Skip to yearly menu bar Skip to main content


Workshop

Deep Generative Model in Machine Learning: Theory, Principle and Efficacy

Wei Huang ⋅ Mingyuan Bai ⋅ Andi Han ⋅ Taiji Suzuki ⋅ Qibin Zhao ⋅ Bamdev Mishra ⋅ Denny Wu ⋅ Ye Yuan ⋅ Maud Lemercier ⋅ Ernest Ryu
Project Page

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
6:00 PM
Opening Remarks
7:30 PM
Poster 1
8:20 PM
Nancy F. Chen
9:00 PM
Oral 1
9:30 PM
Lunch Break
11:00 PM
Sinho Chewi
11:50 PM
Jerry Li
12:30 AM
Poster 2
1:20 AM
Benedikt Hartl
2:00 AM
Oral 2
2:30 AM
Awards
2:40 AM
Closing Remarks
Towards Black-Box Membership Inference Attack for Diffusion Models
Jingwei Li ⋅ Jing Dong ⋅ Tianxing He ⋅ Jingzhao Zhang
DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories
Hongzhe Cheng ⋅ Tianyou Zheng ⋅ Tianyi Zhang ⋅ Matthew Johnson-Roberson ⋅ William Zhi
Improving Single Noise Level Denoising Samplers with Restricted Gaussian Oracles
Leello Dadi ⋅ Andrej Janchevski ⋅ Volkan Cevher
Remasking Discrete Diffusion Models with Inference-Time Scaling
Guanghan Wang ⋅ Yair Schiff ⋅ Subham Sahoo ⋅ Volodymyr Kuleshov
Fourier Head: Helping Large Language Models Learn Complex Probability Distributions
Nate Gillman ⋅ Daksh Aggarwal ⋅ Michael Freeman ⋅ Saurabh Singh ⋅ Chen Sun
Large Language Diffusion Models
Shen Nie ⋅ Fengqi Zhu ⋅ Zebin You ⋅ Xiaolu Zhang ⋅ Jingyang Ou ⋅ Jun Hu ⋅ JUN ZHOU ⋅ Yankai Lin ⋅ Ji-Rong Wen ⋅ Chongxuan Li
Weak-to-Strong Diffusion with Reflection
Lichen Bai ⋅ Masashi Sugiyama ⋅ Zeke Xie
Image-Alchemy : Advancing Subject Fidelity in Personalized Text-to-Image Generation
Kaustubh Sharma ⋅ Ojasva Nema ⋅ Amritanshu Tiwari ⋅ Cherish Puniani
A Theory for Conditional Generative Modeling on Multiple Data Sources
Rongzhen Wang ⋅ Yan Zhang ⋅ Chenyu Zheng ⋅ Chongxuan Li ⋅ Guoqiang Wu
Sample Quality-Likelihood trade-off in Diffusion Models
Yasin Esfandiari ⋅ Stefan Bauer ⋅ Sebastian Stich ⋅ Andrea Dittadi
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
Victor Weixin Liang ⋅ Lili Yu ⋅ Liang Luo ⋅ Srini Iyer ⋅ Ning Dong ⋅ Chunting Zhou ⋅ Gargi Ghosh ⋅ Mike Lewis ⋅ Scott Yih ⋅ Luke Zettlemoyer ⋅ Victoria Lin
Graph Discrete Diffusion: a Spectral Study
Olga Zaghen ⋅ Manuel Madeira ⋅ Laura Toni ⋅ Pascal Frossard
Your Image is Secretly the Last Frame of a Pseudo Video
Wenlong Chen ⋅ Wenlin Chen ⋅ Lapo Rastrelli ⋅ Yingzhen Li
Chimera: State Space Models Beyond Sequences
Aakash Sunil Lahoti ⋅ Tanya Marwah ⋅ Ratish Puduppully ⋅ Albert Gu
Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion
Nguyen ⋅ Chieh-Hsin Lai ⋅ Yuhta Takida ⋅ Naoki Murata ⋅ Toshimitsu Uesaka ⋅ Stefano Ermon ⋅ Yuki Mitsufuji
Probability-Flow ODE in Infinite-Dimensional Function Spaces
Kunwoo Na ⋅ Junghyun Lee ⋅ Se-Young Yun ⋅ Sungbin Lim
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
Grigory Bartosh ⋅ Dmitry P. Vetrov ⋅ Christian A. Naesseth
Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer
Junpeng Jiang ⋅ Gangyi Hong ⋅ Hengtong Hu ⋅ Lijun Zhou ⋅ Tianyi Yan ⋅ Yida Wang ⋅ Kun Zhan ⋅ Peng Jia ⋅ XianPeng Lang ⋅ Miao Zhang
