Junqi ZHAO

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.

1 to 4 of 4 Results

Replication Data for: Two Causally Related Needles in a Video Haystack Dec 10, 2025 Li, Miaoyu; Chao, Qin; Li, Boyang, 2025, "Replication Data for: Two Causally Related Needles in a Video Haystack", https://doi.org/10.21979/N9/WCSXMT, DR-NTU (Data), V1 Causal2Needles is a benchmark dataset and evaluation toolkit designed to assess the capabilities of both proprietary and open-source multimodal large language models in long-video understanding. It features a large number of "2-needle" questions, where the model must locate and r...
Replication Data for: Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events Dec 10, 2025 Chinchure, Aditya; Ravi, Sahithya; Ng, Raymond; Shwartz, Vered; Li, Boyang; Sigal, Leonid, 2025, "Replication Data for: Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events", https://doi.org/10.21979/N9/HOAFUL, DR-NTU (Data), V1 BlackSwanSuite is a benchmark for evaluating VLMs’ ability to reason about unexpected events through abductive and defeasible tasks. The tasks either artificially limit the amount of visual information provided to models while questioning them about hidden unexpected events, or p...
Replication Data for: SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models Dec 10, 2025 Zhang, Wenyu; Ng, Wei En; Ma, Lixin; Wang, Yuwen; Zhao, Junqi; Koenecke, Allison; Li, Boyang; Wang, Lu, 2025, "Replication Data for: SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models", https://doi.org/10.21979/N9/HI9OFD, DR-NTU (Data), V2 SPHERE (Spatial Perception and Hierarchical Evaluation of Reasoning) is a hierarchical evaluation framework built on a new human-annotated dataset of 2,285 question–answer pairs. It systematically probes models across increasing levels of complexity, from fundamental skills to mu...
Replication Data for: What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases Dec 10, 2025 Tiong, Anthony Meng Huat; Zhao, Junqi; Li, Boyang; Li, Junnan; Hoi, Steven C.H.; Xiong, Caiming, 2025, "Replication Data for: What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases", https://doi.org/10.21979/N9/SL0VV1, DR-NTU (Data), V1 The OLIVE dataset is a highly diverse, human-corrected multi-modal collection designed to simulate the variety and idiosyncrasies of user queries vision-language models (VLMs) face in real-world scenarios. It supports the training and evaluation of VLMs in conditions that more cl...

Replication Data for: Two Causally Related Needles in a Video Haystack

Dec 10, 2025

Li, Miaoyu; Chao, Qin; Li, Boyang, 2025, "Replication Data for: Two Causally Related Needles in a Video Haystack", https://doi.org/10.21979/N9/WCSXMT, DR-NTU (Data), V1

Causal2Needles is a benchmark dataset and evaluation toolkit designed to assess the capabilities of both proprietary and open-source multimodal large language models in long-video understanding. It features a large number of "2-needle" questions, where the model must locate and r...

Replication Data for: Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events

Dec 10, 2025

Chinchure, Aditya; Ravi, Sahithya; Ng, Raymond; Shwartz, Vered; Li, Boyang; Sigal, Leonid, 2025, "Replication Data for: Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events", https://doi.org/10.21979/N9/HOAFUL, DR-NTU (Data), V1

BlackSwanSuite is a benchmark for evaluating VLMs’ ability to reason about unexpected events through abductive and defeasible tasks. The tasks either artificially limit the amount of visual information provided to models while questioning them about hidden unexpected events, or p...

Replication Data for: SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models

Dec 10, 2025

Zhang, Wenyu; Ng, Wei En; Ma, Lixin; Wang, Yuwen; Zhao, Junqi; Koenecke, Allison; Li, Boyang; Wang, Lu, 2025, "Replication Data for: SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models", https://doi.org/10.21979/N9/HI9OFD, DR-NTU (Data), V2

SPHERE (Spatial Perception and Hierarchical Evaluation of Reasoning) is a hierarchical evaluation framework built on a new human-annotated dataset of 2,285 question–answer pairs. It systematically probes models across increasing levels of complexity, from fundamental skills to mu...

Replication Data for: What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases

Dec 10, 2025

Tiong, Anthony Meng Huat; Zhao, Junqi; Li, Boyang; Li, Junnan; Hoi, Steven C.H.; Xiong, Caiming, 2025, "Replication Data for: What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases", https://doi.org/10.21979/N9/SL0VV1, DR-NTU (Data), V1

The OLIVE dataset is a highly diverse, human-corrected multi-modal collection designed to simulate the variety and idiosyncrasies of user queries vision-language models (VLMs) face in real-world scenarios. It supports the training and evaluation of VLMs in conditions that more cl...

Add Data

Share Dataverse

Link Dataverse

Reset Modifications