works on

From the 3 of 7 linked papers with an AI index.

collaborators

7 papers

cs.CV2026

Understanding Knowledge Transfer Mechanism in Heterogeneous MLLM Fusion: A Simple Linear Approach

Yinghao Hou, Jiahe Fan, Yuanhao Pu +2

The paper introduces a simple linear probe called Cross-Scale Directional Parameter Injection (CDPI) to study how knowledge transfers when heterogeneous multimodal large language m…

cs.IR2026

PSG: Pair-Space Generation for Efficient Generative Reranking

Chao Feng, Li Ma, Xiancheng Gao +3

The paper introduces Pair-Space Generation (PSG), which generates ordered item pairs instead of single items to speed up generative reranking in recommender systems while preservin…

cs.IR2026

DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval

Yuanhao Pu, Chenghao Zhang, Chao Feng +2

The paper introduces DIRECTOR, a parallel reranking framework that uses dynamic retrieval indices and entropy‑regularized optimal transport to generate duplicate‑free recommendatio…

astro-ph.IM2026

SpecZoo: An AI-Powered Platform for Spectral Analysis and Visualization in Science and Education

Yuan-Hao Pu, Guo-Hong Lei, Yang Xu +2

Astronomical spectra, which encode rich astrophysical and chemical information, are fundamental to understanding celestial objects and universal laws. The advent of large-scale spe…

cs.LG2026

Beyond Surrogates: A Quantitative Analysis for Inter-Metric Relationships

Yuanhao Pu, Defu Lian, Enhong Chen

The Consistency property between surrogate losses and evaluation metrics has been extensively studied to ensure that minimizing a loss leads to metric optimality. However, the dire…

cs.LG2026

Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss

Yuanhao Pu, Defu Lian, Enhong Chen

The Softmax loss is one of the most widely employed surrogate objectives for classification and ranking tasks. To elucidate its theoretical properties, the Fenchel-Young framework…