Search Results for author:
Found 191 papers, 81 papers with code
Friendly Topic Assistant for Transformer Based Abstractive Summarization
Abstractive document summarization is a comprehensive task including document understanding and summary generation, in which area Transformer-based models have achieved the state-of-the-art performance.
BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging
This measurement and the modulation masks are fed into our Recurrent Neural Network (RNN) to reconstruct the desired high-speed frames.
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling.
Distributed Zonotopic Fusion Estimation for Multi-sensor Systems
To reduce the conservatism of the DZFE with optimal parameters, we enhance our approach with an improved zonotope fusion criterion, which further improves the estimation performance of this DZFE by constructing tight strips for the intersection.
LLM4Tag: Automatic Tagging System for Information Retrieval via Large Language Models
First, a graph-based tag recall module is designed to effectively and comprehensively construct a small-scale highly relevant candidate tag set.
Scalable Distributed Reproduction Numbers of Network Epidemics with Differential Privacy
However, both local and cluster distributed reproduction numbers can reveal the frequency of interactions between nodes in a network, which raises privacy concerns.
Deceptive Sequential Decision-Making via Regularized Policy Optimization
Autonomous systems are increasingly expected to operate in the presence of adversaries, though an adversary may infer sensitive information simply by observing a system, without even needing to interact with it.
Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
In this paper, we address the lifelong sequential behavior incomprehension problem in large language models (LLMs) for recommendation, where LLMs struggle to extract useful information from long user behavior sequences, even within their context limits.
Duplex: Dual Prototype Learning for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to enable models to recognize novel compositions of visual states and objects that were absent during training.
Swin-X2S: Reconstructing 3D Shape from 2D Biplanar X-ray with Swin Transformers
A dimension-expanding module is introduced to bridge the encoder and decoder, ensuring a smooth conversion from 2D pixels to 3D voxels.
Dual-level Adaptive Incongruity-enhanced Model for Multimodal Sarcasm Detection
Existing methods primarily focused on the incongruity between text and image information for sarcasm detection.
An Automatic Graph Construction Framework based on Large Language Models for Recommendation
However, most existing GNN-based recommendation methods focus on the optimization of model structures and learning strategies based on pre-defined graphs, neglecting the importance of the graph construction stage.
Numerical Pruning for Efficient Autoregressive Models
Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing.
LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers
In this paper, we show that performing the full computation of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps.
MIND: Effective Incorrect Assignment Detection through a Multi-Modal Structure-Enhanced Language Model
The rapid growth of academic publications has exacerbated the issue of author name ambiguity in online digital libraries.
LIBER: Lifelong User Behavior Modeling Based on Large Language Models
On the one hand, it presents difficulties for LLMs in effectively capturing the dynamic shifts in user interests within these sequences, and on the other hand, there exists the issue of substantial computational overhead if the LLMs necessitate recurrent calls upon each update to the user sequences.
Circuit Complexity Bounds for RoPE-based Transformer Architecture
In this work, we establish a circuit complexity bound for Transformers with $\mathsf{RoPE}$ attention.
Stability Analysis of Distributed Estimators for Large-Scale Interconnected Systems: Time-Varying and Time-Invariant Cases
Then, the distributed estimator is proved to be stable if the DMRE remains uniformly bounded.
Training Compute-Optimal Protein Language Models
We explore optimally training protein language models, an area of significant interest in biological research where guidance on best practices is limited.
Beyond Positive History: Re-ranking with List-level Hybrid Feedback
It captures user's preferences and behavior patterns with three modules: a Disentangled Interest Miner to disentangle the user's preferences into interests and disinterests, a Sequential Preference Mixer to learn users' entangled preferences considering the context of feedback, and a Comparison-aware Pattern Extractor to capture user's behavior patterns within each list.
Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent
Our results demonstrate that as long as the input data has a constant condition number, e. g., $n = O(d)$, the linear looped Transformers can achieve a small error by multi-step gradient descent during in-context learning.
HSR-Enhanced Sparse Attention Acceleration
Our approach achieves a running time of $O(mn^{4/5})$ significantly faster than the naive approach $O(mn)$ for attention generation, where $n$ is the context length, $m$ is the query length, and $d$ is the hidden dimension.
Scalable Weibull Graph Attention Autoencoder for Modeling Document Networks
Although existing variational graph autoencoders (VGAEs) have been widely used for modeling and generating graph-structured data, most of them are still not flexible enough to approximate the sparse and skewed latent node representations, especially those of document relational networks (DRNs) with discrete observations.
