Profiles2023-2026
Tianshu Yu
School of Data Science, The Chinese University of Hong Kong, Shenzhen
23Papers
21Last author
34Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers23
- From Fields to Random TreesAuthor 3 of 3ICLR 2026 · 80 citations
- GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic TasksAuthor 12 of 12ICLR 2026 · 6 citations
- Learning What to Trust: Bayesian Prior-Guided Optimization for Visual GenerationAuthor 4 of 5CVPR 2026 · 4 citations
- Incomplete Data, Complete Dynamics: A Diffusion ApproachAuthor 5 of 5ICLR 2026 · 3 citations
- Neural Graduated Assignment for Maximum Common Edge SubgraphsAuthor 5 of 5ICLR 2026 · 3 citations
- Beyond the Heatmap: A Rigorous Evaluation of Component Impact in MCTS-Based TSP SolversAuthor 5 of 5ICLR 2026 · 1 citation
- Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow MatchingAuthor 4 of 4ICML 2026 · 1 citation
- AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree SearchAuthor 7 of 7ACL Findings 2026
- Physically-Informed Flow Matching with Graph Neural Networks for Complex Fluid DynamicsAuthor 2 of 2AAAI 2026
- The Underappreciated Power of Vision Models for Graph Structural UnderstandingAuthor 9 of 9NeurIPS 2025 · 7 citations
- TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational EnsemblesAuthor 4 of 5NeurIPS 2025 · 6 citations
- ReKG-MCTS: Reinforcing LLM Reasoning on Knowledge Graphs via Training-Free Monte Carlo Tree SearchAuthor 3 of 3ACL Findings 2025 · 3 citations
- Improving Task-Specific Multimodal Sentiment Analysis with General MLLMs via PromptingAuthor 5 of 5NeurIPS 2025 · 2 citations
- Graph Learning with Distributional Edge LayoutsAuthor 3 of 3KDD 2025 · 1 citation
- Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup TheoryAuthor 6 of 6KDD 2025 · 1 citation
- Enhancing Generalizability in Molecular Conformation Generation with METRIZATION-Informed Geometric Diffusion PretrainingAuthor 7 of 7AAAI 2025
- Generating Physical Dynamics under PriorsAuthor 3 of 3ICLR 2025
- HyperPLR: Hypergraph Generation through Projection, Learning, and ReconstructionAuthor 2 of 2ICLR 2025
- Sampling from Binary Quadratic Distributions via Stochastic LocalizationAuthor 4 of 4ICML 2025
- Towards Robust Multimodal Sentiment Analysis with Incomplete DataAuthor 3 of 3NeurIPS 2024 · 90 citations
- Boosting Graph Pooling with Persistent HomologyAuthor 3 of 3NeurIPS 2024 · 20 citations
- Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment AnalysisAuthor 6 of 6EMNLP 2023 · 131 citations
- Learning to Decouple Complex SystemsAuthor 2 of 2ICML 2023 · 4 citations
