AmbigDocs: Reasoning across Documents on Different Entities under the Same Name

Different entities with the same name can be difficult to distinguish. Handling confusing entity mentions is a crucial skill for language models (LMs). For example, given the question "Where was Michael Jordan educated?" and a set of documents discussing different people named Michael Jordan, can LMs distinguish entity mentions to generate a cohesive answer to the question? To test this ability, we introduce a new benchmark, AmbigDocs. By leveraging Wikipedia's disambiguation pages, we identify a set of documents, belonging to different entities who share an ambiguous name. From these documents, we generate questions containing an ambiguous name and their corresponding sets of answers. Our analysis reveals that current state-of-the-art models often yield ambiguous answers or incorrectly merge information belonging to different entities. We establish an ontology categorizing four types of incomplete answers and automatic evaluation metrics to identify such categories. We lay the foundation for future work on reasoning across multiple documents with ambiguous entities.

Stochastic approach for elliptic problems in perforated domains

A wide range of applications in science and engineering involve a PDE model in a domain with perforations, such as perforated metals or air filters. Solving such perforated domain problems suffers from computational challenges related to resolving the scale imposed by the geometries of perforations. We propose a neural network-based mesh-free approach for perforated domain problems. The method is robust and efficient in capturing various configuration scales, including the averaged macroscopic behavior of the solution that involves a multiscale nature induced by small perforations. The new approach incorporates the derivative-free loss method that uses a stochastic representation or the Feynman-Kac formulation. In particular, we implement the Neumann boundary condition for the derivative-free loss method to handle the interface between the domain and perforations. A suite of stringent numerical tests is provided to support the proposed method's efficacy in handling various perforation scales.

Crafting In-context Examples according to LMs' Parametric Knowledge

In-context learning has been applied to knowledge-rich tasks such as question answering. In such scenarios, in-context examples are used to trigger a behaviour in the language model: namely, it should surface information stored in its parametric knowledge. We study the construction of in-context example sets, with a focus on the parametric knowledge of the model regarding in-context examples. We identify 'known' examples, where models can correctly answer from its parametric knowledge, and 'unknown' ones. Our experiments show that prompting with 'unknown' examples decreases the performance, potentially as it encourages hallucination rather than searching its parametric knowledge. Constructing an in-context example set that presents both known and unknown information performs the best across diverse settings. We perform analysis on three multi-answer question answering datasets, which allows us to further study answer set ordering strategies based on the LM's knowledge about each answer. Together, our study sheds lights on how to best construct in-context example sets for knowledge-rich tasks.

Learning In-between Imagery Dynamics via Physical Latent Spaces

We present a framework designed to learn the underlying dynamics between two images observed at consecutive time steps. The complex nature of image data and the lack of temporal information pose significant challenges in capturing the unique evolving patterns. Our proposed method focuses on estimating the intermediary stages of image evolution, allowing for interpretability through latent dynamics while preserving spatial correlations with the image. By incorporating a latent variable that follows a physical model expressed in partial differential equations (PDEs), our approach ensures the interpretability of the learned model and provides insight into corresponding image dynamics. We demonstrate the robustness and effectiveness of our learning framework through a series of numerical tests using geoscientific imagery data.

An analysis of the derivative-free loss method for solving PDEs

This study analyzes the derivative-free loss method to solve a certain class of elliptic PDEs using neural networks. The derivative-free loss method uses the Feynman-Kac formulation, incorporating stochastic walkers and their corresponding average values. We investigate the effect of the time interval related to the Feynman-Kac formulation and the walker size in the context of computational efficiency, trainability, and sampling errors. Our analysis shows that the training loss bias is proportional to the time interval and the spatial gradient of the neural network while inversely proportional to the walker size. We also show that the time interval must be sufficiently long to train the network. These analytic results tell that we can choose the walker size as small as possible based on the optimal lower bound of the time interval. We also provide numerical tests supporting our analysis.

Adaptive Tracking of a Single-Rigid-Body Character in Various Environments

Since the introduction of DeepMimic [Peng et al. 2018], subsequent research has focused on expanding the repertoire of simulated motions across various scenarios. In this study, we propose an alternative approach for this goal, a deep reinforcement learning method based on the simulation of a single-rigid-body character. Using the centroidal dynamics model (CDM) to express the full-body character as a single rigid body (SRB) and training a policy to track a reference motion, we can obtain a policy that is capable of adapting to various unobserved environmental changes and controller transitions without requiring any additional learning. Due to the reduced dimension of state and action space, the learning process is sample-efficient. The final full-body motion is kinematically generated in a physically plausible way, based on the state of the simulated SRB character. The SRB simulation is formulated as a quadratic programming (QP) problem, and the policy outputs an action that allows the SRB character to follow the reference motion. We demonstrate that our policy, efficiently trained within 30 minutes on an ultraportable laptop, has the ability to cope with environments that have not been experienced during learning, such as running on uneven terrain or pushing a box, and transitions between learned policies, without any additional learning.

A Neural Network Approach for Homogenization of Multiscale Problems

We propose a neural network-based approach to the homogenization of multiscale problems. The proposed method uses a derivative-free formulation of a training loss, which incorporates Brownian walkers to find the macroscopic description of a multiscale PDE solution. Compared with other network-based approaches for multiscale problems, the proposed method is free from the design of hand-crafted neural network architecture and the cell problem to calculate the homogenization coefficient. The exploration neighborhood of the Brownian walkers affects the overall learning trajectory. We determine the bounds of micro- and macro-time steps that capture the local heterogeneous and global homogeneous solution behaviors, respectively, through a neural network. The bounds imply that the computational cost of the proposed method is independent of the microscale periodic structure for the standard periodic problems. We validate the efficiency and robustness of the proposed method through a suite of linear and nonlinear multiscale problems with periodic and random field coefficients.

Hierarchical Learning to Solve Partial Differential Equations Using Physics-Informed Neural Networks

The neural network-based approach to solving partial differential equations has attracted considerable attention due to its simplicity and flexibility in representing the solution of the partial differential equation. In training a neural network, the network learns global features corresponding to low-frequency components while high-frequency components are approximated at a much slower rate. For a class of equations in which the solution contains a wide range of scales, the network training process can suffer from slow convergence and low accuracy due to its inability to capture the high-frequency components. In this work, we propose a hierarchical approach to improve the convergence rate and accuracy of the neural network solution to partial differential equations. The proposed method comprises multi-training levels in which a newly introduced neural network is guided to learn the residual of the previous level approximation. By the nature of neural networks' training process, the high-level correction is inclined to capture the high-frequency components. We validate the efficiency and robustness of the proposed hierarchical approach through a suite of linear and nonlinear partial differential equations.

Understanding the Stability of Deep Control Policies for Biped Locomotion

Achieving stability and robustness is the primary goal of biped locomotion control. Recently, deep reinforce learning (DRL) has attracted great attention as a general methodology for constructing biped control policies and demonstrated significant improvements over the previous state-of-the-art. Although deep control policies have advantages over previous controller design approaches, many questions remain unanswered. Are deep control policies as robust as human walking? Does simulated walking use similar strategies as human walking to maintain balance? Does a particular gait pattern similarly affect human and simulated walking? What do deep policies learn to achieve improved gait stability? The goal of this study is to answer these questions by evaluating the push-recovery stability of deep policies compared to human subjects and a previous feedback controller. We also conducted experiments to evaluate the effectiveness of variants of DRL algorithms.