Search Results for author:
Found 44 papers, 13 papers with code
Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
We finally introduce a scalable preference data construction strategy that consistently enhances model performance as the sample scale increases.
Decoder-Only LLMs are Better Controllers for Diffusion Models
Groundbreaking advancements in text-to-image generation have recently been achieved with the emergence of diffusion models.
Reasoning based on symbolic and parametric knowledge bases: a survey
Then, we provide a comprehensive overview of reasoning methods using symbolic knowledge bases, parametric knowledge bases, and both of them.
Early Dementia Detection Using Multiple Spontaneous Speech Prompts: The PROCESS Challenge
Dementia is associated with various cognitive impairments and typically manifests only after significant progression, making intervention at this stage often ineffective.
General Geospatial Inference with a Population Dynamics Foundation Model
To address this, we introduce a Population Dynamics Foundation Model (PDFM) that aims to capture the relationships between diverse data modalities and is applicable to a broad range of geospatial tasks.
MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems.
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
To further enhance the robustness of DBP models, we introduce Adversarial Denoising Diffusion Training (ADDT), which incorporates classifier-guided adversarial perturbations into diffusion training, thereby strengthening the DBP models' ability to purify adversarial perturbations.
Region-Based Representations Revisited
We investigate whether region-based representations are effective for recognition.
Efficiently Visualizing Large Graphs
Performing SPLEE to obtain a high-dimensional embedding of the large-scale graph and then using t-SGNE to reduce its dimension for visualization, we are able to visualize graphs with up to 300K nodes and 1M edges within 5 minutes and achieve approximately 10% improvement in visualization quality.
Decomposed Prompt Tuning via Low-Rank Reparameterization
While prompt tuning approaches have achieved competitive performance with high efficiency, we observe that they invariably employ the same initialization process, wherein the soft prompt is either randomly initialized or derived from an existing embedding vocabulary.
DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.
SPM: Structured Pretraining and Matching Architectures for Relevance Modeling in Meituan Search
At pretraining stage, we propose an effective pretraining method that employs both query and multiple fields of document as inputs, including an effective information compression method for lengthy fields.
Continual Learning in Open-vocabulary Classification with Complementary Memory Systems
We introduce a method for flexible and efficient continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in human cognition.
Masked Images Are Counterfactual Samples for Robust Fine-tuning
In this paper, based on causal analysis of the aforementioned problems, we propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
Sequential edge detection using joint hierarchical Bayesian learning
This paper introduces a new sparse Bayesian learning (SBL) algorithm that jointly recovers a temporal sequence of edge maps from noisy and under-sampled Fourier data.
Determinate Node Selection for Semi-supervised Classification Oriented Graph Convolutional Networks
Graph Convolutional Networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data.
Semi-supervised Learning with Deterministic Labeling and Large Margin Projection
Optimal leading forest (OLF) has been observed to have the advantage of revealing the difference evolution along a path within a subtree.
Contributions of Shape, Texture, and Color in Visual Recognition
We use human experiments to confirm that both HVE and humans predominantly use some specific features to support the classification of specific classes (e. g., texture is the dominant feature to distinguish a zebra from other quadrupeds, both for humans and HVE).
Contrastive Information Transfer for Pre-Ranking Systems
In this paper, we focus on the information transfer from ranking to pre-ranking stage.
PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch
Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images.
Sequential image recovery using joint hierarchical Bayesian learning
We specifically consider the case where each data set is missing vital information, which prevents the accurate recovery of the individual images.
Automated WBRT Treatment Planning via Deep Learning Auto-Contouring and Customizable Landmark-Based Field Aperture Design
In this work, we developed and evaluated a novel pipeline consisting of two landmark-based field aperture generation approaches for WBRT treatment planning; they are fully automated and customizable.
Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction
However, the retrieval-based methods are sub-optimal and would cause more or less information losses, and it's difficult to balance the effectiveness and efficiency of the retrieval algorithm.
AutoFAS: Automatic Feature and Architecture Selection for Pre-Ranking System
Industrial search and recommendation systems mostly follow the classic multi-stage information retrieval paradigm: matching, pre-ranking, ranking, and re-ranking stages.
End-to-end Mapping in Heterogeneous Systems Using Graph Representation Learning
To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of high-level programs down to the universal intermediate representation, extracting the specific computational patterns and predicting which code segments would run best on a specific core in heterogeneous hardware platforms.
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization
(2) They lack convexity constraints, which is important for meaningfully manipulating specific attributes for downstream tasks.
Towards Generic Interface for Human-Neural Network Knowledge Exchange
Take image classification as an example, HNI visualizes the reasoning logic of a NN with class-specific Structural Concept Graphs (c-SCG), which are human-interpretable.
ASGARD: A Single-cell Guided pipeline to Aid Repurposing of Drugs
Intercellular heterogeneity is a major obstacle to successful precision medicine.
Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction
Dialogue-based relation extraction (DiaRE) aims to detect the structural information from unstructured utterances in dialogues.
Interventional Video Grounding with Dual Contrastive Learning
2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.
EMface: Detecting Hard Faces by Exploring Receptive Field Pyraminds
Modern face detectors employ feature pyramids to deal with scale variation.
A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts
Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability.
Generative Auto-Encoder: Non-adversarial Controllable Synthesis with Disentangled Exploration
DEAE can become a generative model and synthesis semantic controllable samples by interpolating latent code, which can even synthesis novel attribute value never is shown in the original dataset.
Robust Autonomous Landing of UAV in Non-Cooperative Environments based on Dynamic Time Camera-LiDAR Fusion
We have conducted extensive autonomous landing experiments in a variety of familiar or completely unknown environments, verifying that our model can adaptively balance the accuracy and speed, and the UAV can robustly select a safe landing site.
Enhance Gender and Identity Preservation in Face Aging Simulation for Infants and Toddlers
We trained our model using the publicly available UTKFace dataset and evaluated our model by simulating up to 100 years of aging on 1, 156 male and 1, 207 female infant and toddler face photos.
Batch Sequential Adaptive Designs for Global Optimization
The computation burden of the new method is much lighter, and the points clustering is also avoided.
A Vertex Cut based Framework for Load Balancing and Parallelism Optimization in Multi-core Systems
High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems. The rapid increase in the consumption of memory and computational resources by these models demands the use of multi-core parallel systems to scale the execution of the complex emerging applications that depend on them.
Template-Instance Loss for Offline Handwritten Chinese Character Recognition
The long-standing challenges for offline handwritten Chinese character recognition (HCCR) are twofold: Chinese characters can be very diverse and complicated while similarly looking, and cursive handwriting (due to increased writing speed and infrequent pen lifting) makes strokes and even characters connected together in a flowing manner.
Vehicle Detection in Deep Learning
Computer vision is developing rapidly with the support of deep learning techniques.
A Supervised STDP-based Training Algorithm for Living Neural Networks
Neural networks have shown great potential in many applications like speech recognition, drug discovery, image classification, and object detection.
Complexity-Adaptive Distance Metric for Object Proposals Generation
Distance metric plays a key role in grouping superpixels to produce object proposals for object detection.
1-HKUST: Object Detection in ILSVRC 2014
We participated in the object detection track of ILSVRC 2014 and received the fourth place among the 38 teams.
Shadow Removal from Single RGB-D Images
We present the first automatic method to remove shadows from single RGB-D images.
