activity
20202026
most citedCheck It Again: Progressive Visual Question Answering via Visual Entailment

2 citations · 2 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CV2026

Absorbing Gradient Conflicts: Modeling Semantic Variance via Kent Distributions for Cross-Modal Hashing

Hengjie Zhu, Dayan Wu, Zihao Zhang +5

Supervised proxy-based deep cross-modal hashing has become the dominant paradigm for large-scale retrieval. However, prevalent methods model class proxies as deterministic points i…

cs.CV2026

Beyond Post-Quantization: Native Hash Learning with a Dedicated HASH Token

Xinze Liu, Ding Wang, Dayan Wu +4

Efficient large-scale image retrieval requires compact representations that preserve semantic similarity under fast Hamming-space search. Deep hashing is appealing, but most existi…

cs.CL2022

Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization

Ruipeng Jia, Xingxing Zhang, Yanan Cao +3

In zero-shot multilingual extractive text summarization, a model is typically trained on English summarization dataset and then applied on summarization datasets of other languages…

cs.CL2021

Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation

Yuanxin Liu, Fandong Meng, Zheng Lin +2

Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find th…

cs.CV20212 cited

Check It Again: Progressive Visual Question Answering via Visual Entailment

Qingyi Si, Zheng Lin, Mingyu Zheng +2

While sophisticated Visual Question Answering models have achieved remarkable success, they tend to answer questions only according to superficial correlations between question and…

cs.CL2021

ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques

Yuanxin Liu, Zheng Lin, Fengcheng Yuan

Pre-trained language models of the BERT family have defined the state-of-the-arts in a wide range of NLP tasks. However, the performance of BERT-based models is mainly driven by th…