Search Results for author:
Found 1109 papers, 386 papers with code
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
Face Analysis Project on MXNet
Ranked #5 on
Lightweight Face Recognition
on AgeDB-30
Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages
While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages.
FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content
In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input.
FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating various dynamically audio-consistent talking faces, termed Listening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio.
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
Specifically, we consider the general SFT training data, consisting of a small amount of expert data mixed with a large proportion of sub-optimal data, without any preference labels.
Ranked #22 on
Code Generation
on HumanEval
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
The virtual API server contains a caching system and API simulators which are complementary to alleviate the change in API status.
FedML: A Research Library and Benchmark for Federated Machine Learning
Federated learning (FL) is a rapidly growing research field in machine learning.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i. e., EfficientDeRain, which is able to process a rainy image within 10~ms (i. e., around 6~ms on average), over 80 times faster than the state-of-the-art method (i. e., RCDNet), while achieving similar de-rain effects.
In-Context Demonstration Selection with Cross Entropy Difference
Our method is based on the observation that the effectiveness of in-context demonstrations negatively correlates with the perplexity of the test example by a language model that was finetuned on that demonstration.
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
Given the cost and difficulty of cleaning these datasets by humans, we introduce a systematic framework for evaluating the credibility of datasets, identifying label errors, and evaluating the influence of noisy labels in the curated language data, specifically focusing on unsafe comments and conversation classification.
graph2vec: Learning Distributed Representations of Graphs
Recent works on representation learning for graph structured data predominantly focus on learning distributed representations of graph substructures such as nodes and subgraphs.
Ranked #1 on
Malware Detection
on Android Malware Dataset
Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization
Z-Code++ creates new state of the art on 9 out of 13 text summarization tasks across 5 languages.
Unifying Vision, Text, and Layout for Universal Document Processing
UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation.
Ranked #5 on
Visual Question Answering (VQA)
on InfographicVQA
(using extra training data)
Fine-tune BERT for Extractive Summarization
BERT, a pre-trained Transformer model, has achieved ground-breaking performance on multiple NLP tasks.
Extractive Document Summarization
Extractive Summarization
+1
Text Summarization with Pretrained Encoders
For abstractive summarization, we propose a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two (the former is pretrained while the latter is not).
PFLlib: Personalized Federated Learning Algorithm Library
Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL) has gained significant prominence as a research direction within the FL domain.
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding
We pretrained a large {\SST} model on a synthetic Structured3D dataset, which is an order of magnitude larger than the ScanNet dataset.
Ranked #2 on
3D Object Detection
on S3DIS
(using extra training data)
Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models
This necessitates a new branch of research focusing on the parameter-efficient adaptation of PLMs, dubbed as delta tuning in this paper.
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis.
Ranked #4 on
3D Object Classification
on ModelNet40
Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
The Adaptive O-CNN encoder takes the planar patch normal and displacement as input and performs 3D convolutions only at the octants at each level, while the Adaptive O-CNN decoder infers the shape occupancy and subdivision status of octants at each level and estimates the best plane normal and displacement for each leaf octant.
Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion
Acquiring complete and clean 3D shape and scene data is challenging due to geometric occlusion and insufficient views during 3D capturing.
Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination
Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various shape analysis tasks with competitive performance to supervised methods.
Ranked #2 on
3D Semantic Segmentation
on PartNet
3D Point Cloud Linear Classification
3D Semantic Segmentation
THUMT: An Open Source Toolkit for Neural Machine Translation
This paper introduces THUMT, an open-source toolkit for neural machine translation (NMT) developed by the Natural Language Processing Group at Tsinghua University.
Improving the Transformer Translation Model with Document-Level Context
Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge.
Learning to Copy for Automatic Post-Editing
To better identify translation errors, our method learns the representations of source sentences and system outputs in an interactive way.
Countering Malicious DeepFakes: Survey, Battleground, and Horizon
To fill this gap, in this paper, we provide a comprehensive overview and detailed analysis of the research work on the topic of DeepFake generation, DeepFake detection as well as evasion of DeepFake detection, with more than 318 research papers carefully surveyed.
Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
Large end-to-end neural open-domain chatbots are becoming increasingly popular.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization.
CPM-2: Large-scale Cost-effective Pre-trained Language Models
We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference.
