Search Results for author:
Found 35 papers, 11 papers with code
DocTabQA: Answering Questions from Long Documents Using Tables
To the best of our knowledge, this problem has not been previously explored.
Mutagenesis screen to map the functions of parameters of Large Language Models
Large Language Models (LLMs) have significantly advanced artificial intelligence, excelling in numerous tasks.
Empowering Graph Invariance Learning with Deep Spurious Infomax
To bridge this gap, we introduce a novel graph invariance learning paradigm, which induces a robust and general inductive bias.
CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis.
FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs).
Slight Corruption in Pre-training Data Makes Better Diffusion Models
They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with paired data and conditions, such as image-text and image-class pairs.
RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection
Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs.
Ranked #11 on
Open Vocabulary Object Detection
on LVIS v1.0
(using extra training data)
ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model
Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images.
DLAFormer: An End-to-End Transformer For Document Layout Analysis
Document layout analysis (DLA) is crucial for understanding the physical layout and logical structure of documents, serving information retrieval, document summarization, knowledge extraction, etc.
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
Our approach relaxes the discrete jailbreak optimization into a continuous optimization and progressively increases the sparsity of the optimizing vectors.
Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis
Our end-to-end system achieves state-of-the-art performance on two large-scale document layout analysis datasets (PubLayNet and DocLayNet), a high-quality hierarchical document structure reconstruction dataset (HRDoc), and our Comp-HRDoc benchmark.
UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents
This unified approach allows for the definition of various relation types and effectively tackles hierarchical relationships in form-like documents.
Dynamic Relation Transformer for Contextual Text Block Detection
Contextual Text Block Detection (CTBD) is the task of identifying coherent text blocks within the complexity of natural scenes.
Is Certifying $\ell_p$ Robustness Still Worthwhile?
There are three layers to this inquiry, which we address in this paper: (1) why do we care about robustness research?
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT
Previous mainstream audio-and-text LLMs use discrete audio tokens to represent both input and output audio; however, they suffer from performance degradation on tasks such as automatic speech recognition, speech-to-text translation, and speech enhancement over models using continuous speech features.
A Recipe for Improved Certifiable Robustness
A key challenge, supported both theoretically and empirically, is that robustness demands greater network capacity and more data than standard training.
Completing Visual Objects via Bridging Generation and Segmentation
This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components.
FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec
We also demonstrate that the pre-trained models are suitable for downstream tasks, including automatic speech recognition and personalized text-to-speech synthesis.
A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images
In this paper, we present a new question-answering (QA) based key-value pair extraction approach, called KVPFormer, to robustly extracting key-value relationships between entities from form-like document images.
Unlocking Deterministic Robustness Certification on ImageNet
We show that fast ways of bounding the Lipschitz constant for conventional ResNets are loose, and show how to address this by designing a new residual block, leading to the \emph{Linear ResNet} (LiResNet) architecture.
Enhanced Training of Query-Based Object Detection via Selective Query Recollection
This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage.
Ranked #14 on
Object Detection
on COCO 2017 val
Contextual Expressive Text-to-Speech
To achieve this task, we construct a synthetic dataset and develop an effective framework.
The VolcTrans System for WMT22 Multilingual Machine Translation Task
This report describes our VolcTrans system for the WMT22 shared task on large-scale multilingual machine translation.
Composite FORCE learning of chaotic echo state networks for time-series prediction
Echo state network (ESN), a kind of recurrent neural networks, consists of a fixed reservoir in which neurons are connected randomly and recursively and obtains the desired output only by training output connection weights.
Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior
In the asymmetric codec, we adopt a mixed multi-path residual block (MMRB) to gradually extract weak texture features of input images, which can better preserve the original facial features and avoid excessive fantasy.
ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents
In this paper, we propose a new multi-modal backbone network by concatenating a BERTgrid to an intermediate layer of a CNN model, where the input of CNN is a document image and the BERTgrid is a grid of word embeddings, to generate a more powerful grid-based document representation, named ViBERTgrid.
Text to Image Generation with Semantic-Spatial Aware GAN
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions.
Contrast and Order Representations for Video Self-Supervised Learning
To address this, we present a contrast-and-order representation (CORP) framework for learning self-supervised video representations that can automatically capture both the appearance information within each frame and temporal information across different frames.
Ranked #3 on
Self-Supervised Action Recognition Linear
on UCF101
Action Recognition
Self-Supervised Action Recognition Linear
+1
Is normalization indispensable for training deep neural network?
In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation.
A Neural Architecture Search based Framework for Liquid State Machine Design
By exploring the design space in network architectures and parameters, recent works have demonstrated great potential for improving the accuracy of LSM model with low complexity.
RotationOut as a Regularization Method for Neural Network
We further use a noise analysis method to interpret the difference between RotationOut and Dropout in co-adaptation reduction.
Higher-order Network for Action Recognition
Capturing spatiotemporal dynamics is an essential topic in video recognition.
Qiniu Submission to ActivityNet Challenge 2018
We also propose new non-local-based models for further improvement on the recognition accuracy.
MSDNN: Multi-Scale Deep Neural Network for Salient Object Detection
Salient object detection is a fundamental problem and has been received a great deal of attentions in computer vision.
