Metrics
1,067,526 Downloads

Deposit, archive and share your final research data in DR-NTU (Data)

DR-NTU (Data) is for research data deposit. For research paper deposits, please use DR-NTU.

Mission: DR-NTU (Data) curates, stores, preserves, makes available and enables the download of digital data generated by the NTU research community. The repository develops and provides guidance for managing, sharing, and reusing research data to promote responsible data sharing in support of open science and research integrity.

Who can deposit? NTU faculty, research staff and students.

What can be deposited? Final, non-sensitive research data from projects carried out at NTU. The uploaded content must not infringe upon the copyrights or other intellectual property rights, and must be void of all identifiable information.

How to deposit?

Useful links: FAQs | Collection Guidelines | NTU Research Data Management | General terms of use and Privacy policy

Featured Dataverses

In order to use this feature you must have at least one published dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

Advanced Search

1 to 10 of 77,215 Results
Jun 5, 2026 - Other Projects of the Liu Team
Zihan, Teng; Jiayu, Zhao; Wentao, Ren; Minhao, Fan; Tianrui, Ma; Song, Chen; Weichen, Liu, 2026, "SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention", https://doi.org/10.21979/N9/EKDD1U, DR-NTU (Data), V1
The dataset includes the source codes and readme file for implementing the design presented in the paper "SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention"
Python Source Code - 19.2 KB - MD5: c3962d5ffe8f88fab9b28860fb597dad
Python Source Code - 4.2 KB - MD5: 4d30b749f9ab2bdb71ceaf29811715ce
Python Source Code - 17.4 KB - MD5: 5bfa7e0070bc8b5f3d0ea86bbbc735df
Python Source Code - 75.7 KB - MD5: 5b1bf9b449b69577d3970bee8d47b850
Python Source Code - 13.8 KB - MD5: 5de6fd85a931fc0807bd3cb4226142e7
Python Source Code - 9.0 KB - MD5: c50f440efc320f35bbec339eaf756d39
Python Source Code - 8.5 KB - MD5: 8721173c58521271adb3718a40ae64d6
Python Source Code - 89 B - MD5: ba8993227812e8d158d1e320a3795628
Add Data

Log in to create a dataverse or add a dataset.

Share Dataverse

Share this dataverse on your favorite social media networks.

Link Dataverse
Reset Modifications

Are you sure you want to reset the selected metadata fields? If you do this, any customizations (hidden, required, optional) you have done will no longer appear.