CLRNet: Cross Layer Refinement Network for Lane Detection
In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy.
Ranked #1 on
Lane Detection
on LLAMAS
Datasets for Large Language Models: A Comprehensive Survey
Additionally, a comprehensive review of the existing available dataset resources is also provided, including statistics from 444 datasets, covering 8 language categories and spanning 32 domains.
Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
Internet search affects people's cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good.
How Powerful are Performance Predictors in Neural Architecture Search?
Early methods in the rapidly developing field of neural architecture search (NAS) required fully training thousands of neural networks.
Learning Entity and Relation Embeddings for Knowledge Graph Completion
Knowledge graph completion aims to perform link prediction between entities.
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
In this work, we present Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks.
Use What You Have: Video Retrieval Using Representations From Collaborative Experts
The rapid growth of video on the internet has made searching for video content using natural language queries a significant challenge.
Ranked #24 on
Video Retrieval
on MSVD
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
This report summarizes the results of the first edition of the challenge together with the findings of the participants.
TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval
In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets to construct powerful video encoders.
SecureBoost: A Lossless Federated Learning Framework
This federated learning system allows the learning process to be jointly conducted over multiple parties with common user samples but different feature sets, which corresponds to a vertically partitioned data set.
Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention
In our approach, the encoding of sentence is a two-stage process.
Ranked #73 on
Natural Language Inference
on SNLI
Actionable Recourse in Linear Classification
We present integer programming tools to ensure recourse in linear classification problems without interfering in model development.
Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data.
Hierarchical Transformers for Multi-Document Summarization
In this paper, we develop a neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner.
A Survey of Visual Transformers
Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP).
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.
Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation
In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD.
Invertible Denoising Network: A Light Solution for Real Noise Removal
InvDN transforms the noisy input into a low-resolution clean image and a latent representation containing noise.
Auto-Exposure Fusion for Single-Image Shadow Removal
We conduct extensive experiments on the ISTD, ISTD+, and SRD datasets to validate our method's effectiveness and show better performance in shadow regions and comparable performance in non-shadow regions over the state-of-the-art methods.
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
These observations require us to rethink the treatment of noisy labels, and we hope the availability of these two datasets would facilitate the development and evaluation of future learning with noisy label solutions.
Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding
Data diversity and abundance are essential for improving the performance and generalization of models in natural language processing and 2D vision.
DialogSum: A Real-Life Scenario Dialogue Summarization Dataset
Proposal of large-scale datasets has facilitated research on deep neural models for news summarization.
Abstractive Dialogue Summarization
Common Sense Reasoning
+3
DialogSum Challenge: Results of the Dialogue Summarization Shared Task
We report the results of DialogSum Challenge, the shared task on summarizing real-life scenario dialogues at INLG 2022.
Towards a Unified Multi-Dimensional Evaluator for Text Generation
We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.
Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields
In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control.
Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
Vulnerability identification is crucial to protect the software systems from attacks for cyber security.
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
In this work, we present G-Eval, a framework of using large language models with chain-of-thoughts (CoT) and a form-filling paradigm, to assess the quality of NLG outputs.
Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems
We propose a copy-augmented and feature-enriched sequence to sequence (seq2seq) model, which outperforms existing models by 3. 2% on the Math23K dataset and serves as a strong baseline of the Ape210K dataset.
Physics-informed deep learning for incompressible laminar flows
Physics-informed deep learning has drawn tremendous interest in recent years to solve computational physics problems, whose basic concept is to embed physical laws to constrain/inform neural networks, with the need of less data for training a reliable model.
Minimum Risk Training for Neural Machine Translation
We propose minimum risk training for end-to-end neural machine translation.
Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection
In addition, these detectors primarily rely on category names and overlook the rich contextual information that language can provide, which is essential for capturing open vocabulary concepts that are typically rare and not well-represented by category names alone.
DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
For a dialogue, it corrupts a window of text with dialogue-inspired noise, and guides the model to reconstruct this window based on the content of the remaining conversation.
Learning Structured Text Representations
In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations.
Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness
In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples.
Deep Implicit Moving Least-Squares Functions for 3D Reconstruction
We incorporate IMLS surface generation into deep neural networks for inheriting both the flexibility of point sets and the high quality of implicit surfaces.
Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data
Surprisingly, we found that REtrieving from the traINing datA (REINA) only can lead to significant gains on multiple NLG and NLU tasks.
Directed Acyclic Transformer for Non-Autoregressive Machine Translation
Non-autoregressive Transformers (NATs) significantly reduce the decoding latency by generating all tokens in parallel.
SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation
We further complement the evaluation metrics of 3D generative models with the shading-image-based Fr\'echet inception distance (FID) scores to better assess visual quality and shape distribution of the generated shapes.
Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations
Our method encodes the volumetric field of a 3D shape with an adaptive feature volume organized by an octree and applies a compact multilayer perceptron network for mapping the features to the field value at each 3D position.
Cross-Modal Causal Intervention for Medical Report Generation
Medical report generation (MRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating the corresponding medical reports according to the given radiology image.
Visual Causal Scene Refinement for Video Question Answering
Our VCSR involves two essential modules: i) the Question-Guided Refiner (QGR) module, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention; ii) the Causal Scene Separator (CSS) module, which discovers a collection of visual causal and non-causal scenes based on the visual-linguistic causal relevance and estimates the causal effect of the scene-separating intervention in a contrastive learning manner.
CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning
We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox containing a rich set of state-of-the-art causal relation discovery and causal inference methods for various visual-linguistic reasoning tasks, such as VQA, image/video captioning, medical report generation, model generalization and robustness, etc.
Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Despite advancements in LLMs, knowledge-based reasoning remains a longstanding issue due to the fragility of knowledge recall and inference.
Small Models are Valuable Plug-ins for Large Language Models
Large language models (LLMs) such as GPT-3 and GPT-4 are powerful but their weights are often publicly unavailable and their immense sizes make the models difficult to be tuned with common hardware.
Modeling Coverage for Neural Machine Translation
Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate.
Fusing Context Into Knowledge Graph for Commonsense Question Answering
However, although a KG contains rich structural information, it lacks the context to provide a more precise understanding of the concepts.
Ranked #4 on
Common Sense Reasoning
on CommonsenseQA
(using extra training data)
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9
This challenge track aims to expand the coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots
Our framework features a two-stream encoder, an active fusion decoder (AFD) and a dual-task regularization approach.
Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training
Besides, we conduct further analysis to better verify the effectiveness of different components of our approach and various settings of pre-training.
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed.
To Smooth or Not? When Label Smoothing Meets Noisy Labels
We provide understandings for the properties of LS and NLS when learning with noisy labels.
Ranked #9 on
Learning with noisy labels
on CIFAR-10N-Random3
Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars
Neural radiance fields are capable of reconstructing high-quality drivable human avatars but are expensive to train and render.
Physics informed deep learning for computational elastodynamics without labeled data
In this paper, we present a physics-informed neural network (PINN) with mixed-variable output to model elastodynamics problems without resort to labeled data, in which the I/BCs are hardly imposed.
PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
Partial differential equations (PDEs) play a fundamental role in modeling and simulating problems across a wide range of disciplines.
Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems
In this paper, we conduct the first comprehensive and systematic study of the adversarial attacks on SR systems (SRSs) to understand their security weakness in the practical blackbox setting.
Context Gates for Neural Machine Translation
In neural machine translation (NMT), generation of a target word depends on both source and target contexts.
Neural Machine Translation with Reconstruction
Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy.
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets.
Rank Minimization for Snapshot Compressive Imaging
We further investigate the special structure of the sampling process in SCI to tackle the computational workload and memory issues in SCI reconstruction.
Federated Transfer Learning for EEG Signal Classification
The success of deep learning (DL) methods in the Brain-Computer Interfaces (BCI) field for classification of electroencephalographic (EEG) recordings has been restricted by the lack of large datasets.
ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation
We view the reconstruction of CAD models in the boundary representation (B-Rep) as the detection of geometric primitives of different orders, i. e. vertices, edges and surface patches, and the correspondence of primitives, which are holistically modeled as a chain complex, and show that by modeling such comprehensive structures more complete and regularized reconstructions can be achieved.
Parameter-free $\ell_p$-Box Decoding of LDPC Codes
The Alternating Direction Method of Multipliers (ADMM) decoding of Low Density Parity Check (LDPC) codes has received many attentions due to its excellent performance at the error floor region.