Treating Brain-inspired Memories as Priors for Diffusion Model to Forecast Multivariate Time Series
To better capture temporal patterns, we get inspiration from humans' memory mechanisms and propose a channel-shared, brain-inspired memory module for MTS.
ChemDFM-X: Towards Large Multimodal Model for Chemistry
Rapid developments of AI tools are expected to offer unprecedented assistance to the research of natural science including chemistry.
Channel-wise Influence: Estimating Data Influence for Multivariate Time Series
To fill this gap, we propose a channel-wise influence function, which is the first method that can estimate the influence of different channels in MTS, utilizing a first-order gradient approximation that leverages the more informative average gradient of the data set.
Disentangled Generative Graph Representation Learning
This oversight results in non-robustness and a lack of explainability.
Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models
Recommender systems (RSs) play a pervasive role in today's online services, yet their closed-loop nature constrains their access to open-world knowledge.
HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Prediction
This paper proposes HybridOcc, a hybrid 3D volume query proposal method generated by Transformer framework and NeRF representation and refined in a coarse-to-fine SSC prediction framework.
AIE: Auction Information Enhanced Framework for CTR Prediction in Online Advertising
Click-Through Rate (CTR) prediction is a fundamental technique for online advertising recommendation and the complex online competitive auction process also brings many difficulties to CTR optimization.
A Decoding Acceleration Framework for Industrial Deployable LLM-based Recommender Systems
This generation inefficiency stems from the autoregressive nature of LLMs, and a promising direction for acceleration is speculative decoding, a Draft-then-Verify paradigm that increases the number of generated tokens per decoding step.
Instruction Tuning-free Visual Token Complement for Multimodal LLMs
However, current research is inherently constrained by challenges such as the need for high-quality instruction pairs and the loss of visual information in image-to-text training objectives.
Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation
Thus, LLMs only see a small fraction of the datasets (e. g., less than 10%) instead of the whole datasets, limiting their exposure to the full training space.
A Non-negative VAE:the Generalized Gamma Belief Network
The gamma belief network (GBN), often regarded as a deep topic model, has demonstrated its potential for uncovering multi-layer interpretable latent representations in text data.
HICEScore: A Hierarchical Metric for Image Captioning Evaluation
By detecting local visual regions and textual phrases, HICE-S builds an interpretable hierarchical scoring mechanism, breaking through the barriers of the single-scale structure of existing reference-free metrics.
All Roads Lead to Rome: Unveiling the Trajectory of Recommender Systems Across the LLM Era
Recommender systems (RS) are vital for managing information overload and delivering personalized content, responding to users' diverse information needs.
MemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Models
The preferences embedded in the user's historical dialogue sessions and the current session exhibit continuity and sequentiality, and we refer to CRSs with this characteristic as sequential CRSs.
ELCoRec: Enhance Language Understanding with Co-Propagation of Numerical and Categorical Features for Recommendation
Concretely, we propose to inject the preference understanding capability into LLM via a GAT expert model where the user preference is better encoded by parallelly propagating the temporal relations, and rating signals as well as various side information of historical items.
Physics-Informed AI Inverter
This letter devises an AI-Inverter that pilots the use of a physics-informed neural network (PINN) to enable AI-based electromagnetic transient simulations (EMT) of grid-forming inverters.
TraceNet: Segment one thing efficiently
To address this, we propose and formulate a one tap driven single instance segmentation task that segments a single instance selected by a user via a positive tap.
Intermittent Encryption Strategies for Anti-Eavesdropping Estimation
A linear encryption scheme is utilized, which first linearly transforms innovation via an encryption matrix and then encrypts some components of the transformed innovation.
Advancing Graph Generation through Beta Diffusion
Diffusion models have excelled in generating natural images and are now being adapted to a variety of data types, including graphs.
MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
Multiple Sequence Alignment (MSA) plays a pivotal role in unveiling the evolutionary trajectories of protein families.
Large Language Models Make Sample-Efficient Recommender Systems
Hence, we propose and verify our core viewpoint: Large Language Models Make Sample-Efficient Recommender Systems.
FINED: Feed Instance-Wise Information Need with Essential and Disentangled Parametric Knowledge from the Past
In this paper, we propose FINED to Feed INstance-wise information need with Essential and Disentangled parametric knowledge from past data for recommendation enhancement.
