Siyuan Li

52

Papers

415

Total Citations

Papers (52)

MogaNet: Multi-order Gated Aggregation Network

Make RepVGG Greater Again: A Quantization-Aware Approach

Matching Anything by Segmenting Anything

MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding

FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio

SemiReward: A General Reward Model for Semi-supervised Learning

CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph

Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing

From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing

Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation

SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking

Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

One2Any: One-Reference 6D Pose Estimation for Any Object

Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings

MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction

DaCapo: Score Distillation as Stacked Bridge for Fast and High-quality 3D Editing

3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

AlphaFold Database Debiasing for Robust Inverse Folding

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning

Multi-View 3D Point Tracking

Tracking Every Thing in the Wild

AutoMix: Unveiling the Power of Mixup for Stronger Classifiers

Single Image Deraining: A Comprehensive Benchmark Analysis

Video-Bench: Human-Aligned Video Generation Benchmark

Dual-branch Graph Feature Learning for NLOS Imaging

SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks

3515 Protein 3D Graph Structure Learning for Robust Structure-Based Protein Property Prediction

Robust Visual Imitation Learning with Inverse Dynamics Representations

UniDepth: Universal Monocular Metric Depth Estimation

VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences

Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge

Learning to Predict Mutational Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning

UniK3D: Universal Camera Monocular 3D Estimation

Deformation-Aware Unpaired Image Translation for Pose Estimation on Laboratory Animals

Style Transformer for Image Inversion and Editing

UMT: Unified Multi-Modal Transformers for Joint Video Moment Retrieval and Highlight Detection

Hyperspherical Consistency Regularization

CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment

Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning

OVTrack: Open-Vocabulary Multiple Object Tracking

Cascade-DETR: Delving into High-Quality Universal Object Detection

DLME: Deep Local-Flatness Manifold Embedding

Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards

Offline Reinforcement Learning with Reverse Model-based Imagination

Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

CUP: Critic-Guided Policy Reuse

Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration

Harnessing Hard Mixed Samples with Decoupled Regularizer

Understanding the Limitations of Deep Models for Molecular property prediction: Insights and Solutions

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning