Search Results for author:
Found 32 papers, 11 papers with code
Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation
Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks.
External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system.
Enhancing Visual Inspection Capability of Multi-Modal Large Language Models on Medical Time Series with Supportive Conformalized and Interpretable Small Specialized Models
Large language models (LLMs) exhibit remarkable capabilities in visual inspection of medical time-series data, achieving proficiency comparable to human clinicians.
Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences
Since its introduction, the transformer has shifted the development trajectory away from traditional models (e. g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal tokens.
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit
The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy.
InterFormer: Towards Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction
A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction.
Enhancing Graph Neural Networks in Large-scale Traffic Incident Analysis with Concurrency Hypothesis
The extensive experiments, utilizing real-world data across states and cities in the USA, demonstrate that integrating CP into 12 state-of-the-art GNN architectures leads to significant improvements, with gains ranging from 3% to 13% in F1 score and 1. 3% to 9% in AUC metrics.
ERCache: An Efficient and Reliable Caching Framework for Large-Scale User Representations in Meta's Ads System
The increasing complexity of deep learning models used for calculating user representations presents significant challenges, particularly with limited computational resources and strict service-level agreements (SLAs).
Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Exploration
The high-level agent walks on the simplified knowledge graph to provide stage-wise hints for the low-level agent walking on the original knowledge graph.
TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC).
FLAME Diffuser: Wildfire Image Synthesis using Mask Guided Diffusion
Specifically, the fusion of Perlin noise in this work significantly improved the quality of synthesized images.
Enhancing Digital Hologram Reconstruction Using Reverse-Attention Loss for Untrained Physics-Driven Deep Learning Models with Uncertain Distance
Untrained Physics-based Deep Learning (DL) methods for digital holography have gained significant attention due to their benefits, such as not requiring an annotated training dataset, and providing interpretability since utilizing the governing laws of hologram formation.
LogicNet: A Logical Consistency Embedded Face Attribute Learning Network
We explore the potential reasons for this oversight and introduce two pressing challenges to the field: 1) How can we ensure that a model, when trained with data checked for logical consistency, yields predictions that are logically consistent?
PACOL: Poisoning Attacks Against Continual Learners
In this work, we demonstrate that continual learning systems can be manipulated by malicious misinformation and present a new category of data poisoning attacks specific for continual learners, which we refer to as {\em Poisoning Attacks Against Continual Learners} (PACOL).
Scaling User Modeling: Large-scale Online User Representations for Ads Personalization in Meta
To address these challenges, we present Scaling User Modeling (SUM), a framework widely deployed in Meta's ads ranking system, designed to facilitate efficient and scalable sharing of online user representation across hundreds of ads models.
AutoML for Large Capacity Modeling of Meta's Ranking Systems
The large scale of models and tight production schedule requires AutoML to outperform human baselines by only using a small number of model evaluation trials (around 100).
MTS-LOF: Medical Time-Series Representation Learning via Occlusion-Invariant Features
MTS-LOF leverages the strengths of contrastive learning and Masked Autoencoder (MAE) methods, offering a unique approach to representation learning for medical time series data.
Learning on Bandwidth Constrained Multi-Source Data with MIMO-inspired DPP MAP Inference
A determinant-preserved sparse representation of selected samples is used to perform sample precoding in local sources to be processed by DPP.
Knowledge Distillation Under Ideal Joint Classifier Assumption
Within this context, softmax regression representation learning serves as a widely embraced approach, leveraging a pre-established teacher network to guide the learning process of a diminutive student network.
RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples
However, the number of selected samples is restricted to the rank of the kernel matrix implied by the dimensionality of data samples.
A Transformer-based Diffusion Probabilistic Model for Heart Rate and Blood Pressure Forecasting in Intensive Care Unit
The TDSTF model showed state-of-the-art performance in predicting vital signs in the ICU, outperforming other models' ability to predict distributions of vital signs and being more computationally efficient.
Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs
Answering factual questions with temporal intent over knowledge graphs (temporal KGQA) attracts rising attention in recent years.
Ranked #1 on
Question Answering
on TempQuestions
DeScoD-ECG: Deep Score-Based Diffusion Model for ECG Baseline Wander and Noise Removal
Significance: This study is one of the first to extend the conditional diffusion-based generative model for ECG noise removal, and the DeScoD-ECG has the potential to be widely used in biomedical applications.
Ranked #2 on
ECG Denoising
on QT-NSTDB
DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction
To overcome the challenge brought by DHEN's deeper and multi-layer structure in training, we propose a novel co-designed training system that can further improve the training efficiency of DHEN.
Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review
This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated vehicles.
Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models
Deep learning recommendation models (DLRMs) are used across many business-critical services at Facebook and are the single largest AI application in terms of infrastructure demand in its data-centers.
Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention
We equip the SPA blocks on a network designed for real image denoising.
Deep DIH : Statistically Inferred Reconstruction of Digital In-Line Holography by Deep Learning
Recently, end-to-end deep learning-based methods have been utilized to reconstruct the object wavefront (as a surrogate for the 3D structure of the object) directly from a single-shot in-line digital hologram.
Channel Locality Block: A Variant of Squeeze-and-Excitation
In this paper, we proposed a variant of SE block based on channel locality.
Cognitive Consistency Routing Algorithm of Capsule-network
Artificial Neural Networks (ANNs) are computational models inspired by the central nervous system (especially the brain) of animals and are used to estimate or generate unknown approximation functions relied on large amounts of inputs.
A Context-aware Attention Network for Interactive Question Answering
Employing these attention mechanisms, our model accurately understands when it can output an answer or when it requires generating a supplementary question for additional input depending on different contexts.
Point-of-Interest Recommendations: Learning Potential Check-ins from Friends
The emergence of Location-based Social Network (LBSN) services provides a wonderful opportunity to build personalized Point-of-Interest (POI) recommender systems.