DisCo: Towards Harmonious Disentanglement and Collaboration between Tabular and Semantic Space for Recommendation
In this paper, we propose DisCo to Disentangle the unique patterns from the two representation spaces and Collaborate the two spaces for recommendation enhancement, where both the specificity and the consistency of the two spaces are captured.
GSTalker: Real-time Audio-Driven Talking Face Generation via Deformable Gaussian Splatting
We present GStalker, a 3D audio-driven talking face generation model with Gaussian Splatting for both fast training (40 minutes) and real-time rendering (125 FPS) with a 3$\sim$5 minute video for training material, in comparison with previous 2D and 3D NeRF-based modeling frameworks which require hours of training and seconds of rendering per frame.
Retrieval-Oriented Knowledge for Click-Through Rate Prediction
The framework features a knowledge base that preserves and imitates the retrieved \& aggregated representations using a decomposition-reconstruction paradigm.
BOND: Bootstrapping From-Scratch Name Disambiguation with Multi-task Promoting
Therefore, we present BOND, which bootstraps the local and global informative signals to promote each other in an end-to-end regime.
Play to Your Strengths: Collaborative Intelligence of Conventional Recommender Models and Large Language Models
The rise of large language models (LLMs) has opened new opportunities in Recommender Systems (RSs) by enhancing user behavior modeling and content understanding.
Neural Image Compression with Quantization Rectifier
This paper presents a novel quantization rectifier (QR) method for image compression that leverages image feature correlation to mitigate the impact of quantization.
ERASE: Benchmarking Feature Selection Methods for Deep Recommender Systems
Secondly, the existing literature's lack of detailed analysis on selection attributes, based on large-scale datasets and a thorough comparison among selection techniques and DRS backbones, restricts the generalizability of findings and impedes deployment on DRS.
Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting
The forecasting of Multivariate Time Series (MTS) has long been an important but challenging task.
MeaCap: Memory-Augmented Zero-shot Image Captioning
The framework of MeaCap achieves the state-of-the-art performance on a series of zero-shot IC settings.
Towards Efficient and Effective Unlearning of Large Language Models for Recommendation
However, in order to protect user privacy and optimize utility, it is also crucial for LLMRec to intentionally forget specific user data, which is generally referred to as recommendation unlearning.
OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining
We envisage that OAG-Bench can serve as a common ground for the community to evaluate and compare algorithms in academic graph mining, thereby accelerating algorithm development and advancement in this field.
FedCore: Straggler-Free Federated Learning with Distributed Coresets
Federated learning (FL) is a machine learning paradigm that allows multiple clients to collaboratively train a shared model while keeping their data on-premise.
ChemDFM: A Large Language Foundation Model for Chemistry
In its utmost form, such a generalist AI chemist could be referred to as Chemical General Intelligence.
xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein
We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pre-training framework.
SnapCap: Efficient Snapshot Compressive Video Captioning
To address these problems, in this paper, we propose a novel VC pipeline to generate captions directly from the compressed measurement, which can be captured by a snapshot compressive sensing camera and we dub our model SnapCap.
keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM
Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, especially for question answering.
YAYI 2: Multilingual Open-Source Large Language Models
As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to the artificial general intelligence.
FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction
The traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality, which capture the collaborative signals via feature interaction modeling.
Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection
First, instead of learning the continuous representations, we preserve the typical normal patterns as discrete iconic prototypes, and confirm the importance of Vector Quantization in preventing the model from falling into the shortcut.
Ranked #1 on
Multi-class Anomaly Detection
on MVTec AD
ClickPrompt: CTR Models are Strong Prompt Generators for Adapting Language Models to CTR Prediction
Traditional CTR models convert the multi-field categorical data into ID features via one-hot encoding, and extract the collaborative signals among features.
Differentially Private Reward Functions in Policy Synthesis for Markov Decision Processes
Markov decision processes often seek to maximize a reward function, but onlookers may infer reward functions by observing the states and actions of such systems, revealing sensitive information.
HAMUR: Hyper Adapter for Multi-Domain Recommendation
Secondly, due to the distribution differences among domains, the utilization of static parameters in existing methods limits their flexibility to adapt to diverse domains.
Scenario-Aware Hierarchical Dynamic Network for Multi-Scenario Recommendation
To address these limitations, we propose a Scenario-Aware Hierarchical Dynamic Network for Multi-Scenario Recommendations (HierRec), which perceives implicit patterns adaptively and conducts explicit and implicit scenario modeling jointly.
ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
With large language models (LLMs) achieving remarkable breakthroughs in natural language processing (NLP) domains, LLM-enhanced recommender systems have received much attention and have been actively explored currently.
A hybrid Decoder-DeepONet operator regression framework for unaligned observation data
Results illustrate the advantages of Decoder-DeepONet and Multi-Decoder-DeepONet in handling unaligned observation data and showcase their potentials in improving prediction accuracy.
AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation
In the domain of streaming recommender systems, conventional methods for addressing new user IDs or item IDs typically involve assigning initial ID embeddings randomly.
Prototypes-oriented Transductive Few-shot Learning with Conditional Transport
Transductive Few-Shot Learning (TFSL) has recently attracted increasing attention since it typically outperforms its inductive peer by leveraging statistics of query samples.
PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification
We find that by formulating the multi-label classification as a CT problem, we can exploit the interactions between the image and label efficiently by minimizing the bidirectional CT cost.
Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models
In this work, we propose an Open-World Knowledge Augmented Recommendation Framework with Large Language Models, dubbed KAR, to acquire two types of external knowledge from LLMs -- the reasoning knowledge on user preferences and the factual knowledge on items.
How Can Recommender Systems Benefit from Large Language Models: A Survey
In this paper, we conduct a comprehensive survey on this research direction from the perspective of the whole pipeline in real-world recommender systems.
CTRL: Connect Collaborative and Language Model for CTR Prediction
Both tabular data and converted textual data are regarded as two different modalities and are separately fed into the collaborative CTR model and pre-trained language model.
Remote State Estimation with Posterior-Based Stochastic Event-Triggered Schedule
A posterior-based SET mechanism is proposed, which determines whether to transmit data by the effect of the measurement on the posterior estimate.
Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models
For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts.
Geometry-based spherical JND modeling for 360$^\circ$ display
Second, we extend our 2D-JND model to SJND by jointly exploiting latitude projection and field of view during 360$^\circ$ display.
Compressed Interaction Graph based Framework for Multi-behavior Recommendation
However, it is challenging to explore multi-behavior data due to the unbalanced data distribution and sparse target behavior, which lead to the inadequate modeling of high-order relations when treating multi-behavior data ''as features'' and gradient conflict in multitask learning when treating multi-behavior data ''as labels''.
ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing
Zero-shot capability has been considered as a new revolution of deep learning, letting machines work on tasks without curated training data.
Web-Scale Academic Name Disambiguation: the WhoIsWho Benchmark, Leaderboard, and Toolkit
The toolkit is at https://github. com/THUDM/WhoIsWho.
Multi-Task Deep Recommender Systems: A Survey
Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge.
Cross-Fusion Rule for Personalized Federated Learning
To overcome these challenges, a multi-layer multi-fusion strategy framework is proposed in this paper, i. e., the server adopts the network layer parameters of each client upload model as the basic unit of fusion for information-sharing calculation.
Differential Privacy in Cooperative Multiagent Planning
We synthesize policies that are robust to privacy by reducing the value of the total correlation.
Learning stability of partially observed switched linear systems
In this paper, we propose an algorithm for deciding stability of switched linear systems under arbitrary switching based purely on observed output data.
Semantic-aware Contrastive Learning for More Accurate Semantic Parsing
Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an autoregressive fashion.
Secure Fusion Estimation Against FDI Sensor Attacks in Cyber-Physical Systems
This paper is concerned with the problem of secure multi-sensors fusion estimation for cyber-physical systems, where sensor measurements may be tampered with by false data injection (FDI) attacks.
Position-Aware Contrastive Alignment for Referring Image Segmentation
The main challenge of this task is to understand the visual and linguistic content simultaneously and to find the referred object accurately among all instances in the image.
1st Place Solution for YouTubeVOS Challenge 2022: Referring Video Object Segmentation
The task of referring video object segmentation aims to segment the object in the frames of a given video to which the referring expressions refer.
Toward an AI-enabled Connected Industry: AGV Communication and Sensor Measurement Datasets
This paper presents two wireless measurement campaigns in industrial testbeds: industrial Vehicle-to-vehicle (iV2V) and industrial Vehicle-to-infrastructure plus Sensor (iV2I+), together with detailed information about the two captured datasets.
