Shikui Tu
YOU?
Author Swipe
View article: DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement Open
Relation extraction enables the construction of structured knowledge for many downstream applications. While large language models (LLMs) have shown great promise in this domain, most existing methods concentrate on relation classification…
View article: Spatiotemporal single-cell architecture of gene expression in the Caenorhabditis elegans germ cells
Spatiotemporal single-cell architecture of gene expression in the Caenorhabditis elegans germ cells Open
Spermatogenesis is an intricate and tightly controlled process encompassing various layers of gene expression regulation. Despite the advance of our current understanding, the developmental trajectory and regulatory mechanisms dictating sp…
View article: Argonaute CSR-1A promotes H3K9me3 maintenance to protect somatic development in offspring
Argonaute CSR-1A promotes H3K9me3 maintenance to protect somatic development in offspring Open
Parental stress can be encoded into altered epigenetic information to influence their offspring. Concurrently, it is vital for the preservation of a parent's epigenetic information, despite environmental challenges, to ensure accurate inhe…
View article: Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge
Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge Open
The effectiveness of model training heavily relies on the quality of available training resources. However, budget constraints often impose limitations on data collection efforts. To tackle this challenge, we introduce causal exploration i…
View article: Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations
Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations Open
General intelligence requires quick adaption across tasks. While existing reinforcement learning (RL) methods have made progress in generalization, they typically assume only distribution changes between source and target domains. In this …
View article: Parallel Belief Contraction via Order Aggregation
Parallel Belief Contraction via Order Aggregation Open
The standard ``serial'' (aka ``singleton'') model of belief contraction models the manner in which an agent's corpus of beliefs responds to the removal of a single item of information. One salient extension of this model introduces the ide…
View article: Not All Layers of LLMs Are Necessary During Inference
Not All Layers of LLMs Are Necessary During Inference Open
Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. However, not all requests posed to LLMs are equally difficult to handle. Through analysis, we show that for some tasks, LLMs …
View article: Multilevel Attention Network with Semi-supervised Domain Adaptation for Drug-Target Prediction
Multilevel Attention Network with Semi-supervised Domain Adaptation for Drug-Target Prediction Open
Prediction of drug-target interactions (DTIs) is a crucial step in drug discovery, and deep learning methods have shown great promise on various DTI datasets. However, existing approaches still face several challenges, including limited la…
View article: Efficient retrosynthetic planning with MCTS exploration enhanced A* search
Efficient retrosynthetic planning with MCTS exploration enhanced A* search Open
Retrosynthetic planning, which aims to identify synthetic pathways for target molecules from starting materials, is a fundamental problem in synthetic chemistry. Computer-aided retrosynthesis has made significant progress, in which heurist…
View article: A Deep Reinforcement Learning Approach for Portfolio Management in Non‐Short‐Selling Market
A Deep Reinforcement Learning Approach for Portfolio Management in Non‐Short‐Selling Market Open
Reinforcement learning (RL) has been applied to financial portfolio management in recent years. Current studies mostly focus on profit accumulation without much consideration of risk. Some risk‐return balanced studies extract features from…
View article: KGDiff: towards explainable target-aware molecule generation with knowledge guidance
KGDiff: towards explainable target-aware molecule generation with knowledge guidance Open
Designing 3D molecules with high binding affinity for specific protein targets is crucial in drug design. One challenge is that the atomic interaction between molecules and proteins in 3D space has to be taken into account. However, the ex…
View article: GLPocket: A Multi-Scale Representation Learning Approach for Protein Binding Site Prediction
GLPocket: A Multi-Scale Representation Learning Approach for Protein Binding Site Prediction Open
Protein binding site prediction is an important prerequisite for the discovery of new drugs. Usually, natural 3D U-Net is adopted as the standard site prediction framework to do per-voxel binary mask classification. However, this scheme on…
View article: PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editing
PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editing Open
Diffusion models have showcased their remarkable capability to synthesize diverse and high-quality images, sparking interest in their application for real image editing. However, existing diffusion-based approaches for local image editing …
