Search Results for author:
Found 27 papers, 23 papers with code
KC-ISA: An Implicit Sentiment Analysis Model Combining Knowledge Enhancement and Context Features
Moreover, to verify the generality of the model, we also conduct experiments on two common sentiment analysis datasets.
HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
The remarkable success of the autoregressive paradigm has made significant advancement in Multimodal Large Language Models (MLLMs), with powerful models like Show-o, Transfusion and Emu3 achieving notable progress in unified image understanding and generation.
No More Adam: Learning Rate Scaling at Initialization is All You Need
By adjusting learning rates without relying on adaptive second-order momentum, SGD-SaI helps prevent training imbalances from the very first iteration and cuts the optimizer's memory usage by half compared to AdamW.
GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning
Also, we evaluate how taxonomy prediction can boost other three function prediction tasks by MTL.
EditWorld: Simulating World Dynamics for Instruction-Following Image Editing
Therefore, this work, EditWorld, introduces a new editing task, namely world-instructed image editing, which defines and categorizes the instructions grounded by various world scenarios.
ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training
We propose ProtLLM, a versatile cross-modal large language model (LLM) for both protein-centric and protein-language tasks.
A Systematic Study of Joint Representation Learning on Protein Sequences and Structures
Recent sequence representation learning methods based on Protein Language Models (PLMs) excel in sequence-based tasks, but their direct adaptation to tasks involving protein structures remains a challenge.
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
On downstream tasks, ProtST enables both supervised learning and zero-shot prediction.
Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction
Considering the essential protein conformational variations, we enhance DiffPreT by a method called Siamese Diffusion Trajectory Prediction (SiamDiff) to capture the correlation between different conformers of a protein.
EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data
We study EurNets in two important domains for image and protein structure modeling.
PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding
However, there is a lack of a standard benchmark to evaluate the performance of different methods, which hinders the progress of deep learning in this field.
HIRL: A General Framework for Hierarchical Image Representation Learning
This framework aims to learn multiple semantic representations for each image, and these representations are structured to encode image semantics from fine-grained to coarse-grained.
Spotlights: Probing Shapes from Spherical Viewpoints
Recent years have witnessed the surge of learned representations that directly build upon point clouds.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Protein Representation Learning by Geometric Structure Pretraining
Despite the effectiveness of sequence-based approaches, the power of pretraining on known protein structures, which are available in smaller numbers only, has not been explored for protein property prediction, though protein structures are known to be determinants of protein function.
TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery
However, lacking domain knowledge (e. g., which tasks to work on), standard benchmarks and data preprocessing pipelines are the main obstacles for machine learning researchers to work in this domain.
HCSC: Hierarchical Contrastive Selective Coding
In this framework, a set of hierarchical prototypes are constructed and also dynamically updated to represent the hierarchical semantic structures underlying the data in the latent space.
Joint Modeling of Visual Objects and Relations for Scene Graph Generation
We further propose an efficient and effective algorithm for inference based on mean-field variational inference, in which we first provide a warm initialization by independently predicting the objects and their relations according to the current model, followed by a few iterations of relational reasoning.
Cross-category Video Highlight Detection via Set-based Learning
For tackling such practical problem, we propose a Dual-Learner-based Video Highlight Detection (DL-VHD) framework.
PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation
Extensive experiments demonstrate that our method can soundly boost the performance on both cross-domain object detection and segmentation for state-of-the-art techniques.
Self-supervised Graph-level Representation Learning with Local and Global Structure
This paper studies unsupervised/self-supervised whole-graph representation learning, which is critical in many tasks such as molecule properties prediction in drug and material discovery.
Graphical Modeling for Multi-Source Domain Adaptation
Multi-Source Domain Adaptation (MSDA) focuses on transferring the knowledge from multiple source domains to the target domain, which is a more practical and challenging problem compared to the conventional single-source domain adaptation.
GraphSAD: Learning Graph Representations with Structure-Attribute Disentanglement
We propose to disentangle graph structure and node attributes into two distinct sets of representations, and such disentanglement can be done in either the input or the embedding space.
Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
Transferring knowledges learned from multiple source domains to target domain is a more practical and challenging task than conventional single-source domain adaptation.
Domain Adaptation
Multi-Source Unsupervised Domain Adaptation
Cross-domain Detection via Graph-induced Prototype Alignment
To mitigate these problems, we propose a Graph-induced Prototype Alignment (GPA) framework to seek for category-level domain alignment via elaborate prototype representations.
Adversarial Domain Adaptation with Domain Mixup
In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains.
Learning Context Graph for Person Search
Person re-identification has achieved great progress with deep convolutional neural networks.
