70 citations · 184 across the 16 of their papers we have counts for
18 papers
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…
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…
Semantic Loss Functions for Neuro-Symbolic Structured Prediction
Kareem Ahmed, Stefano Teso, Paolo Morettin +8
Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the in…
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…
Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners
Xiaojuan Tang, Zilong Zheng, Jiaqi Li +4
The emergent few-shot reasoning capabilities of Large Language Models (LLMs) have excited the natural language and machine learning community over recent years. Despite of numerous…
RulE: Knowledge Graph Reasoning with Rule Embedding
Xiaojuan Tang, Song-Chun Zhu, Yitao Liang +1
Knowledge graph (KG) reasoning is an important problem for knowledge graphs. In this paper, we propose a novel and principled framework called \textbf{RulE} (stands for {Rul}e {E}m…
SQA3D: Situated Question Answering in 3D Scenes
Xiaojian Ma, Silong Yong, Zilong Zheng +4
We propose a new task to benchmark scene understanding of embodied agents: Situated Question Answering in 3D Scenes (SQA3D). Given a scene context (e.g., 3D scan), SQA3D requires t…
Neural-Symbolic Recursive Machine for Systematic Generalization
Qing Li, Yixin Zhu, Yitao Liang +3
Current learning models often struggle with human-like systematic generalization, particularly in learning compositional rules from limited data and extrapolating them to novel com…
Towards an Interpretable Latent Space in Structured Models for Video Prediction
Rushil Gupta, Vishal Sharma, Yash Jain +3
We focus on the task of future frame prediction in video governed by underlying physical dynamics. We work with models which are object-centric, i.e., explicitly work with object r…
Handling Missing Data in Decision Trees: A Probabilistic Approach
Pasha Khosravi, Antonio Vergari, YooJung Choi +2
Decision trees are a popular family of models due to their attractive properties such as interpretability and ability to handle heterogeneous data. Concurrently, missing data is a…
On Effective Parallelization of Monte Carlo Tree Search
Anji Liu, Yitao Liang, Ji Liu +2
Despite its groundbreaking success in Go and computer games, Monte Carlo Tree Search (MCTS) is computationally expensive as it requires a substantial number of rollouts to construc…
Off-Policy Deep Reinforcement Learning with Analogous Disentangled Exploration
Anji Liu, Yitao Liang, Guy Van den Broeck
Off-policy reinforcement learning (RL) is concerned with learning a rewarding policy by executing another policy that gathers samples of experience. While the former policy (i.e. t…
SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning
Albert Zhao, Tong He, Yitao Liang +3
We describe a policy learning approach to map visual inputs to driving controls conditioned on turning command that leverages side tasks on semantics and object affordances via a l…
On Tractable Computation of Expected Predictions
Pasha Khosravi, YooJung Choi, Yitao Liang +2
Computing expected predictions of discriminative models is a fundamental task in machine learning that appears in many interesting applications such as fairness, handling missing v…
What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features
Pasha Khosravi, Yitao Liang, YooJung Choi +1
While discriminative classifiers often yield strong predictive performance, missing feature values at prediction time can still be a challenge. Classifiers may not behave as expect…
Learning Logistic Circuits
Yitao Liang, Guy Van den Broeck
This paper proposes a new classification model called logistic circuits. On MNIST and Fashion datasets, our learning algorithm outperforms neural networks that have an order of mag…
Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing
Zehong Hu, Yitao Liang, Yang Liu +1
Incentive mechanisms for crowdsourcing are designed to incentivize financially self-interested workers to generate and report high-quality labels. Existing mechanisms are often dev…
A Semantic Loss Function for Deep Learning with Symbolic Knowledge
Jingyi Xu, Zilu Zhang, Tal Friedman +2
This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output…