51 citations · 108 across the 37 of their papers we have counts for
40 papers
Latent State Utilization in Probabilistic Circuits
Zilei Shao, Anji Liu
Probabilistic circuits (PCs) are generative models that support efficient probabilistic inference. Adding latent states to a PC increases its representational capacity, but yields…
Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
Silong Yong, Anji Liu, Cunxi Dai +5
A common way for trajectory planning is to leverage generative models trained on large collections of expert trajectories. At inference time, the model generates executable traject…
Breaking the Factorization Barrier in Diffusion Language Models
Ian Li, Zilei Shao, Benjie Wang +3
Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the ``factorization barrier'': the assumption that simultaneously pr…
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…
Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning
Kaichen He, Zihao Wang, Muyao Li +2
The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models. However, existing agents are typically confined to static, predefined actio…
Learning Tractable Distributions Of Language Model Continuations
Gwen Yidou-Weng, Ian Li, Anji Liu +4
Controlled generation imposes sequence-level constraints (syntax, style, safety) that depend on future tokens, making exact conditioning of an autoregressive LM intractable. Tracta…
OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
Zihao Wang, Muyao Li, Kaichen He +4
The choice of action spaces is a critical yet unresolved challenge in developing capable, end-to-end trainable agents. This paper first presents a large-scale, systematic compariso…
Zero-Variance Gradients for Variational Autoencoders
Zilei Shao, Anji Liu, Guy Van den Broeck
Training deep generative models like Variational Autoencoders (VAEs) requires propagating gradients through stochastic latent variables, which introduces estimation variance that c…
Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
Shaofei Cai, Zhancun Mu, Haiwen Xia +3
While Reinforcement Learning (RL) has achieved remarkable success in language modeling, its triumph hasn't yet fully translated to visuomotor agents. A primary challenge in RL mode…
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…
Rethinking Probabilistic Circuit Parameter Learning
Anji Liu, Zilei Shao, Guy Van den Broeck
Probabilistic Circuits (PCs) offer a computationally scalable framework for generative modeling, supporting exact and efficient inference of a wide range of probabilistic queries.…
Open-World Skill Discovery from Unsegmented Demonstrations
Jingwen Deng, Zihao Wang, Shaofei Cai +2
Learning skills in open-world environments is essential for developing agents capable of handling a variety of tasks by combining basic skills. Online demonstration videos are typi…
ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment
Shaofei Cai, Zhancun Mu, Anji Liu +1
We aim to develop a goal specification method that is semantically clear, spatially sensitive, domain-agnostic, and intuitive for human users to guide agent interactions in 3D envi…
Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion
Vinh Tong, Hoang Trung-Dung, Anji Liu +2
In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model. Two main strategies have emerged for learning invarian…
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…
GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents
Shaofei Cai, Bowei Zhang, Zihao Wang +4
Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets (no language i…
MineStudio: A Streamlined Package for Minecraft AI Agent Development
Shaofei Cai, Zhancun Mu, Kaichen He +4
Minecraft's complexity and diversity as an open world make it a perfect environment to test if agents can learn, adapt, and tackle a variety of unscripted tasks. However, the devel…
ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
Shaofei Cai, Zihao Wang, Kewei Lian +4
Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is…
Discrete Copula Diffusion
Anji Liu, Oliver Broadrick, Mathias Niepert +1
Discrete diffusion models have recently shown significant progress in modeling complex data, such as natural languages and DNA sequences. However, unlike diffusion models for conti…
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…
Scaling Tractable Probabilistic Circuits: A Systems Perspective
Anji Liu, Kareem Ahmed, Guy Van den Broeck
Probabilistic Circuits (PCs) are a general framework for tractable deep generative models, which support exact and efficient probabilistic inference on their learned distributions.…
Learning to Discretize Denoising Diffusion ODEs
Vinh Tong, Hoang Trung-Dung, Anji Liu +2
Diffusion Probabilistic Models (DPMs) are generative models showing competitive performance in various domains, including image synthesis and 3D point cloud generation. Sampling fr…
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
Zihao Wang, Anji Liu, Haowei Lin +3
We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-…
Image Inpainting via Tractable Steering of Diffusion Models
Anji Liu, Mathias Niepert, Guy Van den Broeck
Diffusion models are the current state of the art for generating photorealistic images. Controlling the sampling process for constrained image generation tasks such as inpainting,…