Disentangling Past-Future Modeling in Sequential Recommendation via Dual Networks
Sequential recommendation (SR) plays an important role in personalized recommender systems because it captures dynamic and diverse preferences from users' real-time increasing behaviors.
IntTower: the Next Generation of Two-Tower Model for Pre-Ranking System
FE-Block module performs fine-grained and early feature interactions to capture the interactive signals between user and item towers explicitly and CIR module leverages a contrastive interaction regularization to further enhance the interactions implicitly.
HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding
With the tree-likeness property of hyperbolic space, the underlying semantic hierarchy among words and topics can be better exploited to mine more interpretable topics.
Knowledge-Aware Bayesian Deep Topic Model
We propose a Bayesian generative model for incorporating prior domain knowledge into hierarchical topic modeling.
Generating Persuasive Responses to Customer Reviews with Multi-Source Prior Knowledge in E-commerce
A multi-aspect attentive network is proposed to automatically attend to different aspects in a review and ensure most of the issues are tackled.
Ordinal Graph Gamma Belief Network for Social Recommender Systems
To build recommender systems that not only consider user-item interactions represented as ordinal variables, but also exploit the social network describing the relationships between the users, we develop a hierarchical Bayesian model termed ordinal graph factor analysis (OGFA), which jointly models user-item and user-user interactions.
AGO-Net: Association-Guided 3D Point Cloud Object Detection Network
A feasible method is investigated to construct conceptual scenes without external datasets.
Task Aligned Meta-learning based Augmented Graph for Cold-Start Recommendation
In this paper, we propose a Task aligned Meta-learning based Augmented Graph (TMAG) to address cold-start recommendation.
Distributed Event-Triggered Nonlinear Fusion Estimation under Resource Constraints
This paper studies the event-triggered distributed fusion estimation problems for a class of nonlinear networked multisensor fusion systems without noise statistical characteristics.
Distributed Estimation for Interconnected Systems with Arbitrary Coupling Structures
By merging these subsystem-level stability conditions and the optimization-based estimator gain design, the distributed, stable and optimal estimators are proposed.
A Comprehensive Survey on Automated Machine Learning for Recommendations
Deep recommender systems (DRS) are critical for current commercial online service providers, which address the issue of information overload by recommending items that are tailored to the user's interests and preferences.
Update Compression for Deep Neural Networks on the Edge
In this paper, we consider the scenario where retraining can be done on the server side based on a copy of the DNN model, with only the necessary data transmitted to the edge to update the deployed model.
Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings
This paper introduces a new topic-modeling framework where each document is viewed as a set of word embedding vectors and each topic is modeled as an embedding vector in the same embedding space.
Asynchronous Optimisation for Event-based Visual Odometry
Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range.
Motion-aware Dynamic Graph Neural Network for Video Compressive Sensing
Video snapshot compressive imaging (SCI) utilizes a 2D detector to capture sequential video frames and compress them into a single measurement.
Neural Re-ranking in Multi-stage Recommender Systems: A Review
As the final stage of the multi-stage recommender system (MRS), re-ranking directly affects user experience and satisfaction by rearranging the input ranking lists, and thereby plays a critical role in MRS. With the advances in deep learning, neural re-ranking has become a trending topic and been widely applied in industrial applications.
Binary Neural Networks as a general-propose compute paradigm for on-device computer vision
For binary neural networks (BNNs) to become the mainstream on-device computer vision algorithm, they must achieve a superior speed-vs-accuracy tradeoff than 8-bit quantization and establish a similar degree of general applicability in vision tasks.
A Variational Edge Partition Model for Supervised Graph Representation Learning
This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities, each of which contributes to the edges via a logical OR mechanism.
Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector
In fact, advanced EO satellites perform deep learning-based cloud detection on board the satellites and downlink only clear-sky data to save precious bandwidth.
MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction
With the help of two novel CNN-based multi-interest extractors, self-supervision signals are discovered with full considerations of different interest representations (point-wise and union-wise), interest dependencies (short-range and long-range), and interest correlations (inter-item and intra-item).
AIM: Automatic Interaction Machine for Click-Through Rate Prediction
To address these three issues mentioned above, we propose Automatic Interaction Machine (AIM) with three core components, namely, Feature Interaction Search (FIS), Interaction Function Search (IFS) and Embedding Dimension Search (EDS), to select significant feature interactions, appropriate interaction functions and necessary embedding dimensions automatically in a unified framework.
