collaborators

21 papers

cs.LG2026

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…

cs.LG2026

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

Alexi Gladstone, Heng Ji, Yilun Du

The paper proposes Explorative Modeling, a new training paradigm that selects the best among multiple candidate generations to improve generative models, adding a third pretraining…

cs.LG2026

From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models

Seunggeun Kim, Jaeyeon Kim, Taekyun Lee +4

The paper investigates how to give language models a native ability to reason and generate text in any order, introducing insertion‑based and latent‑space masked diffusion methods…

cs.LG2026

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…

cs.LG2026

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…

cs.CL2026

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…