View article: Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation
Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation Open
Graphic sketch representations are effective for representing sketches. Existing methods take the patches cropped from sketches as the graph nodes, and construct the edges based on sketch's drawing order or Euclidean distances on the canva…
View article: Self-Supervised Bidirectional Learning for Graph Matching
Self-Supervised Bidirectional Learning for Graph Matching Open
Deep learning methods have demonstrated promising performance on the NP-hard Graph Matching (GM) problems. However, the state-of-the-art methods usually require the ground-truth labels, which may take extensive human efforts or be impracti…
View article: Mammalian PIWI-piRNA-target complexes reveal features for broad and efficient target-silencing
Mammalian PIWI-piRNA-target complexes reveal features for broad and efficient target-silencing Open
The PIWI-interacting RNA (piRNA) pathway is an adaptive defense system wherein piRNAs guide PIWI-family Argonaute proteins to recognize and silence ever-evolving selfish genetic elements and ensure genome integrity. Driven by this intensiv…
View article: MGAE-DC: Predicting the synergistic effects of drug combinations through multi-channel graph autoencoders
MGAE-DC: Predicting the synergistic effects of drug combinations through multi-channel graph autoencoders Open
Accurate prediction of synergistic effects of drug combinations can reduce the experimental costs for drug development and facilitate the discovery of novel efficacious combination therapies for clinical studies. The drug combinations with…
View article: DrugGen: a database of <i>de novo</i>-generated molecular binders for specified target proteins
DrugGen: a database of <i>de novo</i>-generated molecular binders for specified target proteins Open
De novo molecular generation is a promising approach to drug discovery, building novel molecules from the scratch that can bind the target proteins specifically. With the increasing availability of machine learning algorithms and computati…
View article: Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation
Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation Open
Graphic sketch representations are effective for representing sketches. Existing methods take the patches cropped from sketches as the graph nodes, and construct the edges based on sketch's drawing order or Euclidean distances on the canva…
View article: AlphaDrug: protein target specific de novo molecular generation
AlphaDrug: protein target specific de novo molecular generation Open
Traditional drug discovery is very laborious, expensive, and time-consuming, due to the huge combinatorial complexity of the discrete molecular search space. Researchers have turned to machine learning methods for help to tackle this diffi…
View article: IA-FaceS: A Bidirectional Method for Semantic Face Editing
IA-FaceS: A Bidirectional Method for Semantic Face Editing Open
Semantic face editing has achieved substantial progress in recent years. Known as a growingly popular method, latent space manipulation performs face editing by changing the latent code of an input face to liberate users from painting skil…
View article: GLH/VASA helicases promote germ granule formation to ensure the fidelity of piRNA-mediated transcriptome surveillance
GLH/VASA helicases promote germ granule formation to ensure the fidelity of piRNA-mediated transcriptome surveillance Open
The ability to distinguish non-self from self is the key characteristic for any defense system. piRNAs function as guardians of the genome by silencing non- self nucleic acids and transposable elements in animals. Many piRNA factors are en…
View article: Identification of RPS28 as a Promising Therapeutic Target for Osteosarcoma Patients with Poor Prognoses Stratified by a Seven-Gene Signature
Identification of RPS28 as a Promising Therapeutic Target for Osteosarcoma Patients with Poor Prognoses Stratified by a Seven-Gene Signature Open
Osteosarcoma (OSA) is the most common primary malignant bone tumor. More than 40% of patients with OSA have poor prognoses. We aimed to discover a biomarker for patient stratification and therapeutic targets for these high-risk patients. U…
View article: Deep Rival Penalized Competitive Learning for Low-resolution Face Recognition
Deep Rival Penalized Competitive Learning for Low-resolution Face Recognition Open
Current face recognition tasks are usually carried out on high-quality face images, but in reality, most face images are captured under unconstrained or poor conditions, e.g., by video surveillance. Existing methods are featured by learnin…
View article: IA-GM: A Deep Bidirectional Learning Method for Graph Matching
IA-GM: A Deep Bidirectional Learning Method for Graph Matching Open
Existing deep learning methods for graph matching(GM) problems usually considered affinity learningto assist combinatorial optimization in a feedforward pipeline, and parameter learning is executed by back-propagating the gradients of the …