Information Theory Information Theory
When Optimizing $f$-divergence is Robust with Label Noise
We show when maximizing a properly defined $f$-divergence measure with respect to a classifier's predictions and the supervised labels is robust with label noise.
Ranked #13 on
Learning with noisy labels
on CIFAR-10N-Aggregate
WDNet: Watermark-Decomposition Network for Visible Watermark Removal
Visible watermarks are widely-used in images to protect copyright ownership.
End-to-End Full-Atom Antibody Design
Finally, the updated antibody is docked to the epitope via the alignment of the shadow paratope.
Multi-modal Graph Learning for Disease Prediction
For disease prediction tasks, most existing graph-based methods tend to define the graph manually based on specified modality (e. g., demographic information), and then integrated other modalities to obtain the patient representation by Graph Representation Learning (GRL).
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Scene Segmentation
We introduce SAMPro3D for zero-shot 3D indoor scene segmentation.
Detecting Corrupted Labels Without Training a Model to Predict
In this paper, from a more data-centric perspective, we propose a training-free solution to detect corrupted labels.
MogFace: Towards a Deeper Appreciation on Face Detection
As a result, practical solutions on label assignment, scale-level data augmentation, and reducing false alarms are necessary for advancing face detectors.
Ranked #13 on
Face Detection
on WIDER Face (Easy)
Commonsense-Focused Dialogues for Response Generation: An Empirical Study
Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet.
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos.
Conditional Antibody Design as 3D Equivariant Graph Translation
Specifically, the relative improvement to baselines is about 23% in antigen-binding CDR design and 34% for affinity optimization.
Large Language Model Unlearning
To the best of our knowledge, our work is among the first to explore LLM unlearning.
TransZero: Attribute-guided Transformer for Zero-Shot Learning
Although some attention-based models have attempted to learn such region features in a single image, the transferability and discriminative attribute localization of visual features are typically neglected.
HHHFL: Hierarchical Heterogeneous Horizontal Federated Learning for Electroencephalography
To verify the effectiveness of our approach, we conduct experiments on a real-world EEG dataset, consisting of heterogeneous data collected from diverse devices.
Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
The prediction of physicochemical properties from molecular structures is a crucial task for artificial intelligence aided molecular design.
Ranked #2 on
Drug Discovery
on QM9
Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video.
Multimodal Federated Learning via Contrastive Representation Ensemble
In this work, we propose Contrastive Representation Ensemble and Aggregation for Multimodal FL (CreamFL), a multimodal federated learning framework that enables training larger server models from clients with heterogeneous model architectures and data modalities, while only communicating knowledge on public dataset.
GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis
Instead of relying solely on GPT to identify vulnerabilities, which can lead to high false positives and is limited by GPT's pre-trained knowledge, we utilize GPT as a versatile code understanding tool.
Encoding physics to learn reaction-diffusion processes
Modeling complex spatiotemporal dynamical systems, such as the reaction-diffusion processes, have largely relied on partial differential equations (PDEs).
Macro action selection with deep reinforcement learning in StarCraft
These rules are not scalable and efficient enough to cope with the enormous yet partially observed state space in the game.
Boba: Authoring and Visualizing Multiverse Analyses
Multiverse analysis is an approach to data analysis in which all "reasonable" analytic decisions are evaluated in parallel and interpreted collectively, in order to foster robustness and transparency.
Human-Computer Interaction
"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets.
UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization
The high annotation costs and diverse demands of various summarization tasks motivate the development of few-shot summarization.
MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization
MediaSum, a large-scale media interview dataset consisting of 463. 6K transcripts with abstractive summaries.
Mask-Align: Self-Supervised Neural Word Alignment
Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks.
U-Net: Machine Reading Comprehension with Unanswerable Questions
A key subtask is to reliably predict whether the question is unanswerable.
Ranked #12 on
Question Answering
on SQuAD2.0 dev
Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization
We further design an automatic agent team optimization algorithm based on an unsupervised metric termed $\textit{Agent Importance Score}$, enabling the selection of best agents based on the contribution each agent makes.
