Search Results for author:
Found 48 papers, 29 papers with code
Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives
As large language models (LLMs) continue to scale, their enhanced performance often proves insufficient for solving domain-specific tasks.
Informed Correctors for Discrete Diffusion Models
However, for absorbing state diffusion, an important class of discrete diffusion models, the standard forward-backward corrector can be ineffective in fixing such errors, resulting in subpar sample quality.
ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models
Inspired from the huge success of large language models (LLMs) and following GPT (generative pre-trained transformer), we bring causal (i. e., unidirectional) generation into VDMs, and use past frames as prompt to generate future frames.
Simplified and Generalized Masked Diffusion for Discrete Data
In this work, we aim to provide a simple and general framework that unlocks the full potential of masked diffusion models.
Non-confusing Generation of Customized Concepts in Diffusion Models
We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs).
Cross-Lingual Transfer for Natural Language Inference via Multilingual Prompt Translator
To efficiently transfer soft prompt, we propose a novel framework, Multilingual Prompt Translator (MPT), where a multilingual prompt translator is introduced to properly process crucial knowledge embedded in prompt by changing language knowledge while retaining task knowledge.
Preparing Lessons for Progressive Training on Language Models
The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes.
How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering
A typical approach to KBQA is semantic parsing, which translates a question into an executable logical form in a formal language.
Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions
During reasoning, for leaf nodes, LLMs choose a more confident answer from Closed-book QA that employs parametric knowledge and Open-book QA that employs retrieved external knowledge, thus eliminating the negative retrieval problem.
Human Motion Generation: A Survey
In this survey, we present a comprehensive literature review of human motion generation, which, to the best of our knowledge, is the first of its kind in this field.
Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering
To facilitate reasoning, we propose a novel two-stage XQA framework, Reasoning over Hierarchical Question Decomposition Tree (RoHT).
Hybrid and Collaborative Passage Reranking
In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme.
Sequence Modeling with Multiresolution Convolutional Memory
Popular approaches in the space tradeoff between the memory burden of brute-force enumeration and comparison, as in transformers, the computational burden of complicated sequential dependencies, as in recurrent neural networks, or the parameter burden of convolutional networks with many or large filters.
Learning Absorption Rates in Glucose-Insulin Dynamics from Meal Covariates
In this paper, we propose to learn the effects of macronutrition content from glucose-insulin data and meal covariates.
BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization
In this work, we are dedicated to leveraging the BERT pre-training success and modeling the domain-specific statistics to fertilize the sign language recognition~(SLR) model.
G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks
Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e. g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora.
Neural Eigenfunctions Are Structured Representation Learners
Unlike prior spectral methods such as Laplacian Eigenmap that operate in a nonparametric manner, Neural Eigenmap leverages NeuralEF to parametrically model eigenfunctions using a neural network.
GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation
Subject to the huge semantic gap between natural and formal languages, neural semantic parsing is typically bottlenecked by its complexity of dealing with both input semantics and output syntax.
HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval
It also achieves about +4. 9 AR on COCO and +3. 8 AR on Flickr30K than LightingDot and achieves comparable performance with the state-of-the-art (SOTA) fusion-based model METER.
NeuralEF: Deconstructing Kernels by Deep Neural Networks
Learning the principal eigenfunctions of an integral operator defined by a kernel and a data distribution is at the core of many machine learning problems.
Gradient Estimation with Discrete Stein Operators
Gradient estimation -- approximating the gradient of an expectation with respect to the parameters of a distribution -- is central to the solution of many machine learning problems.
Schema-Free Dependency Parsing via Sequence Generation
To remedy these drawbacks, we propose to achieve universal and schema-free Dependency Parsing (DP) via Sequence Generation (SG) DPSG by utilizing only the pre-trained language model (PLM) without any auxiliary structures or parsing algorithms.
Double Control Variates for Gradient Estimation in Discrete Latent Variable Models
We introduce a variance reduction technique for score function estimators that makes use of double control variates.