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
Kaizhen Zhu ⋅ Mokai Pan ⋅ Yuexin Ma ⋅ Yanwei Fu ⋅ Jingyi Yu ⋅ Jingya Wang ⋅ Ye Shi
Attention Scheme Inspired Softmax Regression
Zhihang Li ⋅ Zhizhou Sha ⋅ Zhao Song ⋅ Mingda Wan
LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities
Florian Sestak ⋅ Artur Toshev ⋅ Andreas Fürst ⋅ Günter Klambauer ⋅ Andreas Mayr ⋅ Johannes Brandstetter
Solving Bayesian inverse problems with diffusion priors and off-policy RL
Luca Scimeca ⋅ Siddarth Venkatraman ⋅ Moksh Jain ⋅ Minsu Kim ⋅ Marcin Sendera ⋅ Mohsin Hasan ⋅ Alexandre Adam ⋅ Yashar Hezaveh ⋅ Laurence Perreault-Levasseur ⋅ Yoshua Bengio ⋅ Glen Berseth ⋅ Nikolay Malkin
Statistical Foundations of Conditional Diffusion Transformers
Jerry Yao-Chieh Hu ⋅ Weimin Wu ⋅ Yi-Chen Lee ⋅ Yu-Chao Huang ⋅ Minshuo Chen ⋅ Han Liu
Flows don't cross in high dimension
Teodora Reu ⋅ Sixtine Dromigny ⋅ Michael Bronstein ⋅ Francisco Vargas
Unpaired Point Cloud Completion using Unbalanced Optimal Transport map
Taekyung Lee ⋅ Jaemoo Choi ⋅ Jaewoong Choi ⋅ Myungjoo Kang
MCM: Multi-layer Concept Map for Efficient Concept Learning from Masked Images
Yuwei Sun ⋅ Lu Mi ⋅ Ippei Fujisawa ⋅ Ryota Kanai
AtropDiff: Data-Scarce Atropisomer Generation via Multi-Task Pretrained Classifier-Guided Diffusion
Letian Chen ⋅ Xi Wang ⋅ Gufeng Yu ⋅ Caihua Shan ⋅ Yang Yang
Causal Representation Learning and Inference via Mixture-Based Priors
Avinash Kori ⋅ Carles Balsells Rodas ⋅ Ben Glocker ⋅ Yingzhen Li ⋅ Francesco Locatello
Towards Training One-Step Diffusion Models Without Distillation
Mingtian Zhang ⋅ Jiajun He ⋅ Wenlin Chen ⋅ Zijing Ou ⋅ José Miguel Hernández Lobato ⋅ David Ha ⋅ David Barber
How Well Does Your Tabular Generator Learn the Structure of Tabular Data?
Xiangjian Jiang ⋅ Nikola Simidjievski ⋅ Mateja Jamnik
Demystifying Long Chain-of-Thought Reasoning in LLMs
Edward Yeo ⋅ Yuxuan Tong ⋅ Xinyao Niu ⋅ Graham Neubig ⋅ Xiang Yue
Path Planning for Masked Diffusion Models with Applications to Biological Sequence Generation
Zhangzhi Peng ⋅ Zachary Bezemek ⋅ Sawan Patel ⋅ Jarrid Rector-Brooks ⋅ Sherwood Yao ⋅ Alexander Tong ⋅ Pranam Chatterjee
Design Editing for Offline Model-based Optimization
Ye Yuan ⋅ Youyuan Zhang ⋅ Can Chen ⋅ Haolun Wu ⋅ Melody Li ⋅ Jianmo Li ⋅ Jim Clark ⋅ Xue Liu
Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
Maitreya Patel ⋅ Song Wen ⋅ Dimitris Metaxas ⋅ 'YZ' Yezhou Yang
Efficient Molecular Conformer Generation with SO(3) Averaged Flow-Matching and Reflow
Zhonglin Cao ⋅ Mario Geiger ⋅ Allan Costa ⋅ Danny Reidenbach ⋅ Karsten Kreis ⋅ Tomas Geffner ⋅ Franco Pellegrini ⋅ Guoqing Zhou ⋅ Emine Kucukbenli
CoDe: Blockwise Control for Denoising Diffusion Models
Anuj Singh ⋅ Sayak Mukherjee ⋅ Ahmad Beirami ⋅ Hadi J. Rad
UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation
Shuhan Guo ⋅ Yatao Bian ⋅ Ruibing Wang ⋅ Nan Yin ⋅ Quanming Yao
High-Order Matching for One-Step Shortcut Diffusion Models
Bo Chen ⋅ Chengyue Gong ⋅ Xiaoyu Li ⋅ Yingyu Liang ⋅ Zhizhou Sha ⋅ Zhenmei Shi ⋅ Zhao Song ⋅ Mingda Wan