Enhancing Explicit and Implicit Feature Interactions via Information Sharing for Parallel Deep CTR Models
The state-of-the-art deep CTR models with parallel structure (e. g., DCN) learn explicit and implicit feature interactions through independent parallel networks.
Kalman-Like Filter under Binary Sensors
When considering linear dynamic systems, a conservative estimation error covariance with adjustable parameters is constructed by matrix inequality, and then an optimal filter gain is derived by minimizing its trace.
TopicNet: Semantic Graph-Guided Topic Discovery
Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy.
Occlusion-Robust Object Pose Estimation with Holistic Representation
State-of-the-art (SOTA) object pose estimators take a two-stage approach, where the first stage predicts 2D landmarks using a deep network and the second stage solves for 6DOF pose from 2D-3D correspondences.
Ranked #2 on
6D Pose Estimation using RGB
on YCB-Video
A Prototype-Oriented Framework for Unsupervised Domain Adaptation
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space.
Enhanced Sequential Covariance Intersection Fusion
For this criterion, it is proved that the fusion results are not affected by the fusion structure, and thus the fusion performance can be guaranteed.
Edge Partition Modulated Graph Convolutional Networks
In this paper, we introduce a relational graph generative process to model how the observed edges are generated by aggregating the node interactions over multiple overlapping node communities, each of which represents a particular type of relation that contributes to the edges via a logical OR mechanism.
Crossformer: Transformer with Alternated Cross-Layer Guidance
Crossformer with states sharing not only provides the desired cross-layer guidance and regularization but also reduces the memory requirement.
Extracting Attentive Social Temporal Excitation for Sequential Recommendation
In this paper, we propose a novel time-aware sequential recommendation framework called Social Temporal Excitation Networks (STEN), which introduces temporal point processes to model the fine-grained impact of friends' behaviors on the user s dynamic interests in an event-level direct paradigm.
Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network
In this paper, we propose an optical flow-aided recurrent neural network for dual video SCI systems, which provides high-quality decoding in seconds.
Physical Adversarial Attacks on an Aerial Imagery Object Detector
In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images.
Graph Contrastive Learning for Anomaly Detection
To achieve the contrastive objective, we design a graph neural network encoder that can infer and further remove suspicious links during message passing, as well as learn the global context of the input graph.
Practical Challenges in Real-time Demand Response
We report on a real-time demand response experiment with 100 controllable devices.
EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering
As a result, the backbone learns the shared knowledge among all clusters while modulated weights extract the cluster-specific features.
Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervision
In this paper, we propose a new framework for unsupervised MRC.
Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network
However, they often assume in the prior that the topics at each layer are independently drawn from the Dirichlet distribution, ignoring the dependencies between the topics both at the same layer and across different layers.
A Spacecraft Dataset for Detection, Segmentation and Parts Recognition
We also provide evaluations with state-of-the-art methods in object detection and instance segmentation as a benchmark for the dataset.
From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding
During synchronous decoding: the utterance paraphrasing is constrained by the structure of the logical form, therefore the canonical utterance can be paraphrased controlledly; the semantic decoding is guided by the semantics of the canonical utterance, therefore its logical form can be generated unsupervisedly.
Bayesian Attention Belief Networks
Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks.
Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning
Inspired by recent successes in integrating semantic topics into this task, this paper develops a plug-and-play hierarchical-topic-guided image paragraph generation framework, which couples a visual extractor with a deep topic model to guide the learning of a language model.
Wide-Beam Array Antenna Power Gain Maximization via ADMM Framework
This paper proposes two algorithms to maximize the minimum array power gain in a wide-beam mainlobe by solving the power gain pattern synthesis (PGPS) problem with and without sidelobe constraints.
Memory-Efficient Network for Large-scale Video Compressive Sensing
With the knowledge of masks, optimization algorithms or deep learning methods are employed to reconstruct the desired high-speed video frames from this snapshot measurement.
MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing
To capture high-speed videos using a two-dimensional detector, video snapshot compressive imaging (SCI) is a promising system, where the video frames are coded by different masks and then compressed to a snapshot measurement.
Privacy-Preserving Kickstarting Deep Reinforcement Learning with Privacy-Aware Learners
We then develop a kickstarted deep reinforcement learning algorithm for the student that is privacy-aware because we calibrate its objective with the parameters of the teacher's privacy mechanism.
Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation
Experiments show that: (1) Our knowledge-to-text framework is effective and achieves state-of-the-art performance on CommonsenseQA dataset, providing a simple and strong knowledge-enhanced baseline for CQA; (2) The potential of knowledge is still far from being fully exploited in CQA -- there is a significant performance gap from current models to our models with golden knowledge; and (3) Context-sensitive knowledge selection, heterogeneous knowledge exploitation, and commonsense-rich language models are promising CQA directions.
Topic-aware Contextualized Transformers
Moving beyond conventional Transformers that ignore longer-range word dependencies and contextualize their word representations at the segment level, the proposed method not only captures global semantic coherence of all segments and global word concurrence patterns, but also enriches the representation of each token by adapting it to its local context, which is not limited to the segment it resides in and can be flexibly defined according to the task.
An Embedding Learning Framework for Numerical Features in CTR Prediction
In this paper, we propose a novel embedding learning framework for numerical features in CTR prediction (AutoDis) with high model capacity, end-to-end training and unique representation properties preserved.
CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking
In this paper, we propose CODE, which first pre-trains an expert linking model by contrastive learning on AMiner such that it can capture the representation and matching patterns of experts without supervised signals, then it is fine-tuned between AMiner and external sources to enhance the models transferability in an adversarial manner.
Bidirectional Convolutional Poisson Gamma Dynamical Systems
Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but also sentence-level stochastic temporal transitions.
Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network
To analyze a collection of interconnected documents, relational topic models (RTMs) have been developed to describe both the link structure and document content, exploring their underlying relationships via a single-layer latent representation with limited expressive capability.
Bayesian Attention Modules
Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability.
Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
On the contrary, the recent advances of deep learning promote neural reasoning on knowledge graphs, which is robust to the ambiguous and noisy data, but lacks interpretability compared to symbolic reasoning.
Variational Temporal Deep Generative Model for Radar HRRP Target Recognition
We develop a recurrent gamma belief network (rGBN) for radar automatic target recognition (RATR) based on high-resolution range profile (HRRP), which characterizes the temporal dependence across the range cells of HRRP.
Can weight sharing outperform random architecture search? An investigation with TuNAS
Efficient Neural Architecture Search methods based on weight sharing have shown good promise in democratizing Neural Architecture Search for computer vision models.
Optimizing Voting Order on Sequential Juries: A Median Voter Theorem and Beyond
Each juror has an ability in [0, 1], which is proportional to the probability of A given a positive signal, an analog of Condorcet's p for binary signals.
Deep Autoencoding Topic Model with Scalable Hybrid Bayesian Inference
Given a posterior sample of the global parameters, in order to efficiently infer the local latent representations of a document under DATM across all stochastic layers, we propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a Weibull distribution based stochastic downward generative model.
Comparison and Benchmark of Graph Clustering Algorithms
Graph clustering is widely used in analysis of biological networks, social networks and etc.
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
By incorporating regular convolutions in the search space and directly optimizing the network architectures for object detection, we obtain a family of object detection models, MobileDets, that achieve state-of-the-art results across mobile accelerators.
Topological Sweep for Multi-Target Detection of Geostationary Space Objects
In this paper, we propose a novel multi-target detection technique based on topological sweep, to find GEO objects from a short sequence of optical images.
Robust Synthesis of Wind Turbine Generators to Support Microgrid Frequency Considering Linearization-Induced Uncertainty
The capability to switch between grid-connected and islanded modes has promoted adoption of microgrid technology for powering remote locations.
Global weak solutions for Landau-Lifshitz flows and heat flows associated to micromagnetic energy functional
We follow the idea of Wang \cite{W} to show the existence of global weak solutions to the Cauchy problems of Landau-Lifshtiz type equations and related heat flows from a $n$-dimensional Euclidean domain $\Om$ or a $n$-dimensional closed Riemannian manifold $M$ into a 2-dimensional unit sphere $\U^{2}$.
Analysis of PDEs
Recurrent Hierarchical Topic-Guided RNN for Language Generation
To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation.
MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
We propose MnasFPN, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models.
Ranked #237 on
Object Detection
on COCO test-dev
SCR-Graph: Spatial-Causal Relationships based Graph Reasoning Network for Human Action Prediction
In temporal dimension, we designed a knowledge graph based causal reasoning module and map the past actions to temporal causal features through Diffusion RNN.
Recurrent Hierarchical Topic-Guided Neural Language Models
To simultaneously capture syntax and semantics from a text corpus, we propose a new larger-context language model that extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation.
End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization
To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end.