Program Transfer for Answering Complex Questions over Knowledge Bases
In this paper, we propose the approach of program transfer, which aims to leverage the valuable program annotations on the rich-resourced KBs as external supervision signals to aid program induction for the low-resourced KBs that lack program annotations.
TWAG: A Topic-Guided Wikipedia Abstract Generator
Wikipedia abstract generation aims to distill a Wikipedia abstract from web sources and has met significant success by adopting multi-document summarization techniques.
Sampling with Mirrored Stein Operators
We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries.
Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
We introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability.
TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph
Multi-hop Question Answering (QA) is a challenging task because it requires precise reasoning with entity relations at every step towards the answer.
Neural Networks as Inter-Domain Inducing Points
Equivalences between infinite neural networks and Gaussian processes have been established for explaining the functional prior and training dynamics of deep learning models.
Nonparametric Score Estimators
Estimating the score, i. e., the gradient of log density function, from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models that involve flexible yet intractable densities.
Unbiased Scene Graph Generation from Biased Training
Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e. g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach".
Ranked #3 on
Scene Graph Generation
on Visual Genome
Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model
Specifically, as for the knowledge embedding model, we utilize TransE to implicitly complete two KGs towards consistency and learn relational constraints between entities.
Sparse Orthogonal Variational Inference for Gaussian Processes
We introduce a new interpretation of sparse variational approximations for Gaussian processes using inducing points, which can lead to more scalable algorithms than previous methods.
Scalable Training of Inference Networks for Gaussian-Process Models
Inference in Gaussian process (GP) models is computationally challenging for large data, and often difficult to approximate with a small number of inducing points.
Sliced Score Matching: A Scalable Approach to Density and Score Estimation
However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions.
Functional Variational Bayesian Neural Networks
We introduce functional variational Bayesian neural networks (fBNNs), which maximize an Evidence Lower BOund (ELBO) defined directly on stochastic processes, i. e. distributions over functions.
Explainable and Explicit Visual Reasoning over Scene Graphs
We aim to dismantle the prevalent black-box neural architectures used in complex visual reasoning tasks, into the proposed eXplainable and eXplicit Neural Modules (XNMs), which advance beyond existing neural module networks towards using scene graphs --- objects as nodes and the pairwise relationships as edges --- for explainable and explicit reasoning with structured knowledge.
Ranked #10 on
Visual Question Answering (VQA)
on CLEVR
DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
We propose DeepChannel, a robust, data-efficient, and interpretable neural model for extractive document summarization.
Learning to Embed Sentences Using Attentive Recursive Trees
Sentence embedding is an effective feature representation for most deep learning-based NLP tasks.
Semi-crowdsourced Clustering with Deep Generative Models
We propose a new approach that includes a deep generative model (DGM) to characterize low-level features of the data, and a statistical relational model for noisy pairwise annotations on its subset.
A Spectral Approach to Gradient Estimation for Implicit Distributions
Recently there have been increasing interests in learning and inference with implicit distributions (i. e., distributions without tractable densities).
Message Passing Stein Variational Gradient Descent
Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational inference and Markov Chain Monte Carlo methods.
On Modeling Sense Relatedness in Multi-prototype Word Embedding
To enhance the expression ability of distributional word representation learning model, many researchers tend to induce word senses through clustering, and learn multiple embedding vectors for each word, namely multi-prototype word embedding model.
ZhuSuan: A Library for Bayesian Deep Learning
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning.
Kernel Implicit Variational Inference
Recent progress in variational inference has paid much attention to the flexibility of variational posteriors.
Towards Better Analysis of Deep Convolutional Neural Networks
Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification.
Building Memory with Concept Learning Capabilities from Large-scale Knowledge Base
We present a new perspective on neural knowledge base (KB) embeddings, from which we build a framework that can model symbolic knowledge in the KB together with its learning process.
