4 citations · 8 across the 7 of their papers we have counts for
8 papers
Vocabulary-Incomplete Unsupervised Vision-Language Model Adaptation
Si Qin, Jiawei Tang, Yaxin Hou +4
In certain real-world scenarios, obtaining labeled data is excessively expensive, motivating increasing interest in adapting models without annotations. Vision-language models (VLM…
R2LED: Equipping Retrieval and Refinement in Lifelong User Modeling with Semantic IDs for CTR Prediction
Qidong Liu, Gengnan Wang, Zhichen Liu +6
Lifelong user modeling, which leverages users' long-term behavior sequences for CTR prediction, has been widely applied in personalized services. Existing methods generally adopted…
Semantic Purification for Conditional Representation Learning
Jiaquan Wang, Yan Lyu, Chen Li +1
Conditional representation learning aims to extract criterion-specific features for customized tasks. Recent methods construct conditional subspaces spanned by criterion-specific t…
HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection
Chunze Yang, Wenjie Zhao, Yue Tang +5
Precision pathology relies on detecting fine-grained morphological abnormalities within specific Regions of Interest (ROIs), as these local, texture-rich cues - rather than global…
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
5 Team, Aohan Zeng, Xin Lv +167
We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that s…
A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation
Penglong Zhai, Yifang Yuan, Fanyi Di +7
Generative retrieval-based recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. However, in large-scale recomm…
SwitchTab: Switched Autoencoders Are Effective Tabular Learners
Jing Wu, Suiyao Chen, Qi Zhao +9
Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or…
Refine Neutrino Events Reconstruction with BEiT-3
Chen Li, Hao Cai, Xianyang Jiang
Neutrino Events Reconstruction has always been crucial for IceCube Neutrino Observatory. In the Kaggle competition "IceCube -- Neutrinos in Deep Ice", many solutions use Transforme…