2 citations · 2 across the 12 of their papers we have counts for
14 papers
Hierarchical Gaussian Processes for Survey Weighting: Local Equivalent Weights in Structured Populations
Seonghun Lee
Regression-based survey weighting connects model-based population estimation with design-based inference through equivalent weights. For nonlinear models, equivalent weights can be…
Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems
Woosang Jeon, Jaeyeon Kim, Sham Kakade +6
Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on problems governed by complex global…
From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models
Seunggeun Kim, Jaeyeon Kim, Taekyun Lee +4
Many discrete reasoning tasks, such as code generation, are inherently non-causal: programmers move between high-level structure and local details, a process we call any-order infe…
Retrofitting Linear Attention into Diffusion Language Models
Jinha Kim, Younghun Roh, Jaeyeon Kim
Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding. Recent dLLMs commonly use blockwise se…
Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
Jaeyeon Kim, Jonathan Geuter, David Alvarez-Melis +2
Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces. By generating sequences in any order and allowing for parallel decod…
Fine-Tuning Masked Diffusion for Provable Self-Correction
Jaeyeon Kim, Seunggeun Kim, Taekyun Lee +4
A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Models (MDMs) have emerged as a promi…
Selective Underfitting in Diffusion Models
Kiwhan Song, Jaeyeon Kim, Sitan Chen +3
Diffusion models have emerged as the principal paradigm for generative modeling across various domains. During training, they learn the score function, which in turn is used to gen…
Any-Order Flexible Length Masked Diffusion
Jaeyeon Kim, Lee Cheuk-Kit, Carles Domingo-Enrich +5
Masked diffusion models (MDMs) have recently emerged as a promising alternative to autoregressive models over discrete domains. MDMs generate sequences in an any-order, parallel fa…
Delta Rectified Flow Sampling for Text-to-Image Editing
Gaspard Beaudouin, Minghan Li, Jaeyeon Kim +2
We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation…
LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)
Junsu Kim, Jaeyeon Kim, Ernest K. Ryu
Low-rank adaptation (LoRA) has become a standard approach for fine-tuning large foundation models. However, our theoretical understanding of LoRA remains limited as prior analyses…
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
Jaeyeon Kim, Kulin Shah, Vasilis Kontonis +2
In recent years, masked diffusion models (MDMs) have emerged as a promising alternative approach for generative modeling over discrete domains. Compared to autoregressive models (A…
Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique
TaeHo Yoon, Jaeyeon Kim, Jaewook J. Suh +1
Recently, accelerated algorithms using the anchoring mechanism for minimax optimization and fixed-point problems have been proposed, and matching complexity lower bounds establish…
Mirror Duality in Convex Optimization
Jaeyeon Kim, Chanwoo Park, Asuman Ozdaglar +2
While first-order optimization methods are usually designed to efficiently reduce the function value , there has been recent interest in methods efficiently reducing the magn…
Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value
Jaeyeon Kim, Asuman Ozdaglar, Chanwoo Park +1
In convex optimization, first-order optimization methods efficiently minimizing function values have been a central subject study since Nesterov's seminal work of 1983. Recently, h…