimization layers.
Mentions per week
PapersCodeDiscussion
Earliest sources
- A Decision-Focused Neural Optimization Framework for Personalized Route Reproduction from Vehicle TrajectoriesPapers · 6 Oct 2026 · Gyeongjun Kim, Yeseul Kang, Keemin Sohn
- How Many Candidates Does a One-Step World Model Need? A Random-Codebook Account of Nearest-of-m Training on Frozen DINO TokensPapers · 9 Nov 2026 · Yong Hwi Song, Keon Myung Lee
Latest sources
- How Many Candidates Does a One-Step World Model Need? A Random-Codebook Account of Nearest-of-m Training on Frozen DINO TokensPapers · 9 Nov 2026 · Yong Hwi Song, Keon Myung Lee
- A Decision-Focused Neural Optimization Framework for Personalized Route Reproduction from Vehicle TrajectoriesPapers · 6 Oct 2026 · Gyeongjun Kim, Yeseul Kang, Keemin Sohn