# MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Our MetaMath-7B model achieves 66. 4% on GSM8K and 19. 4% on MATH, exceeding the state-of-the-art models of the same size by 11. 5% and 8. 7%.

Ranked #15 on Math Word Problem Solving on MATH (using extra training data)

25

# Learning Disentangled Avatars with Hybrid 3D Representations

Towards this end, both explicit and implicit 3D representations are heavily studied for a holistic modeling and capture of the whole human (e. g., body, clothing, face and hair), but neither representation is an optimal choice in terms of representation efficacy since different parts of the human avatar have different modeling desiderata.

# Controlling Text-to-Image Diffusion by Orthogonal Finetuning

To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks.

# Nonparametric Iterative Machine Teaching

In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast convergence to a target model.

5

# MeshDiffusion: Score-based Generative 3D Mesh Modeling

We consider the task of generating realistic 3D shapes, which is useful for a variety of applications such as automatic scene generation and physical simulation.

628

# Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap

We then use hyperspherical uniformity (which characterizes the degree of uniformity on the unit hypersphere) as a unified framework to quantify these two objectives.

# One-shot Implicit Animatable Avatars with Model-based Priors

Most of these methods fail to achieve realistic reconstruction when only a single image is available.

# Human-in-the-Loop Mixup

We focus on the synthetic data used in mixup: a powerful regularizer shown to improve model robustness, generalization, and calibration.

2

# Iterative Teaching by Data Hallucination

We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i. e., a pool of finite samples), which greatly limits the teacher's capability.

4

# Continual Learning by Modeling Intra-Class Variation

It has been observed that neural networks perform poorly when the data or tasks are presented sequentially.

11

# Structural Causal 3D Reconstruction

This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images.

# Data-Efficient Learning via Minimizing Hyperspherical Energy

no code implementations30 Jun 2022, ,

Finally, we demonstrate the empirical performance of MHEAL in a wide range of applications on data-efficient learning, including deep clustering, distribution matching, version space sampling and deep active learning.

# Locality Sensitive Teaching

However, as one of the most influential and practical MT paradigms, iterative machine teaching (IMT) is prohibited on IoT devices due to its inefficient and unscalable algorithms.

# Towards Principled Disentanglement for Domain Generalization

To tackle this challenge, we first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG).

48

# Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence

Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses.

33

# Provable Lifelong Learning of Representations

We prove that for any desired accuracy on all tasks, the dimension of the representation remains close to that of the underlying representation.

# Iterative Teaching by Label Synthesis

In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner.

# Self-Supervised 3D Face Reconstruction via Conditional Estimation

We present a conditional estimation (CEST) framework to learn 3D facial parameters from 2D single-view images by self-supervised training from videos.

# Pre-training Molecular Graph Representation with 3D Geometry

However, the lack of 3D information in real-world scenarios has significantly impeded the learning of geometric graph representation.

129

# SphereFace Revived: Unifying Hyperspherical Face Recognition

As one of the earliest works in hyperspherical face recognition, SphereFace explicitly proposed to learn face embeddings with large inter-class angular margin.

1

# SphereFace2: Binary Classification is All You Need for Deep Face Recognition

In this paper, we start by identifying the discrepancy between training and evaluation in the existing multi-class classification framework and then discuss the potential limitations caused by the "competitive" nature of softmax normalization.

# Learning with Hyperspherical Uniformity

Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation.

7

# Iterative Graph Self-Distillation

Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs.

# Orthogonal Over-Parameterized Training

The inductive bias of a neural network is largely determined by the architecture and the training algorithm.

13

# Angular Visual Hardness

We also find that AVH has a statistically significant correlation with human visual hardness.

# Neural Similarity Learning

By generalizing inner product with a bilinear matrix, we propose the neural similarity which serves as a learnable parametric similarity measure for CNNs.

33

# Regularizing Neural Networks via Minimizing Hyperspherical Energy

Inspired by the Thomson problem in physics where the distribution of multiple propelling electrons on a unit sphere can be modeled via minimizing some potential energy, hyperspherical energy minimization has demonstrated its potential in regularizing neural networks and improving their generalization power.

22

# Meta Architecture Search

Neural Architecture Search (NAS) has been quite successful in constructing state-of-the-art models on a variety of tasks.

21

# Coupled Variational Bayes via Optimization Embedding

This flexible function class couples the variational distribution with the original parameters in the graphical models, allowing end-to-end learning of the graphical models by back-propagation through the variational distribution.

10

# Simultaneous Edge Alignment and Learning

Edge detection is among the most fundamental vision problems for its role in perceptual grouping and its wide applications.

124

# Disjoint Mapping Network for Cross-modal Matching of Voices and Faces

We propose a novel framework, called Disjoint Mapping Network (DIMNet), for cross-modal biometric matching, in particular of voices and faces.

# Learning towards Minimum Hyperspherical Energy

In light of this intuition, we reduce the redundancy regularization problem to generic energy minimization, and propose a minimum hyperspherical energy (MHE) objective as generic regularization for neural networks.

147

# Decoupled Networks

Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations.

2

# Iterative Learning with Open-set Noisy Labels

We refer to this more complex scenario as the \textbf{open-set noisy label} problem and show that it is nontrivial in order to make accurate predictions.

10

# Additive Margin Softmax for Face Verification

9 code implementations17 Jan 2018, , ,

In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works.

477

# Deep Hyperspherical Learning

In light of such challenges, we propose hyperspherical convolution (SphereConv), a novel learning framework that gives angular representations on hyperspheres.

# Towards Black-box Iterative Machine Teaching

We propose an active teacher model that can actively query the learner (i. e., make the learner take exams) for estimating the learner's status and provably guide the learner to achieve faster convergence.

# Iterative Machine Teaching

Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner.

8

# SphereFace: Deep Hypersphere Embedding for Face Recognition

This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space.

1,559

# Large-Margin Softmax Loss for Convolutional Neural Networks

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs).

343

# Robust Elastic Net Regression

no code implementations15 Nov 2015, ,

We propose a robust elastic net (REN) model for high-dimensional sparse regression and give its performance guarantees (both the statistical error bound and the optimization bound).

# Jointly Learning Non-negative Projection and Dictionary with Discriminative Graph Constraints for Classification

Sparse coding with dictionary learning (DL) has shown excellent classification performance.

# Efficient Face Alignment via Locality-constrained Representation for Robust Recognition

no code implementations25 Jul 2015, , ,

Practical face recognition has been studied in the past decades, but still remains an open challenge.

# Structured Occlusion Coding for Robust Face Recognition

We propose the structured occlusion coding (SOC) to address occlusion problems.

# KCRC-LCD: Discriminative Kernel Collaborative Representation with Locality Constrained Dictionary for Visual Categorization

The LCD similarity measure can be kernelized under KCRC, which theoretically links CRC and LCD under the kernel method.

Cannot find the paper you are looking for? You can Submit a new open access paper.