activity
20242026
collaborators

5 papers

cs.LG2026

Lookahead Path Likelihood Optimization for Diffusion LLMs

Xuejie Liu, Yap Vit Chun, Yitao Liang +1

Diffusion Large Language Models (dLLMs) support arbitrary-order generation, yet their inference performance critically depends on the unmasking order. Existing strategies rely on h…

cs.CL2025

Tractable Transformers for Flexible Conditional Generation

Anji Liu, Xuejie Liu, Dayuan Zhao +3

Non-autoregressive (NAR) generative models are valuable because they can handle diverse conditional generation tasks in a more principled way than their autoregressive (AR) counter…

cs.CV2025

Plug-and-Play Context Feature Reuse for Efficient Masked Generation

Xuejie Liu, Anji Liu, Guy Van den Broeck +1

Masked generative models (MGMs) have emerged as a powerful framework for image synthesis, combining parallel decoding with strong bidirectional context modeling. However, generatin…

cs.LG2025

A Tractable Inference Perspective of Offline RL

Xuejie Liu, Anji Liu, Guy Van den Broeck +1

A popular paradigm for offline Reinforcement Learning (RL) tasks is to first fit the offline trajectories to a sequence model, and then prompt the model for actions that lead to hi…

cs.LG2024

OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents

Zihao Wang, Shaofei Cai, Zhancun Mu +7

This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textua…