2 citations · 3 across the 21 of their papers we have counts for
26 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…
Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Models
Ji Zhang, Zixin Liu, Yiran Ding +3
An interaction has two parts: someone decides to act, and then chooses whom to act on. Temporal link prediction has concentrated on the second, and we show that it is blind to the…
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…
Beckmann Transport Models: From Autonomous Flows to One-Step Maps
Lee Cheuk-Kit, Florentin Coeurdoux, Yuyuan Chen +5
We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so long as the t…
Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning
Hansen Jin Lillemark, Alex Rojas, Zachary Novack +5
Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedu…
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…
Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
Alexi Gladstone, Heng Ji, Yilun Du
The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages. Generative modeling, however, has rem…
Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
Michal Balcerak, Suprosanna Shit, Chinmay Prabhakar +4
Generative modeling of discrete data, such as graphs, underpins many scientific and industrial applications, including molecular discovery and materials design. In these domains, p…
World Action Models are Zero-shot Policies
Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng +33
State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce Drea…
Generative Modeling via Drifting
Mingyang Deng, He Li, Tianhong Li +2
Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iter…
A Very Big Video Reasoning Suite
Maijunxian Wang, Ruisi Wang, Juyi Lin +53
Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally c…
Unsupervised Decomposition and Recombination with Discriminator-Driven Diffusion Models
Archer Wang, Emile Anand, Yilun Du +1
Decomposing complex data into factorized representations can reveal reusable components and enable synthesizing new samples via component recombination. We investigate this in the…
MoCo: A One-Stop Shop for Model Collaboration Research
Shangbin Feng, Yuyang Bai, Ziyuan Yang +17
Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multiple LMs collaborate, compose, an…
Generalizable Reasoning through Compositional Energy Minimization
Alexandru Oarga, Yilun Du
Generalization is a key challenge in machine learning, specifically in reasoning tasks, where models are expected to solve problems more complex than those encountered during train…
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Aayush Karan, Yilun Du
Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning…
Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
Runqian Wang, Yilun Du
We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics…
Geometry-aware Policy Imitation
Yiming Li, Nael Darwiche, Amirreza Razmjoo +4
We propose a Geometry-aware Policy Imitation (GPI) approach that rethinks imitation learning by treating demonstrations as geometric curves rather than collections of state-action…
Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
Evgenii Opryshko, Junwei Quan, Claas Voelcker +2
Offline goal-conditioned reinforcement learning (GCRL) often struggles with long-horizon tasks, where errors in value estimation accumulate and produce unreliable policies. It is t…
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…
Energy-Based Transformers are Scalable Learners and Thinkers
Alexi Gladstone, Ganesh Nanduru, Md Mofijul Islam +7
Inference-time computation techniques, analogous to human System 2 Thinking, have recently become popular for improving model performances. However, most existing approaches suffer…
Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models
Louis Béthune, David Vigouroux, Yilun Du +3
What is the shortest path between two data points lying in a high-dimensional space? While the answer is trivial in Euclidean geometry, it becomes significantly more complex when t…
Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers
Shalev Lifshitz, Sheila A. McIlraith, Yilun Du
By utilizing more computational resources at test-time, large language models (LLMs) can improve without additional training. One common strategy uses verifiers to evaluate candida…
History-Guided Video Diffusion
Kiwhan Song, Boyuan Chen, Max Simchowitz +3
Classifier-free guidance (CFG) is a key technique for improving conditional generation in diffusion models, enabling more accurate control while enhancing sample quality. It is nat…