Alert button

"Information": models, code, and papers
Alert button

Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix

Dec 05, 2023
Xinyu Ma, Xuebo Liu, Min Zhang

Viaarxiv icon

DocLLM: A layout-aware generative language model for multimodal document understanding

Dec 31, 2023
Dongsheng Wang, Natraj Raman, Mathieu Sibue, Zhiqiang Ma, Petr Babkin, Simerjot Kaur, Yulong Pei, Armineh Nourbakhsh, Xiaomo Liu

Viaarxiv icon

Neural Networks Against (and For) Self-Training: Classification with Small Labeled and Large Unlabeled Sets

Dec 31, 2023
Payam Karisani

Viaarxiv icon

Analyzing Local Representations of Self-supervised Vision Transformers

Dec 31, 2023
Ani Vanyan, Alvard Barseghyan, Hakob Tamazyan, Vahan Huroyan, Hrant Khachatrian, Martin Danelljan

Viaarxiv icon

DXAI: Explaining Classification by Image Decomposition

Dec 30, 2023
Elnatan Kadar, Guy Gilboa

Viaarxiv icon

Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback

Dec 30, 2023
Yinglun Xu, Gagandeep Singh

Viaarxiv icon

Tensor Networks for Explainable Machine Learning in Cybersecurity

Dec 29, 2023
Borja Aizpurua, Roman Orus

Viaarxiv icon

History Filtering in Imperfect Information Games: Algorithms and Complexity

Nov 24, 2023
Christopher Solinas, Douglas Rebstock, Nathan R. Sturtevant, Michael Buro

Viaarxiv icon

More than Correlation: Do Large Language Models Learn Causal Representations of Space?

Dec 26, 2023
Yida Chen, Yixian Gan, Sijia Li, Li Yao, Xiaohan Zhao

Viaarxiv icon

ArcMMLU: A Library and Information Science Benchmark for Large Language Models

Nov 30, 2023
Shitou Zhang, Zuchao Li, Xingshen Liu, Liming Yang, Ping Wang

Figure 1 for ArcMMLU: A Library and Information Science Benchmark for Large Language Models
Figure 2 for ArcMMLU: A Library and Information Science Benchmark for Large Language Models
Figure 3 for ArcMMLU: A Library and Information Science Benchmark for Large Language Models
Figure 4 for ArcMMLU: A Library and Information Science Benchmark for Large Language Models
Viaarxiv icon