Marton Havasi
11 papers · 2018–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (18)
📈
Trend Setter
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Deep Learning
(8)
Models
(7)
Artificial Intelligence
(5)
Machine Learning
(5)
Core AI
(4)
Optimization & Theory
(4)
Computer Vision
(3)
Generation · Computer Vision
(2)
Techniques
(2)
Natural Language Processing
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Core Methods
(1)
Generation · Natural Language Processing
(1)
Processing
(1)
Keywords
variational autoencoder
(2)
flow matching
(2)
concept bottleneck model
(2)
variational inference
(2)
image generation
(2)
generative modeling
(2)
bits-back coding
(2)
latent diffusion model
(2)
kl divergence
(1)
markov chain
(1)
hyperparameter optimization
(1)
generative model
(1)
latent representation
(1)
posterior distribution
(1)
model ensembling
(1)
image compression
(1)
discrete diffusion
(1)
jump process
(1)
model ensemble
(1)
interpretable machine learning
(1)
Papers
Boosting Latent Diffusion with Perceptual Objectives
ICLR 2025
Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles
ICLR 2025
Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective
ICLR 2025
Generator Matching: Generative modeling with arbitrary Markov processes
ICLR 2025
On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
NeurIPS 2024
Addressing Leakage in Concept Bottleneck Models
NeurIPS 2022
Learning Optimal Summaries of Clinical Time-series with Concept Bottleneck Models
MLHC 2022
Training independent subnetworks for robust prediction
ICLR 2021
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding
NeurIPS 2020
Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
ICLR 2019
Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo
NeurIPS 2018