Search Results for author:
Found 68 papers, 23 papers with code
Using Natural Sentence Prompts for Understanding Biases in Language Models
Evaluation of biases in language models is often limited to synthetically generated datasets.
NSP-BERT: A Prompt-based Few-Shot Learner through an Original Pre-training Task —— Next Sentence Prediction
Using prompts to utilize language models to perform various downstream tasks, also known as prompt-based learning or prompt-learning, has lately gained significant success in comparison to the pre-train and fine-tune paradigm.
Improving Relevance Quality in Product Search using High-Precision Query-Product Semantic Similarity
Ensuring relevance quality in product search is a critical task as it impacts the customer’s ability to find intended products in the short-term as well as the general perception and trust of the e-commerce system in the long term.
Spelling Correction using Phonetics in E-commerce Search
In E-commerce search, spelling correction plays an important role to find desired products for customers in processing user-typed search queries.
Automated Detection of Epileptic Spikes and Seizures Incorporating a Novel Spatial Clustering Prior
A Magnetoencephalography (MEG) time-series recording consists of multi-channel signals collected by superconducting sensors, with each signal's intensity reflecting magnetic field changes over time at the sensor location.
ChainStream: An LLM-based Framework for Unified Synthetic Sensing
Many applications demand context sensing to offer personalized and timely services.
LV-CadeNet: Long View Feature Convolution-Attention Fusion Encoder-Decoder Network for Clinical MEG Spike Detection
This dataset, characterized by a highly imbalanced distribution of positive and negative samples, accurately represents real-world clinical scenarios.
CoActionGraphRec: Sequential Multi-Interest Recommendations Using Co-Action Graphs
For the Item Tower, we represent each item using its co-action items to capture collaborative signals in a co-action graph that is fully leveraged by the graph neural network component.
The Family of LML Detectors and the Family of LAS Detectors for Massive MIMO Communications
It is proved that a large MIMO channel possesses the LML characteristic, implying and predicting that a local search detector with likelihood ascent, like a wide-sense sequential LAS (WSLAS) detector, can approach the GML detection.
Human-like object concept representations emerge naturally in multimodal large language models
The conceptualization and categorization of natural objects in the human mind have long intrigued cognitive scientists and neuroscientists, offering crucial insights into human perception and cognition.
On the estimation rate of Bayesian PINN for inverse problems
We show that when the partial differential equation admits a classical solution (say $u_\star$), differentiable to order $\beta$, the mean square error of the Bayesian posterior mean is at least of order $n^{-2\beta/(2\beta + d)}$.
Transparent Object Depth Completion
The perception of transparent objects for grasp and manipulation remains a major challenge, because existing robotic grasp methods which heavily rely on depth maps are not suitable for transparent objects due to their unique visual properties.
The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio
With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an urgent need for generalized detection methods.
Trainable Joint Channel Estimation, Detection and Decoding for MIMO URLLC Systems
The receiver design for multi-input multi-output (MIMO) ultra-reliable and low-latency communication (URLLC) systems can be a tough task due to the use of short channel codes and few pilot symbols.
Trustless Audits without Revealing Data or Models
In this work, we show that it is possible to simultaneously allow model providers to keep their model weights (but not architecture) and data secret while allowing other parties to trustlessly audit model and data properties.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Must: Maximizing Latent Capacity of Spatial Transcriptomics Data
MuST integrates the multi-modality information contained in the ST data effectively into a uniform latent space to provide a foundation for all the downstream tasks.
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.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Visual Question Answering (VQA)
on InfographicVQA
Continual Learning through Networks Splitting and Merging with Dreaming-Meta-Weighted Model Fusion
Differently, we propose a continual learning method named Split2MetaFusion which can achieve better trade-off by employing a two-stage strategy: splitting and meta-weighted fusion.
Generating a Map of Well-being Regions using Multiscale Moving Direction Entropy on Mobile Sensors
The well-being of individuals in a crowd is interpreted as a product of the crossover of individuals from heterogeneous communities, which may occur via interactions with other crowds.
Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments
Online learning to rank (ONL2R) is a foundational problem for recommender systems and has received increasing attention in recent years.
Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints
Unlike cloud-based deep learning models that are often large and uniform, edge-deployed models usually demand customization for domain-specific tasks and resource-limited environments.
Learning multi-domain feature relation for visible and Long-wave Infrared image patch matching
Recently, learning-based algorithms have achieved promising performance on cross-spectral image patch matching, which, however, is still far from satisfactory for practical application.
Robust MIMO Detection With Imperfect CSI: A Neural Network Solution
Furthermore, a robust detection network RADMMNet is constructed by unfolding the ADMM iterations and employing both model-driven and data-driven philosophies.
AdaSelection: Accelerating Deep Learning Training through Data Subsampling
In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance.
Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs
By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks.
Boundary-to-Solution Mapping for Groundwater Flows in a Toth Basin
In this paper, the authors propose a new approach to solving the groundwater flow equation in the Toth basin of arbitrary top and bottom topographies using deep learning.
Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis
Fashion representation learning involves the analysis and understanding of various visual elements at different granularities and the interactions among them.
FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Data
In this paper, we propose a new approach called fair recommendation with optimized antidote data (FairRoad), which aims to improve the fairness performances of recommender systems through the construction of a small and carefully crafted antidote dataset.
Artificial Intelligence Security Competition (AISC)
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems.
TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance
Grasp pose estimation is an important issue for robots to interact with the real world.
A microstructure estimation Transformer inspired by sparse representation for diffusion MRI
Thus, the METSC is composed with three stages, an embedding stage, a sparse representation stage, and a mapping stage.
Using Natural Sentences for Understanding Biases in Language Models
Evaluation of biases in language models is often limited to synthetically generated datasets.
CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification
In this paper, we propose the Cross-Modality Attention Contrastive Language-Image Pre-training (CMA-CLIP), a new framework which unifies two types of cross-modality attentions, sequence-wise attention and modality-wise attention, to effectively fuse information from image and text pairs.
Bandit Learning with Joint Effect of Incentivized Sampling, Delayed Sampling Feedback, and Self-Reinforcing User Preferences
We show that the delay impacts in both cases can still be upper bounded by an additive penalty on both the regret and total incentive costs.
MESSFN : a Multi-level and Enhanced Spectral-Spatial Fusion Network for Pan-sharpening
A novel Spectral-Spatial (SS) stream is established to hierarchically derive and fuse the multi-level prior spectral and spatial expertise from the MS stream and the PAN stream.
NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction
Using prompts to utilize language models to perform various downstream tasks, also known as prompt-based learning or prompt-learning, has lately gained significant success in comparison to the pre-train and fine-tune paradigm.
Ranked #4 on
Zero-Shot Text Classification
on AG News
Proof: Accelerating Approximate Aggregation Queries with Expensive Predicates
Given a dataset $\mathcal{D}$, we are interested in computing the mean of a subset of $\mathcal{D}$ which matches a predicate.
ICINet: ICI-Aware Neural Network Based Channel Estimation for Rapidly Time-Varying OFDM Systems
A novel intercarrier interference (ICI)-aware orthogonal frequency division multiplexing (OFDM) channel estimation network ICINet is presented for rapidly time-varying channels.
Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
Prior works on formalizing explanations of a graph neural network (GNN) focus on a single use case - to preserve the prediction results through identifying important edges and nodes.
Self-Supervised Transfer Learning for Hand Mesh Recovery From Binocular Images
Traditional methods for RGB hand mesh recovery usually need to train a separate model for each dataset with the corresponding ground truth and are hardly adapted to new scenarios without the ground truth for supervision.
Toward Human-Like Grasp: Dexterous Grasping via Semantic Representation of Object-Hand
We first build a dataset by accurately segmenting the functional areas of the object and annotating semantic touch code for each functional area to guide the dexterous hand to complete the functional grasp and post-grasp manipulation.
How Data Augmentation affects Optimization for Linear Regression
Our results apply to arbitrary augmentation schemes, revealing complex interactions between learning rates and augmentations even in the convex setting.