A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis
To handle the multi-scale temporal patterns and multivariate dependencies, we propose a novel temporal patching approach to model the time series as multi-scale patches, and employ MLPs to capture intra- and inter-patch variations and channel-wise correlations.
Goal-Oriented Gaze Estimation for Zero-Shot Learning
Therefore, we introduce a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL.
Synthetic Benchmarks for Scientific Research in Explainable Machine Learning
In this work, we address this issue by releasing XAI-Bench: a suite of synthetic datasets along with a library for benchmarking feature attribution algorithms.
Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning
Moreover, they train their model to distinguish positive visual-language pairs from negative ones randomly collected from other videos, ignoring the highly confusing video segments within the same video.
Ranked #7 on
Temporal Sentence Grounding
on Charades-STA
VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
Vertical Federated Learning (VFL) has emerged as a collaborative training paradigm that allows participants with different features of the same group of users to accomplish cooperative training without exposing their raw data or model parameters.
Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging
Snapshot compressive imaging (SCI) aims to capture the high-dimensional (usually 3D) images using a 2D sensor (detector) in a single snapshot.
Cross Modal Retrieval with Querybank Normalisation
In this work we first show that, despite their effectiveness, state-of-the-art joint embeddings suffer significantly from the longstanding "hubness problem" in which a small number of gallery embeddings form the nearest neighbours of many queries.
Ranked #5 on
Video Retrieval
on QuerYD
Model Sparsity Can Simplify Machine Unlearning
We show in both theory and practice that model sparsity can boost the multi-criteria unlearning performance of an approximate unlearner, closing the approximation gap, while continuing to be efficient.
Federated Machine Learning: Concept and Applications
We propose a possible solution to these challenges: secure federated learning.
A Second-Order Approach to Learning with Instance-Dependent Label Noise
We first provide evidences that the heterogeneous instance-dependent label noise is effectively down-weighting the examples with higher noise rates in a non-uniform way and thus causes imbalances, rendering the strategy of directly applying methods for class-dependent label noise questionable.
PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents
PEARL outperforms zero-shot and chain-of-thought prompting on this dataset, and ablation experiments show that each stage of PEARL is critical to its performance.
Learning to Remember Translation History with a Continuous Cache
Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information.
Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification
Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples.
Deep Learning for 3D Human Pose Estimation and Mesh Recovery: A Survey
To the best of our knowledge, this survey is arguably the first to comprehensively cover deep learning methods for 3D human pose estimation, including both single-person and multi-person approaches, as well as human mesh recovery, encompassing methods based on explicit models and implicit representations.
Attribute Attention for Semantic Disambiguation in Zero-Shot Learning
Zero-shot learning (ZSL) aims to accurately recognize unseen objects by learning mapping matrices that bridge the gap between visual information and semantic attributes.
GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow
However, the availability of free and open-source simulators is limited, and the installation and configuration process can be daunting for beginners and interdisciplinary researchers.
"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
We hope this task and dataset can promote further research on TOD and subjective content understanding.
subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs
Also, we show that the subgraph vectors could be used for building a deep learning variant of Weisfeiler-Lehman graph kernel.
Fully Sparse Fusion for 3D Object Detection
In this paper, we study how to effectively leverage image modality in the emerging fully sparse architecture.
Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexes
On small molecule dataset for predicting quantum chemical properties, PaxNet reduces the prediction error by 15% and uses 73% less memory than the best baseline.
Molecular Property Prediction
Protein-Ligand Affinity Prediction
Physics-aware Graph Neural Network for Accurate RNA 3D Structure Prediction
In this work, we propose a Graph Neural Network (GNN)-based scoring function trained only with the atomic types and coordinates on limited solved RNA 3D structures for distinguishing accurate structural models.
A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems
Molecular sciences address a wide range of problems involving molecules of different types and sizes and their complexes.
Ranked #1 on
Drug Discovery
on QM9
Asynchronous Bidirectional Decoding for Neural Machine Translation
The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation.
Attention-based sequence-to-sequence model for speech recognition: development of state-of-the-art system on LibriSpeech and its application to non-native English
Recent research has shown that attention-based sequence-to-sequence models such as Listen, Attend, and Spell (LAS) yield comparable results to state-of-the-art ASR systems on various tasks.