On the Power of Context Enhanced Learning in LLMs
Xingyu Zhu ⋅ Abhishek Panigrahi ⋅ Sanjeev Arora
Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models
Francesco Maria Gabriele Insulla ⋅ Santiago Aranguri
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
Siddarth Venkatraman ⋅ Mohsin Hasan ⋅ Minsu Kim ⋅ Luca Scimeca ⋅ Marcin Sendera ⋅ Yoshua Bengio ⋅ Glen Berseth ⋅ Nikolay Malkin
Masked Generative Nested Transformers with Decode Time Scaling
Sahil Goyal ⋅ Debapriya Tula ⋅ Gagan Jain ⋅ Pradeep Shenoy ⋅ Prateek Jain ⋅ Sujoy Paul
Variational Rectified Flow Matching
Pengsheng Guo ⋅ Alex Schwing
On the Cone Effect in the Learning Dynamics
Zhanpeng Zhou ⋅ Yongyi Yang ⋅ Jie Ren ⋅ Mahito Sugiyama ⋅ Junchi Yan
Transcending Bayesian Inference: Transformers Extrapolate Rules Compositionally Under Model Misspecification
Szilvia Ujváry ⋅ Anna Mészáros ⋅ Wieland Brendel ⋅ Patrik Reizinger ⋅ Ferenc Huszar
Provable Maximum Entropy Manifold Exploration via Diffusion Models
Riccardo De Santi ⋅ Marin Vlastelica ⋅ Ya-Ping Hsieh ⋅ Zebang Shen ⋅ Niao He ⋅ Andreas Krause
Mamba State-Space Models Are Lyapunov-Stable Learners
John Halloran ⋅ Manbir Gulati ⋅ Paul Roysdon
Revisiting Noise Schedule Design for Diffusion Training
Tiankai Hang ⋅ Shuyang Gu ⋅ Xin Geng ⋅ Baining Guo
Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
Thomas Jiralerspong ⋅ Berton Earnshaw ⋅ Jason Hartford ⋅ Yoshua Bengio ⋅ Luca Scimeca
INFO-SEDD: Continuous Time Markov Chains as Scalable Information Metrics Estimators
Alberto Foresti ⋅ Giulio Franzese ⋅ Pietro Michiardi
Trustworthy Image Super-Resolution via Generative Pseudoinverse
Andreas Floros ⋅ Seyed-Mohsen Moosavi-Dezfooli ⋅ Pier Dragotti
Demystifying the Token Dynamics of Deep Selective State Space Models
Thieu Vo ⋅ Duy-Tung Pham ⋅ Xin Tong ⋅ Tan Nguyen
PAC Privacy Preserving Diffusion Models
Qipan Xu ⋅ Youlong Ding ⋅ Xinxi Zhang ⋅ Jie Gao ⋅ Hao Wang
BALANCED LATENT SPACE OF DIFFUSION MODELS FOR COUNTERFACTUAL GENERATION
Baohua Yan ⋅ Qingyuan Liu ⋅ Zhaobin Mo ⋅ Kangrui Ruan ⋅ Xuan Di
DIFFUSION MODELS LEARN LOW-DIMENSIONAL DISTRIBUTIONS VIA SUBSPACE CLUSTERING
Peng Wang ⋅ Huijie Zhang ⋅ Zekai Zhang ⋅ Siyi Chen ⋅ Yi Ma ⋅ Qing Qu
Measuring Semantic Information Production in Generative Diffusion Models
Florian Handke ⋅ Felix Koulischer ⋅ Gabriel Raya ⋅ Luca Ambrogioni
Identifying metric structures of deep latent variable models
Stas Syrota ⋅ Yevgen Zainchkovskyy ⋅ Johnny Xi ⋅ Benjamin Bloem-Reddy ⋅ Søren Hauberg
GRAPH GENERATIVE PRE-TRAINED TRANSFORMER
Xiaohui Chen ⋅ Yinkai Wang ⋅ Jiaxing He ⋅ Yuanqi Du ⋅ Soha Hassoun ⋅ Xiaolin Xu ⋅ Liping Liu
Flow Along the K-Amplitude for Generative Modeling
weitao du ⋅ Shuning Chang ⋅ Jiasheng Tang ⋅ Yu Rong ⋅ Fan Wang ⋅ Shengchao Liu
On the Query Complexity of Verifier-Assisted Language Generation
Edoardo Botta ⋅ Yuchen Li ⋅ Aashay Mehta ⋅ Jordan Ash ⋅ Cyril Zhang ⋅ Andrej Risteski
Leveraging shared feature representation in cross-domain alignment of decision thresholds for electronic health records data.