Data augmentation as stochastic optimization
We present a theoretical framework recasting data augmentation as stochastic optimization for a sequence of time-varying proxy losses.
Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings
In this paper, we intend to minimize the energy cost of an HVAC system in a multi-zone commercial building under dynamic pricing with the consideration of random zone occupancy, thermal comfort, and indoor air quality comfort.
Multi-objective Ranking via Constrained Optimization
In this paper, we introduce an Augmented Lagrangian based method to incorporate the multiple objectives (MO) in a search ranking algorithm.
Sem-LSD: A Learning-based Semantic Line Segment Detector
Combined with high-level semantics, Sem-LS is more robust under cluttered environment compared with existing line-shaped representations.
Evolving the Olfactory System
In this study, we address the optimality of evolutionary design in olfactory circuits by studying artificial neural networks trained to sense odors.
Testing Robustness Against Unforeseen Adversaries
To narrow in on this discrepancy between research and reality we introduce ImageNet-UA, a framework for evaluating model robustness against a range of unforeseen adversaries, including eighteen new non-L_p attacks.
Towards Reducing Biases in Combining Multiple Experts Online
In many real life situations, including job and loan applications, gatekeepers must make justified and fair real-time decisions about a person's fitness for a particular opportunity.
Transfer of Adversarial Robustness Between Perturbation Types
We study the transfer of adversarial robustness of deep neural networks between different perturbation types.
Learning Vine Copula Models For Synthetic Data Generation
Moreover, we demonstrate that the model is able to generate high-quality samples in a variety of applications, making it a good candidate for synthetic data generation.
Limited Gradient Descent: Learning With Noisy Labels
We modified the labels of a few samples in a noisy dataset to obtain false labels and to create a reverse pattern.
HBE: Hand Branch Ensemble Network for Real-time 3D Hand Pose Estimation
The structural design inspiration of the HBE network comes from the understanding of the differences in the functional importance of different fingers.
An automatic taxonomy of galaxy morphology using unsupervised machine learning
We then apply the technique to the HST CANDELS fields, creating a catalogue of approximately 60, 000 classifications.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies
Sparsifying Neural Network Connections for Face Recognition
This paper proposes to learn high-performance deep ConvNets with sparse neural connections, referred to as sparse ConvNets, for face recognition.
From random walks to distances on unweighted graphs
Using these techniques we generalize results on the degeneracy of hitting times and analyze a metric based on the Laplace transformed hitting time (LTHT).
DeepID3: Face Recognition with Very Deep Neural Networks
Very deep neural networks recently achieved great success on general object recognition because of their superb learning capacity.
Deeply learned face representations are sparse, selective, and robust
(2) Its neurons in higher layers are highly selective to identities and identity-related attributes.
Ranked #1 on
Face Verification
on Oulu-CASIA
Metric recovery from directed unweighted graphs
We demonstrate empirically that the estimator performs well on simulated examples as well as on real-world co-purchasing graphs even with a small number of points and degree scaling as low as $\log(n)$.
Deep Learning Face Representation by Joint Identification-Verification
The learned DeepID2 features can be well generalized to new identities unseen in the training data.
Deep Learning Face Representation from Predicting 10,000 Classes
When learned as classifiers to recognize about 10, 000 face identities in the training set and configured to keep reducing the neuron numbers along the feature extraction hierarchy, these deep ConvNets gradually form compact identity-related features in the top layers with only a small number of hidden neurons.
Deep Learning Face Representation from Predicting 10,000 Classes
When learned as classifiers to recognize about 10, 000 face identities in the training set and configured to keep reducing the neuron numbers along the feature extraction hierarchy, these deep ConvNets gradually form compact identity-related features in the top layers with only a small number of hidden neurons.
Ranked #6 on
Face Verification
on Labeled Faces in the Wild
Deep Convolutional Network Cascade for Facial Point Detection
At each level, the outputs of multiple networks are fused for robust and accurate estimation.
Natural Evolution Strategies
This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms.
Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices
We present a new way of converting a reversible finite Markov chain into a nonreversible one, with a theoretical guarantee that the asymptotic variance of the MCMC estimator based on the non-reversible chain is reduced.