A Discourse Signal Annotation System for RST Trees
This paper presents a new system for open-ended discourse relation signal annotation in the framework of Rhetorical Structure Theory (RST), implemented on top of an online tool for RST annotation.
Real-World Image Datasets for Federated Learning
Federated learning is a new machine learning paradigm which allows data parties to build machine learning models collaboratively while keeping their data secure and private.
Robust Unlearnable Examples: Protecting Data Against Adversarial Learning
To address this concern, methods are proposed to make data unlearnable for deep learning models by adding a type of error-minimizing noise.
Crystal Structure Prediction by Joint Equivariant Diffusion
To be specific, DiffCSP jointly generates the lattice and atom coordinates for each crystal by employing a periodic-E(3)-equivariant denoising model, to better model the crystal geometry.
QuerYD: A video dataset with high-quality text and audio narrations
We introduce QuerYD, a new large-scale dataset for retrieval and event localisation in video.
Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields
Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or occupancy values.
ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities
Specifically, ACN adopts a novel co-training network, which enables a coupled learning process for both full modality and missing modality to supplement each other's domain and feature representations, and more importantly, to recover the `missing' information of absent modalities.
Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models
However, existing visual instruction tuning methods only utilize image-language instruction data to align the language and image modalities, lacking a more fine-grained cross-modal alignment.
Single Document Summarization as Tree Induction
In this paper, we conceptualize single-document extractive summarization as a tree induction problem.
Learning by Turning: Neural Architecture Aware Optimisation
To address this problem, this paper conducts a combined study of neural architecture and optimisation, leading to a new optimiser called Nero: the neuronal rotator.
Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation
The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i. e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation.
Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos.
Cross-Modal Retrieval for Motion and Text via DopTriple Loss
On the latest HumanML3D dataset, we achieve a recall of 62. 9% for motion retrieval and 71. 5% for text retrieval (both based on R@10).
Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification
To address above issues, we propose a novel learning framework named \textbf{EDITOR} to select diverse tokens from vision Transformers for multi-modal object ReID.
Sample Elicitation
We also show a connection between this sample elicitation problem and $f$-GAN, and how this connection can help reconstruct an estimator of the distribution based on collected samples.
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting.
Image Classification with Label Noise
Learning with noisy labels
Some Practice for Improving the Search Results of E-commerce
In the Amazon KDD Cup 2022, we aim to apply natural language processing methods to improve the quality of search results that can significantly enhance user experience and engagement with search engines for e-commerce.
Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion
Radar is ubiquitous in autonomous driving systems due to its low cost and good adaptability to bad weather.
Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination
Based on this intuition, in this paper, we devote to distinguishing and exploiting word-level domain contexts for multi-domain NMT.
Learning Program Semantics with Code Representations: An Empirical Study
However, currently, a comprehensive and systematic study on evaluating different program representation techniques across diverse tasks is still missed.
TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective
We investigate the reasons for this phenomenon and discover that the existing data augmentation approach and hard sample mining strategy are incompatible with ViTs-based FR backbone due to the lack of tailored consideration on preserving face structural information and leveraging each local token information.
Distributionally Robust Post-hoc Classifiers under Prior Shifts
We investigate the problem of training models that are robust to shifts caused by changes in the distribution of class-priors or group-priors.
Plug-and-Play Algorithms for Video Snapshot Compressive Imaging
On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm.
Molecule Generation by Principal Subgraph Mining and Assembling
Molecule generation is central to a variety of applications.
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
Besides, the attack is further enhanced by adaptively tuning the translations of object and background.
GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search
Specifically, we propose to construct graphs for the source code and queries with bidirectional GGNN (BiGGNN) to capture the local structural information of the source code and queries.
Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs
Pretraining molecular representation models without labels is fundamental to various applications.
MACSum: Controllable Summarization with Mixed Attributes
We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization based on hard prompt tuning and soft prefix tuning.
Sparse Modular Activation for Efficient Sequence Modeling
To validate the effectiveness of SMA on sequence modeling, we design a novel neural architecture, SeqBoat, which employs SMA to sparsely activate a Gated Attention Unit (GAU) based on the state representations learned from an SSM.
Ranked #2 on
Long-range modeling
on LRA
Hierarchical Attention Based Position-Aware Network for Aspect-Level Sentiment Analysis
Aspect-level sentiment analysis aims to identify the sentiment of a specific target in its context.
