Tianshu Yu

From Fields to Random Trees

Neural Graduated Assignment for Maximum Common Edge Subgraphs

Incomplete Data, Complete Dynamics: A Diffusion Approach

GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

Beyond the Heatmap: A Rigorous Evaluation of Component Impact in MCTS-Based TSP Solvers

Chem-R: Learning to Reason as a Chemist

Towards Principled Task Grouping for Multi-Task Learning

AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search

NeuroLifting: Neural Inference on Markov Random Fields at Scale

EVA-MILP: Towards Standardized Evaluation of MILP Instance Generation

Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage

The Underappreciated Power of Vision Models for Graph Structural Understanding

TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles

Improving Task-Specific Multimodal Sentiment Analysis with General MLLMs via Prompting

Generating Physical Dynamics under Priors

HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction

Prompt-Guided Distillation from Multimodal Large Language Models to Task-specific Models for Multimodal Sentiment Analysis

Sampling from Binary Quadratic Distributions via Stochastic Localization

Enhancing Graph Self-Supervised Learning with Graph Interplay

Are spectral augmentations necessary in contrast-based graph self-supervised learning?

Fragment-Augmented Diffusion for Molecular Conformation Generation

NeuroLifting: Neural Inference on Markov Random Fields at Scale

Rethinking the "Heatmap + Monte Carlo Tree Search'' Paradigm for Solving Large Scale TSP