Elena Gal ⋅ Anshul Thakur ⋅ Soheila Molaei ⋅ Andrew Soltan ⋅ David Clifton
Graph transformers express monadic second-order logic
Tamara Drucks ⋅ Mahito Sugiyama
FullDiffusion: Diffusion Models Without Time Truncation
Shohei Taniguchi ⋅ Masahiro Suzuki ⋅ Yusuke Iwasawa ⋅ Yutaka Matsuo
An Improved Sample Complexity for Rank-1 Matrix Sensing
Zhihang Li ⋅ Zhizhou Sha ⋅ Zhao Song ⋅ Mingda Wan
Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts
Anh Bui ⋅ Khanh Doan ⋅ Trung Le ⋅ Paul Montague ⋅ Tamas Abraham ⋅ Dinh Phung
Unifying Causal and Object-centric Representation Learning allows Causal Composition
Avinash Kori ⋅ Ben Glocker ⋅ David Ha ⋅ Francesco Locatello
LapLoss: Laplacian Pyramid-based Multiscale Loss for Image Translation
Krish Didwania ⋅ Ishaan Gakhar ⋅ Prakhar Arya ⋅ Sanskriti Labroo
Frame Generation in Hilbert Space: Generative Interpolation of Measurement Data for Quantum Parameter Adaptation
Chen-Yu Liu ⋅ Kuan-Cheng Chen ⋅ Samuel Chen ⋅ Wei-Hao Huang ⋅ Wei-Jia Huang ⋅ Yen Jui Chang
Hidden in the Noise: Two-Stage Robust Watermarking for Images
Kasra Arabi ⋅ Benjamin Feuer ⋅ R. Teal Witter ⋅ Chinmay Hegde ⋅ Niv Cohen
How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
Alessandro Favero ⋅ Antonio Sclocchi ⋅ Francesco Cagnetta ⋅ Pascal Frossard ⋅ Matthieu Wyart
Gumbel-Softmax Score and Flow Matching for Discrete Biological Sequence Generation
Sophia Tang ⋅ Yinuo Zhang ⋅ Alexander Tong ⋅ Pranam Chatterjee
Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
Jerry Yao-Chieh Hu ⋅ Maojiang Su ⋅ En-Jui Kuo ⋅ Zhao Song ⋅ Han Liu
Interleaved Gibbs Diffusion for Constrained Generation
Gautham Anil ⋅ Sachin Yadav ⋅ Dheeraj Nagaraj ⋅ Karthikeyan Shanmugam ⋅ Prateek Jain
Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity
Victor Weixin Liang ⋅ Junhong Shen ⋅ Genghan Zhang ⋅ Ning Dong ⋅ Luke Zettlemoyer ⋅ Lili Yu
Nonparametric Distributional Black-box Optimization via Diffusion Process
YUEMING LYU ⋅ Atsushi Nitanda ⋅ Ivor Tsang
Training Consistency Models with Variational Noise Coupling
Gianluigi Silvestri ⋅ Luca Ambrogioni ⋅ Chieh-Hsin Lai ⋅ Yuhta Takida ⋅ Yuki Mitsufuji
DDPM Score Matching Is Asymptotically Efficient
Sinho Chewi ⋅ Alkis Kalavasis ⋅ Anay Mehrotra ⋅ Omar Montasser
PHYSICS-INFORMED GENERATIVE APPROACHES FOR WIRELESS CHANNEL MODELING
Satyavrat Wagle ⋅ Akshay Malhotra ⋅ Shahab Hamidi-Rad ⋅ Aditya Sant ⋅ David Love ⋅ Christopher Brinton
Distance-Based Tree-Sliced Wasserstein Distance
Viet-Hoang Tran ⋅ Minh-Khoi Nguyen-Nhat ⋅ Trang Pham ⋅ Thanh Chu ⋅ Tam Le ⋅ Tan Nguyen
The Diffusion Duality
Subham Sahoo ⋅ Justin Deschenaux ⋅ Aaron Gokaslan ⋅ Guanghan Wang ⋅ Justin Chiu ⋅ Volodymyr Kuleshov