Aspect-Based Sentiment Analysis (ABSA)
Feature Engineering
+2
Generating Summaries with Topic Templates and Structured Convolutional Decoders
Existing neural generation approaches create multi-sentence text as a single sequence.
Image Formation Model Guided Deep Image Super-Resolution
We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution.
SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
To bridge the gap between the reference points of salient queries and Transformer detectors, we propose SAlient Point-based DETR (SAP-DETR) by treating object detection as a transformation from salient points to instance objects.
EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models
However, the capability of VLMs to "think" from a first-person perspective, a crucial attribute for advancing autonomous agents and robotics, remains largely unexplored.
OMGEval: An Open Multilingual Generative Evaluation Benchmark for Large Language Models
We evaluate several representative multilingual LLMs on the proposed OMGEval, which we believe will provide a valuable reference for the community to further understand and improve the multilingual capability of LLMs.
AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audio
To this end, we propose to achieve personalized spatial audio by reconstructing 3D human ears with single-view images.
AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception
Driver distraction has become a significant cause of severe traffic accidents over the past decade.
Reinforcement Learning with Perturbed Rewards
For instance, the state-of-the-art PPO algorithm is able to obtain 84. 6% and 80. 8% improvements on average score for five Atari games, with error rates as 10% and 30% respectively.
Harvesting Ambient RF for Presence Detection Through Deep Learning
With presence detection, how to collect training data with human presence can have a significant impact on the performance.
Interpolation between Residual and Non-Residual Networks
Although ordinary differential equations (ODEs) provide insights for designing network architectures, its relationship with the non-residual convolutional neural networks (CNNs) is still unclear.
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Nonetheless, finding anchor points remains a non-trivial task, and the estimation accuracy is also often throttled by the number of available anchor points.
Image Classification with Human Noise
Image Classification with Label Noise
+1
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition
Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance.
Ranked #20 on
Skeleton Based Action Recognition
on NTU RGB+D 120
DRT: A Lightweight Single Image Deraining Recursive Transformer
Over parameterization is a common technique in deep learning to help models learn and generalize sufficiently to the given task; nonetheless, this often leads to enormous network structures and consumes considerable computing resources during training.
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models
Pretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts.
SCALoss: Side and Corner Aligned Loss for Bounding Box Regression
In this paper, we propose Side Overlap~(SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases.
Want To Reduce Labeling Cost? GPT-3 Can Help
Data annotation is a time-consuming and labor-intensive process for many NLP tasks.
SEC4SR: A Security Analysis Platform for Speaker Recognition
To bridge this gap, we present SEC4SR, the first platform enabling researchers to systematically and comprehensively evaluate adversarial attacks and defenses in SR. SEC4SR incorporates 4 white-box and 2 black-box attacks, 24 defenses including our novel feature-level transformations.
Integrating Vectorized Lexical Constraints for Neural Machine Translation
In this work, we propose to open this black box by directly integrating the constraints into NMT models.
Physics-informed Deep Super-resolution for Spatiotemporal Data
High-fidelity simulation of complex physical systems is exorbitantly expensive and inaccessible across spatiotemporal scales.
Anonymization for Skeleton Action Recognition
Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the privacy of subjects while having competitive recognition performance.
TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning
To overcome these limitations, we take advantage of the multi-scale temporal dependencies within videos and proposes a novel video self-supervised learning framework named Temporal Contrastive Graph Learning (TCGL), which jointly models the inter-snippet and intra-snippet temporal dependencies for temporal representation learning with a hybrid graph contrastive learning strategy.
On Robust Prefix-Tuning for Text Classification
Recently, prefix-tuning has gained increasing attention as a parameter-efficient finetuning method for large-scale pretrained language models.
Privacy-preserving Collaborative Learning with Automatic Transformation Search
Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.
Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation
To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning.
HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
Specifically, HSVA aligns the semantic and visual domains by adopting a hierarchical two-step adaptation, i. e., structure adaptation and distribution adaptation.
Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN
However, both strategies are faced with some immediate problems: raw features cannot represent various properties of nodes (e. g., structure information), and representations learned by supervised GNN may suffer from the poor performance of the classifier on the poisoned graph.
