Li, Siyuan
83 publications
ICLR
2025
MeToken: Uniform Micro-Environment Token Boosts Post-Translational Modification Prediction
NeurIPS
2025
ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
ICCV
2025
Rep-MTL: Unleashing the Power of Representation-Level Task Saliency for Multi-Task Learning
AAAI
2025
Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning
AAAI
2025
SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
CVPR
2024
FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
NeurIPS
2024
PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
AAAI
2024
Protein 3D Graph Structure Learning for Robust Structure-Based Protein Property Prediction
ICLR
2024
RDesign: Hierarchical Data-Efficient Representation Learning for Tertiary Structure-Based RNA Design
NeurIPS
2024
Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
ICML
2024
Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences
ICML
2024
VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling
ECCV
2024
Walker: Self-Supervised Multiple Object Tracking by Walking on Temporal Object Appearance Graphs
AAAI
2023
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification Without Concrete Text Labels
NeurIPS
2023
Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration
NeurIPS
2023
Understanding the Limitations of Deep Models for Molecular Property Prediction: Insights and Solutions
CVPR
2022
UMT: Unified Multi-Modal Transformers for Joint Video Moment Retrieval and Highlight Detection