Search Results for author:
Found 50 papers, 24 papers with code
SkyLadder: Better and Faster Pretraining via Context Window Scheduling
Recent advancements in LLM pretraining have featured ever-expanding context windows to process longer sequences.
Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction
Decoding visual stimuli from neural activity is essential for understanding the human brain.
Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow
In this work, we propose a novel common spatiotemporal fusion between frame and event modalities for high-dynamic scene optical flow, including visual boundary localization and motion correlation fusion.
LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification
Despite its promise, the effective application of speculative decoding in LLMs still confronts three key challenges: the increasing memory demands of the draft model, the distribution shift between the short-training corpora and long-context inference, and inefficiencies in attention implementation.
DataLab: A Unified Platform for LLM-Powered Business Intelligence
To achieve this unification, we design a domain knowledge incorporation module tailored for enterprise-specific BI tasks, an inter-agent communication mechanism to facilitate information sharing across the BI workflow, and a cell-based context management strategy to enhance context utilization efficiency in BI notebooks.
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
To address this, we develop AnchorAttention, a plug-and-play attention method that alleviates numerical issues caused by BFloat16, improves long-context capabilities, and speeds up training.
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.
Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks
To mimic the behavior of doctors, who typically begin by reviewing the entire image before concentrating on specific regions for a thorough evaluation, we aim to enhance the capability of medical MLLMs in understanding anatomical regions within entire medical scans.
Multi-Channel Factor Analysis: Identifiability and Asymptotics
The development of these identifiability conditions enables asymptotic analysis of estimators obtained by maximizing a Gaussian likelihood, which are shown to be consistent and asymptotically normal even under misspecification of the latent factor distribution.
GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation
Efficient human pose estimation remains a hurdle, especially for whole-body pose estimation with numerous keypoints.
S&D Messenger: Exchanging Semantic and Domain Knowledge for Generic Semi-Supervised Medical Image Segmentation
Semi-supervised medical image segmentation (SSMIS) has emerged as a promising solution to tackle the challenges of time-consuming manual labeling in the medical field.
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems.
ADLDA: A Method to Reduce the Harm of Data Distribution Shift in Data Augmentation
This study introduces a novel data augmentation technique, ADLDA, aimed at mitigating the negative impact of data distribution shifts caused by the data augmentation process in computer vision task.
Research on geometric figure classification algorithm based on Deep Learning
In recent years, with the rapid development of computer information technology, the development of artificial intelligence has been accelerating.
Towards Better Text-to-Image Generation Alignment via Attention Modulation
To achieve this, we incorporate a temperature control mechanism within the early phases of the self-attention modules to mitigate entity leakage issues.
AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
We further introduce a Semantic Memory along with a Channel Semantic Grouping strategy to ensure that unlabeled features adequately represent labeled features.
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
Our method strategically embeds connections between pieces of copyrighted information and text references in poisoning data while carefully dispersing that information, making the poisoning data inconspicuous when integrated into a clean dataset.
Can AI Be as Creative as Humans?
With the rise of advanced generative AI models capable of tasks once reserved for human creativity, the study of AI's creative potential becomes imperative for its responsible development and application.
Narrowing the semantic gaps in U-Net with learnable skip connections: The case of medical image segmentation
Hence, both modules establish a learnable connection to solve the semantic gaps between the encoder and the decoder, which leads to a high-performance segmentation model for medical images.
Efficient Dataset Distillation via Minimax Diffusion
Observing that key factors for constructing an effective surrogate dataset are representativeness and diversity, we design additional minimax criteria in the generative training to enhance these facets for the generated images of diffusion models.
Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation
As a result, there is growing interest in using semi-supervised learning (SSL) techniques to train models with limited labeled data.
Model-enhanced Vector Index
We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.
On Copyright Risks of Text-to-Image Diffusion Models
Specifically, we introduce a data generation pipeline to systematically produce data for studying copyright in diffusion models.
Lightweight Super-Resolution Head for Human Pose Estimation
We first propose the SR head, which predicts heatmaps with a spatial resolution higher than the input feature maps (or even consistent with the input image) by super-resolution, to effectively reduce the quantization error and the dependence on further post-processing.
DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation
Aiming to solve this issue, we present a novel Dual-debiased Heterogeneous Co-training (DHC) framework for semi-supervised 3D medical image segmentation.
Subclass-balancing Contrastive Learning for Long-tailed Recognition
We overcome these drawbacks by a novel ``subclass-balancing contrastive learning (SBCL)'' approach that clusters each head class into multiple subclasses of similar sizes as the tail classes and enforce representations to capture the two-layer class hierarchy between the original classes and their subclasses.
Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective
Graph neural networks (GNNs) have pioneered advancements in graph representation learning, exhibiting superior feature learning and performance over multilayer perceptrons (MLPs) when handling graph inputs.
Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce
An effective ranking model should give a personalized ranking list for each user according to the user preference.
Dynamic Data Augmentation via MCTS for Prostate MRI Segmentation
However, manually configuring a generic augmentation combination and parameters for different datasets is non-trivial due to inconsistent acquisition approaches and data distributions.
Boosting Visual-Language Models by Exploiting Hard Samples
In this work, we present HELIP, a cost-effective strategy tailored to enhance the performance of existing CLIP models without the need for training a model from scratch or collecting additional data.
Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
In this paper, we propose a novel module to explicitly extract motion and appearance information via a unifying operation.
Ranked #1 on
Video Frame Interpolation
on UCF101
Artificial Intelligence Security Competition (AISC)
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems.
Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph
To answer this question, we theoretically study the concentration property of features obtained by neighborhood aggregation on homophilic and heterophilic graphs, introduce the single-pass augmentation-free graph contrastive learning loss based on the property, and provide performance guarantees for the minimizer of the loss on downstream tasks.
BEBERT: Efficient and Robust Binary Ensemble BERT
Pre-trained BERT models have achieved impressive accuracy on natural language processing (NLP) tasks.
Understanding Programmatic Weak Supervision via Source-aware Influence Function
Programmatic Weak Supervision (PWS) aggregates the source votes of multiple weak supervision sources into probabilistic training labels, which are in turn used to train an end model.
Augmentation-Free Graph Contrastive Learning with Performance Guarantee
Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data.
FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes
Most fair machine learning methods either highly rely on the sensitive information of the training samples or require a large modification on the target models, which hinders their practical application.
From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems
With the prevalence of deep learning based embedding approaches, recommender systems have become a proven and indispensable tool in various information filtering applications.
Deep Active Learning by Leveraging Training Dynamics
Active learning theories and methods have been extensively studied in classical statistical learning settings.
UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer
Specifically, the CTrans module is an alternate of the U-Net skip connections, which consists of a sub-module to conduct the multi-scale Channel Cross fusion with Transformer (named CCT) and a sub-module Channel-wise Cross-Attention (named CCA) to guide the fused multi-scale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity.
Ranked #3 on
Medical Image Segmentation
on GlaS
Controllable Gradient Item Retrieval
A better way is to present a sequence of products with increasingly floral attributes based on the white dress, and allow the customer to select the most satisfactory one from the sequence.
Adversarial Data Generation of Multi-category Marked Temporal Point Processes with Sparse, Incomplete, and Small Training Samples
The transformation of training data to the distribution facilitates the accurate capture of underlying process characteristics despite the sparseness and incompleteness of data.
Secure Network Release with Link Privacy
Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).
Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
Graph neural networks (GNNs) have achieved superior performance in various applications, but training dedicated GNNs can be costly for large-scale graphs.
Secure Deep Graph Generation with Link Differential Privacy
Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).
Park: An Open Platform for Learning-Augmented Computer Systems
We present Park, a platform for researchers to experiment with Reinforcement Learning (RL) for computer systems.
Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders
While node semantics have been extensively explored in social networks, little research attention has been paid to profile edge semantics, i. e., social relations.
Learning to Transfer via Modelling Multi-level Task Dependency
Besides, the understanding of relationships among tasks has been ignored by most of the current methods.
Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm
Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability.
