collaborators

5 papers

cs.CL2026

Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence

Shengyin Sun, Yiming Li, Renxi Liu +5

Judge Decoding accelerates LLM inference by relaxing the strict verification of Speculative Decoding, yet it typically relies on expensive and noisy supervision. In this work, we r…

cs.LG2025

Enhanced Pre-training of Graph Neural Networks for Million-Scale Heterogeneous Graphs

Shengyin Sun, Chen Ma, Jiehao Chen

In recent years, graph neural networks (GNNs) have facilitated the development of graph data mining. However, training GNNs requires sufficient labeled task-specific data, which is…

cs.CL2025

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling

Shengyin Sun, Yiming Li, Xing Li +8

Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources durin…

cs.IR2025

Hyperbolic Contrastive Learning with Model-augmentation for Knowledge-aware Recommendation

Shengyin Sun, Chen Ma

Benefiting from the effectiveness of graph neural networks (GNNs) and contrastive learning, GNN-based contrastive learning has become mainstream for knowledge-aware recommendation.…

cs.AI2025

GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation

Shengyin Sun, Wenhao Yu, Yuxiang Ren +5

Retrosynthesis prediction focuses on identifying reactants capable of synthesizing a target product. Typically, the retrosynthesis prediction involves two phases: Reaction Center I…