🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

METEOR is a NICE dataset for complex and unstructured scenarios in autonomous driving tasks.

AZTR is a framework for both edge devices and decent GPUS!

A little extra multimodal data can help the knowledge distillation!

There must be a reason for getting fat. It’s not surprising that two of us who sneaked food met in the midnight 🤔 Seeing your chubby back, I silently poured a glass of water to dispel the idea of ​​eating night food😎

Big thanks to the leading author Tianrui Guan (On Job Market) and all the coauthors!

How to strengthen both CNNs and Transformers? Check our work “SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers” on Oct. 2nd (1:30pm-6pm) at #ICCV2023 Workshop on New Ideas in Vision Transformers A P01 ArXiv: arxiv.org/abs/2308.07110

🔥CoBig shoutout to Google for launching their groundbreaking large multimodal model #Gemini. 🚩However, there are still obvious hallucinations with Gemini. Here are a few examples with Gemini Pro. Want to learn more? Look at our HallusionBench Paper: arxiv.org/pdf/2310.14566…

📢 Sharing a couple of interesting observations and results of #GeminiAI Pro Vision on our #HallusionBench (Big thanks to Google DeepMind for making those API available! 🙏): 1. Language hallucination is a significant issue, often resulting in outputs that include irrelevant

See you Saturday 17:15-19:17 at Naupaka #51 #WACV2024 For aerial videos, we proposed MITFAS to focus on the regions corresponding to salient motions and find the more informative frames by using mutual information. Ruiqi Xian Dinesh Manocha GAMMA UMD

Join us at #93 of the Poster session on Thursday, February 22! #AAAI24 GAMMA UMD Say hi to Shan Yang there! Our ICAR can recommend items with good visual compatibility including similarity (color, geometry, texture, etc.) and complementarity (like table vs chair).

📢Thrilled to share our latest work #AutoHallusion, an automatic hallucination pipeline that scales up the benchmark generation process. 🌐 Webpage & Examples: wuxiyang1996.github.io/autohallusion_…… 📷 Arxiv: arxiv.org/abs/2406.10900 👀Please stay tuned for our future updates! Thanks a lot

Xijun Wang Xijun Wang will be presenting "ViLA: Efficient Video-Language Alignment for Video Question Answering", which addresses both efficient frame sampling and effective cross-modal alignment! 🗣️ Time: October 3, 4:30pm - 6:30pm Location: Poster session 6, ID 274

#ECCV2024 Visit our ViLA poster and Say Hi to Prof. Ming C. Lin ! Time: October 3, 4:30pm - 6:30pm Location: Poster session 6, ID 274 Arxiv: arxiv.org/abs/2312.08367 Code: github.com/xijun-cs/ViLA Big shout-out to Shan Yang! GAMMA UMD

.Xijun Wang will be presenting “SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition”, which utilizes prompt learning for aerial video action recognition. ✈️ Thurs Oct 17 17:30 - 17:45 Room 6

AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for VLMs Xiyang Wu*, Tianrui Guan (On Job Market)*, D Li, S Huang, X Liu, Xijun Wang, Ruiqi Xian, Abhinav Shrivastava, Furong Huang, Jordan Boyd-Graber, Tianyi Zhou, Dinesh Manocha 11/3; 16:00-17:30 - Riverfront Hall Website: wuxiyang1996.github.io/autohallusion_…

More details are in our paper, now on arXiv: arxiv.org/abs/2504.03889 Thanks to my collaborators: Xijun Wang, Ashwinee Panda, Micah Goldblum, Ronen Basri, Tom Goldstein, David Jacobs

LLMs know how to make use of short cuts! This is a good exploration on the potential LLM redundancy. Check our paper for more details!