Ranked #1 on
6D Pose Estimation using RGB
on LineMOD
(Accuracy metric)
Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement
We propose an approach to estimate the 6DOF pose of a satellite, relative to a canonical pose, from a single image.
KCAT: A Knowledge-Constraint Typing Annotation Tool
Fine-grained Entity Typing is a tough task which suffers from noise samples extracted from distant supervision.
Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling
For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework.
Convolutional Poisson Gamma Belief Network
For text analysis, one often resorts to a lossy representation that either completely ignores word order or embeds each word as a low-dimensional dense feature vector.
Searching for MobileNetV3
We achieve new state of the art results for mobile classification, detection and segmentation.
Ranked #9 on
Classification
on InDL
VHEGAN: Variational Hetero-Encoder Randomized GAN for Zero-Shot Learning
To extract and relate visual and linguistic concepts from images and textual descriptions for text-based zero-shot learning (ZSL), we develop variational hetero-encoder (VHE) that decodes text via a deep probabilisitic topic model, the variational posterior of whose local latent variables is encoded from an image via a Weibull distribution based inference network.
Low-Power Computer Vision: Status, Challenges, Opportunities
In addition to mobile phones, many autonomous systems rely on visual data for making decisions and some of these systems have limited energy (such as unmanned aerial vehicles also called drones and mobile robots).
Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering
Recently, distant supervision has gained great success on Fine-grained Entity Typing (FET).
Low Power Inference for On-Device Visual Recognition with a Quantization-Friendly Solution
The IEEE Low-Power Image Recognition Challenge (LPIRC) is an annual competition started in 2015 that encourages joint hardware and software solutions for computer vision systems with low latency and power.
Sentence Rewriting for Semantic Parsing
A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology.
Deep Poisson gamma dynamical systems
We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequentially observed multivariate count data, improving previously proposed models by not only mining deep hierarchical latent structure from the data, but also capturing both first-order and long-range temporal dependencies.
2018 Low-Power Image Recognition Challenge
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcomputing. ieee. org/lpirc) is an annual competition started in 2015.
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
This paper proposes a neural semantic parsing approach -- Sequence-to-Action, which models semantic parsing as an end-to-end semantic graph generation process.
Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing
Semantic parsers critically rely on accurate and high-coverage lexicons.
MnasNet: Platform-Aware Neural Architecture Search for Mobile
In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency.
Ranked #903 on
Image Classification
on ImageNet
Accurate Text-Enhanced Knowledge Graph Representation Learning
Previous representation learning techniques for knowledge graph representation usually represent the same entity or relation in different triples with the same representation, without considering the ambiguity of relations and entities.
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget.
WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling
To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and autoencoding variational Bayes.
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes.
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
We present MorphNet, an approach to automate the design of neural network structures.
Investigating the content and form of referring expressions in Mandarin: introducing the Mtuna corpus
East Asian languages are thought to handle reference differently from languages such as English, particularly in terms of the marking of definiteness and number.
Recognizing irregular entities in biomedical text via deep neural networks
We evaluate our models on two datasets for recognizing regular and irreg- ular biomedical entities.
Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to different latent factors and hidden layers.
Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation
Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output.
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
We present a class of efficient models called MobileNets for mobile and embedded vision applications.
Ranked #246 on
Object Detection
on COCO test-dev
(using extra training data)
Seeing into Darkness: Scotopic Visual Recognition
Images are formed by counting how many photons traveling from a given set of directions hit an image sensor during a given time interval.
Gamma Belief Networks
To infer multilayer deep representations of high-dimensional discrete and nonnegative real vectors, we propose an augmentable gamma belief network (GBN) that factorizes each of its hidden layers into the product of a sparse connection weight matrix and the nonnegative real hidden units of the next layer.
The Poisson Gamma Belief Network
Example results on text analysis illustrate interesting relationships between the width of the first layer and the inferred network structure, and demonstrate that the PGBN, whose hidden units are imposed with correlated gamma priors, can add more layers to increase its performance gains over Poisson factor analysis, given the same limit on the width of the first layer.
Learning Fine-grained Image Similarity with Deep Ranking
This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images. It has higher learning capability than models based on hand-crafted features.
Predicting response time and error rates in visual search
A model of human visual search is proposed.
On the Analysis of Multi-Channel Neural Spike Data
Nonparametric Bayesian methods are developed for analysis of multi-channel spike-train data, with the feature learning and spike sorting performed jointly.
