338 citations · 338 across the 10 of their papers we have counts for
10 papers
Understanding Knowledge Transfer Mechanism in Heterogeneous MLLM Fusion: A Simple Linear Approach
Yinghao Hou, Jiahe Fan, Yuanhao Pu +2
Training-free fusion of heterogeneous multimodal large language models (MLLMs) provides a direct route for cross-scale capability transfer, yet improvements in aggregate performanc…
PSG: Pair-Space Generation for Efficient Generative Reranking
Chao Feng, Li Ma, Xiancheng Gao +3
Modern recommender systems adopt Generator-Evaluator (G-E) for list-wise reranking: a generator produces sequences from candidates and an evaluator scores them at sequence-level to…
DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval
Yuanhao Pu, Chenghao Zhang, Chao Feng +2
Reranking is a combinatorial decision problem that aims to select and order a high-utility slate from a request-specific candidate set. A major line of generative rerankers adopts…
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…
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…
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…
NDCG-Consistent Softmax Approximation with Accelerated Convergence
Yuanhao Pu, Defu Lian, Xiaolong Chen +3
Ranking tasks constitute fundamental components of extreme similarity learning frameworks, where extremely large corpora of objects are modeled through relative similarity relation…
Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction
Qi Liu, Xingyuan Tang, Jianqiang Huang +9
Natural content and advertisement coexist in industrial recommendation systems but differ in data distribution. Concretely, traffic related to the advertisement is considerably spa…
Invariant Representation via Decoupling Style and Spurious Features from Images
Ruimeng Li, Yuanhao Pu, Zhaoyi Li +2
This paper considers the out-of-distribution (OOD) generalization problem under the setting that both style distribution shift and spurious features exist and domain labels are mis…
When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
Jin Chen, Zheng Liu, Xu Huang +9
The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of…