BridgeVoC: Insights into Using Schrödinger Bridge for Neural Vocoders
Tong Lei ⋅ Andong Li ⋅ Rilin Chen ⋅ Dong Yu ⋅ Meng Yu ⋅ Jing Lu ⋅ Chengshi Zheng
Unifying Autoregressive And Diffusion-Based Sequence Generation
Nima Fathi ⋅ Torsten Scholak ⋅ Pierre-André Noël
Neural Genetic Search in Discrete Spaces
Hyeonah Kim ⋅ Sanghyeok Choi ⋅ Jiwoo Son ⋅ Jinkyoo Park ⋅ Changhyun Kwon
Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering
Mark Beliaev ⋅ Wei Yang ⋅ Madhura Raju ⋅ Jiachen Sun ⋅ Xinghai Hu
Flow Matching Neural Processes
Hussen Abu Hamad ⋅ Dan Rosenbaum
Cellular-Guided Graph Generative Model
Yiming Huang ⋅ Tolga Birdal
The Space Between: On Folding, Symmetries and Sampling
Michal Lewandowski ⋅ Bernhard Heinzl ⋅ Raphael Pisoni ⋅ Bernhard A. Moser
Multi-view Geometry-Aware Diffusion Transformer for Indoor Novel View Synthesis
Xueyang Kang ⋅ Zhengkang Xiang ⋅ Zezheng Zhang ⋅ Kourosh Khoshelham
Edge-preserving noise for diffusion models
Jente Vandersanden ⋅ Sascha Holl ⋅ Xingchang Huang ⋅ Gurprit Singh
RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignment
Chao Wang ⋅ Giulio Franzese ⋅ alessandro finamore ⋅ Pietro Michiardi
Score as Action: Fine-Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
Hanyang Zhao ⋅ Haoxian Chen ⋅ Ji Zhang ⋅ David Yao ⋅ Wenpin Tang
Identifiable Object Representations under Spatial Ambiguities
Avinash Kori ⋅ Francesca Toni ⋅ Ben Glocker
Symmetry-Preserving Diffusion Models via Target Symmetrization
Vinh Tong ⋅ Yun Ye ⋅ Trung-Dung Hoang ⋅ Anji Liu ⋅ Guy Van den Broeck ⋅ Mathias Niepert
Stable Consistency Tuning: Understanding and Improving Consistency Models
Fu-Yun Wang ⋅ Zhengyang Geng ⋅ Hongsheng Li
Diffusion-Based Planning for Autonomous Driving with Flexible Guidance
Yinan Zheng ⋅ Ruiming Liang ⋅ Kexin ZHENG ⋅ Jinliang Zheng ⋅ Liyuan Mao ⋅ Jianxiong Li ⋅ Weihao Gu ⋅ Rui Ai ⋅ Shengbo Li ⋅ Xianyuan Zhan ⋅ Jingjing Liu
Towards Variational Flow Matching on General Geometries
Olga Zaghen ⋅ Floor Eijkelboom ⋅ Alison Pouplin ⋅ Erik Bekkers
Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency
Jerry Yao-Chieh Hu ⋅ Wei-Po Wang ⋅ Ammar Gilani ⋅ Chenyang Li ⋅ Zhao Song ⋅ Han Liu
Diffusion Models Do Not Implicitly Learn Conditional Independence
Sachit Gaudi ⋅ Gautam Sreekumar ⋅ Vishnu Boddeti
Better Sampling as a Path to Stronger VAEs
Aziz Shameem ⋅ Amit Sethi
Spherical Tree-Sliced Wasserstein Distance
Viet-Hoang Tran ⋅ Thanh Chu ⋅ Minh-Khoi Nguyen-Nhat ⋅ Trang Pham ⋅ Tam Le ⋅ Tan Nguyen
DIME: Deterministic Information Maximizing Autoencoder
Alokendu Mazumder ⋅ Chirag Garg ⋅ Tirthajit Baruah ⋅ Punit Rathore
A Reversible Solver for Diffusion SDEs
Zander W. Blasingame ⋅ Chen Liu